RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-25 20:23:11 +01:00
Code Issues Projects Releases Wiki Activity

[PowerPC] Update Refactored Load/Store Implementation, XForm VSX Patterns, and Tests

Browse Source 
This patch includes the following updates to the load/store refactoring effort introduced in D93370:
 - Update various VSX patterns that use to "force" an XForm, to instead just XForm.
   This allows the ability for the patterns to compute the most optimal addressing
   mode (and to produce a DForm instruction when possible)
- Update pattern and test case for the LXVD2X/STXVD2X intrinsics
- Update LIT test cases that use to use the XForm instruction to use the DForm instruction

Differential Revision: https://reviews.llvm.org/D95115
This commit is contained in:
Amy Kwan 2021-07-13 20:33:23 -05:00
parent b8f7435c4c
commit 9f4ca39c11
89 changed files with 3698 additions and 7850 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

76
lib/Target/PowerPC/PPCInstrVSX.td
View File

@ -316,13 +316,13 @@ let hasSideEffects = 0 in {
let CodeSize = 3 in
def XFLOADf64 : PseudoXFormMemOp<(outs vsfrc:$XT), (ins memrr:$src),
"#XFLOADf64",
[(set f64:$XT, (load ForceXForm:$src))]>;
[(set f64:$XT, (load XForm:$src))]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in
def LXVD2X : XX1Form_memOp<31, 844,
(outs vsrc:$XT), (ins memrr:$src),
"lxvd2x $XT, $src", IIC_LdStLFD,
[(set v2f64:$XT, (int_ppc_vsx_lxvd2x ForceXForm:$src))]>;
[]>;
def LXVDSX : XX1Form_memOp<31, 332,
(outs vsrc:$XT), (ins memrr:$src),
@ -347,7 +347,7 @@ let hasSideEffects = 0 in {
let CodeSize = 3 in
def XFSTOREf64 : PseudoXFormMemOp<(outs), (ins vsfrc:$XT, memrr:$dst),
"#XFSTOREf64",
[(store f64:$XT, ForceXForm:$dst)]>;
[(store f64:$XT, XForm:$dst)]>;
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
// The behaviour of this instruction is endianness-specific so we provide no
@ -1128,7 +1128,7 @@ let Predicates = [HasVSX, HasP8Vector] in {
let CodeSize = 3 in
def XFLOADf32 : PseudoXFormMemOp<(outs vssrc:$XT), (ins memrr:$src),
"#XFLOADf32",
[(set f32:$XT, (load ForceXForm:$src))]>;
[(set f32:$XT, (load XForm:$src))]>;
// Pseudo instruction LIWAX will be expanded to LXSIWAX or LFIWAX later
def LIWAX : PseudoXFormMemOp<(outs vsfrc:$XT), (ins memrr:$src),
"#LIWAX",
@ -1151,7 +1151,7 @@ let Predicates = [HasVSX, HasP8Vector] in {
let CodeSize = 3 in
def XFSTOREf32 : PseudoXFormMemOp<(outs), (ins vssrc:$XT, memrr:$dst),
"#XFSTOREf32",
[(store f32:$XT, ForceXForm:$dst)]>;
[(store f32:$XT, XForm:$dst)]>;
// Pseudo instruction STIWX will be expanded to STXSIWX or STFIWX later
def STIWX : PseudoXFormMemOp<(outs), (ins vsfrc:$XT, memrr:$dst),
"#STIWX",
@ -2453,6 +2453,7 @@ def DblwdCmp {
// [HasVSX, IsLittleEndian]
// [HasVSX, NoP9Vector]
// [HasVSX, NoP9Vector, IsLittleEndian]
// [HasVSX, NoP9Vector, IsBigEndian]
// [HasVSX, HasOnlySwappingMemOps]
// [HasVSX, HasOnlySwappingMemOps, IsBigEndian]
// [HasVSX, HasP8Vector]
@ -3136,14 +3137,19 @@ defm : ScalToVecWPermute<
(SUBREG_TO_REG (i64 1), (XFLOADf64 ForceXForm:$src), sub_64)>;
} // HasVSX, NoP9Vector, IsLittleEndian
let Predicates = [HasVSX, NoP9Vector, IsBigEndian] in {
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x ForceXForm:$src)),
(LXVD2X ForceXForm:$src)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, ForceXForm:$dst),
(STXVD2X $rS, ForceXForm:$dst)>;
} // HasVSX, NoP9Vector, IsBigEndian
// Any VSX subtarget that only has loads and stores that load in big endian
// order regardless of endianness. This is really pre-Power9 subtargets.
let Predicates = [HasVSX, HasOnlySwappingMemOps] in {
def : Pat<(v2f64 (PPClxvd2x ForceXForm:$src)), (LXVD2X ForceXForm:$src)>;
// Stores.
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, ForceXForm:$dst),
(STXVD2X $rS, ForceXForm:$dst)>;
def : Pat<(PPCstxvd2x v2f64:$rS, ForceXForm:$dst), (STXVD2X $rS, ForceXForm:$dst)>;
} // HasVSX, HasOnlySwappingMemOps
@ -3167,8 +3173,8 @@ let Predicates = [HasVSX, HasOnlySwappingMemOps, IsBigEndian] in {
let Predicates = [HasVSX, HasP8Vector] in {
def : Pat<(int_ppc_vsx_xxleqv v4i32:$A, v4i32:$B),
(XXLEQV $A, $B)>;
def : Pat<(f64 (extloadf32 ForceXForm:$src)),
(COPY_TO_REGCLASS (XFLOADf32 ForceXForm:$src), VSFRC)>;
def : Pat<(f64 (extloadf32 XForm:$src)),
(COPY_TO_REGCLASS (XFLOADf32 XForm:$src), VSFRC)>;
def : Pat<(f32 (fpround (f64 (extloadf32 ForceXForm:$src)))),
(f32 (XFLOADf32 ForceXForm:$src))>;
def : Pat<(f64 (any_fpextend f32:$src)),
@ -3803,48 +3809,34 @@ def : Pat<(v1i128 (bswap v1i128 :$A)),
(v1i128 (COPY_TO_REGCLASS (XXBRQ (COPY_TO_REGCLASS $A, VSRC)), VRRC))>;
// D-Form Load/Store
def : Pat<(v4i32 (quadwOffsetLoad DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(v4f32 (quadwOffsetLoad DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(v2i64 (quadwOffsetLoad DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(v2f64 (quadwOffsetLoad DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(f128 (quadwOffsetLoad DQForm:$src)),
foreach Ty = [v4i32, v4f32, v2i64, v2f64] in {
def : Pat<(Ty (load DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(Ty (load XForm:$src)), (LXVX XForm:$src)>;
def : Pat<(store Ty:$rS, DQForm:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(store Ty:$rS, XForm:$dst), (STXVX $rS, XForm:$dst)>;
}
def : Pat<(f128 (load DQForm:$src)),
(COPY_TO_REGCLASS (LXV memrix16:$src), VRRC)>;
def : Pat<(f128 (load XForm:$src)),
(COPY_TO_REGCLASS (LXVX XForm:$src), VRRC)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x DQForm:$src)), (LXV memrix16:$src)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x XForm:$src)), (LXVX XForm:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x XForm:$src)), (LXVX XForm:$src)>;
def : Pat<(quadwOffsetStore v4f32:$rS, DQForm:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore v4i32:$rS, DQForm:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore v2f64:$rS, DQForm:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(quadwOffsetStore f128:$rS, DQForm:$dst),
def : Pat<(store f128:$rS, DQForm:$dst),
(STXV (COPY_TO_REGCLASS $rS, VSRC), memrix16:$dst)>;
def : Pat<(quadwOffsetStore v2i64:$rS, DQForm:$dst), (STXV $rS, memrix16:$dst)>;
def : Pat<(store f128:$rS, XForm:$dst),
(STXVX (COPY_TO_REGCLASS $rS, VSRC), XForm:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, DQForm:$dst),
(STXV $rS, memrix16:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, DQForm:$dst),
(STXV $rS, memrix16:$dst)>;
def : Pat<(v2f64 (nonQuadwOffsetLoad ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(v2i64 (nonQuadwOffsetLoad ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(v4f32 (nonQuadwOffsetLoad ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(v4i32 (nonQuadwOffsetLoad ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(v4i32 (int_ppc_vsx_lxvw4x ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(v2f64 (int_ppc_vsx_lxvd2x ForceXForm:$src)), (LXVX ForceXForm:$src)>;
def : Pat<(f128 (nonQuadwOffsetLoad ForceXForm:$src)),
(COPY_TO_REGCLASS (LXVX ForceXForm:$src), VRRC)>;
def : Pat<(nonQuadwOffsetStore f128:$rS, ForceXForm:$dst),
(STXVX (COPY_TO_REGCLASS $rS, VSRC), ForceXForm:$dst)>;
def : Pat<(nonQuadwOffsetStore v2f64:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(nonQuadwOffsetStore v2i64:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(nonQuadwOffsetStore v4f32:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(nonQuadwOffsetStore v4i32:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, ForceXForm:$dst),
(STXVX $rS, ForceXForm:$dst)>;
def : Pat<(int_ppc_vsx_stxvw4x v4i32:$rS, XForm:$dst),
(STXVX $rS, XForm:$dst)>;
def : Pat<(int_ppc_vsx_stxvd2x v2f64:$rS, XForm:$dst),
(STXVX $rS, XForm:$dst)>;
// Build vectors from i8 loads
defm : ScalToVecWPermute<v8i16, ScalarLoads.ZELi8,

8
test/CodeGen/PowerPC/PR33671.ll
View File

@ -25,8 +25,8 @@ entry:
store <4 x i32> %2, <4 x i32>* %0, align 16
ret void
; CHECK-LABEL: test2
; CHECK: addi 3, 3, 8
; CHECK: addi [[REG:[0-9]+]], 4, 4
; CHECK: lxvx [[LD:[0-9]+]], 0, 3
; CHECK: stxvx [[LD]], 0, [[REG]]
; CHECK: li [[REG:[0-9]+]], 8
; CHECK: lxvx [[LD:[0-9]+]], 3, [[REG]]
; CHECK: li [[REG2:[0-9]+]], 4
; CHECK: stxvx [[LD]], 4, [[REG2]]
}

2
test/CodeGen/PowerPC/VSX-XForm-Scalars.ll
View File

@ -29,7 +29,7 @@ define void @testExpandPostRAPseudo(i32* nocapture readonly %ptr) {
; CHECK-P9: addis r4, r2, .LC0@toc@ha
; CHECK-P9: lxvwsx vs0, 0, r3
; CHECK-P9: ld r4, .LC0@toc@l(r4)
; CHECK-P9: stxvx vs0, 0, r4
; CHECK-P9: stxv vs0, 0(r4)
; CHECK-P9: lis r4, 1024
; CHECK-P9: lfiwax f0, 0, r3
; CHECK-P9: addis r3, r2, .LC1@toc@ha

10
test/CodeGen/PowerPC/aix-dfltabi-rsrvd-reg.ll
View File

@ -85,15 +85,15 @@ entry:
; EXTABI: body: |
; EXTABI: bb.0.entry:
; EXTABI: liveins: $f1, $x4
; EXTABI-DAG: renamable $f0 = XFLOADf64 $zero8, renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; EXTABI-DAG: renamable $f0 = LFD 0, renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; EXTABI-DAG: renamable $f0 = nofpexcept XSADDDP killed renamable $f0, renamable $f1, implicit $rm
; EXTABI-DAG: renamable $vf31 = nofpexcept XSMULDP killed renamable $f1, renamable $f1, implicit $rm
; EXTABI: XFSTOREf64 killed renamable $f0, $zero8, renamable $x4 :: (volatile store (s64) into %ir.b, align 4)
; EXTABI: STFD killed renamable $f0, 0, renamable $x4 :: (volatile store (s64) into %ir.b, align 4)
; EXTABI-LABEL: INLINEASM
; EXTABI-DAG: renamable $f0 = XFLOADf64 $zero8, renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; EXTABI-DAG: renamable $f0 = LFD 0, renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; EXTABI-DAG: renamable $f0 = nofpexcept XSADDDP killed renamable $vf31, killed renamable $f0, implicit $rm
; EXTABI-DAG: XFSTOREf64 killed renamable $f0, $zero8, renamable $x4 :: (volatile store (s64) into %ir.b, align 4)
; EXTABI: renamable $f1 = XFLOADf64 $zero8, killed renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; EXTABI-DAG: STFD killed renamable $f0, 0, renamable $x4 :: (volatile store (s64) into %ir.b, align 4)
; EXTABI: renamable $f1 = LFD 0, killed renamable $x4 :: (volatile load (s64) from %ir.b, align 4)
; DFLABI-LABEL: vec_test

48
test/CodeGen/PowerPC/aix-p9-insert-extract.ll
View File

@ -455,14 +455,14 @@ define <8 x i16> @shuffle_vector_halfword_0_4(<8 x i16> %a) {
; CHECK-64-LABEL: shuffle_vector_halfword_0_4:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C0(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_halfword_0_4:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C0(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -534,14 +534,14 @@ define <8 x i16> @shuffle_vector_halfword_3_4(<8 x i16> %a) {
; CHECK-64-LABEL: shuffle_vector_halfword_3_4:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C1(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_halfword_3_4:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C1(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -613,14 +613,14 @@ define <8 x i16> @shuffle_vector_halfword_6_4(<8 x i16> %a) {
; CHECK-64-LABEL: shuffle_vector_halfword_6_4:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C2(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_halfword_6_4:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C2(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -642,14 +642,14 @@ define <8 x i16> @shuffle_vector_halfword_7_4(<8 x i16> %a) {
; CHECK-64-LABEL: shuffle_vector_halfword_7_4:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C3(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_halfword_7_4:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C3(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1703,14 +1703,14 @@ define <16 x i8> @shuffle_vector_byte_1_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_1_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C4(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_1_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C4(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1732,14 +1732,14 @@ define <16 x i8> @shuffle_vector_byte_2_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_2_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C5(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_2_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C5(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1811,14 +1811,14 @@ define <16 x i8> @shuffle_vector_byte_5_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_5_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C6(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_5_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C6(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1840,14 +1840,14 @@ define <16 x i8> @shuffle_vector_byte_6_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_6_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C7(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_6_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C7(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1869,14 +1869,14 @@ define <16 x i8> @shuffle_vector_byte_7_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_7_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C8(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_7_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C8(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -1973,14 +1973,14 @@ define <16 x i8> @shuffle_vector_byte_11_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_11_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C9(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_11_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C9(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -2002,14 +2002,14 @@ define <16 x i8> @shuffle_vector_byte_12_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_12_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C10(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_12_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C10(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:
@ -2081,14 +2081,14 @@ define <16 x i8> @shuffle_vector_byte_15_8(<16 x i8> %a) {
; CHECK-64-LABEL: shuffle_vector_byte_15_8:
; CHECK-64: # %bb.0: # %entry
; CHECK-64-NEXT: ld 3, L..C11(2)
; CHECK-64-NEXT: lxvx 35, 0, 3
; CHECK-64-NEXT: lxv 35, 0(3)
; CHECK-64-NEXT: vperm 2, 2, 2, 3
; CHECK-64-NEXT: blr
;
; CHECK-32-LABEL: shuffle_vector_byte_15_8:
; CHECK-32: # %bb.0: # %entry
; CHECK-32-NEXT: lwz 3, L..C11(2)
; CHECK-32-NEXT: lxvx 35, 0, 3
; CHECK-32-NEXT: lxv 35, 0(3)
; CHECK-32-NEXT: vperm 2, 2, 2, 3
; CHECK-32-NEXT: blr
entry:

12
test/CodeGen/PowerPC/aix-vec-arg-spills-callee.ll
View File

@ -41,10 +41,8 @@ entry:
; MIR32: isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
; MIR32: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
; MIR32: renamable $[[GPR1:r[0-9]+]] = ADDI %fixed-stack.2, 0
; MIR32: renamable $[[GPR2:r[0-9]+]] = ADDI %fixed-stack.0, 0
; MIR32: renamable $f{{[0-9]+}} = XFLOADf64 $zero, killed renamable $[[GPR1]]
; MIR32: renamable $f{{[0-9]+}} = XFLOADf64 $zero, killed renamable $[[GPR2]]
; MIR32: renamable $f{{[0-9]+}} = LFD 0, %fixed-stack.2
; MIR32: renamable $f{{[0-9]+}} = LFD 0, %fixed-stack.0
; 64BIT-LABEL: .test:
; 64BIT-DAG: lfd {{[0-9]+}}, 80(1)
@ -62,7 +60,5 @@ entry:
; MIR64: isImmutable: true, isAliased: false, callee-saved-register: '', callee-saved-restored: true,
; MIR64: debug-info-variable: '', debug-info-expression: '', debug-info-location: '' }
; MIR64: renamable $[[GPR1:x[0-9]+]] = ADDI8 %fixed-stack.2, 0
; MIR64: renamable $[[GPR2:x[0-9]+]] = ADDI8 %fixed-stack.0, 0
; MIR64: renamable $f{{[0-9]+}} = XFLOADf64 $zero8, killed renamable $[[GPR1]]
; MIR64: renamable $f{{[0-9]+}} = XFLOADf64 $zero8, killed renamable $[[GPR2]]
; MIR64: renamable $f{{[0-9]+}} = LFD 0, %fixed-stack.2
; MIR64: renamable $f{{[0-9]+}} = LFD 0, %fixed-stack.0

27
test/CodeGen/PowerPC/aix-vector-vararg-fixed-caller.ll
View File

@ -8,6 +8,8 @@
; RUN: FileCheck --check-prefix=64BIT %s
define void @caller() {
; 32BIT-LABEL: name: caller
; 32BIT: bb.0.entry:
; 32BIT: ADJCALLSTACKDOWN 88, 0, implicit-def dead $r1, implicit $r1
@ -23,26 +25,25 @@ define void @caller() {
; 32BIT: STW killed [[ORI1]], 80, $r1 :: (store (s32), align 8)
; 32BIT: [[LWZtoc1:%[0-9]+]]:gprc = LWZtoc %const.1, $r2 :: (load (s32) from got)
; 32BIT: [[LXVW4X1:%[0-9]+]]:vsrc = LXVW4X $zero, killed [[LWZtoc1]] :: (load (s128) from constant-pool)
; 32BIT: [[LWZtoc2:%[0-9]+]]:gprc = LWZtoc %const.2, $r2 :: (load (s32) from got)
; 32BIT: [[XFLOADf64_:%[0-9]+]]:vsfrc = XFLOADf64 $zero, killed [[LWZtoc2]] :: (load (s64) from constant-pool)
; 32BIT: [[LWZtoc2:%[0-9]+]]:gprc_and_gprc_nor0 = LWZtoc %const.2, $r2 :: (load (s32) from got)
; 32BIT: [[LFD:%[0-9]+]]:f8rc = LFD 0, killed [[LWZtoc2]] :: (load (s64) from constant-pool)
; 32BIT: [[LIS2:%[0-9]+]]:gprc = LIS 16393
; 32BIT: [[ORI2:%[0-9]+]]:gprc = ORI killed [[LIS2]], 8697
; 32BIT: [[LIS3:%[0-9]+]]:gprc = LIS 61467
; 32BIT: [[ORI3:%[0-9]+]]:gprc = ORI killed [[LIS3]], 34414
; 32BIT: [[LWZtoc3:%[0-9]+]]:gprc = LWZtoc %const.3, $r2 :: (load (s32) from got)
; 32BIT: [[XFLOADf64_1:%[0-9]+]]:vsfrc = XFLOADf64 $zero, killed [[LWZtoc3]] :: (load (s64) from constant-pool)
; 32BIT: [[LWZtoc3:%[0-9]+]]:gprc_and_gprc_nor0 = LWZtoc %const.3, $r2 :: (load (s32) from got)
; 32BIT: [[LFD1:%[0-9]+]]:f8rc = LFD 0, killed [[LWZtoc3]] :: (load (s64) from constant-pool)
; 32BIT: [[LI1:%[0-9]+]]:gprc = LI 55
; 32BIT: $r3 = COPY [[LI1]]
; 32BIT: $v2 = COPY [[LXVW4X1]]
; 32BIT: $f1 = COPY [[XFLOADf64_]]
; 32BIT: $f1 = COPY [[LFD]]
; 32BIT: $r9 = COPY [[ORI2]]
; 32BIT: $r10 = COPY [[ORI3]]
; 32BIT: $f2 = COPY [[XFLOADf64_1]]
; 32BIT: $f2 = COPY [[LFD1]]
; 32BIT: BL_NOP <mcsymbol .callee[PR]>, csr_aix32_altivec, implicit-def dead $lr, implicit $rm, implicit $r3, implicit $v2, implicit $f1, implicit $r9, implicit $r10, implicit $f2, implicit $r2, implicit-def $r1, implicit-def $v2
; 32BIT: ADJCALLSTACKUP 88, 0, implicit-def dead $r1, implicit $r1
; 32BIT: [[COPY:%[0-9]+]]:vsrc = COPY $v2
; 32BIT: BLR implicit $lr, implicit $rm
; 64BIT-LABEL: name: caller
; 64BIT: bb.0.entry:
; 64BIT: ADJCALLSTACKDOWN 120, 0, implicit-def dead $r1, implicit $r1
@ -60,10 +61,10 @@ define void @caller() {
; 64BIT: [[LXVW4X1:%[0-9]+]]:vsrc = LXVW4X $zero8, killed [[LDtocCPT1]] :: (load (s128) from constant-pool)
; 64BIT: [[LD:%[0-9]+]]:g8rc = LD 104, $x1 :: (load (s64))
; 64BIT: [[LD1:%[0-9]+]]:g8rc = LD 96, $x1 :: (load (s64))
; 64BIT: [[LDtocCPT2:%[0-9]+]]:g8rc = LDtocCPT %const.2, $x2 :: (load (s64) from got)
; 64BIT: [[XFLOADf64_:%[0-9]+]]:vsfrc = XFLOADf64 $zero8, killed [[LDtocCPT2]] :: (load (s64) from constant-pool)
; 64BIT: [[LDtocCPT3:%[0-9]+]]:g8rc = LDtocCPT %const.3, $x2 :: (load (s64) from got)
; 64BIT: [[XFLOADf64_1:%[0-9]+]]:vsfrc = XFLOADf64 $zero8, killed [[LDtocCPT3]] :: (load (s64) from constant-pool)
; 64BIT: [[LDtocCPT2:%[0-9]+]]:g8rc_and_g8rc_nox0 = LDtocCPT %const.2, $x2 :: (load (s64) from got)
; 64BIT: [[LFD:%[0-9]+]]:f8rc = LFD 0, killed [[LDtocCPT2]] :: (load (s64) from constant-pool)
; 64BIT: [[LDtocCPT3:%[0-9]+]]:g8rc_and_g8rc_nox0 = LDtocCPT %const.3, $x2 :: (load (s64) from got)
; 64BIT: [[LFD1:%[0-9]+]]:f8rc = LFD 0, killed [[LDtocCPT3]] :: (load (s64) from constant-pool)
; 64BIT: [[LIS8_1:%[0-9]+]]:g8rc = LIS8 16393
; 64BIT: [[ORI8_2:%[0-9]+]]:g8rc = ORI8 killed [[LIS8_1]], 8697
; 64BIT: [[RLDIC1:%[0-9]+]]:g8rc = RLDIC killed [[ORI8_2]], 32, 1
@ -72,11 +73,11 @@ define void @caller() {
; 64BIT: [[LI8_1:%[0-9]+]]:g8rc = LI8 55
; 64BIT: $x3 = COPY [[LI8_1]]
; 64BIT: $v2 = COPY [[LXVW4X1]]
; 64BIT: $f1 = COPY [[XFLOADf64_]]
; 64BIT: $f1 = COPY [[LFD]]
; 64BIT: $x7 = COPY [[ORI8_3]]
; 64BIT: $x9 = COPY [[LD1]]
; 64BIT: $x10 = COPY [[LD]]
; 64BIT: $f2 = COPY [[XFLOADf64_1]]
; 64BIT: $f2 = COPY [[LFD1]]
; 64BIT: BL8_NOP <mcsymbol .callee[PR]>, csr_ppc64_altivec, implicit-def dead $lr8, implicit $rm, implicit $x3, implicit $v2, implicit $f1, implicit $x7, implicit $x9, implicit $x10, implicit $f2, implicit $x2, implicit-def $r1, implicit-def $v2
; 64BIT: ADJCALLSTACKUP 120, 0, implicit-def dead $r1, implicit $r1
; 64BIT: [[COPY:%[0-9]+]]:vsrc = COPY $v2

5
test/CodeGen/PowerPC/aix32-vector-vararg-fixed-callee.ll
View File

@ -14,10 +14,9 @@ define double @callee(i32 %count, <4 x i32> %vsi, double %next, ...) {
; CHECK: STW killed [[ADDI]], 0, %stack.0.arg_list :: (store (s32) into %ir.0)
; CHECK: [[ADDI1:%[0-9]+]]:gprc = ADDI %fixed-stack.0, 15
; CHECK: [[RLWINM:%[0-9]+]]:gprc_and_gprc_nor0 = RLWINM killed [[ADDI1]], 0, 0, 27
; CHECK: [[ADDI2:%[0-9]+]]:gprc = nuw ADDI killed [[RLWINM]], 16
; CHECK: [[XFLOADf64_:%[0-9]+]]:vsfrc = XFLOADf64 $zero, killed [[ADDI2]] :: (load (s64) from %ir.4, align 16)
; CHECK: [[LFD:%[0-9]+]]:f8rc = LFD 16, killed [[RLWINM]] :: (load (s64) from %ir.4, align 16)
; CHECK: LIFETIME_END %stack.0.arg_list
; CHECK: $f1 = COPY [[XFLOADf64_]]
; CHECK: $f1 = COPY [[LFD]]
; CHECK: BLR implicit $lr, implicit $rm, implicit $f1
entry:
%arg_list = alloca i8*, align 4

5
test/CodeGen/PowerPC/aix64-vector-vararg-fixed-callee.ll
View File

@ -21,10 +21,9 @@ define double @callee(i32 signext %count, <4 x i32> %vsi, double %next, ...) {
; CHECK: STD killed [[ADDI8_]], 0, %stack.0.arg_list :: (store (s64) into %ir.0)
; CHECK: [[ADDI8_1:%[0-9]+]]:g8rc = ADDI8 %fixed-stack.0, 15
; CHECK: [[RLDICR:%[0-9]+]]:g8rc_and_g8rc_nox0 = RLDICR killed [[ADDI8_1]], 0, 59
; CHECK: [[LI8_:%[0-9]+]]:g8rc = LI8 16
; CHECK: [[XFLOADf64_:%[0-9]+]]:vsfrc = XFLOADf64 killed [[RLDICR]], killed [[LI8_]] :: (load (s64) from %ir.4, align 16)
; CHECK: [[LFD:%[0-9]+]]:f8rc = LFD 16, killed [[RLDICR]] :: (load (s64) from %ir.4, align 16)
; CHECK: LIFETIME_END %stack.0.arg_list
; CHECK: $f1 = COPY [[XFLOADf64_]]
; CHECK: $f1 = COPY [[LFD]]
; CHECK: BLR8 implicit $lr8, implicit $rm, implicit $f1
entry:
%arg_list = alloca i8*, align 8

