RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2025-01-31 20:51:52 +01:00
Code Issues Projects Releases Wiki Activity

[AArch64][SVE] Add bfloat16 support to perm and select intrinsics

Browse Source 
Summary:
Added for following intrinsics:

  * zip1, zip2, zip1q, zip2q
  * trn1, trn2, trn1q, trn2q
  * uzp1, uzp2, uzp1q, uzp2q
  * splice
  * rev
  * sel

Reviewed By: david-arm

Differential Revision: https://reviews.llvm.org/D82182
This commit is contained in:
Cullen Rhodes 2020-06-18 17:25:18 +00:00
parent 31c721c75b
commit 8543c38ff5
3 changed files with 109 additions and 14 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

32
lib/Target/AArch64/SVEInstrFormats.td
View File

@ -1124,9 +1124,10 @@ multiclass sve_int_perm_reverse_z<string asm, SDPatternOperator op> {
def : SVE_1_Op_Pat<nxv4i32, op, nxv4i32, !cast<Instruction>(NAME # _S)>; def : SVE_1_Op_Pat<nxv4i32, op, nxv4i32, !cast<Instruction>(NAME # _S)>;
def : SVE_1_Op_Pat<nxv2i64, op, nxv2i64, !cast<Instruction>(NAME # _D)>; def : SVE_1_Op_Pat<nxv2i64, op, nxv2i64, !cast<Instruction>(NAME # _D)>;
def : SVE_1_Op_Pat<nxv8f16, op, nxv8f16, !cast<Instruction>(NAME # _H)>; def : SVE_1_Op_Pat<nxv8bf16, op, nxv8bf16, !cast<Instruction>(NAME # _H)>;
def : SVE_1_Op_Pat<nxv4f32, op, nxv4f32, !cast<Instruction>(NAME # _S)>; def : SVE_1_Op_Pat<nxv8f16, op, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_1_Op_Pat<nxv2f64, op, nxv2f64, !cast<Instruction>(NAME # _D)>; def : SVE_1_Op_Pat<nxv4f32, op, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_1_Op_Pat<nxv2f64, op, nxv2f64, !cast<Instruction>(NAME # _D)>;
} }
class sve_int_perm_reverse_p<bits<2> sz8_64, string asm, PPRRegOp pprty> class sve_int_perm_reverse_p<bits<2> sz8_64, string asm, PPRRegOp pprty>
@ -1320,10 +1321,11 @@ multiclass sve_int_sel_vvv<string asm, SDPatternOperator op> {
def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>; def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>; def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
def : SVE_3_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>; def : SVE_3_Op_Pat<nxv8bf16, op, nxv8i1, nxv8bf16, nxv8bf16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>; def : SVE_3_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv2f32, op, nxv2i1, nxv2f32, nxv2f32, !cast<Instruction>(NAME # _D)>; def : SVE_3_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>; def : SVE_3_Op_Pat<nxv2f32, op, nxv2i1, nxv2f32, nxv2f32, !cast<Instruction>(NAME # _D)>;
def : SVE_3_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>;
def : InstAlias<"mov $Zd, $Pg/m, $Zn", def : InstAlias<"mov $Zd, $Pg/m, $Zn",
(!cast<Instruction>(NAME # _B) ZPR8:$Zd, PPRAny:$Pg, ZPR8:$Zn, ZPR8:$Zd), 1>; (!cast<Instruction>(NAME # _B) ZPR8:$Zd, PPRAny:$Pg, ZPR8:$Zn, ZPR8:$Zd), 1>;
@ -2212,10 +2214,11 @@ multiclass sve_int_perm_bin_perm_zz<bits<3> opc, string asm,
def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>; def : SVE_2_Op_Pat<nxv4i32, op, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>; def : SVE_2_Op_Pat<nxv2i64, op, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
def : SVE_2_Op_Pat<nxv8f16, op, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>; def : SVE_2_Op_Pat<nxv8bf16, op, nxv8bf16, nxv8bf16, !cast<Instruction>(NAME # _H)>;
def : SVE_2_Op_Pat<nxv4f16, op, nxv4f16, nxv4f16, !cast<Instruction>(NAME # _S)>; def : SVE_2_Op_Pat<nxv8f16, op, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_2_Op_Pat<nxv4f32, op, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>; def : SVE_2_Op_Pat<nxv4f16, op, nxv4f16, nxv4f16, !cast<Instruction>(NAME # _S)>;
def : SVE_2_Op_Pat<nxv2f64, op, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>; def : SVE_2_Op_Pat<nxv4f32, op, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_2_Op_Pat<nxv2f64, op, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>;
} }
//===----------------------------------------------------------------------===// //===----------------------------------------------------------------------===//
@ -5806,9 +5809,10 @@ multiclass sve_int_perm_splice<string asm, SDPatternOperator op> {
def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>; def : SVE_3_Op_Pat<nxv4i32, op, nxv4i1, nxv4i32, nxv4i32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>; def : SVE_3_Op_Pat<nxv2i64, op, nxv2i1, nxv2i64, nxv2i64, !cast<Instruction>(NAME # _D)>;
def : SVE_3_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>; def : SVE_3_Op_Pat<nxv8bf16, op, nxv8i1, nxv8bf16, nxv8bf16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>; def : SVE_3_Op_Pat<nxv8f16, op, nxv8i1, nxv8f16, nxv8f16, !cast<Instruction>(NAME # _H)>;
def : SVE_3_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>; def : SVE_3_Op_Pat<nxv4f32, op, nxv4i1, nxv4f32, nxv4f32, !cast<Instruction>(NAME # _S)>;
def : SVE_3_Op_Pat<nxv2f64, op, nxv2i1, nxv2f64, nxv2f64, !cast<Instruction>(NAME # _D)>;
} }
class sve2_int_perm_splice_cons<bits<2> sz8_64, string asm, class sve2_int_perm_splice_cons<bits<2> sz8_64, string asm,