156
test/CodeGen/PowerPC/build-vector-tests.ll
View File

@ -858,14 +858,14 @@ define <4 x i32> @fromDiffConstsi() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsi:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsi:
@ -927,7 +927,7 @@ define <4 x i32> @fromDiffMemConsDi(i32* nocapture readonly %arr) {
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: addis r3, r2, .LCPI7_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI7_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: blr
;
@ -1022,11 +1022,11 @@ define <4 x i32> @fromDiffMemVarDi(i32* nocapture readonly %arr, i32 signext %el
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: sldi r4, r4, 2
; P9BE-NEXT: add r3, r3, r4
; P9BE-NEXT: addi r3, r3, -12
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: li r4, -12
; P9BE-NEXT: lxvx v2, r3, r4
; P9BE-NEXT: addis r3, r2, .LCPI9_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI9_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: blr
;
@ -1034,11 +1034,11 @@ define <4 x i32> @fromDiffMemVarDi(i32* nocapture readonly %arr, i32 signext %el
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: sldi r4, r4, 2
; P9LE-NEXT: add r3, r3, r4
; P9LE-NEXT: addi r3, r3, -12
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: li r4, -12
; P9LE-NEXT: lxvx v2, r3, r4
; P9LE-NEXT: addis r3, r2, .LCPI9_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI9_0@toc@l
; P9LE-NEXT: lxvx v3, 0, r3
; P9LE-NEXT: lxv v3, 0(r3)
; P9LE-NEXT: vperm v2, v2, v2, v3
; P9LE-NEXT: blr
;
@ -1383,14 +1383,14 @@ define <4 x i32> @fromDiffConstsConvftoi() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI16_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI16_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvftoi:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI16_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI16_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvftoi:
@ -1448,7 +1448,7 @@ define <4 x i32> @fromDiffMemConsDConvftoi(float* nocapture readonly %ptr) {
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: addis r3, r2, .LCPI18_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI18_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: xvcvspsxws v2, v2
; P9BE-NEXT: blr
@ -1458,7 +1458,7 @@ define <4 x i32> @fromDiffMemConsDConvftoi(float* nocapture readonly %ptr) {
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: addis r3, r2, .LCPI18_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI18_0@toc@l
; P9LE-NEXT: lxvx v3, 0, r3
; P9LE-NEXT: lxv v3, 0(r3)
; P9LE-NEXT: vperm v2, v2, v2, v3
; P9LE-NEXT: xvcvspsxws v2, v2
; P9LE-NEXT: blr
@ -1837,14 +1837,14 @@ define <4 x i32> @fromDiffConstsConvdtoi() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI25_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI25_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvdtoi:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI25_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI25_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvdtoi:
@ -1953,23 +1953,23 @@ define <4 x i32> @fromDiffMemConsDConvdtoi(double* nocapture readonly %ptr) {
;
; P8BE-LABEL: fromDiffMemConsDConvdtoi:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f3, 0, r3
; P8BE-NEXT: lfd f0, 24(r3)
; P8BE-NEXT: lfd f1, 8(r3)
; P8BE-NEXT: lfd f2, 16(r3)
; P8BE-NEXT: lfd f0, 16(r3)
; P8BE-NEXT: lfd f1, 0(r3)
; P8BE-NEXT: lfd f2, 24(r3)
; P8BE-NEXT: lfd f3, 8(r3)
; P8BE-NEXT: xxmrghd vs0, vs0, vs1
; P8BE-NEXT: xxmrghd vs1, vs2, vs3
; P8BE-NEXT: xvcvdpsxws v2, vs0
; P8BE-NEXT: xvcvdpsxws v3, vs1
; P8BE-NEXT: vmrgew v2, v2, v3
; P8BE-NEXT: vmrgew v2, v3, v2
; P8BE-NEXT: blr
;
; P8LE-LABEL: fromDiffMemConsDConvdtoi:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f3, 0, r3
; P8LE-NEXT: lfd f0, 24(r3)
; P8LE-NEXT: lfd f1, 8(r3)
; P8LE-NEXT: lfd f2, 16(r3)
; P8LE-NEXT: lfd f3, 0(r3)
; P8LE-NEXT: xxmrghd vs0, vs1, vs0
; P8LE-NEXT: xxmrghd vs1, vs3, vs2
; P8LE-NEXT: xvcvdpsxws v2, vs0
@ -2377,14 +2377,14 @@ define <4 x i32> @fromDiffConstsui() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI37_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI37_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsui:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI37_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI37_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsui:
@ -2446,7 +2446,7 @@ define <4 x i32> @fromDiffMemConsDui(i32* nocapture readonly %arr) {
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: addis r3, r2, .LCPI39_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI39_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: blr
;
@ -2541,11 +2541,11 @@ define <4 x i32> @fromDiffMemVarDui(i32* nocapture readonly %arr, i32 signext %e
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: sldi r4, r4, 2
; P9BE-NEXT: add r3, r3, r4
; P9BE-NEXT: addi r3, r3, -12
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: li r4, -12
; P9BE-NEXT: lxvx v2, r3, r4
; P9BE-NEXT: addis r3, r2, .LCPI41_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI41_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: blr
;
@ -2553,11 +2553,11 @@ define <4 x i32> @fromDiffMemVarDui(i32* nocapture readonly %arr, i32 signext %e
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: sldi r4, r4, 2
; P9LE-NEXT: add r3, r3, r4
; P9LE-NEXT: addi r3, r3, -12
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: li r4, -12
; P9LE-NEXT: lxvx v2, r3, r4
; P9LE-NEXT: addis r3, r2, .LCPI41_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI41_0@toc@l
; P9LE-NEXT: lxvx v3, 0, r3
; P9LE-NEXT: lxv v3, 0(r3)
; P9LE-NEXT: vperm v2, v2, v2, v3
; P9LE-NEXT: blr
;
@ -2902,14 +2902,14 @@ define <4 x i32> @fromDiffConstsConvftoui() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI48_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI48_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvftoui:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI48_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI48_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvftoui:
@ -2967,7 +2967,7 @@ define <4 x i32> @fromDiffMemConsDConvftoui(float* nocapture readonly %ptr) {
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: addis r3, r2, .LCPI50_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI50_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: vperm v2, v2, v2, v3
; P9BE-NEXT: xvcvspuxws v2, v2
; P9BE-NEXT: blr
@ -2977,7 +2977,7 @@ define <4 x i32> @fromDiffMemConsDConvftoui(float* nocapture readonly %ptr) {
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: addis r3, r2, .LCPI50_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI50_0@toc@l
; P9LE-NEXT: lxvx v3, 0, r3
; P9LE-NEXT: lxv v3, 0(r3)
; P9LE-NEXT: vperm v2, v2, v2, v3
; P9LE-NEXT: xvcvspuxws v2, v2
; P9LE-NEXT: blr
@ -3357,14 +3357,14 @@ define <4 x i32> @fromDiffConstsConvdtoui() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI57_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI57_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvdtoui:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI57_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI57_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvdtoui:
@ -3473,23 +3473,23 @@ define <4 x i32> @fromDiffMemConsDConvdtoui(double* nocapture readonly %ptr) {
;
; P8BE-LABEL: fromDiffMemConsDConvdtoui:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f3, 0, r3
; P8BE-NEXT: lfd f0, 24(r3)
; P8BE-NEXT: lfd f1, 8(r3)
; P8BE-NEXT: lfd f2, 16(r3)
; P8BE-NEXT: lfd f0, 16(r3)
; P8BE-NEXT: lfd f1, 0(r3)
; P8BE-NEXT: lfd f2, 24(r3)
; P8BE-NEXT: lfd f3, 8(r3)
; P8BE-NEXT: xxmrghd vs0, vs0, vs1
; P8BE-NEXT: xxmrghd vs1, vs2, vs3
; P8BE-NEXT: xvcvdpuxws v2, vs0
; P8BE-NEXT: xvcvdpuxws v3, vs1
; P8BE-NEXT: vmrgew v2, v2, v3
; P8BE-NEXT: vmrgew v2, v3, v2
; P8BE-NEXT: blr
;
; P8LE-LABEL: fromDiffMemConsDConvdtoui:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f3, 0, r3
; P8LE-NEXT: lfd f0, 24(r3)
; P8LE-NEXT: lfd f1, 8(r3)
; P8LE-NEXT: lfd f2, 16(r3)
; P8LE-NEXT: lfd f3, 0(r3)
; P8LE-NEXT: xxmrghd vs0, vs1, vs0
; P8LE-NEXT: xxmrghd vs1, vs3, vs2
; P8LE-NEXT: xvcvdpuxws v2, vs0
@ -3777,14 +3777,14 @@ define <2 x i64> @spltConst1ll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI65_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI65_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst1ll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI65_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI65_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst1ll:
@ -3810,14 +3810,14 @@ define <2 x i64> @spltConst16kll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI66_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI66_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst16kll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI66_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI66_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst16kll:
@ -3843,14 +3843,14 @@ define <2 x i64> @spltConst32kll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI67_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI67_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst32kll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI67_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI67_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst32kll:
@ -3906,14 +3906,14 @@ define <2 x i64> @fromDiffConstsll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI69_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI69_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI69_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI69_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsll:
@ -4240,14 +4240,14 @@ define <2 x i64> @spltCnstConvftoll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI78_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI78_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltCnstConvftoll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI78_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI78_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltCnstConvftoll:
@ -4313,14 +4313,14 @@ define <2 x i64> @fromDiffConstsConvftoll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI80_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI80_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvftoll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI80_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI80_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvftoll:
@ -4360,7 +4360,7 @@ define <2 x i64> @fromDiffMemConsAConvftoll(float* nocapture readonly %ptr) {
;
; P8BE-LABEL: fromDiffMemConsAConvftoll:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfsx f0, 0, r3
; P8BE-NEXT: lfs f0, 0(r3)
; P8BE-NEXT: lfs f1, 4(r3)
; P8BE-NEXT: xxmrghd vs0, vs0, vs1
; P8BE-NEXT: xvcvdpsxds v2, vs0
@ -4368,7 +4368,7 @@ define <2 x i64> @fromDiffMemConsAConvftoll(float* nocapture readonly %ptr) {
;
; P8LE-LABEL: fromDiffMemConsAConvftoll:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfsx f0, 0, r3
; P8LE-NEXT: lfs f0, 0(r3)
; P8LE-NEXT: lfs f1, 4(r3)
; P8LE-NEXT: xxmrghd vs0, vs1, vs0
; P8LE-NEXT: xvcvdpsxds v2, vs0
@ -4602,14 +4602,14 @@ define <2 x i64> @spltCnstConvdtoll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI87_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI87_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltCnstConvdtoll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI87_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI87_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltCnstConvdtoll:
@ -4675,14 +4675,14 @@ define <2 x i64> @fromDiffConstsConvdtoll() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI89_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI89_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvdtoll:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI89_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI89_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvdtoll:
@ -4965,14 +4965,14 @@ define <2 x i64> @spltConst1ull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI97_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI97_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst1ull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI97_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI97_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst1ull:
@ -4998,14 +4998,14 @@ define <2 x i64> @spltConst16kull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI98_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI98_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst16kull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI98_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI98_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst16kull:
@ -5031,14 +5031,14 @@ define <2 x i64> @spltConst32kull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI99_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI99_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltConst32kull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI99_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI99_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltConst32kull:
@ -5094,14 +5094,14 @@ define <2 x i64> @fromDiffConstsull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI101_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI101_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI101_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI101_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsull:
@ -5428,14 +5428,14 @@ define <2 x i64> @spltCnstConvftoull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI110_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI110_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltCnstConvftoull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI110_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI110_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltCnstConvftoull:
@ -5501,14 +5501,14 @@ define <2 x i64> @fromDiffConstsConvftoull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI112_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI112_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvftoull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI112_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI112_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvftoull:
@ -5548,7 +5548,7 @@ define <2 x i64> @fromDiffMemConsAConvftoull(float* nocapture readonly %ptr) {
;
; P8BE-LABEL: fromDiffMemConsAConvftoull:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfsx f0, 0, r3
; P8BE-NEXT: lfs f0, 0(r3)
; P8BE-NEXT: lfs f1, 4(r3)
; P8BE-NEXT: xxmrghd vs0, vs0, vs1
; P8BE-NEXT: xvcvdpuxds v2, vs0
@ -5556,7 +5556,7 @@ define <2 x i64> @fromDiffMemConsAConvftoull(float* nocapture readonly %ptr) {
;
; P8LE-LABEL: fromDiffMemConsAConvftoull:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfsx f0, 0, r3
; P8LE-NEXT: lfs f0, 0(r3)
; P8LE-NEXT: lfs f1, 4(r3)
; P8LE-NEXT: xxmrghd vs0, vs1, vs0
; P8LE-NEXT: xvcvdpuxds v2, vs0
@ -5790,14 +5790,14 @@ define <2 x i64> @spltCnstConvdtoull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI119_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI119_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: spltCnstConvdtoull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI119_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI119_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: spltCnstConvdtoull:
@ -5863,14 +5863,14 @@ define <2 x i64> @fromDiffConstsConvdtoull() {
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: addis r3, r2, .LCPI121_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI121_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r3
; P9BE-NEXT: lxv v2, 0(r3)
; P9BE-NEXT: blr
;
; P9LE-LABEL: fromDiffConstsConvdtoull:
; P9LE: # %bb.0: # %entry
; P9LE-NEXT: addis r3, r2, .LCPI121_0@toc@ha
; P9LE-NEXT: addi r3, r3, .LCPI121_0@toc@l
; P9LE-NEXT: lxvx v2, 0, r3
; P9LE-NEXT: lxv v2, 0(r3)
; P9LE-NEXT: blr
;
; P8BE-LABEL: fromDiffConstsConvdtoull:

4
test/CodeGen/PowerPC/builtins-ppc-p9-f128.ll
View File

@ -112,7 +112,7 @@ entry:
ret fp128 %2
; CHECK-LABEL: insert_exp_qp
; CHECK-DAG: mtfprd [[FPREG:f[0-9]+]], r3
; CHECK-DAG: lxvx [[VECREG:v[0-9]+]]
; CHECK-DAG: lxv [[VECREG:v[0-9]+]]
; CHECK: xsiexpqp v2, [[VECREG]], [[FPREG]]
; CHECK: blr
}
@ -127,7 +127,7 @@ entry:
%1 = call i64 @llvm.ppc.scalar.extract.expq(fp128 %0)
ret i64 %1
; CHECK-LABEL: extract_exp
; CHECK: lxvx [[VECIN:v[0-9]+]]
; CHECK: lxv [[VECIN:v[0-9]+]]
; CHECK: xsxexpqp [[VECOUT:v[0-9]+]], [[VECIN]]
; CHECK: mfvsrd r3, [[VECOUT]]
; CHECK: blr

14
test/CodeGen/PowerPC/canonical-merge-shuffles.ll
View File

@ -421,7 +421,7 @@ define dso_local <8 x i16> @testmrglb3(<8 x i8>* nocapture readonly %a) local_un
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI12_0@toc@ha
; CHECK-P9-BE-NEXT: xxlxor v4, v4, v4
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI12_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-BE-NEXT: blr
;
@ -596,7 +596,7 @@ define dso_local <4 x i32> @replace_undefs_in_splat(<4 x i32> %a) local_unnamed_
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI15_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI15_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vmrgow v2, v3, v2
; CHECK-P9-NEXT: blr
;
@ -604,10 +604,10 @@ define dso_local <4 x i32> @replace_undefs_in_splat(<4 x i32> %a) local_unnamed_
; CHECK-P9-BE: # %bb.0: # %entry
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI15_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI15_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI15_1@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI15_1@toc@l
; CHECK-P9-BE-NEXT: lxvx v4, 0, r3
; CHECK-P9-BE-NEXT: lxv v4, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v4, v3
; CHECK-P9-BE-NEXT: blr
;
@ -656,7 +656,7 @@ define dso_local <16 x i8> @no_RAUW_in_combine_during_legalize(i32* nocapture re
; CHECK-P9-NEXT: lxsiwzx v2, r3, r4
; CHECK-P9-NEXT: addis r3, r2, .LCPI16_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI16_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: blr
;
@ -841,14 +841,14 @@ define dso_local void @testByteSplat() #0 {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lxsibzx v2, 0, r3
; CHECK-P9-NEXT: vspltb v2, v2, 7
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P9-BE-LABEL: testByteSplat:
; CHECK-P9-BE: # %bb.0: # %entry
; CHECK-P9-BE-NEXT: lxsibzx v2, 0, r3
; CHECK-P9-BE-NEXT: vspltb v2, v2, 7
; CHECK-P9-BE-NEXT: stxvx v2, 0, r3
; CHECK-P9-BE-NEXT: stxv v2, 0(r3)
; CHECK-P9-BE-NEXT: blr
;
; CHECK-NOVSX-LABEL: testByteSplat:

26
test/CodeGen/PowerPC/constant-pool.ll
View File

@ -72,7 +72,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret fp128 0xL00000000000000003C00FFFFC5D02B3A
@ -88,7 +88,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <16 x i8> <i8 -128, i8 -127, i8 -126, i8 -125, i8 -124, i8 -123, i8 -122, i8 -121, i8 -120, i8 -119, i8 -118, i8 -117, i8 -116, i8 -115, i8 -114, i8 -113>
@ -104,7 +104,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <8 x i16> <i16 -32768, i16 -32767, i16 -32766, i16 -32765, i16 -32764, i16 -32763, i16 -32762, i16 -32761>
@ -120,7 +120,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI6_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI6_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <4 x i32> <i32 -2147483648, i32 -2147483647, i32 -2147483646, i32 -2147483645>
@ -136,7 +136,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI7_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI7_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <2 x i64> <i64 -9223372036854775808, i64 -9223372036854775807>
@ -152,7 +152,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI8_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI8_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <1 x i128> <i128 -27670116110564327424>
@ -168,7 +168,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI9_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI9_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <4 x float> <float 0x380FFFF840000000, float 0x380FFF57C0000000, float 0x3843FFFB20000000, float 0x3843FF96C0000000>
@ -184,7 +184,7 @@ entry:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI10_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI10_0@toc@l
; CHECK-P9-NEXT: lxvx vs34, 0, r3
; CHECK-P9-NEXT: lxv vs34, 0(r3)
; CHECK-P9-NEXT: blr
entry:
ret <2 x double> <double 2.225070e-308, double 2.225000e-308>
@ -337,15 +337,15 @@ define fp128 @three_constants_f128(fp128 %a, fp128 %c) {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI15_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI15_0@toc@l
; CHECK-P9-NEXT: lxvx vs35, 0, r3
; CHECK-P9-NEXT: lxv vs35, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LCPI15_1@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI15_1@toc@l
; CHECK-P9-NEXT: xsaddqp v2, v2, v3
; CHECK-P9-NEXT: lxvx vs35, 0, r3
; CHECK-P9-NEXT: lxv vs35, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LCPI15_2@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI15_2@toc@l
; CHECK-P9-NEXT: xsaddqp v2, v2, v3
; CHECK-P9-NEXT: lxvx vs35, 0, r3
; CHECK-P9-NEXT: lxv vs35, 0(r3)
; CHECK-P9-NEXT: xsaddqp v2, v2, v3
; CHECK-P9-NEXT: blr
entry:
@ -433,10 +433,10 @@ define <2 x double> @three_constants_vector(<2 x double> %a, <2 x double> %c) {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LCPI17_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI17_0@toc@l
; CHECK-P9-NEXT: lxvx vs0, 0, r3
; CHECK-P9-NEXT: lxv vs0, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LCPI17_1@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI17_1@toc@l
; CHECK-P9-NEXT: lxvx vs2, 0, r3
; CHECK-P9-NEXT: lxv vs2, 0(r3)
; CHECK-P9-NEXT: xvadddp vs1, vs34, vs0
; CHECK-P9-NEXT: xvadddp vs1, vs1, vs2
; CHECK-P9-NEXT: xvadddp vs34, vs1, vs0

4
test/CodeGen/PowerPC/ctrloop-constrained-fp.ll
View File

@ -23,7 +23,7 @@ define void @test(double* %cast) {
; CHECK-NEXT: bl cos
; CHECK-NEXT: nop
; CHECK-NEXT: addi 30, 30, 8
; CHECK-NEXT: stfdx 1, 0, 29
; CHECK-NEXT: stfd 1, 0(29)
; CHECK-NEXT: cmpldi 30, 2040
; CHECK-NEXT: bne 0, .LBB0_1
; CHECK-NEXT: # %bb.2: # %exit
@ -62,7 +62,7 @@ define void @test2(double* %cast) {
; CHECK-NEXT: #
; CHECK-NEXT: lfdu 0, 8(3)
; CHECK-NEXT: xssqrtdp 0, 0
; CHECK-NEXT: stfdx 0, 0, 3
; CHECK-NEXT: stfd 0, 0(3)
; CHECK-NEXT: bdnz .LBB1_1
; CHECK-NEXT: # %bb.2: # %exit
; CHECK-NEXT: blr

2
test/CodeGen/PowerPC/extract-and-store.ll
View File

@ -599,7 +599,7 @@ define dso_local void @test_stores_exceed_vec_size(<4 x i32> %a, i32* nocapture
; CHECK-P9-NEXT: addis r3, r2, .LCPI16_0@toc@ha
; CHECK-P9-NEXT: xxsldwi vs0, vs34, vs34, 1
; CHECK-P9-NEXT: addi r3, r3, .LCPI16_0@toc@l
; CHECK-P9-NEXT: lxvx vs35, 0, r3
; CHECK-P9-NEXT: lxv vs35, 0(r3)
; CHECK-P9-NEXT: li r3, 16
; CHECK-P9-NEXT: stfiwx f0, r5, r3
; CHECK-P9-NEXT: li r3, 20

4
test/CodeGen/PowerPC/f128-aggregates.ll
View File

@ -541,7 +541,7 @@ define fp128 @sum_float128(i32 signext %count, ...) {
; CHECK-NEXT: std r6, 56(r1)
; CHECK-NEXT: std r7, 64(r1)
; CHECK-NEXT: std r8, 72(r1)
; CHECK-NEXT: lxvx v2, 0, r4
; CHECK-NEXT: lxv v2, 0(r4)
; CHECK-NEXT: std r9, 80(r1)
; CHECK-NEXT: std r10, 88(r1)
; CHECK-NEXT: bltlr cr0
@ -565,7 +565,7 @@ define fp128 @sum_float128(i32 signext %count, ...) {
; CHECK-BE-NEXT: std r6, 72(r1)
; CHECK-BE-NEXT: std r7, 80(r1)
; CHECK-BE-NEXT: std r8, 88(r1)
; CHECK-BE-NEXT: lxvx v2, 0, r4
; CHECK-BE-NEXT: lxv v2, 0(r4)
; CHECK-BE-NEXT: std r9, 96(r1)
; CHECK-BE-NEXT: std r10, 104(r1)
; CHECK-BE-NEXT: bltlr cr0

12
test/CodeGen/PowerPC/f128-arith.ll
View File

@ -152,10 +152,10 @@ entry:
define dso_local void @testLdNSt(i8* nocapture readonly %PtrC, fp128* nocapture %PtrF) {
; CHECK-LABEL: testLdNSt:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 4
; CHECK-NEXT: addi r4, r4, 8
; CHECK-NEXT: lxvx vs0, 0, r3
; CHECK-NEXT: stxvx vs0, 0, r4
; CHECK-NEXT: li r5, 4
; CHECK-NEXT: lxvx vs0, r3, r5
; CHECK-NEXT: li r3, 8
; CHECK-NEXT: stxvx vs0, r4, r3
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: testLdNSt:
@ -784,10 +784,10 @@ define fp128 @qp_frem() #0 {
; CHECK-NEXT: .cfi_offset lr, 16
; CHECK-NEXT: addis r3, r2, a@toc@ha
; CHECK-NEXT: addi r3, r3, a@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b@toc@ha
; CHECK-NEXT: addi r3, r3, b@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: bl fmodf128
; CHECK-NEXT: nop
; CHECK-NEXT: addi r1, r1, 32

60
test/CodeGen/PowerPC/f128-compare.ll
View File

@ -15,10 +15,10 @@ define dso_local signext i32 @greater_qp() {
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: iselgt r3, r4, r3
@ -61,10 +61,10 @@ define dso_local signext i32 @less_qp() {
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: isellt r3, r4, r3
@ -104,10 +104,10 @@ define dso_local signext i32 @greater_eq_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: cror 4*cr5+lt, un, lt
@ -149,10 +149,10 @@ define dso_local signext i32 @less_eq_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: cror 4*cr5+lt, un, gt
@ -197,10 +197,10 @@ define dso_local signext i32 @equal_qp() {
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: iseleq r3, r4, r3
@ -241,10 +241,10 @@ define dso_local signext i32 @not_greater_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: iselgt r3, 0, r3
@ -288,10 +288,10 @@ define dso_local signext i32 @not_less_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: isellt r3, 0, r3
@ -333,10 +333,10 @@ define dso_local signext i32 @not_greater_eq_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: crnor 4*cr5+lt, lt, un
@ -378,10 +378,10 @@ define dso_local signext i32 @not_less_eq_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: crnor 4*cr5+lt, gt, un
@ -425,10 +425,10 @@ define dso_local signext i32 @not_equal_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: li r3, 1
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: iseleq r3, 0, r3
@ -470,10 +470,10 @@ define fp128 @greater_sel_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: bgtlr cr0
; CHECK-NEXT: # %bb.1: # %entry
@ -531,10 +531,10 @@ define fp128 @less_sel_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: bltlr cr0
; CHECK-NEXT: # %bb.1: # %entry
@ -592,10 +592,10 @@ define fp128 @greater_eq_sel_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: crnor 4*cr5+lt, un, lt
; CHECK-NEXT: bclr 12, 4*cr5+lt, 0
@ -654,10 +654,10 @@ define fp128 @less_eq_sel_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: crnor 4*cr5+lt, un, gt
; CHECK-NEXT: bclr 12, 4*cr5+lt, 0
@ -716,10 +716,10 @@ define fp128 @equal_sel_qp() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, a_qp@toc@ha
; CHECK-NEXT: addi r3, r3, a_qp@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: addis r3, r2, b_qp@toc@ha
; CHECK-NEXT: addi r3, r3, b_qp@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xscmpuqp cr0, v2, v3
; CHECK-NEXT: beqlr cr0
; CHECK-NEXT: # %bb.1: # %entry

26
test/CodeGen/PowerPC/f128-conv.ll
View File

@ -1144,7 +1144,7 @@ define void @qpConv2dp_02(double* nocapture %res) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-NEXT: lxvx v2, 0, r4
; CHECK-NEXT: lxv v2, 0(r4)
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: stxsd v2, 0(r3)
; CHECK-NEXT: blr
@ -1164,7 +1164,7 @@ define void @qpConv2dp_02(double* nocapture %res) {
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfdx f1, 0, r30
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -1184,7 +1184,7 @@ define void @qpConv2dp_03(double* nocapture %res, i32 signext %idx) {
; CHECK-NEXT: addis r5, r2, .LC7@toc@ha
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: ld r5, .LC7@toc@l(r5)
; CHECK-NEXT: lxvx v2, 0, r5
; CHECK-NEXT: lxv v2, 0(r5)
; CHECK-NEXT: xscvqpdp v2, v2
; CHECK-NEXT: stxsdx v2, r3, r4
; CHECK-NEXT: blr
@ -1251,7 +1251,7 @@ define void @qpConv2dp_04(fp128* nocapture readonly %a, fp128* nocapture readonl
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfdx f1, 0, r30
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -1303,7 +1303,7 @@ define void @qpConv2sp_02(float* nocapture %res) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r4, r2, .LC6@toc@ha
; CHECK-NEXT: ld r4, .LC6@toc@l(r4)
; CHECK-NEXT: lxvx v2, 0, r4
; CHECK-NEXT: lxv v2, 0(r4)
; CHECK-NEXT: xscvqpdpo v2, v2
; CHECK-NEXT: xsrsp f0, v2
; CHECK-NEXT: stfs f0, 0(r3)
@ -1324,7 +1324,7 @@ define void @qpConv2sp_02(float* nocapture %res) {
; CHECK-P8-NEXT: lvx v2, 0, r4
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfsx f1, 0, r30
; CHECK-P8-NEXT: stfs f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -1414,7 +1414,7 @@ define void @qpConv2sp_04(fp128* nocapture readonly %a, fp128* nocapture readonl
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: bl __trunckfsf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: stfsx f1, 0, r30
; CHECK-P8-NEXT: stfs f1, 0(r30)
; CHECK-P8-NEXT: addi r1, r1, 48
; CHECK-P8-NEXT: ld r0, 16(r1)
; CHECK-P8-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -1465,7 +1465,7 @@ define void @dpConv2qp_02(double* nocapture readonly %a) {
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_02:
@ -1475,7 +1475,7 @@ define void @dpConv2qp_02(double* nocapture readonly %a) {
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lfdx f1, 0, r3
; CHECK-P8-NEXT: lfd f1, 0(r3)
; CHECK-P8-NEXT: bl __extenddfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
@ -1501,7 +1501,7 @@ define void @dpConv2qp_02b(double* nocapture readonly %a, i32 signext %idx) {
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: dpConv2qp_02b:
@ -1639,7 +1639,7 @@ define void @spConv2qp_02(float* nocapture readonly %a) {
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_02:
@ -1649,7 +1649,7 @@ define void @spConv2qp_02(float* nocapture readonly %a) {
; CHECK-P8-NEXT: stdu r1, -32(r1)
; CHECK-P8-NEXT: .cfi_def_cfa_offset 32
; CHECK-P8-NEXT: .cfi_offset lr, 16
; CHECK-P8-NEXT: lfsx f1, 0, r3
; CHECK-P8-NEXT: lfs f1, 0(r3)
; CHECK-P8-NEXT: bl __extendsfkf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: addis r3, r2, .LC8@toc@ha
@ -1675,7 +1675,7 @@ define void @spConv2qp_02b(float* nocapture readonly %a, i32 signext %idx) {
; CHECK-NEXT: addis r3, r2, .LC8@toc@ha
; CHECK-NEXT: ld r3, .LC8@toc@l(r3)
; CHECK-NEXT: xscvdpqp v2, v2
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: spConv2qp_02b:

10
test/CodeGen/PowerPC/f128-passByValue.ll
View File

@ -11,7 +11,7 @@ define fp128 @loadConstant() {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LABEL: loadConstant:
@ -31,7 +31,7 @@ define fp128 @loadConstant2(fp128 %a, fp128 %b) {
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-NEXT: lxvx v3, 0, r3
; CHECK-NEXT: lxv v3, 0(r3)
; CHECK-NEXT: xsaddqp v2, v2, v3
; CHECK-NEXT: blr
;
@ -554,7 +554,7 @@ define void @mixParam_03(fp128 %f1, double* nocapture %d1, <4 x i32> %vec1,
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ld r3, 104(r1)
; CHECK-NEXT: stxv v2, 0(r9)
; CHECK-NEXT: stxvx v3, 0, r3
; CHECK-NEXT: stxv v3, 0(r3)
; CHECK-NEXT: mtvsrwa v3, r10
; CHECK-NEXT: lxv v2, 0(r9)
; CHECK-NEXT: xscvsdqp v3, v3
@ -590,7 +590,7 @@ define void @mixParam_03(fp128 %f1, double* nocapture %d1, <4 x i32> %vec1,
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r3, 48
; CHECK-P8-NEXT: stfdx f1, 0, r30
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: ld r30, 64(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: lvx v31, r1, r3 # 16-byte Folded Reload
; CHECK-P8-NEXT: addi r1, r1, 80
@ -650,7 +650,7 @@ define fastcc void @mixParam_03f(fp128 %f1, double* nocapture %d1, <4 x i32> %ve
; CHECK-P8-NEXT: bl __trunckfdf2
; CHECK-P8-NEXT: nop
; CHECK-P8-NEXT: li r3, 48
; CHECK-P8-NEXT: stfdx f1, 0, r30
; CHECK-P8-NEXT: stfd f1, 0(r30)
; CHECK-P8-NEXT: ld r30, 64(r1) # 8-byte Folded Reload
; CHECK-P8-NEXT: lvx v31, r1, r3 # 16-byte Folded Reload
; CHECK-P8-NEXT: addi r1, r1, 80

2
test/CodeGen/PowerPC/f128-truncateNconv.ll
View File

@ -392,7 +392,7 @@ define void @qpConv2udw_testXForm(i64* nocapture %res, i32 signext %idx) {
; CHECK-NEXT: addis r5, r2, .LC0@toc@ha
; CHECK-NEXT: sldi r4, r4, 3
; CHECK-NEXT: ld r5, .LC0@toc@l(r5)
; CHECK-NEXT: lxvx v2, 0, r5
; CHECK-NEXT: lxv v2, 0(r5)
; CHECK-NEXT: xscvqpudz v2, v2
; CHECK-NEXT: stxsdx v2, r3, r4
; CHECK-NEXT: blr

96
test/CodeGen/PowerPC/f128_ldst.ll
View File

@ -31,8 +31,8 @@ entry:
define dso_local fp128 @ld_unalign16___float128___float128(i8* nocapture readonly %ptr) {
; CHECK-LABEL: ld_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 1
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%add.ptr = getelementptr inbounds i8, i8* %ptr, i64 1
@ -45,8 +45,8 @@ entry:
define dso_local fp128 @ld_align16___float128___float128(i8* nocapture readonly %ptr) {
; CHECK-LABEL: ld_align16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 8
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 8
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%add.ptr = getelementptr inbounds i8, i8* %ptr, i64 8
@ -163,7 +163,7 @@ define dso_local fp128 @ld_or___float128___float128(i64 %ptr, i8 zeroext %off) {
; CHECK-LABEL: ld_or___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: or r3, r4, r3
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%conv = zext i8 %off to i64
@ -194,7 +194,7 @@ define dso_local fp128 @ld_not_disjoint16___float128___float128(i64 %ptr) {
; CHECK-LABEL: ld_not_disjoint16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%or = or i64 %ptr, 6
@ -208,8 +208,8 @@ define dso_local fp128 @ld_disjoint_unalign16___float128___float128(i64 %ptr) {
; CHECK-LABEL: ld_disjoint_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 6
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%and = and i64 %ptr, -4096
@ -224,8 +224,8 @@ define dso_local fp128 @ld_disjoint_align16___float128___float128(i64 %ptr) {
; CHECK-LABEL: ld_disjoint_align16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 24
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 24
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%and = and i64 %ptr, -4096
@ -241,7 +241,7 @@ define dso_local fp128 @ld_not_disjoint32___float128___float128(i64 %ptr) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 34463
; CHECK-NEXT: oris r3, r3, 1
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%or = or i64 %ptr, 99999
@ -308,7 +308,7 @@ define dso_local fp128 @ld_not_disjoint64___float128___float128(i64 %ptr) {
; CHECK-P10-NEXT: pli r5, 3567587329
; CHECK-P10-NEXT: rldimi r5, r4, 32, 0
; CHECK-P10-NEXT: or r3, r3, r5
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: ld_not_disjoint64___float128___float128:
@ -318,7 +318,7 @@ define dso_local fp128 @ld_not_disjoint64___float128___float128(i64 %ptr) {
; CHECK-PREP10-NEXT: oris r4, r4, 54437
; CHECK-PREP10-NEXT: ori r4, r4, 4097
; CHECK-PREP10-NEXT: or r3, r3, r4
; CHECK-PREP10-NEXT: lxvx v2, 0, r3
; CHECK-PREP10-NEXT: lxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%or = or i64 %ptr, 1000000000001
@ -386,7 +386,7 @@ define dso_local fp128 @ld_cst_unalign16___float128___float128() {
; CHECK-LABEL: ld_cst_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li r3, 255
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%0 = load fp128, fp128* inttoptr (i64 255 to fp128*), align 16
@ -409,14 +409,14 @@ define dso_local fp128 @ld_cst_unalign32___float128___float128() {
; CHECK-P10-LABEL: ld_cst_unalign32___float128___float128:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 99999
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: ld_cst_unalign32___float128___float128:
; CHECK-PREP10: # %bb.0: # %entry
; CHECK-PREP10-NEXT: lis r3, 1
; CHECK-PREP10-NEXT: ori r3, r3, 34463
; CHECK-PREP10-NEXT: lxvx v2, 0, r3
; CHECK-PREP10-NEXT: lxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%0 = load fp128, fp128* inttoptr (i64 99999 to fp128*), align 16
@ -428,14 +428,14 @@ define dso_local fp128 @ld_cst_align32___float128___float128() {
; CHECK-P10-LABEL: ld_cst_align32___float128___float128:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 9999900
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: ld_cst_align32___float128___float128:
; CHECK-PREP10: # %bb.0: # %entry
; CHECK-PREP10-NEXT: lis r3, 152
; CHECK-PREP10-NEXT: ori r3, r3, 38428
; CHECK-PREP10-NEXT: lxvx v2, 0, r3
; CHECK-PREP10-NEXT: lxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%0 = load fp128, fp128* inttoptr (i64 9999900 to fp128*), align 16
@ -449,7 +449,7 @@ define dso_local fp128 @ld_cst_unalign64___float128___float128() {
; CHECK-P10-NEXT: pli r3, 232
; CHECK-P10-NEXT: pli r4, 3567587329
; CHECK-P10-NEXT: rldimi r4, r3, 32, 0
; CHECK-P10-NEXT: lxvx v2, 0, r4
; CHECK-P10-NEXT: lxv v2, 0(r4)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: ld_cst_unalign64___float128___float128:
@ -458,7 +458,7 @@ define dso_local fp128 @ld_cst_unalign64___float128___float128() {
; CHECK-PREP10-NEXT: rldic r3, r3, 35, 24
; CHECK-PREP10-NEXT: oris r3, r3, 54437
; CHECK-PREP10-NEXT: ori r3, r3, 4097
; CHECK-PREP10-NEXT: lxvx v2, 0, r3
; CHECK-PREP10-NEXT: lxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%0 = load fp128, fp128* inttoptr (i64 1000000000001 to fp128*), align 16
@ -471,7 +471,7 @@ define dso_local fp128 @ld_cst_align64___float128___float128() {
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 244140625
; CHECK-P10-NEXT: rldic r3, r3, 12, 24
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: ld_cst_align64___float128___float128:
@ -479,7 +479,7 @@ define dso_local fp128 @ld_cst_align64___float128___float128() {
; CHECK-PREP10-NEXT: lis r3, 3725
; CHECK-PREP10-NEXT: ori r3, r3, 19025
; CHECK-PREP10-NEXT: rldic r3, r3, 12, 24
; CHECK-PREP10-NEXT: lxvx v2, 0, r3
; CHECK-PREP10-NEXT: lxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%0 = load fp128, fp128* inttoptr (i64 1000000000000 to fp128*), align 4096
@ -502,8 +502,8 @@ entry:
define dso_local void @st_unalign16___float128___float128(i8* nocapture %ptr, fp128 %str) {
; CHECK-LABEL: st_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 1
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%add.ptr = getelementptr inbounds i8, i8* %ptr, i64 1
@ -516,8 +516,8 @@ entry:
define dso_local void @st_align16___float128___float128(i8* nocapture %ptr, fp128 %str) {
; CHECK-LABEL: st_align16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 8
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 8
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%add.ptr = getelementptr inbounds i8, i8* %ptr, i64 8
@ -634,7 +634,7 @@ define dso_local void @st_or1___float128___float128(i64 %ptr, i8 zeroext %off, f
; CHECK-LABEL: st_or1___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: or r3, r4, r3
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%conv = zext i8 %off to i64
@ -665,7 +665,7 @@ define dso_local void @st_not_disjoint16___float128___float128(i64 %ptr, fp128 %
; CHECK-LABEL: st_not_disjoint16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%or = or i64 %ptr, 6
@ -679,8 +679,8 @@ define dso_local void @st_disjoint_unalign16___float128___float128(i64 %ptr, fp1
; CHECK-LABEL: st_disjoint_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 6
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%and = and i64 %ptr, -4096
@ -695,8 +695,8 @@ define dso_local void @st_disjoint_align16___float128___float128(i64 %ptr, fp128
; CHECK-LABEL: st_disjoint_align16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 24
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 24
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
entry:
%and = and i64 %ptr, -4096
@ -712,7 +712,7 @@ define dso_local void @st_not_disjoint32___float128___float128(i64 %ptr, fp128 %
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 34463
; CHECK-NEXT: oris r3, r3, 1
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%or = or i64 %ptr, 99999
@ -779,7 +779,7 @@ define dso_local void @st_not_disjoint64___float128___float128(i64 %ptr, fp128 %
; CHECK-P10-NEXT: pli r5, 3567587329
; CHECK-P10-NEXT: rldimi r5, r4, 32, 0
; CHECK-P10-NEXT: or r3, r3, r5
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: st_not_disjoint64___float128___float128:
@ -789,7 +789,7 @@ define dso_local void @st_not_disjoint64___float128___float128(i64 %ptr, fp128 %
; CHECK-PREP10-NEXT: oris r4, r4, 54437
; CHECK-PREP10-NEXT: ori r4, r4, 4097
; CHECK-PREP10-NEXT: or r3, r3, r4
; CHECK-PREP10-NEXT: stxvx v2, 0, r3
; CHECK-PREP10-NEXT: stxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%or = or i64 %ptr, 1000000000001
@ -857,7 +857,7 @@ define dso_local void @st_cst_unalign16___float128___float128(fp128 %str) {
; CHECK-LABEL: st_cst_unalign16___float128___float128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li r3, 255
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
store fp128 %str, fp128* inttoptr (i64 255 to fp128*), align 16
@ -880,14 +880,14 @@ define dso_local void @st_cst_unalign32___float128___float128(fp128 %str) {
; CHECK-P10-LABEL: st_cst_unalign32___float128___float128:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 99999
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: st_cst_unalign32___float128___float128:
; CHECK-PREP10: # %bb.0: # %entry
; CHECK-PREP10-NEXT: lis r3, 1
; CHECK-PREP10-NEXT: ori r3, r3, 34463
; CHECK-PREP10-NEXT: stxvx v2, 0, r3
; CHECK-PREP10-NEXT: stxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
store fp128 %str, fp128* inttoptr (i64 99999 to fp128*), align 16
@ -899,14 +899,14 @@ define dso_local void @st_cst_align32___float128___float128(fp128 %str) {
; CHECK-P10-LABEL: st_cst_align32___float128___float128:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 9999900
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: st_cst_align32___float128___float128:
; CHECK-PREP10: # %bb.0: # %entry
; CHECK-PREP10-NEXT: lis r3, 152
; CHECK-PREP10-NEXT: ori r3, r3, 38428
; CHECK-PREP10-NEXT: stxvx v2, 0, r3
; CHECK-PREP10-NEXT: stxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
store fp128 %str, fp128* inttoptr (i64 9999900 to fp128*), align 16
@ -920,7 +920,7 @@ define dso_local void @st_cst_unalign64___float128___float128(fp128 %str) {
; CHECK-P10-NEXT: pli r3, 232
; CHECK-P10-NEXT: pli r4, 3567587329
; CHECK-P10-NEXT: rldimi r4, r3, 32, 0
; CHECK-P10-NEXT: stxvx v2, 0, r4
; CHECK-P10-NEXT: stxv v2, 0(r4)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: st_cst_unalign64___float128___float128:
@ -929,7 +929,7 @@ define dso_local void @st_cst_unalign64___float128___float128(fp128 %str) {
; CHECK-PREP10-NEXT: rldic r3, r3, 35, 24
; CHECK-PREP10-NEXT: oris r3, r3, 54437
; CHECK-PREP10-NEXT: ori r3, r3, 4097
; CHECK-PREP10-NEXT: stxvx v2, 0, r3
; CHECK-PREP10-NEXT: stxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
store fp128 %str, fp128* inttoptr (i64 1000000000001 to fp128*), align 16
@ -942,7 +942,7 @@ define dso_local void @st_cst_align64___float128___float128(fp128 %str) {
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 244140625
; CHECK-P10-NEXT: rldic r3, r3, 12, 24
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-PREP10-LABEL: st_cst_align64___float128___float128:
@ -950,7 +950,7 @@ define dso_local void @st_cst_align64___float128___float128(fp128 %str) {
; CHECK-PREP10-NEXT: lis r3, 3725
; CHECK-PREP10-NEXT: ori r3, r3, 19025
; CHECK-PREP10-NEXT: rldic r3, r3, 12, 24
; CHECK-PREP10-NEXT: stxvx v2, 0, r3
; CHECK-PREP10-NEXT: stxv v2, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
store fp128 %str, fp128* inttoptr (i64 1000000000000 to fp128*), align 4096
@ -969,20 +969,20 @@ define dso_local void @testGlob128PtrPlus0() {
; CHECK-P10-BE: # %bb.0: # %entry
; CHECK-P10-BE-NEXT: addis r3, r2, GlobLd128@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobLd128@toc@l
; CHECK-P10-BE-NEXT: lxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: lxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: addis r3, r2, GlobSt128@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobSt128@toc@l
; CHECK-P10-BE-NEXT: stxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: stxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: blr
;
; CHECK-PREP10-LABEL: testGlob128PtrPlus0:
; CHECK-PREP10: # %bb.0: # %entry
; CHECK-PREP10-NEXT: addis r3, r2, GlobLd128@toc@ha
; CHECK-PREP10-NEXT: addi r3, r3, GlobLd128@toc@l
; CHECK-PREP10-NEXT: lxvx vs0, 0, r3
; CHECK-PREP10-NEXT: lxv vs0, 0(r3)
; CHECK-PREP10-NEXT: addis r3, r2, GlobSt128@toc@ha
; CHECK-PREP10-NEXT: addi r3, r3, GlobSt128@toc@l
; CHECK-PREP10-NEXT: stxvx vs0, 0, r3
; CHECK-PREP10-NEXT: stxv vs0, 0(r3)
; CHECK-PREP10-NEXT: blr
entry:
%0 = load fp128, fp128* getelementptr inbounds ([20 x fp128], [20 x fp128]* @GlobLd128, i64 0, i64 0), align 16

2
test/CodeGen/PowerPC/fast-isel-load-store-vsx.ll
View File

@ -17,7 +17,7 @@ entry:
%this.addr = alloca %SomeStruct*, align 8
%V.addr = alloca double, align 8
store %SomeStruct* %this, %SomeStruct** %this.addr, align 8
; ELF64VSX: stfdx {{[0-9][0-9]?}}, 0, {{[1-9][0-9]?}}
; ELF64VSX: stfd {{[0-9][0-9]?}}, -{{[1-9][0-9]?}}({{[1-9][0-9]?}})
store double %V, double* %V.addr, align 8
%this1 = load %SomeStruct*, %SomeStruct** %this.addr
%Val = getelementptr inbounds %SomeStruct, %SomeStruct* %this1, i32 0, i32 0

4
test/CodeGen/PowerPC/float-load-store-pair.ll
View File

@ -42,8 +42,8 @@ define dso_local signext i32 @test() nounwind {
; CHECK-NEXT: ld 4, a15@toc@l(4)
; CHECK-NEXT: lfd 2, a2@toc@l(3)
; CHECK-NEXT: addis 3, 2, a3@toc@ha
; CHECK-NEXT: lxvx 34, 0, 6
; CHECK-NEXT: lxvx 0, 0, 5
; CHECK-NEXT: lxv 34, 0(6)
; CHECK-NEXT: lxv 0, 0(5)
; CHECK-NEXT: li 5, 152
; CHECK-NEXT: lfd 3, a3@toc@l(3)
; CHECK-NEXT: addis 3, 2, a4@toc@ha

20
test/CodeGen/PowerPC/fma-combine.ll
View File

@ -142,11 +142,11 @@ define dso_local float @fma_combine_no_ice() {
; CHECK-FAST-LABEL: fma_combine_no_ice:
; CHECK-FAST: # %bb.0:
; CHECK-FAST-NEXT: addis 3, 2, .LCPI4_0@toc@ha
; CHECK-FAST-NEXT: addis 4, 2, .LCPI4_1@toc@ha
; CHECK-FAST-NEXT: lfs 0, .LCPI4_0@toc@l(3)
; CHECK-FAST-NEXT: lfsx 2, 0, 3
; CHECK-FAST-NEXT: addis 3, 2, .LCPI4_1@toc@ha
; CHECK-FAST-NEXT: lfs 2, 0(3)
; CHECK-FAST-NEXT: lfs 3, .LCPI4_1@toc@l(3)
; CHECK-FAST-NEXT: addis 3, 2, .LCPI4_2@toc@ha
; CHECK-FAST-NEXT: lfs 3, .LCPI4_1@toc@l(4)
; CHECK-FAST-NEXT: lfs 1, .LCPI4_2@toc@l(3)
; CHECK-FAST-NEXT: xsmaddasp 3, 2, 0
; CHECK-FAST-NEXT: xsmaddasp 1, 2, 3
@ -170,11 +170,11 @@ define dso_local float @fma_combine_no_ice() {
; CHECK-LABEL: fma_combine_no_ice:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI4_0@toc@ha
; CHECK-NEXT: addis 4, 2, .LCPI4_1@toc@ha
; CHECK-NEXT: lfs 0, .LCPI4_0@toc@l(3)
; CHECK-NEXT: lfsx 2, 0, 3
; CHECK-NEXT: addis 3, 2, .LCPI4_1@toc@ha
; CHECK-NEXT: lfs 2, 0(3)
; CHECK-NEXT: lfs 3, .LCPI4_1@toc@l(3)
; CHECK-NEXT: addis 3, 2, .LCPI4_2@toc@ha
; CHECK-NEXT: lfs 3, .LCPI4_1@toc@l(4)
; CHECK-NEXT: lfs 1, .LCPI4_2@toc@l(3)
; CHECK-NEXT: fmr 4, 3
; CHECK-NEXT: xsmaddasp 3, 2, 0
@ -202,9 +202,9 @@ define dso_local double @getNegatedExpression_crash(double %x, double %y) {
; CHECK-FAST-LABEL: getNegatedExpression_crash:
; CHECK-FAST: # %bb.0:
; CHECK-FAST-NEXT: addis 3, 2, .LCPI5_1@toc@ha
; CHECK-FAST-NEXT: addis 4, 2, .LCPI5_0@toc@ha
; CHECK-FAST-NEXT: lfs 3, .LCPI5_1@toc@l(3)
; CHECK-FAST-NEXT: lfs 4, .LCPI5_0@toc@l(4)
; CHECK-FAST-NEXT: addis 3, 2, .LCPI5_0@toc@ha
; CHECK-FAST-NEXT: lfs 4, .LCPI5_0@toc@l(3)
; CHECK-FAST-NEXT: xssubdp 0, 1, 3
; CHECK-FAST-NEXT: xsmaddadp 3, 1, 4
; CHECK-FAST-NEXT: xsmaddadp 0, 3, 2
@ -225,9 +225,9 @@ define dso_local double @getNegatedExpression_crash(double %x, double %y) {
; CHECK-LABEL: getNegatedExpression_crash:
; CHECK: # %bb.0:
; CHECK-NEXT: addis 3, 2, .LCPI5_1@toc@ha
; CHECK-NEXT: addis 4, 2, .LCPI5_0@toc@ha
; CHECK-NEXT: lfs 3, .LCPI5_1@toc@l(3)
; CHECK-NEXT: lfs 4, .LCPI5_0@toc@l(4)
; CHECK-NEXT: addis 3, 2, .LCPI5_0@toc@ha
; CHECK-NEXT: lfs 4, .LCPI5_0@toc@l(3)
; CHECK-NEXT: xssubdp 0, 1, 3
; CHECK-NEXT: xsmaddadp 3, 1, 4
; CHECK-NEXT: xsmaddadp 0, 3, 2

32
test/CodeGen/PowerPC/fmf-propagation.ll
View File

@ -311,9 +311,9 @@ define float @sqrt_afn_ieee(float %x) #0 {
; FMF-NEXT: # %bb.1:
; FMF-NEXT: xsrsqrtesp 0, 1
; FMF-NEXT: addis 3, 2, .LCPI11_0@toc@ha
; FMF-NEXT: addis 4, 2, .LCPI11_1@toc@ha
; FMF-NEXT: lfs 2, .LCPI11_0@toc@l(3)
; FMF-NEXT: lfs 3, .LCPI11_1@toc@l(4)
; FMF-NEXT: addis 3, 2, .LCPI11_1@toc@ha
; FMF-NEXT: lfs 3, .LCPI11_1@toc@l(3)
; FMF-NEXT: xsmulsp 1, 1, 0
; FMF-NEXT: xsmulsp 0, 1, 0
; FMF-NEXT: xsmulsp 1, 1, 2
@ -334,9 +334,9 @@ define float @sqrt_afn_ieee(float %x) #0 {
; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 0, 1
; GLOBAL-NEXT: addis 3, 2, .LCPI11_0@toc@ha
; GLOBAL-NEXT: addis 4, 2, .LCPI11_1@toc@ha
; GLOBAL-NEXT: lfs 2, .LCPI11_0@toc@l(3)
; GLOBAL-NEXT: lfs 3, .LCPI11_1@toc@l(4)
; GLOBAL-NEXT: addis 3, 2, .LCPI11_1@toc@ha
; GLOBAL-NEXT: lfs 3, .LCPI11_1@toc@l(3)
; GLOBAL-NEXT: xsmulsp 1, 1, 0
; GLOBAL-NEXT: xsmaddasp 2, 1, 0
; GLOBAL-NEXT: xsmulsp 0, 1, 3
@ -379,9 +379,9 @@ define float @sqrt_afn_preserve_sign(float %x) #1 {
; FMF-NEXT: # %bb.1:
; FMF-NEXT: xsrsqrtesp 0, 1
; FMF-NEXT: addis 3, 2, .LCPI13_0@toc@ha
; FMF-NEXT: addis 4, 2, .LCPI13_1@toc@ha
; FMF-NEXT: lfs 2, .LCPI13_0@toc@l(3)
; FMF-NEXT: lfs 3, .LCPI13_1@toc@l(4)
; FMF-NEXT: addis 3, 2, .LCPI13_1@toc@ha
; FMF-NEXT: lfs 3, .LCPI13_1@toc@l(3)
; FMF-NEXT: xsmulsp 1, 1, 0
; FMF-NEXT: xsmulsp 0, 1, 0
; FMF-NEXT: xsmulsp 1, 1, 2
@ -399,9 +399,9 @@ define float @sqrt_afn_preserve_sign(float %x) #1 {
; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 0, 1
; GLOBAL-NEXT: addis 3, 2, .LCPI13_0@toc@ha
; GLOBAL-NEXT: addis 4, 2, .LCPI13_1@toc@ha
; GLOBAL-NEXT: lfs 2, .LCPI13_0@toc@l(3)
; GLOBAL-NEXT: lfs 3, .LCPI13_1@toc@l(4)
; GLOBAL-NEXT: addis 3, 2, .LCPI13_1@toc@ha
; GLOBAL-NEXT: lfs 3, .LCPI13_1@toc@l(3)
; GLOBAL-NEXT: xsmulsp 1, 1, 0
; GLOBAL-NEXT: xsmaddasp 2, 1, 0
; GLOBAL-NEXT: xsmulsp 0, 1, 3
@ -449,9 +449,9 @@ define float @sqrt_fast_ieee(float %x) #0 {
; FMF-NEXT: # %bb.1:
; FMF-NEXT: xsrsqrtesp 0, 1
; FMF-NEXT: addis 3, 2, .LCPI15_0@toc@ha
; FMF-NEXT: addis 4, 2, .LCPI15_1@toc@ha
; FMF-NEXT: lfs 2, .LCPI15_0@toc@l(3)
; FMF-NEXT: lfs 3, .LCPI15_1@toc@l(4)
; FMF-NEXT: addis 3, 2, .LCPI15_1@toc@ha
; FMF-NEXT: lfs 3, .LCPI15_1@toc@l(3)
; FMF-NEXT: xsmulsp 1, 1, 0
; FMF-NEXT: xsmaddasp 2, 1, 0
; FMF-NEXT: xsmulsp 0, 1, 3
@ -471,9 +471,9 @@ define float @sqrt_fast_ieee(float %x) #0 {
; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 0, 1
; GLOBAL-NEXT: addis 3, 2, .LCPI15_0@toc@ha
; GLOBAL-NEXT: addis 4, 2, .LCPI15_1@toc@ha
; GLOBAL-NEXT: lfs 2, .LCPI15_0@toc@l(3)
; GLOBAL-NEXT: lfs 3, .LCPI15_1@toc@l(4)
; GLOBAL-NEXT: addis 3, 2, .LCPI15_1@toc@ha
; GLOBAL-NEXT: lfs 3, .LCPI15_1@toc@l(3)
; GLOBAL-NEXT: xsmulsp 1, 1, 0
; GLOBAL-NEXT: xsmaddasp 2, 1, 0
; GLOBAL-NEXT: xsmulsp 0, 1, 3
@ -504,9 +504,9 @@ define float @sqrt_fast_preserve_sign(float %x) #1 {
; FMF-NEXT: # %bb.1:
; FMF-NEXT: xsrsqrtesp 0, 1
; FMF-NEXT: addis 3, 2, .LCPI16_0@toc@ha
; FMF-NEXT: addis 4, 2, .LCPI16_1@toc@ha
; FMF-NEXT: lfs 2, .LCPI16_0@toc@l(3)
; FMF-NEXT: lfs 3, .LCPI16_1@toc@l(4)
; FMF-NEXT: addis 3, 2, .LCPI16_1@toc@ha
; FMF-NEXT: lfs 3, .LCPI16_1@toc@l(3)
; FMF-NEXT: xsmulsp 1, 1, 0
; FMF-NEXT: xsmaddasp 2, 1, 0
; FMF-NEXT: xsmulsp 0, 1, 3
@ -523,9 +523,9 @@ define float @sqrt_fast_preserve_sign(float %x) #1 {
; GLOBAL-NEXT: # %bb.1:
; GLOBAL-NEXT: xsrsqrtesp 0, 1
; GLOBAL-NEXT: addis 3, 2, .LCPI16_0@toc@ha
; GLOBAL-NEXT: addis 4, 2, .LCPI16_1@toc@ha
; GLOBAL-NEXT: lfs 2, .LCPI16_0@toc@l(3)
; GLOBAL-NEXT: lfs 3, .LCPI16_1@toc@l(4)
; GLOBAL-NEXT: addis 3, 2, .LCPI16_1@toc@ha
; GLOBAL-NEXT: lfs 3, .LCPI16_1@toc@l(3)
; GLOBAL-NEXT: xsmulsp 1, 1, 0
; GLOBAL-NEXT: xsmaddasp 2, 1, 0
; GLOBAL-NEXT: xsmulsp 0, 1, 3

2
test/CodeGen/PowerPC/fp-strict-conv-f128.ll
View File

@ -617,8 +617,8 @@ define zeroext i32 @ppcq_to_u32(ppc_fp128 %m) #0 {
; P8-NEXT: xxlxor f3, f3, f3
; P8-NEXT: std r30, 112(r1) # 8-byte Folded Spill
; P8-NEXT: lfs f0, .LCPI13_0@toc@l(r3)
; P8-NEXT: fcmpo cr0, f2, f3
; P8-NEXT: lis r3, -32768
; P8-NEXT: fcmpo cr0, f2, f3
; P8-NEXT: xxlxor f3, f3, f3
; P8-NEXT: fcmpo cr1, f1, f0
; P8-NEXT: crand 4*cr5+lt, 4*cr1+eq, lt

6
test/CodeGen/PowerPC/fp128-bitcast-after-operation.ll
View File

@ -45,12 +45,12 @@ entry:
; PPC64-DAG: stfd 2, [[OFFSET_HI:-?[0-9]+]]([[SP:[0-9]+]])
; PPC64-DAG: stfd 1, [[OFFSET_LO:-?[0-9]+]]([[SP]])
; PPC64-DAG: li [[FLIP_BIT:[0-9]+]], 1
; PPC64-DAG: rldic [[FLIP_BIT]], [[FLIP_BIT]], 63, 0
; PPC64-DAG: rldic [[RES:[0-9]+]], [[FLIP_BIT]], 63, 0
; PPC64-DAG: ld [[HI:[0-9]+]], [[OFFSET_LO]]([[SP]])
; PPC64-DAG: ld [[LO:[0-9]+]], [[OFFSET_HI]]([[SP]])
; PPC64-NOT: BARRIER
; PPC64-DAG: xor 3, [[HI]], [[FLIP_BIT]]
; PPC64-DAG: xor 4, [[LO]], [[FLIP_BIT]]
; PPC64-DAG: xor 3, [[HI]], [[RES]]
; PPC64-DAG: xor 4, [[LO]], [[RES]]
; PPC64: blr
; PPC64-P8-LABEL: test_neg:

2
test/CodeGen/PowerPC/instr-properties.ll
View File

@ -3,7 +3,7 @@
; Verify XFLOADf64 didn't implict def 'rm'.
define double @rm() {
; CHECK-P8-LABEL: bb.0.entry
; CHECK-P8: %{{[0-9]+}}:vsfrc = XFLOADf64 $zero8, %{{[0-9]+}} ::
; CHECK-P8: %{{[0-9]+}}:f8rc = LFD target-flags(ppc-toc-lo) %const.0, %{{[0-9]+}}, implicit $x2 ::
entry:
ret double 2.300000e+00
}

24
test/CodeGen/PowerPC/load-shuffle-and-shuffle-store.ll
View File

@ -96,7 +96,7 @@ define <4 x i32> @load_swap10(<4 x i32>* %vp1, <4 x i32>* %vp2) {
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <4 x i32>, <4 x i32>* %vp1
@ -134,7 +134,7 @@ define <4 x i32> @load_swap11(<4 x i32>* %vp1, <4 x i32>* %vp2) {
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; CHECK-P9-BE-NEXT: lxv v2, 0(r4)
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI3_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <4 x i32>, <4 x i32>* %vp1
@ -172,7 +172,7 @@ define <8 x i16> @load_swap20(<8 x i16>* %vp1, <8 x i16>* %vp2){
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <8 x i16>, <8 x i16>* %vp1
@ -210,7 +210,7 @@ define <8 x i16> @load_swap21(<8 x i16>* %vp1, <8 x i16>* %vp2){
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-P9-BE-NEXT: lxv v2, 0(r4)
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <8 x i16>, <8 x i16>* %vp1
@ -346,7 +346,7 @@ define <4 x float> @load_swap50(<4 x float>* %vp1, <4 x float>* %vp2) {
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI9_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI9_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <4 x float>, <4 x float>* %vp1
@ -384,7 +384,7 @@ define <4 x float> @load_swap51(<4 x float>* %vp1, <4 x float>* %vp2) {
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI10_0@toc@ha
; CHECK-P9-BE-NEXT: lxv v2, 0(r4)
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI10_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: blr
%v1 = load <4 x float>, <4 x float>* %vp1
@ -475,7 +475,7 @@ define void @swap_store10(<4 x i32> %v1, <4 x i32> %v2, <4 x i32>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI13_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI13_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr
@ -512,7 +512,7 @@ define void @swap_store11(<4 x i32> %v1, <4 x i32> %v2, <4 x i32>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI14_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI14_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v2, 0, r3
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v3, v3, v2
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr
@ -549,7 +549,7 @@ define void @swap_store20(<8 x i16> %v1, <8 x i16> %v2, <8 x i16>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI15_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI15_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr
@ -586,7 +586,7 @@ define void @swap_store21(<8 x i16> %v1, <8 x i16> %v2, <8 x i16>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI16_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI16_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v2, 0, r3
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v3, v3, v2
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr
@ -745,7 +745,7 @@ define void @swap_store50(<4 x float> %v1, <4 x float> %v2, <4 x float>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI21_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI21_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v3, 0, r3
; CHECK-P9-BE-NEXT: lxv v3, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr
@ -782,7 +782,7 @@ define void @swap_store51(<4 x float> %v1, <4 x float> %v2, <4 x float>* %vp) {
; CHECK-P9-BE: # %bb.0:
; CHECK-P9-BE-NEXT: addis r3, r2, .LCPI22_0@toc@ha
; CHECK-P9-BE-NEXT: addi r3, r3, .LCPI22_0@toc@l
; CHECK-P9-BE-NEXT: lxvx v2, 0, r3
; CHECK-P9-BE-NEXT: lxv v2, 0(r3)
; CHECK-P9-BE-NEXT: vperm v2, v3, v3, v2
; CHECK-P9-BE-NEXT: stxv v2, 0(r7)
; CHECK-P9-BE-NEXT: blr

2
test/CodeGen/PowerPC/lxv-aligned-stack-slots.ll
View File

@ -1,4 +1,4 @@
; RUN: llc -O3 -ppc-late-peephole=false -o - %s | FileCheck %s
; RUN: llc -O3 -ppc-late-peephole=false -ppc-convert-rr-to-ri=false -o - %s | FileCheck %s
target datalayout = "e-m:e-i64:64-n32:64"
target triple = "powerpc64le-unknown-linux-gnu"

4
test/CodeGen/PowerPC/mcm-4.ll
View File

@ -33,7 +33,7 @@ entry:
; MEDIUM-VSX: .quad 0x3f4fd4920b498cf0
; MEDIUM-VSX-LABEL: test_double_const:
; MEDIUM-VSX: addis [[REG1:[0-9]+]], 2, [[VAR]]@toc@ha
; MEDIUM-VSX: lfd {{[0-9]+}}, [[VAR]]@toc@l([[REG1]])
; MEDIUM-VSX: lfd {{[0-9]+}}, 0({{[0-9]+}})
; LARGE: [[VAR:[a-z0-9A-Z_.]+]]:
; LARGE: .quad 0x3f4fd4920b498cf0
@ -47,7 +47,7 @@ entry:
; LARGE-VSX-LABEL: test_double_const:
; LARGE-VSX: addis [[REG1:[0-9]+]], 2, [[VAR2:[a-z0-9A-Z_.]+]]@toc@ha
; LARGE-VSX: ld [[REG2:[0-9]+]], [[VAR2]]@toc@l([[REG1]])
; LARGE-VSX: lfdx {{[0-9]+}}, 0, [[REG2]]
; LARGE-VSX: lfd {{[0-9]+}}, 0({{[0-9]+}})
; MEDIUM-P9: [[VAR:[a-z0-9A-Z_.]+]]:
; MEDIUM-P9: .quad 0x3f4fd4920b498cf0

4
test/CodeGen/PowerPC/mma-acc-spill.ll
View File

@ -46,7 +46,7 @@ define void @intrinsics1(<16 x i8> %vc1, <16 x i8> %vc2, <16 x i8> %vc3, <16 x i
; CHECK-NEXT: stxv vs0, 48(r30)
; CHECK-NEXT: stxv vs1, 32(r30)
; CHECK-NEXT: stxv vs2, 16(r30)
; CHECK-NEXT: stxvx vs3, 0, r30
; CHECK-NEXT: stxv vs3, 0(r30)
; CHECK-NEXT: addi r1, r1, 176
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -88,7 +88,7 @@ define void @intrinsics1(<16 x i8> %vc1, <16 x i8> %vc2, <16 x i8> %vc3, <16 x i
; CHECK-BE-NEXT: xvf16ger2pp acc0, v2, v4
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r30)
; CHECK-BE-NEXT: stxvx vs0, 0, r30
; CHECK-BE-NEXT: stxv vs0, 0(r30)
; CHECK-BE-NEXT: stxv vs3, 48(r30)
; CHECK-BE-NEXT: stxv vs2, 32(r30)
; CHECK-BE-NEXT: ld r30, 240(r1) # 8-byte Folded Reload

4
test/CodeGen/PowerPC/mma-outer-product.ll
View File

@ -31,7 +31,7 @@ define void @intrinsics1(<16 x i8> %vc1, <16 x i8> %vc2, <16 x i8> %vc3, <16 x i
; CHECK-NEXT: stxv vs0, 48(r3)
; CHECK-NEXT: stxv vs1, 32(r3)
; CHECK-NEXT: stxv vs2, 16(r3)
; CHECK-NEXT: stxvx vs3, 0, r3
; CHECK-NEXT: stxv vs3, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-BE-LABEL: intrinsics1:
@ -54,7 +54,7 @@ define void @intrinsics1(<16 x i8> %vc1, <16 x i8> %vc2, <16 x i8> %vc3, <16 x i
; CHECK-BE-NEXT: pmxvf64gernp acc0, vsp34, v0, 0, 0
; CHECK-BE-NEXT: xxmfacc acc0
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: stxvx vs0, 0, r3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: stxv vs3, 48(r3)
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: blr

16
test/CodeGen/PowerPC/mul-const-vector.ll
View File

@ -277,7 +277,7 @@ define <2 x i64> @test1_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test1_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v{{[0-9]+}}, v2, v[[REG2]]
@ -289,7 +289,7 @@ define <2 x i64> @test2_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test2_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-NEXT: vaddudm v{{[0-9]+}}, v2, v[[REG3]]
@ -302,7 +302,7 @@ define <2 x i64> @test3_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test3_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-NEXT: vsubudm v{{[0-9]+}}, v[[REG3]], v2
@ -317,7 +317,7 @@ define <2 x i64> @test4_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test4_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-P8-NEXT: xxlxor v[[REG4:[0-9]+]],
@ -332,7 +332,7 @@ define <2 x i64> @test5_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test5_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-NEXT: vaddudm v[[REG4:[0-9]+]], v2, v[[REG3]]
@ -348,7 +348,7 @@ define <2 x i64> @test6_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test6_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-NEXT: vsubudm v{{[0-9]+}}, v2, v[[REG3]]
@ -364,7 +364,7 @@ define <2 x i64> @test7_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test7_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG4:[0-9]+]], v2, v[[REG2]]
@ -376,7 +376,7 @@ define <2 x i64> @test8_v2i64(<2 x i64> %a) {
; CHECK-LABEL: test8_v2i64:
; CHECK-P8: lxvd2x vs[[REG1:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P8-NEXT: xxswapd v[[REG2:[0-9]+]], vs[[REG1]]
; CHECK-P9: lxvx v[[REG2:[0-9]+]], 0, r{{[0-9]+}}
; CHECK-P9: lxv v[[REG2:[0-9]+]], 0(r{{[0-9]+}})
; CHECK-NOT: vmul
; CHECK-NEXT: vsld v[[REG3:[0-9]+]], v2, v[[REG2]]
; CHECK-NEXT: vsubudm v{{[0-9]+}}, v[[REG3]], v2