80
test/CodeGen/AArch64/sve-intrinsics-perm-select.ll
View File

@ -806,6 +806,14 @@ define <vscale x 2 x i64> @rev_i64(<vscale x 2 x i64> %a) {
ret <vscale x 2 x i64> %res ret <vscale x 2 x i64> %res
} }
define <vscale x 8 x bfloat> @rev_bf16(<vscale x 8 x bfloat> %a) {
; CHECK-LABEL: rev_bf16
; CHECK: rev z0.h, z0.h
; CHECK-NEXT: ret
%res = call <vscale x 8 x bfloat> @llvm.aarch64.sve.rev.nxv8bf16(<vscale x 8 x bfloat> %a)
ret <vscale x 8 x bfloat> %res
}
define <vscale x 8 x half> @rev_f16(<vscale x 8 x half> %a) { define <vscale x 8 x half> @rev_f16(<vscale x 8 x half> %a) {
; CHECK-LABEL: rev_f16 ; CHECK-LABEL: rev_f16
; CHECK: rev z0.h, z0.h ; CHECK: rev z0.h, z0.h
@ -874,6 +882,16 @@ define <vscale x 2 x i64> @splice_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64>
ret <vscale x 2 x i64> %out ret <vscale x 2 x i64> %out
} }
define <vscale x 8 x bfloat> @splice_bf16(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: splice_bf16:
; CHECK: splice z0.h, p0, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.splice.nxv8bf16(<vscale x 8 x i1> %pg,
<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @splice_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @splice_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: splice_f16: ; CHECK-LABEL: splice_f16:
; CHECK: splice z0.h, p0, z0.h, z1.h ; CHECK: splice z0.h, p0, z0.h, z1.h
@ -1168,6 +1186,15 @@ define <vscale x 4 x half> @trn1_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @trn1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: trn1_bf16:
; CHECK: trn1 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.trn1.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @trn1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @trn1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: trn1_f16: ; CHECK-LABEL: trn1_f16:
; CHECK: trn1 z0.h, z0.h, z1.h ; CHECK: trn1 z0.h, z0.h, z1.h
@ -1280,6 +1307,15 @@ define <vscale x 4 x half> @trn2_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @trn2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: trn2_bf16:
; CHECK: trn2 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.trn2.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @trn2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @trn2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: trn2_f16: ; CHECK-LABEL: trn2_f16:
; CHECK: trn2 z0.h, z0.h, z1.h ; CHECK: trn2 z0.h, z0.h, z1.h
@ -1392,6 +1428,15 @@ define <vscale x 4 x half> @uzp1_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @uzp1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: uzp1_bf16:
; CHECK: uzp1 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp1.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @uzp1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @uzp1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: uzp1_f16: ; CHECK-LABEL: uzp1_f16:
; CHECK: uzp1 z0.h, z0.h, z1.h ; CHECK: uzp1 z0.h, z0.h, z1.h
@ -1504,6 +1549,15 @@ define <vscale x 4 x half> @uzp2_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @uzp2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: uzp2_bf16:
; CHECK: uzp2 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp2.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @uzp2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @uzp2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: uzp2_f16: ; CHECK-LABEL: uzp2_f16:
; CHECK: uzp2 z0.h, z0.h, z1.h ; CHECK: uzp2 z0.h, z0.h, z1.h
@ -1616,6 +1670,15 @@ define <vscale x 4 x half> @zip1_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @zip1_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: zip1_bf16:
; CHECK: zip1 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.zip1.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @zip1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @zip1_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: zip1_f16: ; CHECK-LABEL: zip1_f16:
; CHECK: zip1 z0.h, z0.h, z1.h ; CHECK: zip1 z0.h, z0.h, z1.h
@ -1728,6 +1791,15 @@ define <vscale x 4 x half> @zip2_f16_v4(<vscale x 4 x half> %a, <vscale x 4 x ha
ret <vscale x 4 x half> %out ret <vscale x 4 x half> %out
} }
define <vscale x 8 x bfloat> @zip2_bf16(<vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: zip2_bf16:
; CHECK: zip2 z0.h, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.zip2.nxv8bf16(<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @zip2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @zip2_f16(<vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: zip2_f16: ; CHECK-LABEL: zip2_f16:
; CHECK: zip2 z0.h, z0.h, z1.h ; CHECK: zip2 z0.h, z0.h, z1.h
@ -1834,6 +1906,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.rev.nxv16i8(<vscale x 16 x i8>)
declare <vscale x 8 x i16> @llvm.aarch64.sve.rev.nxv8i16(<vscale x 8 x i16>) declare <vscale x 8 x i16> @llvm.aarch64.sve.rev.nxv8i16(<vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.rev.nxv4i32(<vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.rev.nxv4i32(<vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.rev.nxv2i64(<vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.rev.nxv2i64(<vscale x 2 x i64>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.rev.nxv8bf16(<vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.rev.nxv8f16(<vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.rev.nxv8f16(<vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.rev.nxv4f32(<vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.rev.nxv4f32(<vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.rev.nxv2f64(<vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.rev.nxv2f64(<vscale x 2 x double>)
@ -1842,6 +1915,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.splice.nxv16i8(<vscale x 16 x i1>,