2
test/CodeGen/PowerPC/non-debug-mi-search-frspxsrsp.ll
View File

@ -9,7 +9,7 @@ define dso_local void @test(float* nocapture readonly %Fptr, <4 x float>* nocapt
; CHECK-NEXT: addis 5, 2, .LCPI0_0@toc@ha
; CHECK-NEXT: .Ltmp0:
; CHECK-NEXT: .loc 1 2 38 prologue_end
; CHECK-NEXT: lfsx 0, 0, 3
; CHECK-NEXT: lfs 0, 0(3)
; CHECK-NEXT: addis 3, 2, .LCPI0_1@toc@ha
; CHECK-NEXT: .Ltmp1:
; CHECK-NEXT: .loc 1 0 38 is_stmt 0

6
test/CodeGen/PowerPC/p10-splatImm-CPload-pcrel.ll
View File

@ -37,7 +37,7 @@ define dso_local <2 x double> @testDoubleToDoubleFail() local_unnamed_addr {
; CHECK-NOPREFIX: # %bb.0: # %entry
; CHECK-NOPREFIX-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-NOPREFIX-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-NOPREFIX-NEXT: lxvx vs34, 0, r3
; CHECK-NOPREFIX-NEXT: lxv vs34, 0(r3)
; CHECK-NOPREFIX-NEXT: blr
;
; CHECK-BE-LABEL: testDoubleToDoubleFail:
@ -72,7 +72,7 @@ define dso_local <2 x double> @testFloatDenormToDouble() local_unnamed_addr {
; CHECK-NOPREFIX: # %bb.0: # %entry
; CHECK-NOPREFIX-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-NOPREFIX-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-NOPREFIX-NEXT: lxvx vs34, 0, r3
; CHECK-NOPREFIX-NEXT: lxv vs34, 0(r3)
; CHECK-NOPREFIX-NEXT: blr
;
; CHECK-BE-LABEL: testFloatDenormToDouble:
@ -107,7 +107,7 @@ define dso_local <2 x double> @testDoubleToDoubleNaNFail() local_unnamed_addr {
; CHECK-NOPREFIX: # %bb.0: # %entry
; CHECK-NOPREFIX-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-NOPREFIX-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-NOPREFIX-NEXT: lxvx vs34, 0, r3
; CHECK-NOPREFIX-NEXT: lxv vs34, 0(r3)
; CHECK-NOPREFIX-NEXT: blr
;
; CHECK-BE-LABEL: testDoubleToDoubleNaNFail:

6
test/CodeGen/PowerPC/p10-vector-rotate.ll
View File

@ -34,7 +34,7 @@ define <1 x i128> @test_vrlq_cost_mult8(<1 x i128> %x) {
; CHECK-BE: # %bb.0:
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vrlq v2, v3, v2
; CHECK-BE-NEXT: blr
%shl.i = shl <1 x i128> <i128 16>, %x
@ -55,7 +55,7 @@ define <1 x i128> @test_vrlq_cost_non_mult8(<1 x i128> %x) {
; CHECK-BE: # %bb.0:
; CHECK-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vrlq v2, v3, v2
; CHECK-BE-NEXT: blr
%shl.i = shl <1 x i128> <i128 4>, %x
@ -90,7 +90,7 @@ define <1 x i128> @test_vrlqnm(<1 x i128> %a, <1 x i128> %b, <1 x i128> %c) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v5, 0, r3
; CHECK-BE-NEXT: lxv v5, 0(r3)
; CHECK-BE-NEXT: vperm v3, v3, v4, v5
; CHECK-BE-NEXT: vrlqnm v2, v2, v3
; CHECK-BE-NEXT: blr

48
test/CodeGen/PowerPC/p9-vinsert-vextract.ll
View File

@ -451,7 +451,7 @@ define <8 x i16> @shuffle_vector_halfword_0_4(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI16_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI16_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -464,7 +464,7 @@ define <8 x i16> @shuffle_vector_halfword_1_3(<8 x i16> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI17_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI17_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -482,7 +482,7 @@ define <8 x i16> @shuffle_vector_halfword_2_3(<8 x i16> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI18_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI18_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -505,7 +505,7 @@ define <8 x i16> @shuffle_vector_halfword_3_4(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI19_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI19_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -518,7 +518,7 @@ define <8 x i16> @shuffle_vector_halfword_4_3(<8 x i16> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI20_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI20_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -536,7 +536,7 @@ define <8 x i16> @shuffle_vector_halfword_5_3(<8 x i16> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI21_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI21_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -559,7 +559,7 @@ define <8 x i16> @shuffle_vector_halfword_6_4(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI22_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI22_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -577,7 +577,7 @@ define <8 x i16> @shuffle_vector_halfword_7_4(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI23_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI23_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1455,7 +1455,7 @@ define <16 x i8> @shuffle_vector_byte_0_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI56_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI56_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1478,7 +1478,7 @@ define <16 x i8> @shuffle_vector_byte_1_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI57_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI57_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1496,7 +1496,7 @@ define <16 x i8> @shuffle_vector_byte_2_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI58_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI58_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1509,7 +1509,7 @@ define <16 x i8> @shuffle_vector_byte_3_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI59_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI59_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1527,7 +1527,7 @@ define <16 x i8> @shuffle_vector_byte_4_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI60_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI60_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1550,7 +1550,7 @@ define <16 x i8> @shuffle_vector_byte_5_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI61_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI61_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1568,7 +1568,7 @@ define <16 x i8> @shuffle_vector_byte_6_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI62_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI62_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1586,7 +1586,7 @@ define <16 x i8> @shuffle_vector_byte_7_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI63_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI63_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1599,7 +1599,7 @@ define <16 x i8> @shuffle_vector_byte_8_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI64_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI64_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1617,7 +1617,7 @@ define <16 x i8> @shuffle_vector_byte_9_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI65_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI65_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1635,7 +1635,7 @@ define <16 x i8> @shuffle_vector_byte_10_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI66_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI66_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1658,7 +1658,7 @@ define <16 x i8> @shuffle_vector_byte_11_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI67_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI67_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1676,7 +1676,7 @@ define <16 x i8> @shuffle_vector_byte_12_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI68_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI68_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:
@ -1689,7 +1689,7 @@ define <16 x i8> @shuffle_vector_byte_13_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI69_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI69_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1707,7 +1707,7 @@ define <16 x i8> @shuffle_vector_byte_14_7(<16 x i8> %a) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addis 3, 2, .LCPI70_0@toc@ha
; CHECK-NEXT: addi 3, 3, .LCPI70_0@toc@l
; CHECK-NEXT: lxvx 35, 0, 3
; CHECK-NEXT: lxv 35, 0(3)
; CHECK-NEXT: vperm 2, 2, 2, 3
; CHECK-NEXT: blr
;
@ -1730,7 +1730,7 @@ define <16 x i8> @shuffle_vector_byte_15_8(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI71_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI71_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: blr
entry:

54
test/CodeGen/PowerPC/pcrel-linkeropt.ll
View File

@ -110,9 +110,13 @@ define dso_local void @ReadWrite128() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWrite128:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, input128@got@pcrel(0), 1
; CHECK-NEXT: lxvx vs0, 0, r3
; CHECK-NEXT: .Lpcrel4:
; CHECK-NEXT: .reloc .Lpcrel4-8,R_PPC64_PCREL_OPT,.-(.Lpcrel4-8)
; CHECK-NEXT: lxv vs0, 0(r3)
; CHECK-NEXT: pld r3, output128@got@pcrel(0), 1
; CHECK-NEXT: stxvx vs0, 0, r3
; CHECK-NEXT: .Lpcrel5:
; CHECK-NEXT: .reloc .Lpcrel5-8,R_PPC64_PCREL_OPT,.-(.Lpcrel5-8)
; CHECK-NEXT: stxv vs0, 0(r3)
; CHECK-NEXT: blr
entry:
%0 = load i128, i128* @input128, align 16
@ -124,9 +128,9 @@ define dso_local void @ReadWritef32() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWritef32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, inputf32@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel4:
; CHECK-NEXT: .Lpcrel6:
; CHECK-NEXT: xxspltidp vs1, 1078103900
; CHECK-NEXT: .reloc .Lpcrel4-8,R_PPC64_PCREL_OPT,.-(.Lpcrel4-8)
; CHECK-NEXT: .reloc .Lpcrel6-8,R_PPC64_PCREL_OPT,.-(.Lpcrel6-8)
; CHECK-NEXT: lfs f0, 0(r3)
; CHECK-NEXT: pld r3, outputf32@got@pcrel(0), 1
; CHECK-NEXT: xsaddsp f0, f0, f1
@ -143,10 +147,10 @@ define dso_local void @ReadWritef64() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWritef64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, inputf64@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel5:
; CHECK-NEXT: .Lpcrel7:
; CHECK-NEXT: xxsplti32dx vs1, 0, 1075524403
; CHECK-NEXT: xxsplti32dx vs1, 1, 858993459
; CHECK-NEXT: .reloc .Lpcrel5-8,R_PPC64_PCREL_OPT,.-(.Lpcrel5-8)
; CHECK-NEXT: .reloc .Lpcrel7-8,R_PPC64_PCREL_OPT,.-(.Lpcrel7-8)
; CHECK-NEXT: lfd f0, 0(r3)
; CHECK-NEXT: pld r3, outputf64@got@pcrel(0), 1
; CHECK-NEXT: xsadddp f0, f0, f1
@ -165,11 +169,13 @@ define dso_local void @ReadWriteVi32() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWriteVi32:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, inputVi32@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel8:
; CHECK-NEXT: li r4, 45
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: .reloc .Lpcrel8-8,R_PPC64_PCREL_OPT,.-(.Lpcrel8-8)
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: pld r3, outputVi32@got@pcrel(0), 1
; CHECK-NEXT: vinsw v2, r4, 8
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
entry:
%0 = load <4 x i32>, <4 x i32>* @inputVi32, align 16
@ -182,9 +188,13 @@ define dso_local void @ReadWriteVi64() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWriteVi64:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, inputVi64@got@pcrel(0), 1
; CHECK-NEXT: lxvx vs0, 0, r3
; CHECK-NEXT: .Lpcrel9:
; CHECK-NEXT: .reloc .Lpcrel9-8,R_PPC64_PCREL_OPT,.-(.Lpcrel9-8)
; CHECK-NEXT: lxv vs0, 0(r3)
; CHECK-NEXT: pld r3, outputVi64@got@pcrel(0), 1
; CHECK-NEXT: stxvx vs0, 0, r3
; CHECK-NEXT: .Lpcrel10:
; CHECK-NEXT: .reloc .Lpcrel10-8,R_PPC64_PCREL_OPT,.-(.Lpcrel10-8)
; CHECK-NEXT: stxv vs0, 0(r3)
; CHECK-NEXT: blr
entry:
%0 = load <2 x i64>, <2 x i64>* @inputVi64, align 16
@ -196,9 +206,9 @@ define dso_local void @ReadWriteArray() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWriteArray:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, ArrayIn@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel6:
; CHECK-NEXT: .Lpcrel11:
; CHECK-NEXT: pld r4, ArrayOut@got@pcrel(0), 1
; CHECK-NEXT: .reloc .Lpcrel6-8,R_PPC64_PCREL_OPT,.-(.Lpcrel6-8)
; CHECK-NEXT: .reloc .Lpcrel11-8,R_PPC64_PCREL_OPT,.-(.Lpcrel11-8)
; CHECK-NEXT: lwz r3, 28(r3)
; CHECK-NEXT: addi r3, r3, 42
; CHECK-NEXT: stw r3, 8(r4)
@ -229,12 +239,12 @@ define dso_local void @ReadWriteIntPtr() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWriteIntPtr:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, IntPtrIn@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel7:
; CHECK-NEXT: .Lpcrel12:
; CHECK-NEXT: pld r4, IntPtrOut@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel8:
; CHECK-NEXT: .reloc .Lpcrel7-8,R_PPC64_PCREL_OPT,.-(.Lpcrel7-8)
; CHECK-NEXT: .Lpcrel13:
; CHECK-NEXT: .reloc .Lpcrel12-8,R_PPC64_PCREL_OPT,.-(.Lpcrel12-8)
; CHECK-NEXT: ld r3, 0(r3)
; CHECK-NEXT: .reloc .Lpcrel8-8,R_PPC64_PCREL_OPT,.-(.Lpcrel8-8)
; CHECK-NEXT: .reloc .Lpcrel13-8,R_PPC64_PCREL_OPT,.-(.Lpcrel13-8)
; CHECK-NEXT: ld r4, 0(r4)
; CHECK-NEXT: lwz r5, 216(r3)
; CHECK-NEXT: lwz r3, 48(r3)
@ -258,9 +268,9 @@ define dso_local void @ReadWriteFuncPtr() local_unnamed_addr #0 {
; CHECK-LABEL: ReadWriteFuncPtr:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, FuncPtrIn@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel9:
; CHECK-NEXT: .Lpcrel14:
; CHECK-NEXT: pld r4, FuncPtrOut@got@pcrel(0), 1
; CHECK-NEXT: .reloc .Lpcrel9-8,R_PPC64_PCREL_OPT,.-(.Lpcrel9-8)
; CHECK-NEXT: .reloc .Lpcrel14-8,R_PPC64_PCREL_OPT,.-(.Lpcrel14-8)
; CHECK-NEXT: ld r3, 0(r3)
; CHECK-NEXT: std r3, 0(r4)
; CHECK-NEXT: blr
@ -288,8 +298,8 @@ define dso_local void @FuncPtrCall() local_unnamed_addr #0 {
; CHECK-LABEL: FuncPtrCall:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, FuncPtrIn@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel10:
; CHECK-NEXT: .reloc .Lpcrel10-8,R_PPC64_PCREL_OPT,.-(.Lpcrel10-8)
; CHECK-NEXT: .Lpcrel15:
; CHECK-NEXT: .reloc .Lpcrel15-8,R_PPC64_PCREL_OPT,.-(.Lpcrel15-8)
; CHECK-NEXT: ld r12, 0(r3)
; CHECK-NEXT: mtctr r12
; CHECK-NEXT: bctr
@ -304,8 +314,8 @@ define dso_local signext i32 @ReadVecElement() local_unnamed_addr #0 {
; CHECK-LABEL: ReadVecElement:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: pld r3, inputVi32@got@pcrel(0), 1
; CHECK-NEXT: .Lpcrel11:
; CHECK-NEXT: .reloc .Lpcrel11-8,R_PPC64_PCREL_OPT,.-(.Lpcrel11-8)
; CHECK-NEXT: .Lpcrel16:
; CHECK-NEXT: .reloc .Lpcrel16-8,R_PPC64_PCREL_OPT,.-(.Lpcrel16-8)
; CHECK-NEXT: lwa r3, 4(r3)
; CHECK-NEXT: blr
entry:

16
test/CodeGen/PowerPC/pcrel_ldst.ll
View File

@ -1715,20 +1715,20 @@ define dso_local void @testGlob11PtrPlus0() {
; CHECK-P10-BE: # %bb.0: # %entry
; CHECK-P10-BE-NEXT: addis r3, r2, GlobLd11@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobLd11@toc@l
; CHECK-P10-BE-NEXT: lxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: lxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: addis r3, r2, GlobSt11@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobSt11@toc@l
; CHECK-P10-BE-NEXT: stxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: stxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: blr
;
; CHECK-P9-LABEL: testGlob11PtrPlus0:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, GlobLd11@toc@ha
; CHECK-P9-NEXT: addi r3, r3, GlobLd11@toc@l
; CHECK-P9-NEXT: lxvx vs0, 0, r3
; CHECK-P9-NEXT: lxv vs0, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, GlobSt11@toc@ha
; CHECK-P9-NEXT: addi r3, r3, GlobSt11@toc@l
; CHECK-P9-NEXT: stxvx vs0, 0, r3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: testGlob11PtrPlus0:
@ -1999,20 +1999,20 @@ define dso_local void @testGlob12PtrPlus0() {
; CHECK-P10-BE: # %bb.0: # %entry
; CHECK-P10-BE-NEXT: addis r3, r2, GlobLd12@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobLd12@toc@l
; CHECK-P10-BE-NEXT: lxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: lxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: addis r3, r2, GlobSt12@toc@ha
; CHECK-P10-BE-NEXT: addi r3, r3, GlobSt12@toc@l
; CHECK-P10-BE-NEXT: stxvx vs0, 0, r3
; CHECK-P10-BE-NEXT: stxv vs0, 0(r3)
; CHECK-P10-BE-NEXT: blr
;
; CHECK-P9-LABEL: testGlob12PtrPlus0:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, GlobLd12@toc@ha
; CHECK-P9-NEXT: addi r3, r3, GlobLd12@toc@l
; CHECK-P9-NEXT: lxvx vs0, 0, r3
; CHECK-P9-NEXT: lxv vs0, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, GlobSt12@toc@ha
; CHECK-P9-NEXT: addi r3, r3, GlobSt12@toc@l
; CHECK-P9-NEXT: stxvx vs0, 0, r3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: testGlob12PtrPlus0:

8
test/CodeGen/PowerPC/ppc64-align-long-double.ll
View File

@ -33,14 +33,14 @@ define ppc_fp128 @test(%struct.S* byval(%struct.S) %x) nounwind {
;
; CHECK-VSX-LABEL: test:
; CHECK-VSX: # %bb.0: # %entry
; CHECK-VSX-NEXT: std 3, 48(1)
; CHECK-VSX-NEXT: std 6, 72(1)
; CHECK-VSX-NEXT: std 5, 64(1)
; CHECK-VSX-NEXT: std 4, 56(1)
; CHECK-VSX-NEXT: std 5, -16(1)
; CHECK-VSX-NEXT: std 6, -8(1)
; CHECK-VSX-NEXT: lfd 1, -16(1)
; CHECK-VSX-NEXT: lfd 2, -8(1)
; CHECK-VSX-NEXT: std 6, 72(1)
; CHECK-VSX-NEXT: std 5, 64(1)
; CHECK-VSX-NEXT: std 3, 48(1)
; CHECK-VSX-NEXT: std 4, 56(1)
; CHECK-VSX-NEXT: blr
;
; CHECK-P9-LABEL: test:

6
test/CodeGen/PowerPC/ppc64-i128-abi.ll
View File

@ -63,7 +63,7 @@ define <1 x i128> @v1i128_increment_by_one(<1 x i128> %a) nounwind {
; FIXME: li [[R1:r[0-9]+]], 1
; FIXME: li [[R2:r[0-9]+]], 0
; FIXME: mtvsrdd [[V1:v[0-9]+]], [[R2]], [[R1]]
; CHECK-P9: lxvx [[V1:v[0-9]+]]
; CHECK-P9: lxv [[V1:v[0-9]+]]
; CHECK-P9: vadduqm v2, v2, [[V1]]
; CHECK-P9: blr
@ -237,8 +237,8 @@ define <1 x i128> @call_v1i128_increment_by_val() nounwind {
; CHECK-LE: blr
; CHECK-P9-LABEL: @call_v1i128_increment_by_val
; CHECK-P9-DAG: lxvx v2
; CHECK-P9-DAG: lxvx v3
; CHECK-P9-DAG: lxv v2
; CHECK-P9-DAG: lxv v3
; CHECK-P9: bl v1i128_increment_by_val
; CHECK-P9: blr

12
test/CodeGen/PowerPC/ppcf128-constrained-fp-intrinsics.ll
View File

@ -1293,8 +1293,8 @@ define i32 @test_fptoui_ppc_i32_ppc_fp128(ppc_fp128 %first) #0 {
; PC64LE-NEXT: addis 3, 2, .LCPI31_0@toc@ha
; PC64LE-NEXT: xxlxor 3, 3, 3
; PC64LE-NEXT: lfs 0, .LCPI31_0@toc@l(3)
; PC64LE-NEXT: fcmpo 0, 2, 3
; PC64LE-NEXT: lis 3, -32768
; PC64LE-NEXT: fcmpo 0, 2, 3
; PC64LE-NEXT: xxlxor 3, 3, 3
; PC64LE-NEXT: fcmpo 1, 1, 0
; PC64LE-NEXT: crand 20, 6, 0
@ -1428,12 +1428,12 @@ define void @test_constrained_libcall_multichain(float* %firstptr, ppc_fp128* %r
; PC64LE-NEXT: xxlxor 2, 2, 2
; PC64LE-NEXT: li 3, 0
; PC64LE-NEXT: mr 30, 4
; PC64LE-NEXT: lfsx 31, 0, 29
; PC64LE-NEXT: lfs 31, 0(29)
; PC64LE-NEXT: xxlxor 4, 4, 4
; PC64LE-NEXT: std 3, 8(4)
; PC64LE-NEXT: fmr 1, 31
; PC64LE-NEXT: fmr 3, 31
; PC64LE-NEXT: stfdx 31, 0, 4
; PC64LE-NEXT: stfd 31, 0(4)
; PC64LE-NEXT: bl __gcc_qadd
; PC64LE-NEXT: nop
; PC64LE-NEXT: fmr 3, 1
@ -1452,7 +1452,7 @@ define void @test_constrained_libcall_multichain(float* %firstptr, ppc_fp128* %r
; PC64LE-NEXT: bl __powitf2
; PC64LE-NEXT: nop
; PC64LE-NEXT: xsrsp 0, 1
; PC64LE-NEXT: stfsx 0, 0, 29
; PC64LE-NEXT: stfs 0, 0(29)
; PC64LE-NEXT: stfd 1, -16(30)
; PC64LE-NEXT: stfd 2, -8(30)
; PC64LE-NEXT: addi 1, 1, 80
@ -1727,8 +1727,8 @@ define ppc_fp128 @u64_to_ppcq(i64 %m) #0 {
; PC64LE-NEXT: addis 3, 2, .LCPI36_0@toc@ha
; PC64LE-NEXT: xxlxor 4, 4, 4
; PC64LE-NEXT: fmr 30, 1
; PC64LE-NEXT: fmr 31, 2
; PC64LE-NEXT: lfs 3, .LCPI36_0@toc@l(3)
; PC64LE-NEXT: fmr 31, 2
; PC64LE-NEXT: bl __gcc_qadd
; PC64LE-NEXT: nop
; PC64LE-NEXT: cmpdi 30, 0
@ -1879,8 +1879,8 @@ define ppc_fp128 @u128_to_ppcq(i128 %m) #0 {
; PC64LE-NEXT: addis 3, 2, .LCPI38_0@toc@ha
; PC64LE-NEXT: xxlxor 4, 4, 4
; PC64LE-NEXT: fmr 30, 1
; PC64LE-NEXT: fmr 31, 2
; PC64LE-NEXT: lfd 3, .LCPI38_0@toc@l(3)
; PC64LE-NEXT: fmr 31, 2
; PC64LE-NEXT: bl __gcc_qadd
; PC64LE-NEXT: nop
; PC64LE-NEXT: cmpdi 30, 0

2
test/CodeGen/PowerPC/pr30715.ll
View File

@ -67,7 +67,7 @@ for.body: ; preds = %for.body.preheader,
%indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
%exitcond = icmp eq i64 %indvars.iv.next, %wide.trip.count
br i1 %exitcond, label %for.cond.cleanup.loopexit, label %for.body
; CHECK: stfdx
; CHECK: stfd
; CHECK: lxvd2x
}

4
test/CodeGen/PowerPC/pr36292.ll
View File

@ -19,12 +19,12 @@ define void @test() nounwind comdat {
; CHECK-NEXT: .p2align 5
; CHECK-NEXT: .LBB0_1: # %bounds.ok
; CHECK-NEXT: #
; CHECK-NEXT: lfsx 2, 0, 3
; CHECK-NEXT: lfs 2, 0(3)
; CHECK-NEXT: xxlxor 1, 1, 1
; CHECK-NEXT: bl fmodf
; CHECK-NEXT: nop
; CHECK-NEXT: addi 30, 30, 1
; CHECK-NEXT: stfsx 1, 0, 3
; CHECK-NEXT: stfs 1, 0(3)
; CHECK-NEXT: cmpld 30, 29
; CHECK-NEXT: blt+ 0, .LBB0_1
; CHECK-NEXT: .LBB0_2: # %bounds.fail

2
test/CodeGen/PowerPC/pr38087.ll
View File

@ -17,7 +17,7 @@ define void @draw_llvm_vs_variant0(<4 x float> %x) {
; CHECK-NEXT: xvcvsxwsp vs0, v3
; CHECK-NEXT: xxspltw vs0, vs0, 2
; CHECK-NEXT: xvmaddasp vs0, v2, v2
; CHECK-NEXT: stxvx vs0, 0, r3
; CHECK-NEXT: stxv vs0, 0(r3)
; CHECK-NEXT: blr
entry:
%.size = load i32, i32* undef

4
test/CodeGen/PowerPC/pr45628.ll
View File

@ -270,13 +270,13 @@ define <1 x i128> @NO_rotl(<1 x i128> %num) {
; P9-VSX: # %bb.0: # %entry
; P9-VSX-NEXT: addis r3, r2, .LCPI8_0@toc@ha
; P9-VSX-NEXT: addi r3, r3, .LCPI8_0@toc@l
; P9-VSX-NEXT: lxvx v3, 0, r3
; P9-VSX-NEXT: lxv v3, 0(r3)
; P9-VSX-NEXT: addis r3, r2, .LCPI8_1@toc@ha
; P9-VSX-NEXT: addi r3, r3, .LCPI8_1@toc@l
; P9-VSX-NEXT: vslo v4, v2, v3
; P9-VSX-NEXT: vspltb v3, v3, 15
; P9-VSX-NEXT: vsl v3, v4, v3
; P9-VSX-NEXT: lxvx v4, 0, r3
; P9-VSX-NEXT: lxv v4, 0(r3)
; P9-VSX-NEXT: vsro v2, v2, v4
; P9-VSX-NEXT: vspltb v4, v4, 15
; P9-VSX-NEXT: vsr v2, v2, v4

36
test/CodeGen/PowerPC/pre-inc-disable.ll
View File

@ -16,10 +16,10 @@ define signext i32 @test_pre_inc_disable_1(i8* nocapture readonly %pix1, i32 sig
; CHECK-NEXT: xxlxor v3, v3, v3
; CHECK-NEXT: li r6, 0
; CHECK-NEXT: addi r5, r5, .LCPI0_0@toc@l
; CHECK-NEXT: lxvx v2, 0, r5
; CHECK-NEXT: lxv v2, 0(r5)
; CHECK-NEXT: addis r5, r2, .LCPI0_1@toc@ha
; CHECK-NEXT: addi r5, r5, .LCPI0_1@toc@l
; CHECK-NEXT: lxvx v4, 0, r5
; CHECK-NEXT: lxv v4, 0(r5)
; CHECK-NEXT: li r5, 4
; CHECK-NEXT: vperm v0, v3, v5, v2
; CHECK-NEXT: mtctr r5
@ -72,10 +72,10 @@ define signext i32 @test_pre_inc_disable_1(i8* nocapture readonly %pix1, i32 sig
; P9BE-NEXT: xxlxor v3, v3, v3
; P9BE-NEXT: li r6, 0
; P9BE-NEXT: addi r5, r5, .LCPI0_0@toc@l
; P9BE-NEXT: lxvx v2, 0, r5
; P9BE-NEXT: lxv v2, 0(r5)
; P9BE-NEXT: addis r5, r2, .LCPI0_1@toc@ha
; P9BE-NEXT: addi r5, r5, .LCPI0_1@toc@l
; P9BE-NEXT: lxvx v4, 0, r5
; P9BE-NEXT: lxv v4, 0(r5)
; P9BE-NEXT: li r5, 4
; P9BE-NEXT: vperm v0, v3, v5, v2
; P9BE-NEXT: mtctr r5
@ -180,10 +180,10 @@ define signext i32 @test_pre_inc_disable_2(i8* nocapture readonly %pix1, i8* noc
; CHECK-NEXT: lxsd v1, 0(r4)
; CHECK-NEXT: xxlxor v3, v3, v3
; CHECK-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-NEXT: lxvx v4, 0, r3
; CHECK-NEXT: lxv v4, 0(r3)
; CHECK-NEXT: addis r3, r2, .LCPI1_1@toc@ha
; CHECK-NEXT: addi r3, r3, .LCPI1_1@toc@l
; CHECK-NEXT: lxvx v0, 0, r3
; CHECK-NEXT: lxv v0, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: vperm v5, v3, v2, v4
; CHECK-NEXT: vperm v2, v3, v2, v0
@ -207,10 +207,10 @@ define signext i32 @test_pre_inc_disable_2(i8* nocapture readonly %pix1, i8* noc
; P9BE-NEXT: lxsd v1, 0(r4)
; P9BE-NEXT: xxlxor v3, v3, v3
; P9BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; P9BE-NEXT: lxvx v4, 0, r3
; P9BE-NEXT: lxv v4, 0(r3)
; P9BE-NEXT: addis r3, r2, .LCPI1_1@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI1_1@toc@l
; P9BE-NEXT: lxvx v0, 0, r3
; P9BE-NEXT: lxv v0, 0(r3)
; P9BE-NEXT: li r3, 0
; P9BE-NEXT: vperm v5, v3, v2, v4
; P9BE-NEXT: vperm v2, v3, v2, v0
@ -280,7 +280,7 @@ define void @test32(i8* nocapture readonly %pix2, i32 signext %i_pix2) {
; CHECK-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-NEXT: xxlxor v3, v3, v3
; CHECK-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-NEXT: lxvx v4, 0, r3
; CHECK-NEXT: lxv v4, 0(r3)
; CHECK-NEXT: li r3, 4
; CHECK-NEXT: lxsiwzx v5, r5, r3
; CHECK-NEXT: vperm v2, v2, v3, v4
@ -291,7 +291,7 @@ define void @test32(i8* nocapture readonly %pix2, i32 signext %i_pix2) {
; CHECK-NEXT: vslw v3, v3, v4
; CHECK-NEXT: vsubuwm v2, v3, v2
; CHECK-NEXT: xxswapd vs0, v2
; CHECK-NEXT: stxvx vs0, 0, r3
; CHECK-NEXT: stxv vs0, 0(r3)
; CHECK-NEXT: blr
;
; P9BE-LABEL: test32:
@ -301,7 +301,7 @@ define void @test32(i8* nocapture readonly %pix2, i32 signext %i_pix2) {
; P9BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; P9BE-NEXT: xxlxor v3, v3, v3
; P9BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; P9BE-NEXT: lxvx v4, 0, r3
; P9BE-NEXT: lxv v4, 0(r3)
; P9BE-NEXT: li r3, 4
; P9BE-NEXT: lxsiwzx v5, r5, r3
; P9BE-NEXT: vperm v2, v3, v2, v4
@ -312,7 +312,7 @@ define void @test32(i8* nocapture readonly %pix2, i32 signext %i_pix2) {
; P9BE-NEXT: vslw v3, v3, v4
; P9BE-NEXT: vsubuwm v2, v3, v2
; P9BE-NEXT: xxswapd vs0, v2
; P9BE-NEXT: stxvx vs0, 0, r3
; P9BE-NEXT: stxv vs0, 0(r3)
; P9BE-NEXT: blr
entry:
%idx.ext63 = sext i32 %i_pix2 to i64
@ -354,7 +354,7 @@ define void @test16(i16* nocapture readonly %sums, i32 signext %delta, i32 signe
; CHECK-NEXT: vmrghh v2, v3, v2
; CHECK-NEXT: vsplth v3, v3, 3
; CHECK-NEXT: vmrglw v3, v4, v3
; CHECK-NEXT: lxvx v4, 0, r3
; CHECK-NEXT: lxv v4, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: vperm v2, v2, v3, v4
; CHECK-NEXT: xxspltw v3, v2, 2
@ -375,14 +375,14 @@ define void @test16(i16* nocapture readonly %sums, i32 signext %delta, i32 signe
; P9BE-NEXT: addis r6, r2, .LCPI3_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI3_1@toc@l
; P9BE-NEXT: addi r6, r6, .LCPI3_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r6
; P9BE-NEXT: lxv v3, 0(r6)
; P9BE-NEXT: li r6, 0
; P9BE-NEXT: mtvsrwz v4, r6
; P9BE-NEXT: vperm v2, v4, v2, v3
; P9BE-NEXT: vperm v3, v4, v5, v3
; P9BE-NEXT: vsplth v4, v4, 3
; P9BE-NEXT: vmrghw v3, v4, v3
; P9BE-NEXT: lxvx v4, 0, r3
; P9BE-NEXT: lxv v4, 0(r3)
; P9BE-NEXT: li r3, 0
; P9BE-NEXT: vperm v2, v3, v2, v4
; P9BE-NEXT: xxspltw v3, v2, 1
@ -441,7 +441,7 @@ define void @test8(i8* nocapture readonly %sums, i32 signext %delta, i32 signext
; CHECK-NEXT: vmrglw v2, v2, v4
; CHECK-NEXT: vmrglh v3, v3, v4
; CHECK-NEXT: vmrglw v3, v4, v3
; CHECK-NEXT: lxvx v4, 0, r3
; CHECK-NEXT: lxv v4, 0(r3)
; CHECK-NEXT: li r3, 0
; CHECK-NEXT: vperm v2, v3, v2, v4
; CHECK-NEXT: xxspltw v3, v2, 2
@ -461,7 +461,7 @@ define void @test8(i8* nocapture readonly %sums, i32 signext %delta, i32 signext
; P9BE-NEXT: addis r6, r2, .LCPI4_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI4_1@toc@l
; P9BE-NEXT: addi r6, r6, .LCPI4_0@toc@l
; P9BE-NEXT: lxvx v3, 0, r6
; P9BE-NEXT: lxv v3, 0(r6)
; P9BE-NEXT: li r6, 0
; P9BE-NEXT: mtvsrwz v4, r6
; P9BE-NEXT: vperm v2, v4, v2, v3
@ -470,7 +470,7 @@ define void @test8(i8* nocapture readonly %sums, i32 signext %delta, i32 signext
; P9BE-NEXT: vmrghh v3, v3, v4
; P9BE-NEXT: xxspltw v4, v4, 0
; P9BE-NEXT: vmrghw v2, v3, v2
; P9BE-NEXT: lxvx v3, 0, r3
; P9BE-NEXT: lxv v3, 0(r3)
; P9BE-NEXT: li r3, 0
; P9BE-NEXT: vperm v2, v4, v2, v3
; P9BE-NEXT: xxspltw v3, v2, 1

44
test/CodeGen/PowerPC/recipest.ll
View File

@ -136,14 +136,14 @@ define double @foof_fmf(double %a, float %b) nounwind {
; CHECK-P8-LABEL: foof_fmf:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: xsrsqrtesp 0, 2
; CHECK-P8-NEXT: addis 3, 2, .LCPI3_1@toc@ha
; CHECK-P8-NEXT: lfs 3, .LCPI3_1@toc@l(3)
; CHECK-P8-NEXT: addis 3, 2, .LCPI3_0@toc@ha
; CHECK-P8-NEXT: addis 4, 2, .LCPI3_1@toc@ha
; CHECK-P8-NEXT: lfs 3, .LCPI3_0@toc@l(3)
; CHECK-P8-NEXT: lfs 4, .LCPI3_1@toc@l(4)
; CHECK-P8-NEXT: lfs 4, .LCPI3_0@toc@l(3)
; CHECK-P8-NEXT: xsmulsp 2, 2, 0
; CHECK-P8-NEXT: xsmaddasp 3, 2, 0
; CHECK-P8-NEXT: xsmulsp 0, 0, 4
; CHECK-P8-NEXT: xsmulsp 0, 0, 3
; CHECK-P8-NEXT: xsmulsp 3, 0, 3
; CHECK-P8-NEXT: xsmaddasp 4, 2, 0
; CHECK-P8-NEXT: xsmulsp 0, 3, 4
; CHECK-P8-NEXT: xsmuldp 1, 1, 0
; CHECK-P8-NEXT: blr
;
@ -300,14 +300,14 @@ define float @goo_fmf(float %a, float %b) nounwind {
; CHECK-P8-LABEL: goo_fmf:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: xsrsqrtesp 0, 2
; CHECK-P8-NEXT: addis 3, 2, .LCPI7_1@toc@ha
; CHECK-P8-NEXT: lfs 3, .LCPI7_1@toc@l(3)
; CHECK-P8-NEXT: addis 3, 2, .LCPI7_0@toc@ha
; CHECK-P8-NEXT: addis 4, 2, .LCPI7_1@toc@ha
; CHECK-P8-NEXT: lfs 3, .LCPI7_0@toc@l(3)
; CHECK-P8-NEXT: lfs 4, .LCPI7_1@toc@l(4)
; CHECK-P8-NEXT: lfs 4, .LCPI7_0@toc@l(3)
; CHECK-P8-NEXT: xsmulsp 2, 2, 0
; CHECK-P8-NEXT: xsmaddasp 3, 2, 0
; CHECK-P8-NEXT: xsmulsp 0, 0, 4
; CHECK-P8-NEXT: xsmulsp 0, 0, 3
; CHECK-P8-NEXT: xsmulsp 3, 0, 3
; CHECK-P8-NEXT: xsmaddasp 4, 2, 0
; CHECK-P8-NEXT: xsmulsp 0, 3, 4
; CHECK-P8-NEXT: xsmulsp 1, 1, 0
; CHECK-P8-NEXT: blr
;
@ -398,9 +398,9 @@ define float @rsqrt_fmul_fmf(float %a, float %b, float %c) {
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: xsrsqrtesp 0, 1
; CHECK-P8-NEXT: addis 3, 2, .LCPI10_0@toc@ha
; CHECK-P8-NEXT: addis 4, 2, .LCPI10_1@toc@ha
; CHECK-P8-NEXT: lfs 4, .LCPI10_0@toc@l(3)
; CHECK-P8-NEXT: lfs 5, .LCPI10_1@toc@l(4)
; CHECK-P8-NEXT: addis 3, 2, .LCPI10_1@toc@ha
; CHECK-P8-NEXT: lfs 5, .LCPI10_1@toc@l(3)
; CHECK-P8-NEXT: xsmulsp 1, 1, 0
; CHECK-P8-NEXT: xsmaddasp 4, 1, 0
; CHECK-P8-NEXT: xsmulsp 0, 0, 5
@ -502,12 +502,12 @@ define <4 x float> @hoo_fmf(<4 x float> %a, <4 x float> %b) nounwind {
; CHECK-P9-NEXT: xvrsqrtesp 0, 35
; CHECK-P9-NEXT: addis 3, 2, .LCPI12_0@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI12_0@toc@l
; CHECK-P9-NEXT: lxvx 2, 0, 3
; CHECK-P9-NEXT: lxv 2, 0(3)
; CHECK-P9-NEXT: addis 3, 2, .LCPI12_1@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI12_1@toc@l
; CHECK-P9-NEXT: xvmulsp 1, 35, 0
; CHECK-P9-NEXT: xvmaddasp 2, 1, 0
; CHECK-P9-NEXT: lxvx 1, 0, 3
; CHECK-P9-NEXT: lxv 1, 0(3)
; CHECK-P9-NEXT: xvmulsp 0, 0, 1
; CHECK-P9-NEXT: xvmulsp 0, 0, 2
; CHECK-P9-NEXT: xvmulsp 34, 34, 0
@ -959,9 +959,9 @@ define float @goo3_fmf(float %a) nounwind {
; CHECK-P8-NEXT: # %bb.1:
; CHECK-P8-NEXT: xsrsqrtesp 0, 1
; CHECK-P8-NEXT: addis 3, 2, .LCPI23_0@toc@ha
; CHECK-P8-NEXT: addis 4, 2, .LCPI23_1@toc@ha
; CHECK-P8-NEXT: lfs 2, .LCPI23_0@toc@l(3)
; CHECK-P8-NEXT: lfs 3, .LCPI23_1@toc@l(4)
; CHECK-P8-NEXT: addis 3, 2, .LCPI23_1@toc@ha
; CHECK-P8-NEXT: lfs 3, .LCPI23_1@toc@l(3)
; CHECK-P8-NEXT: xsmulsp 1, 1, 0
; CHECK-P8-NEXT: xsmaddasp 2, 1, 0
; CHECK-P8-NEXT: xsmulsp 0, 1, 3
@ -1064,12 +1064,12 @@ define <4 x float> @hoo3_fmf(<4 x float> %a) #1 {
; CHECK-P9-NEXT: xvrsqrtesp 0, 34
; CHECK-P9-NEXT: addis 3, 2, .LCPI25_0@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI25_0@toc@l
; CHECK-P9-NEXT: lxvx 2, 0, 3
; CHECK-P9-NEXT: lxv 2, 0(3)
; CHECK-P9-NEXT: addis 3, 2, .LCPI25_1@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI25_1@toc@l
; CHECK-P9-NEXT: xvmulsp 1, 34, 0
; CHECK-P9-NEXT: xvmaddasp 2, 1, 0
; CHECK-P9-NEXT: lxvx 0, 0, 3
; CHECK-P9-NEXT: lxv 0, 0(3)
; CHECK-P9-NEXT: xvmulsp 0, 1, 0
; CHECK-P9-NEXT: xvmulsp 34, 0, 2
; CHECK-P9-NEXT: blr
@ -1190,13 +1190,13 @@ define <2 x double> @hoo4_fmf(<2 x double> %a) #1 {
; CHECK-P9-NEXT: xvrsqrtedp 0, 34
; CHECK-P9-NEXT: addis 3, 2, .LCPI27_0@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI27_0@toc@l
; CHECK-P9-NEXT: lxvx 2, 0, 3
; CHECK-P9-NEXT: lxv 2, 0(3)
; CHECK-P9-NEXT: addis 3, 2, .LCPI27_1@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI27_1@toc@l
; CHECK-P9-NEXT: xvmuldp 1, 34, 0
; CHECK-P9-NEXT: xxlor 3, 2, 2
; CHECK-P9-NEXT: xvmaddadp 3, 1, 0
; CHECK-P9-NEXT: lxvx 1, 0, 3
; CHECK-P9-NEXT: lxv 1, 0(3)
; CHECK-P9-NEXT: xvmuldp 0, 0, 1
; CHECK-P9-NEXT: xvmuldp 0, 0, 3
; CHECK-P9-NEXT: xvmuldp 3, 34, 0

6
test/CodeGen/PowerPC/register-pressure-reduction.ll
View File

@ -100,15 +100,15 @@ define float @foo_float_reuse_const(float %0, float %1, float %2, float %3) {
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: xsmulsp f1, f2, f1
; CHECK-P8-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-P8-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-P8-NEXT: xssubsp f0, f3, f4
; CHECK-P8-NEXT: lfs f3, .LCPI2_0@toc@l(r3)
; CHECK-P8-NEXT: lfs f4, .LCPI2_1@toc@l(r4)
; CHECK-P8-NEXT: addis r3, r2, .LCPI2_1@toc@ha
; CHECK-P8-NEXT: lfs f4, .LCPI2_1@toc@l(r3)
; CHECK-P8-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-P8-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-P8-NEXT: xsmaddasp f1, f0, f3
; CHECK-P8-NEXT: xsmulsp f0, f2, f4
; CHECK-P8-NEXT: stfsx f0, 0, r3
; CHECK-P8-NEXT: stfs f0, 0(r3)
; CHECK-P8-NEXT: blr
;
; CHECK-FMA-LABEL: foo_float_reuse_const:

931
test/CodeGen/PowerPC/scalar-double-ldst.ll
View File

File diff suppressed because it is too large Load Diff

960
test/CodeGen/PowerPC/scalar-float-ldst.ll
View File

File diff suppressed because it is too large Load Diff

1810
test/CodeGen/PowerPC/scalar-i16-ldst.ll
View File

File diff suppressed because it is too large Load Diff

1840
test/CodeGen/PowerPC/scalar-i32-ldst.ll
View File

File diff suppressed because it is too large Load Diff

1798
test/CodeGen/PowerPC/scalar-i64-ldst.ll
View File

File diff suppressed because it is too large Load Diff

1908
test/CodeGen/PowerPC/scalar-i8-ldst.ll
View File

File diff suppressed because it is too large Load Diff

133
test/CodeGen/PowerPC/scalar_vector_test_1.ll
View File

@ -1,3 +1,4 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu < %s | FileCheck %s --check-prefix=P9LE
; RUN: llc -mcpu=pwr9 -verify-machineinstrs -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names \
@ -15,12 +16,25 @@ define <2 x i64> @s2v_test1(i64* nocapture readonly %int64, <2 x i64> %vec) {
; P9LE-NEXT: lfd f0, 0(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test1:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 0(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test1:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f0, 0, r3
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test1:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f0, 0, r3
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%0 = load i64, i64* %int64, align 8
%vecins = insertelement <2 x i64> %vec, i64 %0, i32 0
@ -34,12 +48,25 @@ define <2 x i64> @s2v_test2(i64* nocapture readonly %int64, <2 x i64> %vec) {
; P9LE-NEXT: lfd f0, 8(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test2:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 8(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test2:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfd f0, 8(r3)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test2:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfd f0, 8(r3)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%arrayidx = getelementptr inbounds i64, i64* %int64, i64 1
%0 = load i64, i64* %arrayidx, align 8
@ -55,13 +82,28 @@ define <2 x i64> @s2v_test3(i64* nocapture readonly %int64, <2 x i64> %vec, i32
; P9LE-NEXT: lfdx f0, r3, r4
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
; P9BE-LABEL: s2v_test3
;
; P9BE-LABEL: s2v_test3:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: sldi r4, r7, 3
; P9BE-NEXT: lfdx f0, r3, r4
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test3:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: sldi r4, r7, 3
; P8LE-NEXT: lfdx f0, r3, r4
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test3:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: sldi r4, r7, 3
; P8BE-NEXT: lfdx f0, r3, r4
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%idxprom = sext i32 %Idx to i64
%arrayidx = getelementptr inbounds i64, i64* %int64, i64 %idxprom
@ -77,12 +119,25 @@ define <2 x i64> @s2v_test4(i64* nocapture readonly %int64, <2 x i64> %vec) {
; P9LE-NEXT: lfd f0, 8(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test4:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 8(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test4:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfd f0, 8(r3)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test4:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfd f0, 8(r3)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%arrayidx = getelementptr inbounds i64, i64* %int64, i64 1
%0 = load i64, i64* %arrayidx, align 8
@ -97,12 +152,25 @@ define <2 x i64> @s2v_test5(<2 x i64> %vec, i64* nocapture readonly %ptr1) {
; P9LE-NEXT: lfd f0, 0(r5)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test5:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 0(r5)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test5:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f0, 0, r5
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test5:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f0, 0, r5
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%0 = load i64, i64* %ptr1, align 8
%vecins = insertelement <2 x i64> %vec, i64 %0, i32 0
@ -116,24 +184,27 @@ define <2 x double> @s2v_test_f1(double* nocapture readonly %f64, <2 x double> %
; P9LE-NEXT: lfd f0, 0(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test_f1:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 0(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test_f1:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f0, 0, r3
; P8LE-NEXT: lfd f0, 0(r3)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test_f1:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f0, 0, r3
; P8BE-NEXT: lfd f0, 0(r3)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%0 = load double, double* %f64, align 8
%vecins = insertelement <2 x double> %vec, double %0, i32 0
@ -147,24 +218,27 @@ define <2 x double> @s2v_test_f2(double* nocapture readonly %f64, <2 x double> %
; P9LE-NEXT: lfd f0, 8(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test_f2:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 8(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test_f2:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfd f0, 8(r3)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test_f2:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfd f0, 8(r3)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%arrayidx = getelementptr inbounds double, double* %f64, i64 1
%0 = load double, double* %arrayidx, align 8
@ -180,27 +254,30 @@ define <2 x double> @s2v_test_f3(double* nocapture readonly %f64, <2 x double> %
; P9LE-NEXT: lfdx f0, r3, r4
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test_f3:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: sldi r4, r7, 3
; P9BE-NEXT: lfdx f0, r3, r4
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test_f3:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: sldi r4, r7, 3
; P8LE-NEXT: lfdx f0, r3, r4
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test_f3:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: sldi r4, r7, 3
; P8BE-NEXT: lfdx f0, r3, r4
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%idxprom = sext i32 %Idx to i64
%arrayidx = getelementptr inbounds double, double* %f64, i64 %idxprom
@ -216,24 +293,27 @@ define <2 x double> @s2v_test_f4(double* nocapture readonly %f64, <2 x double> %
; P9LE-NEXT: lfd f0, 8(r3)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test_f4:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 8(r3)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test_f4:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfd f0, 8(r3)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test_f4:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfd f0, 8(r3)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%arrayidx = getelementptr inbounds double, double* %f64, i64 1
%0 = load double, double* %arrayidx, align 8
@ -248,24 +328,27 @@ define <2 x double> @s2v_test_f5(<2 x double> %vec, double* nocapture readonly %
; P9LE-NEXT: lfd f0, 0(r5)
; P9LE-NEXT: xxmrghd v2, v2, vs0
; P9LE-NEXT: blr
;
; P9BE-LABEL: s2v_test_f5:
; P9BE: # %bb.0: # %entry
; P9BE-NEXT: lfd f0, 0(r5)
; P9BE-NEXT: xxpermdi v2, vs0, v2, 1
; P9BE-NEXT: blr
;
; P8LE-LABEL: s2v_test_f5:
; P8LE: # %bb.0: # %entry
; P8LE-NEXT: lfdx f0, 0, r5
; P8LE-NEXT: lfd f0, 0(r5)
; P8LE-NEXT: xxmrghd v2, v2, vs0
; P8LE-NEXT: blr
;
; P8BE-LABEL: s2v_test_f5:
; P8BE: # %bb.0: # %entry
; P8BE-NEXT: lfdx f0, 0, r5
; P8BE-NEXT: lfd f0, 0(r5)
; P8BE-NEXT: xxpermdi v2, vs0, v2, 1
; P8BE-NEXT: blr
entry:
%0 = load double, double* %ptr1, align 8
%vecins = insertelement <2 x double> %vec, double %0, i32 0

24
test/CodeGen/PowerPC/scalar_vector_test_2.ll
View File

@ -27,18 +27,18 @@ define void @test_liwzx1(<1 x float>* %A, <1 x float>* %B, <1 x float>* %C) {
;
; P8LE-LABEL: test_liwzx1:
; P8LE: # %bb.0:
; P8LE-NEXT: lfsx f0, 0, r3
; P8LE-NEXT: lfsx f1, 0, r4
; P8LE-NEXT: lfs f0, 0(r3)
; P8LE-NEXT: lfs f1, 0(r4)
; P8LE-NEXT: xsaddsp f0, f0, f1
; P8LE-NEXT: stfsx f0, 0, r5
; P8LE-NEXT: stfs f0, 0(r5)
; P8LE-NEXT: blr
;
; P8BE-LABEL: test_liwzx1:
; P8BE: # %bb.0:
; P8BE-NEXT: lfsx f0, 0, r3
; P8BE-NEXT: lfsx f1, 0, r4
; P8BE-NEXT: lfs f0, 0(r3)
; P8BE-NEXT: lfs f1, 0(r4)
; P8BE-NEXT: xsaddsp f0, f0, f1
; P8BE-NEXT: stfsx f0, 0, r5
; P8BE-NEXT: stfs f0, 0(r5)
; P8BE-NEXT: blr
@ -71,20 +71,20 @@ define <1 x float>* @test_liwzx2(<1 x float>* %A, <1 x float>* %B, <1 x float>*
;
; P8LE-LABEL: test_liwzx2:
; P8LE: # %bb.0:
; P8LE-NEXT: lfsx f0, 0, r3
; P8LE-NEXT: lfsx f1, 0, r4
; P8LE-NEXT: lfs f0, 0(r3)
; P8LE-NEXT: lfs f1, 0(r4)
; P8LE-NEXT: mr r3, r5
; P8LE-NEXT: xssubsp f0, f0, f1
; P8LE-NEXT: stfsx f0, 0, r5
; P8LE-NEXT: stfs f0, 0(r5)
; P8LE-NEXT: blr
;
; P8BE-LABEL: test_liwzx2:
; P8BE: # %bb.0:
; P8BE-NEXT: lfsx f0, 0, r3
; P8BE-NEXT: lfsx f1, 0, r4
; P8BE-NEXT: lfs f0, 0(r3)
; P8BE-NEXT: lfs f1, 0(r4)
; P8BE-NEXT: mr r3, r5
; P8BE-NEXT: xssubsp f0, f0, f1
; P8BE-NEXT: stfsx f0, 0, r5
; P8BE-NEXT: stfs f0, 0(r5)
; P8BE-NEXT: blr

28
test/CodeGen/PowerPC/select_const.ll
View File

@ -726,7 +726,7 @@ define double @sel_constants_fadd_constant(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI42_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI42_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: sel_constants_fadd_constant:
@ -741,7 +741,7 @@ define double @sel_constants_fadd_constant(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB42_2
; NO_ISEL-NEXT: .LBB42_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fadd double %sel, 5.1
@ -757,7 +757,7 @@ define double @sel_constants_fsub_constant(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI43_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI43_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: sel_constants_fsub_constant:
@ -772,7 +772,7 @@ define double @sel_constants_fsub_constant(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB43_2
; NO_ISEL-NEXT: .LBB43_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fsub double %sel, 5.1
@ -788,7 +788,7 @@ define double @fsub_constant_sel_constants(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI44_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI44_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: fsub_constant_sel_constants:
@ -803,7 +803,7 @@ define double @fsub_constant_sel_constants(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB44_2
; NO_ISEL-NEXT: .LBB44_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fsub double 5.1, %sel
@ -819,7 +819,7 @@ define double @sel_constants_fmul_constant(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI45_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI45_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: sel_constants_fmul_constant:
@ -834,7 +834,7 @@ define double @sel_constants_fmul_constant(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB45_2
; NO_ISEL-NEXT: .LBB45_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fmul double %sel, 5.1
@ -850,7 +850,7 @@ define double @sel_constants_fdiv_constant(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI46_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI46_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: sel_constants_fdiv_constant:
@ -865,7 +865,7 @@ define double @sel_constants_fdiv_constant(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB46_2
; NO_ISEL-NEXT: .LBB46_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fdiv double %sel, 5.1
@ -881,7 +881,7 @@ define double @fdiv_constant_sel_constants(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI47_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI47_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: fdiv_constant_sel_constants:
@ -896,7 +896,7 @@ define double @fdiv_constant_sel_constants(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB47_2
; NO_ISEL-NEXT: .LBB47_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = fdiv double 5.1, %sel
@ -930,7 +930,7 @@ define double @frem_constant_sel_constants(i1 %cond) {
; ISEL-NEXT: addi 4, 4, .LCPI49_0@toc@l
; ISEL-NEXT: addi 3, 3, .LCPI49_1@toc@l
; ISEL-NEXT: iselgt 3, 3, 4
; ISEL-NEXT: lfdx 1, 0, 3
; ISEL-NEXT: lfd 1, 0(3)
; ISEL-NEXT: blr
;
; NO_ISEL-LABEL: frem_constant_sel_constants:
@ -945,7 +945,7 @@ define double @frem_constant_sel_constants(i1 %cond) {
; NO_ISEL-NEXT: ori 3, 4, 0
; NO_ISEL-NEXT: b .LBB49_2
; NO_ISEL-NEXT: .LBB49_2:
; NO_ISEL-NEXT: lfdx 1, 0, 3
; NO_ISEL-NEXT: lfd 1, 0(3)
; NO_ISEL-NEXT: blr
%sel = select i1 %cond, double -4.0, double 23.3
%bo = frem double 5.1, %sel

12
test/CodeGen/PowerPC/srem-vector-lkk.ll
View File

@ -98,7 +98,7 @@ define <4 x i16> @fold_srem_vec_1(<4 x i16> %x) {
; P9BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; P9BE-NEXT: ori r4, r4, 63249
; P9BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 6
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r3, r3
@ -323,7 +323,7 @@ define <4 x i16> @fold_srem_vec_2(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r3, r3
@ -550,7 +550,7 @@ define <4 x i16> @combine_srem_sdiv(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r7, r3
@ -781,7 +781,7 @@ define <4 x i16> @dont_fold_srem_power_of_two(<4 x i16> %x) {
; P9BE-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; P9BE-NEXT: ori r4, r4, 37253
; P9BE-NEXT: addi r3, r3, .LCPI3_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 6
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r3, r3
@ -975,7 +975,7 @@ define <4 x i16> @dont_fold_srem_one(<4 x i16> %x) {
; P9BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; P9BE-NEXT: ori r4, r4, 30865
; P9BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r3, r3
@ -1164,7 +1164,7 @@ define <4 x i16> @dont_fold_urem_i16_smax(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: extsh r3, r3

64
test/CodeGen/PowerPC/store_fptoi.ll
View File

@ -167,7 +167,7 @@ define void @dpConv2sdw(double* nocapture readonly %a, i64* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2sdw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -191,7 +191,7 @@ define void @dpConv2sw(double* nocapture readonly %a, i32* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2sw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -215,7 +215,7 @@ define void @dpConv2shw(double* nocapture readonly %a, i16* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2shw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: sth 3, 0(4)
@ -240,7 +240,7 @@ define void @dpConv2sb(double* nocapture readonly %a, i8* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2sb:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stb 3, 0(4)
@ -265,7 +265,7 @@ define void @spConv2sdw(float* nocapture readonly %a, i64* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2sdw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -289,7 +289,7 @@ define void @spConv2sw(float* nocapture readonly %a, i32* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2sw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -313,7 +313,7 @@ define void @spConv2shw(float* nocapture readonly %a, i16* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2shw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: sth 3, 0(4)
@ -338,7 +338,7 @@ define void @spConv2sb(float* nocapture readonly %a, i8* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2sb:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stb 3, 0(4)
@ -364,7 +364,7 @@ define void @dpConv2sdw_x(double* nocapture readonly %a, i64* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2sdw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 3
; CHECK-PWR8-NEXT: xscvdpsxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 4, 3
@ -393,7 +393,7 @@ define void @dpConv2sw_x(double* nocapture readonly %a, i32* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2sw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 2
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 4, 3
@ -422,7 +422,7 @@ define void @dpConv2shw_x(double* nocapture readonly %a, i16* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2shw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 5, 5, 1
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
@ -451,7 +451,7 @@ define void @dpConv2sb_x(double* nocapture readonly %a, i8* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2sb_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stbx 3, 4, 5
@ -480,7 +480,7 @@ define void @spConv2sdw_x(float* nocapture readonly %a, i64* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2sdw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 3
; CHECK-PWR8-NEXT: xscvdpsxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 4, 3
@ -509,7 +509,7 @@ define void @spConv2sw_x(float* nocapture readonly %a, i32* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2sw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 2
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 4, 3
@ -538,7 +538,7 @@ define void @spConv2shw_x(float* nocapture readonly %a, i16* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2shw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 5, 5, 1
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
@ -567,7 +567,7 @@ define void @spConv2sb_x(float* nocapture readonly %a, i8* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2sb_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stbx 3, 4, 5
@ -599,7 +599,7 @@ define void @dpConv2udw(double* nocapture readonly %a, i64* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2udw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpuxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -623,7 +623,7 @@ define void @dpConv2uw(double* nocapture readonly %a, i32* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2uw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpuxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -647,7 +647,7 @@ define void @dpConv2uhw(double* nocapture readonly %a, i16* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2uhw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: sth 3, 0(4)
@ -672,7 +672,7 @@ define void @dpConv2ub(double* nocapture readonly %a, i8* nocapture %b) {
;
; CHECK-PWR8-LABEL: dpConv2ub:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stb 3, 0(4)
@ -697,7 +697,7 @@ define void @spConv2udw(float* nocapture readonly %a, i64* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2udw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpuxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -721,7 +721,7 @@ define void @spConv2uw(float* nocapture readonly %a, i32* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2uw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpuxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 0, 4
; CHECK-PWR8-NEXT: blr
@ -745,7 +745,7 @@ define void @spConv2uhw(float* nocapture readonly %a, i16* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2uhw:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: sth 3, 0(4)
@ -770,7 +770,7 @@ define void @spConv2ub(float* nocapture readonly %a, i8* nocapture %b) {
;
; CHECK-PWR8-LABEL: spConv2ub:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stb 3, 0(4)
@ -796,7 +796,7 @@ define void @dpConv2udw_x(double* nocapture readonly %a, i64* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2udw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 3
; CHECK-PWR8-NEXT: xscvdpuxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 4, 3
@ -825,7 +825,7 @@ define void @dpConv2uw_x(double* nocapture readonly %a, i32* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2uw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 2
; CHECK-PWR8-NEXT: xscvdpuxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 4, 3
@ -854,7 +854,7 @@ define void @dpConv2uhw_x(double* nocapture readonly %a, i16* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2uhw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: sldi 5, 5, 1
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
@ -883,7 +883,7 @@ define void @dpConv2ub_x(double* nocapture readonly %a, i8* nocapture %b,
;
; CHECK-PWR8-LABEL: dpConv2ub_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfdx 0, 0, 3
; CHECK-PWR8-NEXT: lfd 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stbx 3, 4, 5
@ -912,7 +912,7 @@ define void @spConv2udw_x(float* nocapture readonly %a, i64* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2udw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 3
; CHECK-PWR8-NEXT: xscvdpuxds 0, 0
; CHECK-PWR8-NEXT: stxsdx 0, 4, 3
@ -941,7 +941,7 @@ define void @spConv2uw_x(float* nocapture readonly %a, i32* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2uw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 3, 5, 2
; CHECK-PWR8-NEXT: xscvdpuxws 0, 0
; CHECK-PWR8-NEXT: stfiwx 0, 4, 3
@ -970,7 +970,7 @@ define void @spConv2uhw_x(float* nocapture readonly %a, i16* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2uhw_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: sldi 5, 5, 1
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
@ -999,7 +999,7 @@ define void @spConv2ub_x(float* nocapture readonly %a, i8* nocapture %b,
;
; CHECK-PWR8-LABEL: spConv2ub_x:
; CHECK-PWR8: # %bb.0: # %entry
; CHECK-PWR8-NEXT: lfsx 0, 0, 3
; CHECK-PWR8-NEXT: lfs 0, 0(3)
; CHECK-PWR8-NEXT: xscvdpsxws 0, 0
; CHECK-PWR8-NEXT: mffprwz 3, 0
; CHECK-PWR8-NEXT: stbx 3, 4, 5