declare <vscale x 8 x i16> @llvm.aarch64.sve.splice.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) declare <vscale x 8 x i16> @llvm.aarch64.sve.splice.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.splice.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.splice.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.splice.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.splice.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.splice.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.splice.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.splice.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.splice.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.splice.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.splice.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.splice.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
@ -1879,6 +1953,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.trn1.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.trn1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.trn1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.trn1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.trn1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.trn1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.trn1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.trn1.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.trn1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.trn1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.trn1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.trn1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.trn1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.trn1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -1892,6 +1967,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.trn2.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.trn2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.trn2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.trn2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.trn2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.trn2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.trn2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.trn2.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.trn2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.trn2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.trn2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.trn2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.trn2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.trn2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -1905,6 +1981,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uzp1.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.uzp1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.uzp1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp1.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.uzp1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.uzp1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.uzp1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.uzp1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.uzp1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.uzp1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -1918,6 +1995,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.uzp2.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.uzp2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.uzp2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.uzp2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.uzp2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.uzp2.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.uzp2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.uzp2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.uzp2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.uzp2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.uzp2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.uzp2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -1931,6 +2009,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.zip1.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.zip1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.zip1.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.zip1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.zip1.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.zip1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.zip1.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.zip1.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.zip1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.zip1.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.zip1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.zip1.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.zip1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.zip1.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)
@ -1944,6 +2023,7 @@ declare <vscale x 8 x i16> @llvm.aarch64.sve.zip2.nxv8i16(<vscale x 8 x i16>, <v
declare <vscale x 4 x i32> @llvm.aarch64.sve.zip2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.zip2.nxv4i32(<vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.zip2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.zip2.nxv2i64(<vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 4 x half> @llvm.aarch64.sve.zip2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>) declare <vscale x 4 x half> @llvm.aarch64.sve.zip2.nxv4f16(<vscale x 4 x half>, <vscale x 4 x half>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.zip2.nxv8bf16(<vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.zip2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.zip2.nxv8f16(<vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.zip2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.zip2.nxv4f32(<vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.zip2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.zip2.nxv2f64(<vscale x 2 x double>, <vscale x 2 x double>)