34
test/CodeGen/PowerPC/swaps-le-6.ll
View File

@ -26,13 +26,14 @@ define void @bar0() {
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: addis r4, r2, .LC1@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lfdx f0, 0, r3
; CHECK-NEXT: lxvd2x vs0, 0, r3
; CHECK-NEXT: ld r3, .LC1@toc@l(r4)
; CHECK-NEXT: lxvd2x vs1, 0, r3
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: lfd f1, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-NEXT: xxmrgld vs0, vs0, vs1
; CHECK-NEXT: xxmrghd vs0, vs0, vs1
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: stxvd2x vs0, 0, r3
; CHECK-NEXT: blr
;
@ -40,14 +41,14 @@ define void @bar0() {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-P9-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-P9-NEXT: lxvx vs0, 0, r3
; CHECK-P9-NEXT: lxv vs0, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LC1@toc@ha
; CHECK-P9-NEXT: ld r3, .LC1@toc@l(r3)
; CHECK-P9-NEXT: lfd f1, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-P9-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-P9-NEXT: xxmrghd vs0, vs0, vs1
; CHECK-P9-NEXT: stxvx vs0, 0, r3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P9-NOVECTOR-LABEL: bar0:
@ -57,11 +58,12 @@ define void @bar0() {
; CHECK-P9-NOVECTOR-NEXT: lxvd2x vs0, 0, r3
; CHECK-P9-NOVECTOR-NEXT: addis r3, r2, .LC1@toc@ha
; CHECK-P9-NOVECTOR-NEXT: ld r3, .LC1@toc@l(r3)
; CHECK-P9-NOVECTOR-NEXT: lfdx f1, 0, r3
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-NOVECTOR-NEXT: lfd f1, 0(r3)
; CHECK-P9-NOVECTOR-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-P9-NOVECTOR-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs1, vs1
; CHECK-P9-NOVECTOR-NEXT: xxmrgld vs0, vs1, vs0
; CHECK-P9-NOVECTOR-NEXT: xxmrghd vs0, vs0, vs1
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-NOVECTOR-NEXT: stxvd2x vs0, 0, r3
; CHECK-P9-NOVECTOR-NEXT: blr
entry:
@ -78,13 +80,14 @@ define void @bar1() {
; CHECK-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-NEXT: addis r4, r2, .LC1@toc@ha
; CHECK-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-NEXT: lfdx f0, 0, r3
; CHECK-NEXT: lxvd2x vs0, 0, r3
; CHECK-NEXT: ld r3, .LC1@toc@l(r4)
; CHECK-NEXT: lxvd2x vs1, 0, r3
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: lfd f1, 0(r3)
; CHECK-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-NEXT: xxpermdi vs0, vs1, vs0, 1
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: stxvd2x vs0, 0, r3
; CHECK-NEXT: blr
;
@ -92,14 +95,14 @@ define void @bar1() {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r3, r2, .LC0@toc@ha
; CHECK-P9-NEXT: ld r3, .LC0@toc@l(r3)
; CHECK-P9-NEXT: lxvx vs0, 0, r3
; CHECK-P9-NEXT: lxv vs0, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LC1@toc@ha
; CHECK-P9-NEXT: ld r3, .LC1@toc@l(r3)
; CHECK-P9-NEXT: lfd f1, 0(r3)
; CHECK-P9-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-P9-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-P9-NEXT: xxpermdi vs0, vs1, vs0, 1
; CHECK-P9-NEXT: stxvx vs0, 0, r3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P9-NOVECTOR-LABEL: bar1:
@ -109,11 +112,12 @@ define void @bar1() {
; CHECK-P9-NOVECTOR-NEXT: lxvd2x vs0, 0, r3
; CHECK-P9-NOVECTOR-NEXT: addis r3, r2, .LC1@toc@ha
; CHECK-P9-NOVECTOR-NEXT: ld r3, .LC1@toc@l(r3)
; CHECK-P9-NOVECTOR-NEXT: lfdx f1, 0, r3
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-NOVECTOR-NEXT: lfd f1, 0(r3)
; CHECK-P9-NOVECTOR-NEXT: addis r3, r2, .LC2@toc@ha
; CHECK-P9-NOVECTOR-NEXT: ld r3, .LC2@toc@l(r3)
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs1, vs1
; CHECK-P9-NOVECTOR-NEXT: xxpermdi vs0, vs0, vs1, 1
; CHECK-P9-NOVECTOR-NEXT: xxpermdi vs0, vs1, vs0, 1
; CHECK-P9-NOVECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-NOVECTOR-NEXT: stxvd2x vs0, 0, r3
; CHECK-P9-NOVECTOR-NEXT: blr
entry:

4
test/CodeGen/PowerPC/tailcall-speculatable-callee.ll
View File

@ -23,7 +23,7 @@ define dso_local void @speculatable_callee_non_return_use_only (double* nocaptur
; CHECK-NEXT: stdu r1, -48(r1)
; CHECK-NEXT: mr r30, r3
; CHECK-NEXT: bl callee
; CHECK-NEXT: stfdx f1, 0, r30
; CHECK-NEXT: stfd f1, 0(r30)
; CHECK-NEXT: addi r1, r1, 48
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload
@ -45,7 +45,7 @@ define dso_local double @speculatable_callee_multi_use (double* nocapture %res,
; CHECK-NEXT: stdu r1, -48(r1)
; CHECK-NEXT: mr r30, r3
; CHECK-NEXT: bl callee
; CHECK-NEXT: stfdx f1, 0, r30
; CHECK-NEXT: stfd f1, 0(r30)
; CHECK-NEXT: addi r1, r1, 48
; CHECK-NEXT: ld r0, 16(r1)
; CHECK-NEXT: ld r30, -16(r1) # 8-byte Folded Reload

12
test/CodeGen/PowerPC/toc-float.ll
View File

@ -50,11 +50,10 @@ define float @floatConstantArray() local_unnamed_addr {
;
; CHECK-P8-LABEL: floatConstantArray:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: addis 3, 2, FArr@toc@ha
; CHECK-P8-NEXT: addis 3, 2, FArr@toc@ha+12
; CHECK-P8-NEXT: addis 4, 2, .LCPI2_0@toc@ha
; CHECK-P8-NEXT: addi 3, 3, FArr@toc@l
; CHECK-P8-NEXT: lfs 0, FArr@toc@l+12(3)
; CHECK-P8-NEXT: lfs 1, .LCPI2_0@toc@l(4)
; CHECK-P8-NEXT: lfs 0, 12(3)
; CHECK-P8-NEXT: xsaddsp 1, 0, 1
; CHECK-P8-NEXT: blr
%1 = load float, float* getelementptr inbounds ([10 x float], [10 x float]* @FArr, i64 0, i64 3), align 4
@ -93,11 +92,10 @@ define double @doubleConstantArray() {
;
; CHECK-P8-LABEL: doubleConstantArray:
; CHECK-P8: # %bb.0:
; CHECK-P8-NEXT: addis 3, 2, d@toc@ha
; CHECK-P8-NEXT: addis 3, 2, d@toc@ha+24
; CHECK-P8-NEXT: addis 4, 2, .LCPI4_0@toc@ha
; CHECK-P8-NEXT: addi 3, 3, d@toc@l
; CHECK-P8-NEXT: lfd 0, d@toc@l+24(3)
; CHECK-P8-NEXT: lfd 1, .LCPI4_0@toc@l(4)
; CHECK-P8-NEXT: lfd 0, 24(3)
; CHECK-P8-NEXT: xsadddp 1, 0, 1
; CHECK-P8-NEXT: blr
%1 = load double, double* getelementptr inbounds ([200 x double], [200 x double]* @d, i64 0, i64 3), align 8
@ -128,8 +126,8 @@ define double @doubleLargeConstantArray() {
; CHECK-P8-NEXT: addis 5, 2, .LCPI5_0@toc@ha
; CHECK-P8-NEXT: addi 3, 3, arr@toc@l
; CHECK-P8-NEXT: ori 4, 4, 32768
; CHECK-P8-NEXT: lfdx 0, 3, 4
; CHECK-P8-NEXT: lfd 1, .LCPI5_0@toc@l(5)
; CHECK-P8-NEXT: lfdx 0, 3, 4
; CHECK-P8-NEXT: xsadddp 1, 0, 1
; CHECK-P8-NEXT: blr
%1 = load double, double* getelementptr inbounds ([20000 x double], [20000 x double]* @arr, i64 0, i64 4096), align 8

8
test/CodeGen/PowerPC/unaligned-addressing-mode.ll
View File

@ -55,10 +55,10 @@ entry:
define void @test_xoaddr(i32* %arr, i32* %arrTo) {
; CHECK-LABEL: test_xoaddr:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 8
; CHECK-NEXT: addi r4, r4, 4
; CHECK-NEXT: lxvx vs0, 0, r3
; CHECK-NEXT: stxvx vs0, 0, r4
; CHECK-NEXT: li r5, 8
; CHECK-NEXT: lxvx vs0, r3, r5
; CHECK-NEXT: li r3, 4
; CHECK-NEXT: stxvx vs0, r4, r3
; CHECK-NEXT: blr
entry:
%arrayidx = getelementptr inbounds i32, i32* %arrTo, i64 1

4
test/CodeGen/PowerPC/unaligned.ll
View File

@ -92,8 +92,8 @@ define void @foo5(double* %p, double* %r) nounwind {
;
; CHECK-VSX-LABEL: foo5:
; CHECK-VSX: # %bb.0: # %entry
; CHECK-VSX-NEXT: lfdx 0, 0, 3
; CHECK-VSX-NEXT: stfdx 0, 0, 4
; CHECK-VSX-NEXT: lfd 0, 0(3)
; CHECK-VSX-NEXT: stfd 0, 0(4)
; CHECK-VSX-NEXT: blr
entry:
%v = load double, double* %p, align 1

10
test/CodeGen/PowerPC/urem-vector-lkk.ll
View File

@ -86,7 +86,7 @@ define <4 x i16> @fold_urem_vec_1(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: clrlwi r4, r3, 16
@ -299,7 +299,7 @@ define <4 x i16> @fold_urem_vec_2(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: clrlwi r3, r3, 16
@ -526,7 +526,7 @@ define <4 x i16> @combine_urem_udiv(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: clrlwi r7, r3, 16
@ -737,7 +737,7 @@ define <4 x i16> @dont_fold_urem_power_of_two(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI3_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 6
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: clrlwi r3, r3, 16
@ -891,7 +891,7 @@ define <4 x i16> @dont_fold_urem_one(<4 x i16> %x) {
; P9BE-NEXT: mtvsrwz v4, r3
; P9BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; P9BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; P9BE-NEXT: lxvx v5, 0, r3
; P9BE-NEXT: lxv v5, 0(r3)
; P9BE-NEXT: li r3, 2
; P9BE-NEXT: vextuhlx r3, r3, v2
; P9BE-NEXT: clrlwi r4, r3, 16

2
test/CodeGen/PowerPC/vavg.ll
View File

@ -140,7 +140,7 @@ define <8 x i16> @test_v8i16_sign_negative(<8 x i16> %m, <8 x i16> %n) {
; CHECK-P9-NEXT: addis 3, 2, .LCPI6_0@toc@ha
; CHECK-P9-NEXT: vadduhm 2, 2, 3
; CHECK-P9-NEXT: addi 3, 3, .LCPI6_0@toc@l
; CHECK-P9-NEXT: lxvx 35, 0, 3
; CHECK-P9-NEXT: lxv 35, 0(3)
; CHECK-P9-NEXT: vadduhm 2, 2, 3
; CHECK-P9-NEXT: vspltish 3, 1
; CHECK-P9-NEXT: vsrah 2, 2, 3

56
test/CodeGen/PowerPC/vec-itofp.ll
View File

@ -53,24 +53,24 @@ define void @test8(<8 x double>* nocapture %Sink, <8 x i16>* nocapture readonly
; CHECK-P9-NEXT: addis r4, r2, .LCPI0_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI0_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI0_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI0_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI0_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI0_2@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI0_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI0_3@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxddp vs3, v2
@ -83,24 +83,24 @@ define void @test8(<8 x double>* nocapture %Sink, <8 x i16>* nocapture readonly
; CHECK-BE-NEXT: addis r4, r2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI0_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI0_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI0_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI0_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI0_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI0_3@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxddp vs3, v2
@ -141,12 +141,12 @@ define void @test4(<4 x double>* nocapture %Sink, <4 x i16>* nocapture readonly
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v2
@ -159,12 +159,12 @@ define void @test4(<4 x double>* nocapture %Sink, <4 x i16>* nocapture readonly
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v2
@ -197,7 +197,7 @@ define void @test2(<2 x double>* nocapture %Sink, <2 x i16>* nocapture readonly
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v2
; CHECK-P9-NEXT: stxv vs0, 0(r3)
@ -209,7 +209,7 @@ define void @test2(<2 x double>* nocapture %Sink, <2 x i16>* nocapture readonly
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v2
; CHECK-BE-NEXT: stxv vs0, 0(r3)
@ -275,27 +275,27 @@ define void @stest8(<8 x double>* nocapture %Sink, <8 x i16>* nocapture readonly
; CHECK-P9-NEXT: lxv v2, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: vextsh2d v2, v2
@ -309,27 +309,27 @@ define void @stest8(<8 x double>* nocapture %Sink, <8 x i16>* nocapture readonly
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs1, 48(r3)
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs2, 0(r3)
; CHECK-BE-NEXT: vextsh2d v2, v2
@ -377,13 +377,13 @@ define void @stest4(<4 x double>* nocapture %Sink, <4 x i16>* nocapture readonly
; CHECK-P9-NEXT: lxv v2, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI4_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI4_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI4_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI4_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsh2d v2, v2
@ -397,13 +397,13 @@ define void @stest4(<4 x double>* nocapture %Sink, <4 x i16>* nocapture readonly
; CHECK-BE-NEXT: addis r4, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: xxlxor v3, v3, v3
; CHECK-BE-NEXT: addi r4, r4, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI4_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI4_1@toc@l
; CHECK-BE-NEXT: vperm v3, v3, v2, v4
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsh2d v2, v2
@ -441,7 +441,7 @@ define void @stest2(<2 x double>* nocapture %Sink, <2 x i16>* nocapture readonly
; CHECK-P9-NEXT: lxv v2, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v2, v2
; CHECK-P9-NEXT: xvcvsxddp vs0, v2
@ -453,7 +453,7 @@ define void @stest2(<2 x double>* nocapture %Sink, <2 x i16>* nocapture readonly
; CHECK-BE-NEXT: lxv v2, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: vextsh2d v2, v2
; CHECK-BE-NEXT: xvcvsxddp vs0, v2

16
test/CodeGen/PowerPC/vec_conv_fp32_to_i16_elts.ll
View File

@ -53,7 +53,7 @@ define i32 @test2elt(i64 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvspdpn f1, vs0
; CHECK-BE-NEXT: xxsldwi vs0, vs0, vs0, 1
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: xscvdpsxws f1, f1
; CHECK-BE-NEXT: xscvdpsxws f0, f0
@ -134,7 +134,7 @@ define i64 @test4elt(<4 x float> %a) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f0, f0
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
@ -273,7 +273,7 @@ define <8 x i16> @test8elt(<8 x float>* nocapture readonly) local_unnamed_addr #
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs2, vs1, vs1, 3
; CHECK-BE-NEXT: xscvspdpn f2, vs2
; CHECK-BE-NEXT: xscvdpsxws f2, f2
@ -537,7 +537,7 @@ define void @test16elt(<16 x i16>* noalias nocapture sret(<16 x i16>) %agg.resul
; CHECK-BE-NEXT: lxv vs1, 0(r4)
; CHECK-BE-NEXT: lxv vs0, 48(r4)
; CHECK-BE-NEXT: addi r5, r5, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r5
; CHECK-BE-NEXT: lxv v2, 0(r5)
; CHECK-BE-NEXT: xxsldwi vs3, vs2, vs2, 3
; CHECK-BE-NEXT: xxswapd vs4, vs2
; CHECK-BE-NEXT: xscvspdpn f5, vs2
@ -683,7 +683,7 @@ define i32 @test2elt_signed(i64 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvspdpn f1, vs0
; CHECK-BE-NEXT: xxsldwi vs0, vs0, vs0, 1
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: xscvdpsxws f1, f1
; CHECK-BE-NEXT: xscvdpsxws f0, f0
@ -764,7 +764,7 @@ define i64 @test4elt_signed(<4 x float> %a) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f0, f0
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
@ -903,7 +903,7 @@ define <8 x i16> @test8elt_signed(<8 x float>* nocapture readonly) local_unnamed
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs2, vs1, vs1, 3
; CHECK-BE-NEXT: xscvspdpn f2, vs2
; CHECK-BE-NEXT: xscvdpsxws f2, f2
@ -1167,7 +1167,7 @@ define void @test16elt_signed(<16 x i16>* noalias nocapture sret(<16 x i16>) %ag
; CHECK-BE-NEXT: lxv vs1, 0(r4)
; CHECK-BE-NEXT: lxv vs0, 48(r4)
; CHECK-BE-NEXT: addi r5, r5, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r5
; CHECK-BE-NEXT: lxv v2, 0(r5)
; CHECK-BE-NEXT: xxsldwi vs3, vs2, vs2, 3
; CHECK-BE-NEXT: xxswapd vs4, vs2
; CHECK-BE-NEXT: xscvspdpn f5, vs2

16
test/CodeGen/PowerPC/vec_conv_fp32_to_i8_elts.ll
View File

@ -58,7 +58,7 @@ define i16 @test2elt(i64 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvspdpn f1, vs0
; CHECK-BE-NEXT: xxsldwi vs0, vs0, vs0, 1
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: xscvdpsxws f1, f1
; CHECK-BE-NEXT: xscvdpsxws f0, f0
@ -142,7 +142,7 @@ define i32 @test4elt(<4 x float> %a) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f0, f0
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
@ -285,7 +285,7 @@ define i64 @test8elt(<8 x float>* nocapture readonly) local_unnamed_addr #2 {
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs2, vs1, vs1, 3
; CHECK-BE-NEXT: xscvspdpn f2, vs2
; CHECK-BE-NEXT: xscvdpsxws f2, f2
@ -550,7 +550,7 @@ define <16 x i8> @test16elt(<16 x float>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs4, vs3, vs3, 3
; CHECK-BE-NEXT: xscvspdpn f4, vs4
; CHECK-BE-NEXT: xscvdpsxws f4, f4
@ -698,7 +698,7 @@ define i16 @test2elt_signed(i64 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvspdpn f1, vs0
; CHECK-BE-NEXT: xxsldwi vs0, vs0, vs0, 1
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: xscvdpsxws f1, f1
; CHECK-BE-NEXT: xscvdpsxws f0, f0
@ -782,7 +782,7 @@ define i32 @test4elt_signed(<4 x float> %a) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-BE-NEXT: xscvspdpn f0, vs0
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f0, f0
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
@ -925,7 +925,7 @@ define i64 @test8elt_signed(<8 x float>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs2, vs1, vs1, 3
; CHECK-BE-NEXT: xscvspdpn f2, vs2
; CHECK-BE-NEXT: xscvdpsxws f2, f2
@ -1190,7 +1190,7 @@ define <16 x i8> @test16elt_signed(<16 x float>* nocapture readonly) local_unnam
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI7_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xxsldwi vs4, vs3, vs3, 3
; CHECK-BE-NEXT: xscvspdpn f4, vs4
; CHECK-BE-NEXT: xscvdpsxws f4, f4

16
test/CodeGen/PowerPC/vec_conv_fp64_to_i16_elts.ll
View File

@ -43,7 +43,7 @@ define i32 @test2elt(<2 x double> %a) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvdpsxws f0, v2
; CHECK-BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
; CHECK-BE-NEXT: mtvsrwz v4, r3
@ -117,7 +117,7 @@ define i64 @test4elt(<4 x double>* nocapture readonly) local_unnamed_addr #1 {
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f2, f1
; CHECK-BE-NEXT: xxswapd vs1, vs1
; CHECK-BE-NEXT: xscvdpsxws f1, f1
@ -242,7 +242,7 @@ define <8 x i16> @test8elt(<8 x double>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xxswapd vs3, vs3
; CHECK-BE-NEXT: xscvdpsxws f3, f3
@ -469,7 +469,7 @@ define void @test16elt(<16 x i16>* noalias nocapture sret(<16 x i16>) %agg.resul
; CHECK-BE-NEXT: lxv vs0, 0(r4)
; CHECK-BE-NEXT: addis r5, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: addi r5, r5, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r5
; CHECK-BE-NEXT: lxv v2, 0(r5)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xscvdpsxws f5, f2
; CHECK-BE-NEXT: xscvdpsxws f6, f1
@ -588,7 +588,7 @@ define i32 @test2elt_signed(<2 x double> %a) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvdpsxws f0, v2
; CHECK-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
; CHECK-BE-NEXT: mtvsrwz v4, r3
@ -662,7 +662,7 @@ define i64 @test4elt_signed(<4 x double>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f2, f1
; CHECK-BE-NEXT: xxswapd vs1, vs1
; CHECK-BE-NEXT: xscvdpsxws f1, f1
@ -787,7 +787,7 @@ define <8 x i16> @test8elt_signed(<8 x double>* nocapture readonly) local_unname
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xxswapd vs3, vs3
; CHECK-BE-NEXT: xscvdpsxws f3, f3
@ -1014,7 +1014,7 @@ define void @test16elt_signed(<16 x i16>* noalias nocapture sret(<16 x i16>) %ag
; CHECK-BE-NEXT: lxv vs0, 0(r4)
; CHECK-BE-NEXT: addis r5, r2, .LCPI7_0@toc@ha
; CHECK-BE-NEXT: addi r5, r5, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r5
; CHECK-BE-NEXT: lxv v2, 0(r5)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xscvdpsxws f5, f2
; CHECK-BE-NEXT: xscvdpsxws f6, f1

16
test/CodeGen/PowerPC/vec_conv_fp64_to_i8_elts.ll
View File

@ -48,7 +48,7 @@ define i16 @test2elt(<2 x double> %a) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvdpsxws f0, v2
; CHECK-BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
; CHECK-BE-NEXT: mtvsrwz v4, r3
@ -125,7 +125,7 @@ define i32 @test4elt(<4 x double>* nocapture readonly) local_unnamed_addr #1 {
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f2, f1
; CHECK-BE-NEXT: xxswapd vs1, vs1
; CHECK-BE-NEXT: xscvdpsxws f1, f1
@ -254,7 +254,7 @@ define i64 @test8elt(<8 x double>* nocapture readonly) local_unnamed_addr #1 {
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xxswapd vs3, vs3
; CHECK-BE-NEXT: xscvdpsxws f3, f3
@ -487,7 +487,7 @@ define <16 x i8> @test16elt(<16 x double>* nocapture readonly) local_unnamed_add
; CHECK-BE-NEXT: lxv vs6, 96(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f7, f7
; CHECK-BE-NEXT: mffprwz r3, f8
; CHECK-BE-NEXT: mtvsrwz v3, r3
@ -603,7 +603,7 @@ define i16 @test2elt_signed(<2 x double> %a) local_unnamed_addr #0 {
; CHECK-BE-NEXT: xscvdpsxws f0, v2
; CHECK-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: mffprwz r3, f0
; CHECK-BE-NEXT: xxswapd vs0, v2
; CHECK-BE-NEXT: mtvsrwz v4, r3
@ -680,7 +680,7 @@ define i32 @test4elt_signed(<4 x double>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs0, 0(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f2, f1
; CHECK-BE-NEXT: xxswapd vs1, vs1
; CHECK-BE-NEXT: xscvdpsxws f1, f1
@ -809,7 +809,7 @@ define i64 @test8elt_signed(<8 x double>* nocapture readonly) local_unnamed_addr
; CHECK-BE-NEXT: lxv vs2, 32(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f4, f3
; CHECK-BE-NEXT: xxswapd vs3, vs3
; CHECK-BE-NEXT: xscvdpsxws f3, f3
@ -1042,7 +1042,7 @@ define <16 x i8> @test16elt_signed(<16 x double>* nocapture readonly) local_unna
; CHECK-BE-NEXT: lxv vs6, 96(r3)
; CHECK-BE-NEXT: addis r3, r2, .LCPI7_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r3
; CHECK-BE-NEXT: lxv v2, 0(r3)
; CHECK-BE-NEXT: xscvdpsxws f7, f7
; CHECK-BE-NEXT: mffprwz r3, f8
; CHECK-BE-NEXT: mtvsrwz v3, r3

8
test/CodeGen/PowerPC/vec_conv_i16_to_fp32_elts.ll
View File

@ -84,7 +84,7 @@ define <4 x float> @test4elt(i64 %a.coerce) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxwsp v2, v2
; CHECK-BE-NEXT: blr
@ -170,12 +170,12 @@ define void @test16elt(<16 x float>* noalias nocapture sret(<16 x float>) %agg.r
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: xxlxor v5, v5, v5
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx v4, 0, r4
; CHECK-P9-NEXT: lxv v4, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-P9-NEXT: vperm v0, v5, v3, v4
; CHECK-P9-NEXT: xvcvuxwsp vs0, v0
; CHECK-P9-NEXT: lxvx v0, 0, r4
; CHECK-P9-NEXT: lxv v0, 0(r4)
; CHECK-P9-NEXT: vperm v3, v5, v3, v0
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxwsp vs1, v3
@ -195,7 +195,7 @@ define void @test16elt(<16 x float>* noalias nocapture sret(<16 x float>) %agg.r
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: xxlxor v5, v5, v5
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: vperm v0, v5, v3, v4
; CHECK-BE-NEXT: vperm v4, v5, v2, v4
; CHECK-BE-NEXT: vmrglh v3, v5, v3

88
test/CodeGen/PowerPC/vec_conv_i16_to_fp64_elts.ll
View File

@ -27,7 +27,7 @@ define <2 x double> @test2elt(i32 %a.coerce) local_unnamed_addr #0 {
; CHECK-P9-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp v2, v2
; CHECK-P9-NEXT: blr
@ -38,7 +38,7 @@ define <2 x double> @test2elt(i32 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp v2, v2
; CHECK-BE-NEXT: blr
@ -76,12 +76,12 @@ define void @test4elt(<4 x double>* noalias nocapture sret(<4 x double>) %agg.re
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v2
@ -94,12 +94,12 @@ define void @test4elt(<4 x double>* noalias nocapture sret(<4 x double>) %agg.re
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v2
@ -154,24 +154,24 @@ define void @test8elt(<8 x double>* noalias nocapture sret(<8 x double>) %agg.re
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_2@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_3@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxddp vs3, v2
@ -183,24 +183,24 @@ define void @test8elt(<8 x double>* noalias nocapture sret(<8 x double>) %agg.re
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_3@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxddp vs3, v2
@ -278,24 +278,24 @@ define void @test16elt(<16 x double>* noalias nocapture sret(<16 x double>) %agg
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: xxlxor v5, v5, v5
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx v4, 0, r4
; CHECK-P9-NEXT: lxv v4, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-P9-NEXT: vperm v0, v5, v3, v4
; CHECK-P9-NEXT: xvcvuxddp vs0, v0
; CHECK-P9-NEXT: lxvx v0, 0, r4
; CHECK-P9-NEXT: lxv v0, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-P9-NEXT: vperm v1, v5, v3, v0
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v1
; CHECK-P9-NEXT: lxvx v1, 0, r4
; CHECK-P9-NEXT: lxv v1, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-P9-NEXT: vperm v6, v5, v3, v1
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxddp vs2, v6
; CHECK-P9-NEXT: lxvx v6, 0, r4
; CHECK-P9-NEXT: lxv v6, 0(r4)
; CHECK-P9-NEXT: vperm v3, v5, v3, v6
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxddp vs3, v3
@ -321,24 +321,24 @@ define void @test16elt(<16 x double>* noalias nocapture sret(<16 x double>) %agg
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: xxlxor v5, v5, v5
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-BE-NEXT: vperm v0, v5, v3, v4
; CHECK-BE-NEXT: xvcvuxddp vs0, v0
; CHECK-BE-NEXT: lxvx v0, 0, r4
; CHECK-BE-NEXT: lxv v0, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-BE-NEXT: vperm v1, v5, v3, v0
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v1
; CHECK-BE-NEXT: lxvx v1, 0, r4
; CHECK-BE-NEXT: lxv v1, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-BE-NEXT: vperm v6, v5, v3, v1
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxddp vs2, v6
; CHECK-BE-NEXT: lxvx v6, 0, r4
; CHECK-BE-NEXT: lxv v6, 0(r4)
; CHECK-BE-NEXT: vperm v3, v5, v3, v6
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxddp vs3, v3
@ -385,7 +385,7 @@ define <2 x double> @test2elt_signed(i32 %a.coerce) local_unnamed_addr #0 {
; CHECK-P9-NEXT: mtvsrwz v2, r3
; CHECK-P9-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v2, v2
; CHECK-P9-NEXT: xvcvsxddp v2, v2
@ -396,7 +396,7 @@ define <2 x double> @test2elt_signed(i32 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: mtvsrwz v2, r3
; CHECK-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: vextsh2d v2, v2
; CHECK-BE-NEXT: xvcvsxddp v2, v2
@ -441,13 +441,13 @@ define void @test4elt_signed(<4 x double>* noalias nocapture sret(<4 x double>)
; CHECK-P9-NEXT: mtvsrd v2, r4
; CHECK-P9-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI5_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI5_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsh2d v2, v2
@ -461,13 +461,13 @@ define void @test4elt_signed(<4 x double>* noalias nocapture sret(<4 x double>)
; CHECK-BE-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: xxlxor v3, v3, v3
; CHECK-BE-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI5_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI5_1@toc@l
; CHECK-BE-NEXT: vperm v3, v3, v2, v4
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsh2d v2, v2
@ -533,27 +533,27 @@ define void @test8elt_signed(<8 x double>* noalias nocapture sret(<8 x double>)
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_2@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_3@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: vextsh2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: vextsh2d v2, v2
@ -566,27 +566,27 @@ define void @test8elt_signed(<8 x double>* noalias nocapture sret(<8 x double>)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_3@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs1, 48(r3)
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs2, 0(r3)
; CHECK-BE-NEXT: vextsh2d v2, v2
@ -682,20 +682,20 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-P9-NEXT: addis r5, r2, .LCPI7_0@toc@ha
; CHECK-P9-NEXT: lxv v2, 0(r4)
; CHECK-P9-NEXT: addi r5, r5, .LCPI7_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r5
; CHECK-P9-NEXT: lxv v3, 0(r5)
; CHECK-P9-NEXT: addis r5, r2, .LCPI7_1@toc@ha
; CHECK-P9-NEXT: addi r5, r5, .LCPI7_1@toc@l
; CHECK-P9-NEXT: lxvx v5, 0, r5
; CHECK-P9-NEXT: lxv v5, 0(r5)
; CHECK-P9-NEXT: addis r5, r2, .LCPI7_2@toc@ha
; CHECK-P9-NEXT: vperm v4, v2, v2, v3
; CHECK-P9-NEXT: addi r5, r5, .LCPI7_2@toc@l
; CHECK-P9-NEXT: vextsh2d v4, v4
; CHECK-P9-NEXT: lxvx v0, 0, r5
; CHECK-P9-NEXT: lxv v0, 0(r5)
; CHECK-P9-NEXT: addis r5, r2, .LCPI7_3@toc@ha
; CHECK-P9-NEXT: xvcvsxddp vs0, v4
; CHECK-P9-NEXT: vperm v4, v2, v2, v5
; CHECK-P9-NEXT: addi r5, r5, .LCPI7_3@toc@l
; CHECK-P9-NEXT: lxvx v1, 0, r5
; CHECK-P9-NEXT: lxv v1, 0(r5)
; CHECK-P9-NEXT: vextsh2d v4, v4
; CHECK-P9-NEXT: xvcvsxddp vs1, v4
; CHECK-P9-NEXT: vperm v4, v2, v2, v0
@ -736,10 +736,10 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_2@toc@ha
; CHECK-BE-NEXT: addi r5, r5, .LCPI7_0@toc@l
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_2@toc@l
; CHECK-BE-NEXT: lxvx v2, 0, r5
; CHECK-BE-NEXT: lxv v2, 0(r5)
; CHECK-BE-NEXT: addis r5, r2, .LCPI7_1@toc@ha
; CHECK-BE-NEXT: addi r5, r5, .LCPI7_1@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r5
; CHECK-BE-NEXT: lxv v3, 0(r5)
; CHECK-BE-NEXT: vperm v0, v5, v4, v2
; CHECK-BE-NEXT: vperm v2, v5, v1, v2
; CHECK-BE-NEXT: vextsh2d v2, v2
@ -751,7 +751,7 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-BE-NEXT: vextsh2d v2, v2
; CHECK-BE-NEXT: vextsh2d v0, v0
; CHECK-BE-NEXT: xvcvsxddp vs3, v2
; CHECK-BE-NEXT: lxvx v2, 0, r4
; CHECK-BE-NEXT: lxv v2, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_3@toc@ha
; CHECK-BE-NEXT: xvcvsxddp vs1, v0
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_3@toc@l
@ -764,7 +764,7 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-BE-NEXT: vextsh2d v3, v3
; CHECK-BE-NEXT: vextsh2d v2, v2
; CHECK-BE-NEXT: xvcvsxddp vs4, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: xvcvsxddp vs6, v2
; CHECK-BE-NEXT: vperm v4, v4, v4, v3
; CHECK-BE-NEXT: vperm v2, v1, v1, v3