11
test/CodeGen/AArch64/sve-intrinsics-sel.ll
View File

@ -57,6 +57,16 @@ define <vscale x 2 x i64> @sel_i64(<vscale x 2 x i1> %pg, <vscale x 2 x i64> %a,
ret <vscale x 2 x i64> %out ret <vscale x 2 x i64> %out
} }
define <vscale x 8 x bfloat> @sel_bf16(<vscale x 8 x i1> %pg, <vscale x 8 x bfloat> %a, <vscale x 8 x bfloat> %b) {
; CHECK-LABEL: sel_bf16:
; CHECK: sel z0.h, p0, z0.h, z1.h
; CHECK-NEXT: ret
%out = call <vscale x 8 x bfloat> @llvm.aarch64.sve.sel.nxv8bf16(<vscale x 8 x i1> %pg,
<vscale x 8 x bfloat> %a,
<vscale x 8 x bfloat> %b)
ret <vscale x 8 x bfloat> %out
}
define <vscale x 8 x half> @sel_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) { define <vscale x 8 x half> @sel_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %b) {
; CHECK-LABEL: sel_f16: ; CHECK-LABEL: sel_f16:
; CHECK: sel z0.h, p0, z0.h, z1.h ; CHECK: sel z0.h, p0, z0.h, z1.h
@ -92,6 +102,7 @@ declare <vscale x 16 x i8> @llvm.aarch64.sve.sel.nxv16i8(<vscale x 16 x i1>, <vs
declare <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>) declare <vscale x 8 x i16> @llvm.aarch64.sve.sel.nxv8i16(<vscale x 8 x i1>, <vscale x 8 x i16>, <vscale x 8 x i16>)
declare <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>) declare <vscale x 4 x i32> @llvm.aarch64.sve.sel.nxv4i32(<vscale x 4 x i1>, <vscale x 4 x i32>, <vscale x 4 x i32>)
declare <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>) declare <vscale x 2 x i64> @llvm.aarch64.sve.sel.nxv2i64(<vscale x 2 x i1>, <vscale x 2 x i64>, <vscale x 2 x i64>)
declare <vscale x 8 x bfloat> @llvm.aarch64.sve.sel.nxv8bf16(<vscale x 8 x i1>, <vscale x 8 x bfloat>, <vscale x 8 x bfloat>)
declare <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>) declare <vscale x 8 x half> @llvm.aarch64.sve.sel.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>) declare <vscale x 4 x float> @llvm.aarch64.sve.sel.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>) declare <vscale x 2 x double> @llvm.aarch64.sve.sel.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)