56
test/CodeGen/PowerPC/vec_conv_i8_to_fp32_elts.ll
View File

@ -79,7 +79,7 @@ define <4 x float> @test4elt(i32 %a.coerce) local_unnamed_addr #1 {
; CHECK-P9-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxwsp v2, v2
; CHECK-P9-NEXT: blr
@ -90,7 +90,7 @@ define <4 x float> @test4elt(i32 %a.coerce) local_unnamed_addr #1 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r3, r3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxwsp v2, v2
; CHECK-BE-NEXT: blr
@ -126,12 +126,12 @@ define void @test8elt(<8 x float>* noalias nocapture sret(<8 x float>) %agg.resu
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxwsp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxwsp vs1, v2
@ -144,12 +144,12 @@ define void @test8elt(<8 x float>* noalias nocapture sret(<8 x float>) %agg.resu
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxwsp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxwsp vs1, v2
@ -200,24 +200,24 @@ define void @test16elt(<16 x float>* noalias nocapture sret(<16 x float>) %agg.r
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxwsp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxwsp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxwsp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxwsp vs3, v2
@ -229,24 +229,24 @@ define void @test16elt(<16 x float>* noalias nocapture sret(<16 x float>) %agg.r
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxwsp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxwsp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxwsp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxwsp vs3, v2
@ -334,7 +334,7 @@ define <4 x float> @test4elt_signed(i32 %a.coerce) local_unnamed_addr #1 {
; CHECK-P9-NEXT: mtvsrwz v2, r3
; CHECK-P9-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: vextsb2w v2, v2
; CHECK-P9-NEXT: xvcvsxwsp v2, v2
@ -345,7 +345,7 @@ define <4 x float> @test4elt_signed(i32 %a.coerce) local_unnamed_addr #1 {
; CHECK-BE-NEXT: mtvsrwz v2, r3
; CHECK-BE-NEXT: addis r3, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: vextsb2w v2, v2
; CHECK-BE-NEXT: xvcvsxwsp v2, v2
@ -386,13 +386,13 @@ define void @test8elt_signed(<8 x float>* noalias nocapture sret(<8 x float>) %a
; CHECK-P9-NEXT: mtvsrd v2, r4
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsb2w v3, v3
; CHECK-P9-NEXT: xvcvsxwsp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsb2w v2, v2
@ -406,13 +406,13 @@ define void @test8elt_signed(<8 x float>* noalias nocapture sret(<8 x float>) %a
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: xxlxor v3, v3, v3
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-BE-NEXT: vperm v3, v3, v2, v4
; CHECK-BE-NEXT: vextsb2w v3, v3
; CHECK-BE-NEXT: xvcvsxwsp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsb2w v2, v2
@ -472,27 +472,27 @@ define void @test16elt_signed(<16 x float>* noalias nocapture sret(<16 x float>)
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsb2w v3, v3
; CHECK-P9-NEXT: xvcvsxwsp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_2@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsb2w v3, v3
; CHECK-P9-NEXT: xvcvsxwsp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_3@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: vextsb2w v3, v3
; CHECK-P9-NEXT: xvcvsxwsp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: vextsb2w v2, v2
@ -505,27 +505,27 @@ define void @test16elt_signed(<16 x float>* noalias nocapture sret(<16 x float>)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: vextsb2w v3, v3
; CHECK-BE-NEXT: xvcvsxwsp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsb2w v3, v3
; CHECK-BE-NEXT: xvcvsxwsp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_3@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs1, 48(r3)
; CHECK-BE-NEXT: vextsb2w v3, v3
; CHECK-BE-NEXT: xvcvsxwsp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs2, 0(r3)
; CHECK-BE-NEXT: vextsb2w v2, v2

120
test/CodeGen/PowerPC/vec_conv_i8_to_fp64_elts.ll
View File

@ -27,7 +27,7 @@ define <2 x double> @test2elt(i16 %a.coerce) local_unnamed_addr #0 {
; CHECK-P9-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp v2, v2
; CHECK-P9-NEXT: blr
@ -38,7 +38,7 @@ define <2 x double> @test2elt(i16 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: addis r3, r2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r3, r3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp v2, v2
; CHECK-BE-NEXT: blr
@ -76,12 +76,12 @@ define void @test4elt(<4 x double>* noalias nocapture sret(<4 x double>) %agg.re
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v2
@ -94,12 +94,12 @@ define void @test4elt(<4 x double>* noalias nocapture sret(<4 x double>) %agg.re
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI1_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI1_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v2
@ -156,24 +156,24 @@ define void @test8elt(<8 x double>* noalias nocapture sret(<8 x double>) %agg.re
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_2@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI2_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI2_3@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxddp vs3, v2
@ -186,24 +186,24 @@ define void @test8elt(<8 x double>* noalias nocapture sret(<8 x double>) %agg.re
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI2_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI2_3@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxddp vs3, v2
@ -290,48 +290,48 @@ define void @test16elt(<16 x double>* noalias nocapture sret(<16 x double>) %agg
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-P9-NEXT: xxlxor v4, v4, v4
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: xvcvuxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: xvcvuxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: xvcvuxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_4@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_4@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: xvcvuxddp vs3, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_5@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_5@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs3, 48(r3)
; CHECK-P9-NEXT: xvcvuxddp vs4, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_6@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_6@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs4, 64(r3)
; CHECK-P9-NEXT: xvcvuxddp vs5, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI3_7@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI3_7@toc@l
; CHECK-P9-NEXT: vperm v3, v4, v2, v3
; CHECK-P9-NEXT: stxv vs5, 80(r3)
; CHECK-P9-NEXT: xvcvuxddp vs6, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v4, v2, v3
; CHECK-P9-NEXT: stxv vs6, 96(r3)
; CHECK-P9-NEXT: xvcvuxddp vs7, v2
@ -343,48 +343,48 @@ define void @test16elt(<16 x double>* noalias nocapture sret(<16 x double>) %agg
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: xvcvuxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 0(r3)
; CHECK-BE-NEXT: xvcvuxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_3@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs1, 16(r3)
; CHECK-BE-NEXT: xvcvuxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_4@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_4@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs2, 32(r3)
; CHECK-BE-NEXT: xvcvuxddp vs3, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_5@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_5@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs3, 48(r3)
; CHECK-BE-NEXT: xvcvuxddp vs4, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_6@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_6@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs4, 64(r3)
; CHECK-BE-NEXT: xvcvuxddp vs5, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI3_7@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI3_7@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs5, 80(r3)
; CHECK-BE-NEXT: xvcvuxddp vs6, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v4, v2, v3
; CHECK-BE-NEXT: stxv vs6, 96(r3)
; CHECK-BE-NEXT: xvcvuxddp vs7, v2
@ -418,7 +418,7 @@ define <2 x double> @test2elt_signed(i16 %a.coerce) local_unnamed_addr #0 {
; CHECK-P9-NEXT: mtvsrwz v2, r3
; CHECK-P9-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-P9-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r3
; CHECK-P9-NEXT: lxv v3, 0(r3)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: vextsb2d v2, v2
; CHECK-P9-NEXT: xvcvsxddp v2, v2
@ -429,7 +429,7 @@ define <2 x double> @test2elt_signed(i16 %a.coerce) local_unnamed_addr #0 {
; CHECK-BE-NEXT: mtvsrwz v2, r3
; CHECK-BE-NEXT: addis r3, r2, .LCPI4_0@toc@ha
; CHECK-BE-NEXT: addi r3, r3, .LCPI4_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r3
; CHECK-BE-NEXT: lxv v3, 0(r3)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: vextsb2d v2, v2
; CHECK-BE-NEXT: xvcvsxddp v2, v2
@ -474,13 +474,13 @@ define void @test4elt_signed(<4 x double>* noalias nocapture sret(<4 x double>)
; CHECK-P9-NEXT: mtvsrwz v2, r4
; CHECK-P9-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI5_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI5_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsb2d v2, v2
@ -494,13 +494,13 @@ define void @test4elt_signed(<4 x double>* noalias nocapture sret(<4 x double>)
; CHECK-BE-NEXT: addis r4, r2, .LCPI5_0@toc@ha
; CHECK-BE-NEXT: xxlxor v3, v3, v3
; CHECK-BE-NEXT: addi r4, r4, .LCPI5_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI5_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI5_1@toc@l
; CHECK-BE-NEXT: vperm v3, v3, v2, v4
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsb2d v2, v2
@ -568,27 +568,27 @@ define void @test8elt_signed(<8 x double>* noalias nocapture sret(<8 x double>)
; CHECK-P9-NEXT: mtvsrd v2, r4
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_2@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI6_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI6_3@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: vextsb2d v2, v2
@ -602,27 +602,27 @@ define void @test8elt_signed(<8 x double>* noalias nocapture sret(<8 x double>)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_0@toc@ha
; CHECK-BE-NEXT: xxlxor v4, v4, v4
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_0@toc@l
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_1@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs0, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_2@toc@l
; CHECK-BE-NEXT: vperm v3, v4, v2, v3
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs1, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI6_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI6_3@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs1, 48(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs2, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs2, 0(r3)
; CHECK-BE-NEXT: vextsb2d v2, v2
@ -728,55 +728,55 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_0@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_0@toc@l
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_1@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_1@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs0, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_2@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_2@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs0, 0(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs1, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_3@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_3@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs1, 16(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs2, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_4@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_4@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs2, 32(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs3, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_5@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_5@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs3, 48(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs4, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_6@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_6@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs4, 64(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs5, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: addis r4, r2, .LCPI7_7@toc@ha
; CHECK-P9-NEXT: addi r4, r4, .LCPI7_7@toc@l
; CHECK-P9-NEXT: vperm v3, v2, v2, v3
; CHECK-P9-NEXT: stxv vs5, 80(r3)
; CHECK-P9-NEXT: vextsb2d v3, v3
; CHECK-P9-NEXT: xvcvsxddp vs6, v3
; CHECK-P9-NEXT: lxvx v3, 0, r4
; CHECK-P9-NEXT: lxv v3, 0(r4)
; CHECK-P9-NEXT: vperm v2, v2, v2, v3
; CHECK-P9-NEXT: stxv vs6, 96(r3)
; CHECK-P9-NEXT: vextsb2d v2, v2
@ -789,55 +789,55 @@ define void @test16elt_signed(<16 x double>* noalias nocapture sret(<16 x double
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_0@toc@ha
; CHECK-BE-NEXT: xxlxor v3, v3, v3
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_0@toc@l
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_1@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_1@toc@l
; CHECK-BE-NEXT: vperm v4, v3, v2, v4
; CHECK-BE-NEXT: vextsb2d v4, v4
; CHECK-BE-NEXT: xvcvsxddp vs0, v4
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_2@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_2@toc@l
; CHECK-BE-NEXT: vperm v4, v3, v2, v4
; CHECK-BE-NEXT: stxv vs0, 16(r3)
; CHECK-BE-NEXT: vextsb2d v4, v4
; CHECK-BE-NEXT: xvcvsxddp vs1, v4
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_3@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_3@toc@l
; CHECK-BE-NEXT: vperm v4, v3, v2, v4
; CHECK-BE-NEXT: stxv vs1, 48(r3)
; CHECK-BE-NEXT: vextsb2d v4, v4
; CHECK-BE-NEXT: xvcvsxddp vs2, v4
; CHECK-BE-NEXT: lxvx v4, 0, r4
; CHECK-BE-NEXT: lxv v4, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_4@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_4@toc@l
; CHECK-BE-NEXT: vperm v3, v3, v2, v4
; CHECK-BE-NEXT: stxv vs2, 80(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs3, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_5@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_5@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs3, 112(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs4, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_6@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_6@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs4, 0(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs5, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: addis r4, r2, .LCPI7_7@toc@ha
; CHECK-BE-NEXT: addi r4, r4, .LCPI7_7@toc@l
; CHECK-BE-NEXT: vperm v3, v2, v2, v3
; CHECK-BE-NEXT: stxv vs5, 32(r3)
; CHECK-BE-NEXT: vextsb2d v3, v3
; CHECK-BE-NEXT: xvcvsxddp vs6, v3
; CHECK-BE-NEXT: lxvx v3, 0, r4
; CHECK-BE-NEXT: lxv v3, 0(r4)
; CHECK-BE-NEXT: vperm v2, v2, v2, v3
; CHECK-BE-NEXT: stxv vs6, 64(r3)
; CHECK-BE-NEXT: vextsb2d v2, v2

2
test/CodeGen/PowerPC/vec_extract_p9.ll
View File

@ -180,7 +180,7 @@ define double @test10(<4 x i32> %a, <4 x i32> %b) {
; CHECK-LE: # %bb.0: # %entry
; CHECK-LE-NEXT: addis 3, 2, .LCPI9_0@toc@ha
; CHECK-LE-NEXT: addi 3, 3, .LCPI9_0@toc@l
; CHECK-LE-NEXT: lxvx 36, 0, 3
; CHECK-LE-NEXT: lxv 36, 0(3)
; CHECK-LE-NEXT: addis 3, 2, .LCPI9_1@toc@ha
; CHECK-LE-NEXT: lfs 0, .LCPI9_1@toc@l(3)
; CHECK-LE-NEXT: vperm 2, 3, 2, 4

10
test/CodeGen/PowerPC/vec_int_ext.ll
View File

@ -12,7 +12,7 @@ define <4 x i32> @vextsb2wLE(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI0_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI0_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: vextsb2w 2, 2
; CHECK-BE-NEXT: blr
@ -43,7 +43,7 @@ define <2 x i64> @vextsb2dLE(<16 x i8> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI1_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI1_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: vextsb2d 2, 2
; CHECK-BE-NEXT: blr
@ -68,7 +68,7 @@ define <4 x i32> @vextsh2wLE(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI2_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI2_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: vextsh2w 2, 2
; CHECK-BE-NEXT: blr
@ -99,7 +99,7 @@ define <2 x i64> @vextsh2dLE(<8 x i16> %a) {
; CHECK-BE: # %bb.0: # %entry
; CHECK-BE-NEXT: addis 3, 2, .LCPI3_0@toc@ha
; CHECK-BE-NEXT: addi 3, 3, .LCPI3_0@toc@l
; CHECK-BE-NEXT: lxvx 35, 0, 3
; CHECK-BE-NEXT: lxv 35, 0(3)
; CHECK-BE-NEXT: vperm 2, 2, 2, 3
; CHECK-BE-NEXT: vextsh2d 2, 2
; CHECK-BE-NEXT: blr
@ -361,7 +361,7 @@ define <8 x i16> @testInvalidExtend(<16 x i8> %a) {
; CHECK-BE-NEXT: extsb 6, 6
; CHECK-BE-NEXT: mtvsrwz 32, 3
; CHECK-BE-NEXT: addi 9, 9, .LCPI11_0@toc@l
; CHECK-BE-NEXT: lxvx 36, 0, 9
; CHECK-BE-NEXT: lxv 36, 0(9)
; CHECK-BE-NEXT: vperm 2, 3, 2, 4
; CHECK-BE-NEXT: mtvsrwz 35, 8
; CHECK-BE-NEXT: vperm 3, 5, 3, 4

68
test/CodeGen/PowerPC/vector-constrained-fp-intrinsics.ll
View File

@ -80,7 +80,7 @@ define <3 x float> @constrained_vector_fdiv_v3f32(<3 x float> %x, <3 x float> %y
; PC64LE9-NEXT: xscvspdpn 1, 1
; PC64LE9-NEXT: xscvspdpn 2, 2
; PC64LE9-NEXT: xscvspdpn 3, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: xsdivsp 0, 1, 0
; PC64LE9-NEXT: xxswapd 1, 35
; PC64LE9-NEXT: xscvspdpn 1, 1
@ -364,7 +364,7 @@ define <3 x float> @constrained_vector_frem_v3f32(<3 x float> %x, <3 x float> %y
; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload
; PC64LE9-NEXT: lfd 30, 64(1) # 8-byte Folded Reload
; PC64LE9-NEXT: addi 3, 3, .LCPI7_0@toc@l
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: xscvdpspn 35, 31
; PC64LE9-NEXT: lfd 31, 72(1) # 8-byte Folded Reload
@ -675,7 +675,7 @@ define <3 x float> @constrained_vector_fmul_v3f32(<3 x float> %x, <3 x float> %y
; PC64LE9-NEXT: xscvspdpn 1, 1
; PC64LE9-NEXT: xscvspdpn 2, 2
; PC64LE9-NEXT: xscvspdpn 3, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: xsmulsp 0, 1, 0
; PC64LE9-NEXT: xxswapd 1, 35
; PC64LE9-NEXT: xscvspdpn 1, 1
@ -836,7 +836,7 @@ define <3 x float> @constrained_vector_fadd_v3f32(<3 x float> %x, <3 x float> %y
; PC64LE9-NEXT: xscvspdpn 1, 1
; PC64LE9-NEXT: xscvspdpn 2, 2
; PC64LE9-NEXT: xscvspdpn 3, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: xsaddsp 0, 1, 0
; PC64LE9-NEXT: xxswapd 1, 35
; PC64LE9-NEXT: xscvspdpn 1, 1
@ -997,7 +997,7 @@ define <3 x float> @constrained_vector_fsub_v3f32(<3 x float> %x, <3 x float> %y
; PC64LE9-NEXT: xscvspdpn 1, 1
; PC64LE9-NEXT: xscvspdpn 2, 2
; PC64LE9-NEXT: xscvspdpn 3, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: xssubsp 0, 1, 0
; PC64LE9-NEXT: xxswapd 1, 35
; PC64LE9-NEXT: xscvspdpn 1, 1
@ -1155,7 +1155,7 @@ define <3 x float> @constrained_vector_sqrt_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -1419,7 +1419,7 @@ define <3 x float> @constrained_vector_pow_v3f32(<3 x float> %x, <3 x float> %y)
; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload
; PC64LE9-NEXT: lfd 30, 64(1) # 8-byte Folded Reload
; PC64LE9-NEXT: addi 3, 3, .LCPI32_0@toc@l
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: xscvdpspn 35, 31
; PC64LE9-NEXT: lfd 31, 72(1) # 8-byte Folded Reload
@ -1846,7 +1846,7 @@ define <3 x float> @constrained_vector_powi_v3f32(<3 x float> %x, i32 %y) #0 {
; PC64LE9-NEXT: lfd 30, 64(1) # 8-byte Folded Reload
; PC64LE9-NEXT: ld 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: addi 3, 3, .LCPI37_0@toc@l
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: xscvdpspn 35, 31
; PC64LE9-NEXT: lfd 31, 72(1) # 8-byte Folded Reload
@ -2228,7 +2228,7 @@ define <3 x float> @constrained_vector_sin_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI42_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -2578,7 +2578,7 @@ define <3 x float> @constrained_vector_cos_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI47_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -2928,7 +2928,7 @@ define <3 x float> @constrained_vector_exp_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI52_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -3278,7 +3278,7 @@ define <3 x float> @constrained_vector_exp2_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI57_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -3628,7 +3628,7 @@ define <3 x float> @constrained_vector_log_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI62_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -3978,7 +3978,7 @@ define <3 x float> @constrained_vector_log10_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI67_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -4328,7 +4328,7 @@ define <3 x float> @constrained_vector_log2_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI72_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -4585,7 +4585,7 @@ define <3 x float> @constrained_vector_rint_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -4816,7 +4816,7 @@ define <3 x float> @constrained_vector_nearbyint_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI82_0@toc@l
; PC64LE9-NEXT: lfd 30, 48(1) # 8-byte Folded Reload
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: addi 1, 1, 64
; PC64LE9-NEXT: ld 0, 16(1)
@ -5138,7 +5138,7 @@ define <3 x float> @constrained_vector_maxnum_v3f32(<3 x float> %x, <3 x float>
; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload
; PC64LE9-NEXT: lfd 30, 64(1) # 8-byte Folded Reload
; PC64LE9-NEXT: addi 3, 3, .LCPI87_0@toc@l
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: xscvdpspn 35, 31
; PC64LE9-NEXT: lfd 31, 72(1) # 8-byte Folded Reload
@ -5379,7 +5379,7 @@ define <3 x float> @constrained_vector_minnum_v3f32(<3 x float> %x, <3 x float>
; PC64LE9-NEXT: lxv 62, 32(1) # 16-byte Folded Reload
; PC64LE9-NEXT: lfd 30, 64(1) # 8-byte Folded Reload
; PC64LE9-NEXT: addi 3, 3, .LCPI92_0@toc@l
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: xscvdpspn 35, 31
; PC64LE9-NEXT: lfd 31, 72(1) # 8-byte Folded Reload
@ -5579,7 +5579,7 @@ define <3 x i32> @constrained_vector_fptosi_v3i32_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI97_0@toc@l
; PC64LE9-NEXT: vmrghw 3, 4, 3
; PC64LE9-NEXT: xscvdpsxws 0, 0
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: mffprwz 3, 0
; PC64LE9-NEXT: mtvsrwz 34, 3
; PC64LE9-NEXT: vperm 2, 2, 3, 4
@ -5837,7 +5837,7 @@ define <3 x i32> @constrained_vector_fptosi_v3i32_v3f64(<3 x double> %x) #0 {
; PC64LE9-NEXT: addis 3, 2, .LCPI105_0@toc@ha
; PC64LE9-NEXT: addi 3, 3, .LCPI105_0@toc@l
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: mffprwz 3, 0
; PC64LE9-NEXT: mtvsrwz 36, 3
; PC64LE9-NEXT: vperm 2, 4, 2, 3
@ -6073,7 +6073,7 @@ define <3 x i32> @constrained_vector_fptoui_v3i32_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI113_0@toc@l
; PC64LE9-NEXT: vmrghw 3, 4, 3
; PC64LE9-NEXT: xscvdpuxws 0, 0
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: mffprwz 3, 0
; PC64LE9-NEXT: mtvsrwz 34, 3
; PC64LE9-NEXT: vperm 2, 2, 3, 4
@ -6330,7 +6330,7 @@ define <3 x i32> @constrained_vector_fptoui_v3i32_v3f64(<3 x double> %x) #0 {
; PC64LE9-NEXT: addis 3, 2, .LCPI121_0@toc@ha
; PC64LE9-NEXT: addi 3, 3, .LCPI121_0@toc@l
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: mffprwz 3, 0
; PC64LE9-NEXT: mtvsrwz 36, 3
; PC64LE9-NEXT: vperm 2, 4, 2, 3
@ -6540,7 +6540,7 @@ define <3 x float> @constrained_vector_fptrunc_v3f64(<3 x double> %x) #0 {
; PC64LE9-NEXT: xsrsp 0, 3
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -6751,7 +6751,7 @@ define <3 x float> @constrained_vector_ceil_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -6866,7 +6866,7 @@ define <3 x float> @constrained_vector_floor_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -6980,7 +6980,7 @@ define <3 x float> @constrained_vector_round_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -7095,7 +7095,7 @@ define <3 x float> @constrained_vector_trunc_v3f32(<3 x float> %x) #0 {
; PC64LE9-NEXT: xscvdpspn 35, 1
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
entry:
@ -7236,7 +7236,7 @@ define <2 x double> @constrained_vector_sitofp_v2f64_v2i16(<2 x i16> %x) #0 {
; PC64LE9: # %bb.0: # %entry
; PC64LE9-NEXT: addis 3, 2, .LCPI155_0@toc@ha
; PC64LE9-NEXT: addi 3, 3, .LCPI155_0@toc@l
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 2, 2, 3
; PC64LE9-NEXT: vextsh2d 2, 2
; PC64LE9-NEXT: xvcvsxddp 34, 34
@ -7451,7 +7451,7 @@ define <3 x float> @constrained_vector_sitofp_v3f32_v3i32(<3 x i32> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI161_0@toc@l
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 3, 4, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: mfvsrwz 3, 34
; PC64LE9-NEXT: mtfprwa 0, 3
; PC64LE9-NEXT: xscvsxdsp 0, 0
@ -7526,7 +7526,7 @@ define <3 x float> @constrained_vector_sitofp_v3f32_v3i64(<3 x i64> %x) #0 {
; PC64LE9-NEXT: mtfprd 0, 5
; PC64LE9-NEXT: xscvsxdsp 0, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr
@ -7800,7 +7800,7 @@ define <2 x double> @constrained_vector_uitofp_v2f64_v2i16(<2 x i16> %x) #0 {
; PC64LE9-NEXT: addis 3, 2, .LCPI173_0@toc@ha
; PC64LE9-NEXT: xxlxor 36, 36, 36
; PC64LE9-NEXT: addi 3, 3, .LCPI173_0@toc@l
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: xvcvuxddp 34, 34
; PC64LE9-NEXT: blr
@ -8014,7 +8014,7 @@ define <3 x float> @constrained_vector_uitofp_v3f32_v3i32(<3 x i32> %x) #0 {
; PC64LE9-NEXT: addi 3, 3, .LCPI179_0@toc@l
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vmrghw 3, 4, 3
; PC64LE9-NEXT: lxvx 36, 0, 3
; PC64LE9-NEXT: lxv 36, 0(3)
; PC64LE9-NEXT: mfvsrwz 3, 34
; PC64LE9-NEXT: mtfprwz 0, 3
; PC64LE9-NEXT: xscvuxdsp 0, 0
@ -8089,7 +8089,7 @@ define <3 x float> @constrained_vector_uitofp_v3f32_v3i64(<3 x i64> %x) #0 {
; PC64LE9-NEXT: mtfprd 0, 5
; PC64LE9-NEXT: xscvuxdsp 0, 0
; PC64LE9-NEXT: vmrghw 2, 3, 2
; PC64LE9-NEXT: lxvx 35, 0, 3
; PC64LE9-NEXT: lxv 35, 0(3)
; PC64LE9-NEXT: xscvdpspn 36, 0
; PC64LE9-NEXT: vperm 2, 4, 2, 3
; PC64LE9-NEXT: blr

2
test/CodeGen/PowerPC/vector-extend-sign.ll
View File

@ -149,7 +149,7 @@ define <2 x i64> @test_none(<2 x i64> %m) {
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: addis 3, 2, .LCPI5_0@toc@ha
; CHECK-P9-NEXT: addi 3, 3, .LCPI5_0@toc@l
; CHECK-P9-NEXT: lxvx 35, 0, 3
; CHECK-P9-NEXT: lxv 35, 0(3)
; CHECK-P9-NEXT: vsld 2, 2, 3
; CHECK-P9-NEXT: vsrad 2, 2, 3
; CHECK-P9-NEXT: blr

88
test/CodeGen/PowerPC/vector-ldst.ll
View File

@ -44,8 +44,8 @@ entry:
define dso_local <16 x i8> @ld_unalign16_vector(i8* nocapture readonly %ptr) {
; CHECK-LABEL: ld_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 1
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_unalign16_vector:
@ -70,8 +70,8 @@ entry:
define dso_local <16 x i8> @ld_align16_vector(i8* nocapture readonly %ptr) {
; CHECK-LABEL: ld_align16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 8
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 8
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_align16_vector:
@ -272,7 +272,7 @@ define dso_local <16 x i8> @ld_or_vector(i64 %ptr, i8 zeroext %off) {
; CHECK-LABEL: ld_or_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: or r3, r4, r3
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_or_vector:
@ -327,7 +327,7 @@ define dso_local <16 x i8> @ld_not_disjoint16_vector(i64 %ptr) {
; CHECK-LABEL: ld_not_disjoint16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_not_disjoint16_vector:
@ -353,8 +353,8 @@ define dso_local <16 x i8> @ld_disjoint_unalign16_vector(i64 %ptr) {
; CHECK-LABEL: ld_disjoint_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 6
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_disjoint_unalign16_vector:
@ -383,8 +383,8 @@ define dso_local <16 x i8> @ld_disjoint_align16_vector(i64 %ptr) {
; CHECK-LABEL: ld_disjoint_align16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 24
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: li r4, 24
; CHECK-NEXT: lxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_disjoint_align16_vector:
@ -414,7 +414,7 @@ define dso_local <16 x i8> @ld_not_disjoint32_vector(i64 %ptr) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 34463
; CHECK-NEXT: oris r3, r3, 1
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_not_disjoint32_vector:
@ -529,7 +529,7 @@ define dso_local <16 x i8> @ld_not_disjoint64_vector(i64 %ptr) {
; CHECK-P10-NEXT: pli r5, 3567587329
; CHECK-P10-NEXT: rldimi r5, r4, 32, 0
; CHECK-P10-NEXT: or r3, r3, r5
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: ld_not_disjoint64_vector:
@ -539,7 +539,7 @@ define dso_local <16 x i8> @ld_not_disjoint64_vector(i64 %ptr) {
; CHECK-P9-NEXT: oris r4, r4, 54437
; CHECK-P9-NEXT: ori r4, r4, 4097
; CHECK-P9-NEXT: or r3, r3, r4
; CHECK-P9-NEXT: lxvx v2, 0, r3
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_not_disjoint64_vector:
@ -665,7 +665,7 @@ define dso_local <16 x i8> @ld_cst_unalign16_vector() {
; CHECK-LABEL: ld_cst_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li r3, 255
; CHECK-NEXT: lxvx v2, 0, r3
; CHECK-NEXT: lxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_cst_unalign16_vector:
@ -712,14 +712,14 @@ define dso_local <16 x i8> @ld_cst_unalign32_vector() {
; CHECK-P10-LABEL: ld_cst_unalign32_vector:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 99999
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: ld_cst_unalign32_vector:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lis r3, 1
; CHECK-P9-NEXT: ori r3, r3, 34463
; CHECK-P9-NEXT: lxvx v2, 0, r3
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_cst_unalign32_vector:
@ -745,14 +745,14 @@ define dso_local <16 x i8> @ld_cst_align32_vector() {
; CHECK-P10-LABEL: ld_cst_align32_vector:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 9999900
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: ld_cst_align32_vector:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lis r3, 152
; CHECK-P9-NEXT: ori r3, r3, 38428
; CHECK-P9-NEXT: lxvx v2, 0, r3
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_cst_align32_vector:
@ -780,7 +780,7 @@ define dso_local <16 x i8> @ld_cst_unalign64_vector() {
; CHECK-P10-NEXT: pli r3, 232
; CHECK-P10-NEXT: pli r4, 3567587329
; CHECK-P10-NEXT: rldimi r4, r3, 32, 0
; CHECK-P10-NEXT: lxvx v2, 0, r4
; CHECK-P10-NEXT: lxv v2, 0(r4)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: ld_cst_unalign64_vector:
@ -789,7 +789,7 @@ define dso_local <16 x i8> @ld_cst_unalign64_vector() {
; CHECK-P9-NEXT: rldic r3, r3, 35, 24
; CHECK-P9-NEXT: oris r3, r3, 54437
; CHECK-P9-NEXT: ori r3, r3, 4097
; CHECK-P9-NEXT: lxvx v2, 0, r3
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_cst_unalign64_vector:
@ -820,7 +820,7 @@ define dso_local <16 x i8> @ld_cst_align64_vector() {
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 244140625
; CHECK-P10-NEXT: rldic r3, r3, 12, 24
; CHECK-P10-NEXT: lxvx v2, 0, r3
; CHECK-P10-NEXT: lxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: ld_cst_align64_vector:
@ -828,7 +828,7 @@ define dso_local <16 x i8> @ld_cst_align64_vector() {
; CHECK-P9-NEXT: lis r3, 3725
; CHECK-P9-NEXT: ori r3, r3, 19025
; CHECK-P9-NEXT: rldic r3, r3, 12, 24
; CHECK-P9-NEXT: lxvx v2, 0, r3
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: ld_cst_align64_vector:
@ -877,8 +877,8 @@ entry:
define dso_local void @st_unalign16_vector(i8* nocapture %ptr, <16 x i8> %str) {
; CHECK-LABEL: st_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 1
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 1
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_unalign16_vector:
@ -903,8 +903,8 @@ entry:
define dso_local void @st_align16_vector(i8* nocapture %ptr, <16 x i8> %str) {
; CHECK-LABEL: st_align16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: addi r3, r3, 8
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 8
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_align16_vector:
@ -1105,7 +1105,7 @@ define dso_local void @st_or1_vector(i64 %ptr, i8 zeroext %off, <16 x i8> %str)
; CHECK-LABEL: st_or1_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: or r3, r4, r3
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_or1_vector:
@ -1160,7 +1160,7 @@ define dso_local void @st_not_disjoint16_vector(i64 %ptr, <16 x i8> %str) {
; CHECK-LABEL: st_not_disjoint16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_not_disjoint16_vector:
@ -1186,8 +1186,8 @@ define dso_local void @st_disjoint_unalign16_vector(i64 %ptr, <16 x i8> %str) {
; CHECK-LABEL: st_disjoint_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 6
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 6
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_disjoint_unalign16_vector:
@ -1216,8 +1216,8 @@ define dso_local void @st_disjoint_align16_vector(i64 %ptr, <16 x i8> %str) {
; CHECK-LABEL: st_disjoint_align16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: rldicr r3, r3, 0, 51
; CHECK-NEXT: ori r3, r3, 24
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: li r4, 24
; CHECK-NEXT: stxvx v2, r3, r4
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_disjoint_align16_vector:
@ -1247,7 +1247,7 @@ define dso_local void @st_not_disjoint32_vector(i64 %ptr, <16 x i8> %str) {
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: ori r3, r3, 34463
; CHECK-NEXT: oris r3, r3, 1
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_not_disjoint32_vector:
@ -1362,7 +1362,7 @@ define dso_local void @st_not_disjoint64_vector(i64 %ptr, <16 x i8> %str) {
; CHECK-P10-NEXT: pli r5, 3567587329
; CHECK-P10-NEXT: rldimi r5, r4, 32, 0
; CHECK-P10-NEXT: or r3, r3, r5
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: st_not_disjoint64_vector:
@ -1372,7 +1372,7 @@ define dso_local void @st_not_disjoint64_vector(i64 %ptr, <16 x i8> %str) {
; CHECK-P9-NEXT: oris r4, r4, 54437
; CHECK-P9-NEXT: ori r4, r4, 4097
; CHECK-P9-NEXT: or r3, r3, r4
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_not_disjoint64_vector:
@ -1498,7 +1498,7 @@ define dso_local void @st_cst_unalign16_vector(<16 x i8> %str) {
; CHECK-LABEL: st_cst_unalign16_vector:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: li r3, 255
; CHECK-NEXT: stxvx v2, 0, r3
; CHECK-NEXT: stxv v2, 0(r3)
; CHECK-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_cst_unalign16_vector:
@ -1545,14 +1545,14 @@ define dso_local void @st_cst_unalign32_vector(<16 x i8> %str) {
; CHECK-P10-LABEL: st_cst_unalign32_vector:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 99999
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: st_cst_unalign32_vector:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lis r3, 1
; CHECK-P9-NEXT: ori r3, r3, 34463
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_cst_unalign32_vector:
@ -1578,14 +1578,14 @@ define dso_local void @st_cst_align32_vector(<16 x i8> %str) {
; CHECK-P10-LABEL: st_cst_align32_vector:
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 9999900
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: st_cst_align32_vector:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lis r3, 152
; CHECK-P9-NEXT: ori r3, r3, 38428
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_cst_align32_vector:
@ -1613,7 +1613,7 @@ define dso_local void @st_cst_unalign64_vector(<16 x i8> %str) {
; CHECK-P10-NEXT: pli r3, 232
; CHECK-P10-NEXT: pli r4, 3567587329
; CHECK-P10-NEXT: rldimi r4, r3, 32, 0
; CHECK-P10-NEXT: stxvx v2, 0, r4
; CHECK-P10-NEXT: stxv v2, 0(r4)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: st_cst_unalign64_vector:
@ -1622,7 +1622,7 @@ define dso_local void @st_cst_unalign64_vector(<16 x i8> %str) {
; CHECK-P9-NEXT: rldic r3, r3, 35, 24
; CHECK-P9-NEXT: oris r3, r3, 54437
; CHECK-P9-NEXT: ori r3, r3, 4097
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_cst_unalign64_vector:
@ -1653,7 +1653,7 @@ define dso_local void @st_cst_align64_vector(<16 x i8> %str) {
; CHECK-P10: # %bb.0: # %entry
; CHECK-P10-NEXT: pli r3, 244140625
; CHECK-P10-NEXT: rldic r3, r3, 12, 24
; CHECK-P10-NEXT: stxvx v2, 0, r3
; CHECK-P10-NEXT: stxv v2, 0(r3)
; CHECK-P10-NEXT: blr
;
; CHECK-P9-LABEL: st_cst_align64_vector:
@ -1661,7 +1661,7 @@ define dso_local void @st_cst_align64_vector(<16 x i8> %str) {
; CHECK-P9-NEXT: lis r3, 3725
; CHECK-P9-NEXT: ori r3, r3, 19025
; CHECK-P9-NEXT: rldic r3, r3, 12, 24
; CHECK-P9-NEXT: stxvx v2, 0, r3
; CHECK-P9-NEXT: stxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-P8-LE-LABEL: st_cst_align64_vector:

248
test/CodeGen/PowerPC/vector-popcnt-128-ult-ugt.ll
View File

@ -11998,7 +11998,7 @@ define <2 x i64> @ugt_1_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI100_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI100_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12063,7 +12063,7 @@ define <2 x i64> @ult_2_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI101_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI101_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12197,7 +12197,7 @@ define <2 x i64> @ugt_2_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI102_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI102_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12331,7 +12331,7 @@ define <2 x i64> @ult_3_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI103_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI103_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12465,7 +12465,7 @@ define <2 x i64> @ugt_3_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI104_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI104_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12599,7 +12599,7 @@ define <2 x i64> @ult_4_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI105_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI105_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12733,7 +12733,7 @@ define <2 x i64> @ugt_4_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI106_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI106_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -12867,7 +12867,7 @@ define <2 x i64> @ult_5_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI107_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI107_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13001,7 +13001,7 @@ define <2 x i64> @ugt_5_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI108_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI108_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13135,7 +13135,7 @@ define <2 x i64> @ult_6_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI109_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI109_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13269,7 +13269,7 @@ define <2 x i64> @ugt_6_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI110_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI110_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13403,7 +13403,7 @@ define <2 x i64> @ult_7_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI111_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI111_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13537,7 +13537,7 @@ define <2 x i64> @ugt_7_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI112_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI112_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13671,7 +13671,7 @@ define <2 x i64> @ult_8_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI113_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI113_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13805,7 +13805,7 @@ define <2 x i64> @ugt_8_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI114_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI114_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -13939,7 +13939,7 @@ define <2 x i64> @ult_9_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI115_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI115_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14073,7 +14073,7 @@ define <2 x i64> @ugt_9_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI116_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI116_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14207,7 +14207,7 @@ define <2 x i64> @ult_10_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI117_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI117_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14341,7 +14341,7 @@ define <2 x i64> @ugt_10_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI118_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI118_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14475,7 +14475,7 @@ define <2 x i64> @ult_11_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI119_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI119_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14609,7 +14609,7 @@ define <2 x i64> @ugt_11_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI120_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI120_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14743,7 +14743,7 @@ define <2 x i64> @ult_12_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI121_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI121_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -14877,7 +14877,7 @@ define <2 x i64> @ugt_12_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI122_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI122_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15011,7 +15011,7 @@ define <2 x i64> @ult_13_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI123_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI123_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15145,7 +15145,7 @@ define <2 x i64> @ugt_13_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI124_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI124_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15279,7 +15279,7 @@ define <2 x i64> @ult_14_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI125_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI125_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15413,7 +15413,7 @@ define <2 x i64> @ugt_14_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI126_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI126_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15547,7 +15547,7 @@ define <2 x i64> @ult_15_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI127_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI127_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15681,7 +15681,7 @@ define <2 x i64> @ugt_15_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI128_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI128_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15815,7 +15815,7 @@ define <2 x i64> @ult_16_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI129_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI129_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -15949,7 +15949,7 @@ define <2 x i64> @ugt_16_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI130_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI130_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16083,7 +16083,7 @@ define <2 x i64> @ult_17_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI131_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI131_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16217,7 +16217,7 @@ define <2 x i64> @ugt_17_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI132_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI132_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16351,7 +16351,7 @@ define <2 x i64> @ult_18_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI133_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI133_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16485,7 +16485,7 @@ define <2 x i64> @ugt_18_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI134_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI134_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16619,7 +16619,7 @@ define <2 x i64> @ult_19_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI135_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI135_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16753,7 +16753,7 @@ define <2 x i64> @ugt_19_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI136_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI136_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -16887,7 +16887,7 @@ define <2 x i64> @ult_20_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI137_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI137_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17021,7 +17021,7 @@ define <2 x i64> @ugt_20_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI138_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI138_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17155,7 +17155,7 @@ define <2 x i64> @ult_21_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI139_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI139_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17289,7 +17289,7 @@ define <2 x i64> @ugt_21_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI140_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI140_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17423,7 +17423,7 @@ define <2 x i64> @ult_22_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI141_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI141_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17557,7 +17557,7 @@ define <2 x i64> @ugt_22_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI142_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI142_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17691,7 +17691,7 @@ define <2 x i64> @ult_23_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI143_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI143_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17825,7 +17825,7 @@ define <2 x i64> @ugt_23_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI144_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI144_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -17959,7 +17959,7 @@ define <2 x i64> @ult_24_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI145_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI145_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18093,7 +18093,7 @@ define <2 x i64> @ugt_24_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI146_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI146_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18227,7 +18227,7 @@ define <2 x i64> @ult_25_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI147_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI147_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18361,7 +18361,7 @@ define <2 x i64> @ugt_25_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI148_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI148_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18495,7 +18495,7 @@ define <2 x i64> @ult_26_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI149_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI149_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18629,7 +18629,7 @@ define <2 x i64> @ugt_26_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI150_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI150_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18763,7 +18763,7 @@ define <2 x i64> @ult_27_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI151_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI151_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -18897,7 +18897,7 @@ define <2 x i64> @ugt_27_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI152_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI152_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19031,7 +19031,7 @@ define <2 x i64> @ult_28_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI153_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI153_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19165,7 +19165,7 @@ define <2 x i64> @ugt_28_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI154_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI154_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19299,7 +19299,7 @@ define <2 x i64> @ult_29_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI155_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI155_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19433,7 +19433,7 @@ define <2 x i64> @ugt_29_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI156_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI156_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19567,7 +19567,7 @@ define <2 x i64> @ult_30_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI157_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI157_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19701,7 +19701,7 @@ define <2 x i64> @ugt_30_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI158_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI158_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19835,7 +19835,7 @@ define <2 x i64> @ult_31_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI159_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI159_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -19969,7 +19969,7 @@ define <2 x i64> @ugt_31_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI160_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI160_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20103,7 +20103,7 @@ define <2 x i64> @ult_32_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI161_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI161_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20237,7 +20237,7 @@ define <2 x i64> @ugt_32_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI162_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI162_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20371,7 +20371,7 @@ define <2 x i64> @ult_33_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI163_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI163_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20505,7 +20505,7 @@ define <2 x i64> @ugt_33_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI164_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI164_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20639,7 +20639,7 @@ define <2 x i64> @ult_34_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI165_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI165_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20773,7 +20773,7 @@ define <2 x i64> @ugt_34_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI166_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI166_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -20907,7 +20907,7 @@ define <2 x i64> @ult_35_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI167_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI167_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21041,7 +21041,7 @@ define <2 x i64> @ugt_35_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI168_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI168_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21175,7 +21175,7 @@ define <2 x i64> @ult_36_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI169_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI169_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21309,7 +21309,7 @@ define <2 x i64> @ugt_36_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI170_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI170_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21443,7 +21443,7 @@ define <2 x i64> @ult_37_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI171_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI171_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21577,7 +21577,7 @@ define <2 x i64> @ugt_37_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI172_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI172_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21711,7 +21711,7 @@ define <2 x i64> @ult_38_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI173_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI173_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21845,7 +21845,7 @@ define <2 x i64> @ugt_38_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI174_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI174_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -21979,7 +21979,7 @@ define <2 x i64> @ult_39_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI175_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI175_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22113,7 +22113,7 @@ define <2 x i64> @ugt_39_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI176_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI176_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22247,7 +22247,7 @@ define <2 x i64> @ult_40_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI177_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI177_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22381,7 +22381,7 @@ define <2 x i64> @ugt_40_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI178_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI178_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22515,7 +22515,7 @@ define <2 x i64> @ult_41_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI179_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI179_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22649,7 +22649,7 @@ define <2 x i64> @ugt_41_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI180_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI180_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22783,7 +22783,7 @@ define <2 x i64> @ult_42_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI181_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI181_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -22917,7 +22917,7 @@ define <2 x i64> @ugt_42_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI182_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI182_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23051,7 +23051,7 @@ define <2 x i64> @ult_43_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI183_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI183_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23185,7 +23185,7 @@ define <2 x i64> @ugt_43_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI184_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI184_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23319,7 +23319,7 @@ define <2 x i64> @ult_44_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI185_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI185_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23453,7 +23453,7 @@ define <2 x i64> @ugt_44_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI186_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI186_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23587,7 +23587,7 @@ define <2 x i64> @ult_45_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI187_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI187_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23721,7 +23721,7 @@ define <2 x i64> @ugt_45_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI188_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI188_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23855,7 +23855,7 @@ define <2 x i64> @ult_46_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI189_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI189_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -23989,7 +23989,7 @@ define <2 x i64> @ugt_46_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI190_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI190_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24123,7 +24123,7 @@ define <2 x i64> @ult_47_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI191_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI191_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24257,7 +24257,7 @@ define <2 x i64> @ugt_47_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI192_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI192_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24391,7 +24391,7 @@ define <2 x i64> @ult_48_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI193_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI193_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24525,7 +24525,7 @@ define <2 x i64> @ugt_48_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI194_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI194_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24659,7 +24659,7 @@ define <2 x i64> @ult_49_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI195_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI195_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24793,7 +24793,7 @@ define <2 x i64> @ugt_49_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI196_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI196_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -24927,7 +24927,7 @@ define <2 x i64> @ult_50_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI197_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI197_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25061,7 +25061,7 @@ define <2 x i64> @ugt_50_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI198_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI198_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25195,7 +25195,7 @@ define <2 x i64> @ult_51_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI199_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI199_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25329,7 +25329,7 @@ define <2 x i64> @ugt_51_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI200_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI200_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25463,7 +25463,7 @@ define <2 x i64> @ult_52_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI201_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI201_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25597,7 +25597,7 @@ define <2 x i64> @ugt_52_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI202_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI202_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25731,7 +25731,7 @@ define <2 x i64> @ult_53_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI203_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI203_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25865,7 +25865,7 @@ define <2 x i64> @ugt_53_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI204_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI204_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -25999,7 +25999,7 @@ define <2 x i64> @ult_54_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI205_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI205_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26133,7 +26133,7 @@ define <2 x i64> @ugt_54_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI206_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI206_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26267,7 +26267,7 @@ define <2 x i64> @ult_55_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI207_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI207_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26401,7 +26401,7 @@ define <2 x i64> @ugt_55_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI208_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI208_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26535,7 +26535,7 @@ define <2 x i64> @ult_56_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI209_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI209_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26669,7 +26669,7 @@ define <2 x i64> @ugt_56_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI210_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI210_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26803,7 +26803,7 @@ define <2 x i64> @ult_57_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI211_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI211_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -26937,7 +26937,7 @@ define <2 x i64> @ugt_57_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI212_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI212_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27071,7 +27071,7 @@ define <2 x i64> @ult_58_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI213_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI213_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27205,7 +27205,7 @@ define <2 x i64> @ugt_58_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI214_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI214_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27339,7 +27339,7 @@ define <2 x i64> @ult_59_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI215_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI215_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27473,7 +27473,7 @@ define <2 x i64> @ugt_59_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI216_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI216_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27607,7 +27607,7 @@ define <2 x i64> @ult_60_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI217_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI217_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27741,7 +27741,7 @@ define <2 x i64> @ugt_60_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI218_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI218_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -27875,7 +27875,7 @@ define <2 x i64> @ult_61_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI219_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI219_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -28009,7 +28009,7 @@ define <2 x i64> @ugt_61_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI220_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI220_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -28143,7 +28143,7 @@ define <2 x i64> @ult_62_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI221_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI221_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -28277,7 +28277,7 @@ define <2 x i64> @ugt_62_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI222_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI222_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 2, 3
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)
@ -28411,7 +28411,7 @@ define <2 x i64> @ult_63_v2i64(<2 x i64> %0) {
; PWR9-NEXT: addis 3, 2, .LCPI223_0@toc@ha
; PWR9-NEXT: vpopcntd 2, 2
; PWR9-NEXT: addi 3, 3, .LCPI223_0@toc@l
; PWR9-NEXT: lxvx 35, 0, 3
; PWR9-NEXT: lxv 35, 0(3)
; PWR9-NEXT: vcmpgtud 2, 3, 2
; PWR9-NEXT: blr
%2 = tail call <2 x i64> @llvm.ctpop.v2i64(<2 x i64> %0)

48
test/CodeGen/PowerPC/vsx-p9.ll
View File

@ -36,8 +36,8 @@ entry:
%1 = load <16 x i8>, <16 x i8>* @ucb, align 16
%add.i = add <16 x i8> %1, %0
tail call void (...) @sink(<16 x i8> %add.i)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vaddubm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -45,8 +45,8 @@ entry:
%3 = load <16 x i8>, <16 x i8>* @scb, align 16
%add.i22 = add <16 x i8> %3, %2
tail call void (...) @sink(<16 x i8> %add.i22)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vaddubm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -54,8 +54,8 @@ entry:
%5 = load <8 x i16>, <8 x i16>* @usb, align 16
%add.i21 = add <8 x i16> %5, %4
tail call void (...) @sink(<8 x i16> %add.i21)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduhm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -63,8 +63,8 @@ entry:
%7 = load <8 x i16>, <8 x i16>* @ssb, align 16
%add.i20 = add <8 x i16> %7, %6
tail call void (...) @sink(<8 x i16> %add.i20)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduhm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -72,8 +72,8 @@ entry:
%9 = load <4 x i32>, <4 x i32>* @uib, align 16
%add.i19 = add <4 x i32> %9, %8
tail call void (...) @sink(<4 x i32> %add.i19)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduwm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -81,8 +81,8 @@ entry:
%11 = load <4 x i32>, <4 x i32>* @sib, align 16
%add.i18 = add <4 x i32> %11, %10
tail call void (...) @sink(<4 x i32> %add.i18)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduwm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -90,8 +90,8 @@ entry:
%13 = load <2 x i64>, <2 x i64>* @ullb, align 16
%add.i17 = add <2 x i64> %13, %12
tail call void (...) @sink(<2 x i64> %add.i17)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vaddudm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -99,8 +99,8 @@ entry:
%15 = load <2 x i64>, <2 x i64>* @sllb, align 16
%add.i16 = add <2 x i64> %15, %14
tail call void (...) @sink(<2 x i64> %add.i16)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vaddudm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -108,8 +108,8 @@ entry:
%17 = load <1 x i128>, <1 x i128>* @uxb, align 16
%add.i15 = add <1 x i128> %17, %16
tail call void (...) @sink(<1 x i128> %add.i15)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduqm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -117,8 +117,8 @@ entry:
%19 = load <1 x i128>, <1 x i128>* @sxb, align 16
%add.i14 = add <1 x i128> %19, %18
tail call void (...) @sink(<1 x i128> %add.i14)
; CHECK: lxvx 34, 0, 3
; CHECK: lxvx 35, 0, 3
; CHECK: lxv 34, 0(3)
; CHECK: lxv 35, 0(3)
; CHECK: vadduqm 2, 3, 2
; CHECK: stxv 34,
; CHECK: bl sink
@ -126,8 +126,8 @@ entry:
%21 = load <4 x float>, <4 x float>* @vfb, align 16
%add.i13 = fadd <4 x float> %20, %21
tail call void (...) @sink(<4 x float> %add.i13)
; CHECK: lxvx 0, 0, 3
; CHECK: lxvx 1, 0, 3
; CHECK: lxv 0, 0(3)
; CHECK: lxv 1, 0(3)
; CHECK: xvaddsp 34, 0, 1
; CHECK: stxv 34,
; CHECK: bl sink
@ -135,8 +135,8 @@ entry:
%23 = load <2 x double>, <2 x double>* @vdb, align 16
%add.i12 = fadd <2 x double> %22, %23
tail call void (...) @sink(<2 x double> %add.i12)
; CHECK: lxvx 0, 0, 3
; CHECK: lxvx 1, 0, 3
; CHECK: lxv 0, 0(3)
; CHECK: lxv 1, 0(3)
; CHECK: xvadddp 0, 0, 1
; CHECK: stxv 0,
; CHECK: bl sink

32
test/CodeGen/PowerPC/vsx.ll
View File

@ -1308,12 +1308,12 @@ define <2 x float> @test44(<2 x i64> %a) {
; CHECK-NEXT: ld r3, -8(r1)
; CHECK-NEXT: std r3, -24(r1)
; CHECK-NEXT: ld r3, -16(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: lfd f0, -24(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfidus f0, f0
; CHECK-NEXT: stfs f0, -48(r1)
; CHECK-NEXT: lfd f0, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfidus f0, f0
; CHECK-NEXT: stfs f0, -64(r1)
; CHECK-NEXT: lxvw4x v2, 0, r3
@ -1329,12 +1329,12 @@ define <2 x float> @test44(<2 x i64> %a) {
; CHECK-REG-NEXT: ld r3, -8(r1)
; CHECK-REG-NEXT: std r3, -24(r1)
; CHECK-REG-NEXT: ld r3, -16(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: lfd f0, -24(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfidus f0, f0
; CHECK-REG-NEXT: stfs f0, -48(r1)
; CHECK-REG-NEXT: lfd f0, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfidus f0, f0
; CHECK-REG-NEXT: stfs f0, -64(r1)
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
@ -1387,12 +1387,12 @@ define <2 x float> @test45(<2 x i64> %a) {
; CHECK-NEXT: ld r3, -8(r1)
; CHECK-NEXT: std r3, -24(r1)
; CHECK-NEXT: ld r3, -16(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: lfd f0, -24(r1)
; CHECK-NEXT: std r3, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfids f0, f0
; CHECK-NEXT: stfs f0, -48(r1)
; CHECK-NEXT: lfd f0, -32(r1)
; CHECK-NEXT: addi r3, r1, -48
; CHECK-NEXT: fcfids f0, f0
; CHECK-NEXT: stfs f0, -64(r1)
; CHECK-NEXT: lxvw4x v2, 0, r3
@ -1408,12 +1408,12 @@ define <2 x float> @test45(<2 x i64> %a) {
; CHECK-REG-NEXT: ld r3, -8(r1)
; CHECK-REG-NEXT: std r3, -24(r1)
; CHECK-REG-NEXT: ld r3, -16(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: lfd f0, -24(r1)
; CHECK-REG-NEXT: std r3, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfids f0, f0
; CHECK-REG-NEXT: stfs f0, -48(r1)
; CHECK-REG-NEXT: lfd f0, -32(r1)
; CHECK-REG-NEXT: addi r3, r1, -48
; CHECK-REG-NEXT: fcfids f0, f0
; CHECK-REG-NEXT: stfs f0, -64(r1)
; CHECK-REG-NEXT: lxvw4x v2, 0, r3
@ -1466,10 +1466,10 @@ define <2 x i64> @test46(<2 x float> %a) {
; CHECK-NEXT: xscvdpuxds f0, f0
; CHECK-NEXT: stfd f0, -32(r1)
; CHECK-NEXT: lfs f0, -48(r1)
; CHECK-NEXT: xscvdpuxds f0, f0
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: xscvdpuxds f0, f0
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
@ -1484,10 +1484,10 @@ define <2 x i64> @test46(<2 x float> %a) {
; CHECK-REG-NEXT: xscvdpuxds f0, f0
; CHECK-REG-NEXT: stfd f0, -32(r1)
; CHECK-REG-NEXT: lfs f0, -48(r1)
; CHECK-REG-NEXT: xscvdpuxds f0, f0
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: xscvdpuxds f0, f0
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16
@ -1533,10 +1533,10 @@ define <2 x i64> @test47(<2 x float> %a) {
; CHECK-NEXT: xscvdpsxds f0, f0
; CHECK-NEXT: stfd f0, -32(r1)
; CHECK-NEXT: lfs f0, -48(r1)
; CHECK-NEXT: xscvdpsxds f0, f0
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -32(r1)
; CHECK-NEXT: xscvdpsxds f0, f0
; CHECK-NEXT: std r3, -8(r1)
; CHECK-NEXT: stfd f0, -24(r1)
; CHECK-NEXT: ld r3, -24(r1)
; CHECK-NEXT: std r3, -16(r1)
; CHECK-NEXT: addi r3, r1, -16
@ -1551,10 +1551,10 @@ define <2 x i64> @test47(<2 x float> %a) {
; CHECK-REG-NEXT: xscvdpsxds f0, f0
; CHECK-REG-NEXT: stfd f0, -32(r1)
; CHECK-REG-NEXT: lfs f0, -48(r1)
; CHECK-REG-NEXT: xscvdpsxds f0, f0
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -32(r1)
; CHECK-REG-NEXT: xscvdpsxds f0, f0
; CHECK-REG-NEXT: std r3, -8(r1)
; CHECK-REG-NEXT: stfd f0, -24(r1)
; CHECK-REG-NEXT: ld r3, -24(r1)
; CHECK-REG-NEXT: std r3, -16(r1)
; CHECK-REG-NEXT: addi r3, r1, -16

71
test/CodeGen/PowerPC/vsx_builtins.ll
View File

@ -1,7 +1,28 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -relocation-model=static -verify-machineinstrs -mcpu=pwr9 \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-P9
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mattr=-power9-vector \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-NOINTRIN
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx \
; RUN: -mtriple=powerpc64le-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-NOINTRIN
; RUN: llc -verify-machineinstrs -mcpu=pwr9 \
; RUN: -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-P9
; RUN: llc -verify-machineinstrs -mcpu=pwr9 -mattr=-power9-vector \
; RUN: -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-INTRIN
; RUN: llc -verify-machineinstrs -mcpu=pwr8 -mattr=+vsx \
; RUN: -mtriple=powerpc64-unknown-linux-gnu \
; RUN: -ppc-vsr-nums-as-vr -ppc-asm-full-reg-names < %s | FileCheck %s \
; RUN: --check-prefixes=CHECK,CHECK-INTRIN
; Function Attrs: nounwind readnone
define <4 x i32> @test1(i8* %a) {
@ -140,3 +161,51 @@ entry:
%.lobit = and i32 %1, 1
ret i32 %.lobit
}
; Function Attrs: nounwind readnone
define <2 x double> @test_lxvd2x(i8* %a) {
; CHECK-P9-LABEL: test_lxvd2x:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: lxv v2, 0(r3)
; CHECK-P9-NEXT: blr
;
; CHECK-NOINTRIN-LABEL: test_lxvd2x:
; CHECK-NOINTRIN: # %bb.0: # %entry
; CHECK-NOINTRIN-NEXT: lxvd2x vs0, 0, r3
; CHECK-NOINTRIN-NEXT: xxswapd v2, vs0
; CHECK-NOINTRIN-NEXT: blr
;
; CHECK-INTRIN-LABEL: test_lxvd2x:
; CHECK-INTRIN: # %bb.0: # %entry
; CHECK-INTRIN-NEXT: lxvd2x v2, 0, r3
; CHECK-INTRIN-NEXT: blr
entry:
%0 = tail call <2 x double> @llvm.ppc.vsx.lxvd2x(i8* %a)
ret <2 x double> %0
}
; Function Attrs: nounwind readnone
declare <2 x double> @llvm.ppc.vsx.lxvd2x(i8*)
; Function Attrs: nounwind readnone
define void @test_stxvd2x(<2 x double> %a, i8* %b) {
; CHECK-P9-LABEL: test_stxvd2x:
; CHECK-P9: # %bb.0: # %entry
; CHECK-P9-NEXT: stxv v2, 0(r5)
; CHECK-P9-NEXT: blr
;
; CHECK-NOINTRIN-LABEL: test_stxvd2x:
; CHECK-NOINTRIN: # %bb.0: # %entry
; CHECK-NOINTRIN-NEXT: xxswapd vs0, v2
; CHECK-NOINTRIN-NEXT: stxvd2x vs0, 0, r5
; CHECK-NOINTRIN-NEXT: blr
;
; CHECK-INTRIN-LABEL: test_stxvd2x:
; CHECK-INTRIN: # %bb.0: # %entry
; CHECK-INTRIN-NEXT: stxvd2x v2, 0, r5
; CHECK-INTRIN-NEXT: blr
entry:
tail call void @llvm.ppc.vsx.stxvd2x(<2 x double> %a, i8* %b)
ret void
}
; Function Attrs: nounwind readnone
declare void @llvm.ppc.vsx.stxvd2x(<2 x double>, i8*)

14
test/CodeGen/PowerPC/vsx_insert_extract_le.ll
View File

@ -19,7 +19,7 @@ define <2 x double> @testi0(<2 x double>* %p1, double* %p2) {
; CHECK-LABEL: testi0:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvd2x vs0, 0, r3
; CHECK-NEXT: lfdx f1, 0, r4
; CHECK-NEXT: lfd f1, 0(r4)
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: xxmrghd v2, vs0, vs1
; CHECK-NEXT: blr
@ -27,14 +27,14 @@ define <2 x double> @testi0(<2 x double>* %p1, double* %p2) {
; CHECK-P8-BE-LABEL: testi0:
; CHECK-P8-BE: # %bb.0:
; CHECK-P8-BE-NEXT: lxvd2x vs0, 0, r3
; CHECK-P8-BE-NEXT: lfdx f1, 0, r4
; CHECK-P8-BE-NEXT: lfd f1, 0(r4)
; CHECK-P8-BE-NEXT: xxpermdi v2, vs1, vs0, 1
; CHECK-P8-BE-NEXT: blr
;
; CHECK-P9-VECTOR-LABEL: testi0:
; CHECK-P9-VECTOR: # %bb.0:
; CHECK-P9-VECTOR-NEXT: lxvd2x vs0, 0, r3
; CHECK-P9-VECTOR-NEXT: lfdx f1, 0, r4
; CHECK-P9-VECTOR-NEXT: lfd f1, 0(r4)
; CHECK-P9-VECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-VECTOR-NEXT: xxmrghd v2, vs0, vs1
; CHECK-P9-VECTOR-NEXT: blr
@ -57,7 +57,7 @@ define <2 x double> @testi1(<2 x double>* %p1, double* %p2) {
; CHECK-LABEL: testi1:
; CHECK: # %bb.0:
; CHECK-NEXT: lxvd2x vs0, 0, r3
; CHECK-NEXT: lfdx f1, 0, r4
; CHECK-NEXT: lfd f1, 0(r4)
; CHECK-NEXT: xxswapd vs0, vs0
; CHECK-NEXT: xxpermdi v2, vs1, vs0, 1
; CHECK-NEXT: blr
@ -65,14 +65,14 @@ define <2 x double> @testi1(<2 x double>* %p1, double* %p2) {
; CHECK-P8-BE-LABEL: testi1:
; CHECK-P8-BE: # %bb.0:
; CHECK-P8-BE-NEXT: lxvd2x vs0, 0, r3
; CHECK-P8-BE-NEXT: lfdx f1, 0, r4
; CHECK-P8-BE-NEXT: lfd f1, 0(r4)
; CHECK-P8-BE-NEXT: xxmrghd v2, vs0, vs1
; CHECK-P8-BE-NEXT: blr
;
; CHECK-P9-VECTOR-LABEL: testi1:
; CHECK-P9-VECTOR: # %bb.0:
; CHECK-P9-VECTOR-NEXT: lxvd2x vs0, 0, r3
; CHECK-P9-VECTOR-NEXT: lfdx f1, 0, r4
; CHECK-P9-VECTOR-NEXT: lfd f1, 0(r4)
; CHECK-P9-VECTOR-NEXT: xxswapd vs0, vs0
; CHECK-P9-VECTOR-NEXT: xxpermdi v2, vs1, vs0, 1
; CHECK-P9-VECTOR-NEXT: blr
@ -100,7 +100,7 @@ define double @teste0(<2 x double>* %p1) {
;
; CHECK-P8-BE-LABEL: teste0:
; CHECK-P8-BE: # %bb.0:
; CHECK-P8-BE-NEXT: lfdx f1, 0, r3
; CHECK-P8-BE-NEXT: lfd f1, 0(r3)
; CHECK-P8-BE-NEXT: blr
;
; CHECK-P9-VECTOR-LABEL: teste0:

4
test/CodeGen/PowerPC/vsx_scalar_ld_st.ll
View File

@ -123,7 +123,7 @@ entry:
store volatile float %conv, float* %ff, align 4
ret void
; CHECK-LABEL: @dblToFloat
; CHECK: lfdx [[REGLD5:[0-9]+]],
; CHECK: lfd [[REGLD5:[0-9]+]],
; CHECK: stfs [[REGLD5]],
; CHECK-P9-LABEL: @dblToFloat
; CHECK-P9: lfd [[REGLD5:[0-9]+]],
@ -139,7 +139,7 @@ entry:
store volatile double %conv, double* %dd, align 8
ret void
; CHECK-LABEL: @floatToDbl
; CHECK: lfsx [[REGLD5:[0-9]+]],
; CHECK: lfs [[REGLD5:[0-9]+]],
; CHECK: stfd [[REGLD5]],
; CHECK-P9-LABEL: @floatToDbl
; CHECK-P9: lfs [[REGLD5:[0-9]+]],