mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-23 19:23:23 +01:00
Revert r225165 and r225169
Even thouh gcc produces simialr instructions as Owen pointed out the two patterns aren’t equivalent in the case where the original subtraction could have caused an overflow. Reverting the same. llvm-svn: 225341
This commit is contained in:
Karthik Bhat
parent
272872c802
commit
d463305416
@ -2760,40 +2760,6 @@ defm ORN : SIMDLogicalThreeVector<0, 0b11, "orn",
|
||||
BinOpFrag<(or node:$LHS, (vnot node:$RHS))> >;
|
||||
defm ORR : SIMDLogicalThreeVector<0, 0b10, "orr", or>;
|
||||
|
||||
// SABD Vd.<T>, Vn.<T>, Vm.<T> Subtracts the elements of Vm from the corresponding
|
||||
// elements of Vn, and places the absolute values of the results in the elements of Vd.
|
||||
def : Pat<(xor (v8i8 (AArch64vashr (v8i8(sub V64:$Rn, V64:$Rm)), (i32 7))),
|
||||
(v8i8 (add (v8i8(sub V64:$Rn, V64:$Rm)),
|
||||
(AArch64vashr (v8i8(sub V64:$Rn, V64:$Rm)), (i32 7))))),
|
||||
(SABDv8i8 V64:$Rn, V64:$Rm)>;
|
||||
def : Pat<(xor (v4i16 (AArch64vashr (v4i16(sub V64:$Rn, V64:$Rm)), (i32 15))),
|
||||
(v4i16 (add (v4i16(sub V64:$Rn, V64:$Rm)),
|
||||
(AArch64vashr (v4i16(sub V64:$Rn, V64:$Rm)), (i32 15))))),
|
||||
(SABDv4i16 V64:$Rn, V64:$Rm)>;
|
||||
def : Pat<(xor (v2i32 (AArch64vashr (v2i32(sub V64:$Rn, V64:$Rm)), (i32 31))),
|
||||
(v2i32 (add (v2i32(sub V64:$Rn, V64:$Rm)),
|
||||
(AArch64vashr (v2i32(sub V64:$Rn, V64:$Rm)), (i32 31))))),
|
||||
(SABDv2i32 V64:$Rn, V64:$Rm)>;
|
||||
def : Pat<(xor (v16i8 (AArch64vashr (v16i8(sub V128:$Rn, V128:$Rm)), (i32 7))),
|
||||
(v16i8 (add (v16i8(sub V128:$Rn, V128:$Rm)),
|
||||
(AArch64vashr (v16i8(sub V128:$Rn, V128:$Rm)), (i32 7))))),
|
||||
(SABDv16i8 V128:$Rn, V128:$Rm)>;
|
||||
def : Pat<(xor (v8i16 (AArch64vashr (v8i16(sub V128:$Rn, V128:$Rm)), (i32 15))),
|
||||
(v8i16 (add (v8i16(sub V128:$Rn, V128:$Rm)),
|
||||
(AArch64vashr (v8i16(sub V128:$Rn, V128:$Rm)), (i32 15))))),
|
||||
(SABDv8i16 V128:$Rn, V128:$Rm)>;
|
||||
def : Pat<(xor (v4i32 (AArch64vashr (v4i32(sub V128:$Rn, V128:$Rm)), (i32 31))),
|
||||
(v4i32 (add (v4i32(sub V128:$Rn, V128:$Rm)),
|
||||
(AArch64vashr (v4i32(sub V128:$Rn, V128:$Rm)), (i32 31))))),
|
||||
(SABDv4i32 V128:$Rn, V128:$Rm)>;
|
||||
|
||||
def : Pat<(v2f32 (fabs (fsub V64:$Rn, V64:$Rm))),
|
||||
(FABDv2f32 V64:$Rn, V64:$Rm)>;
|
||||
def : Pat<(v4f32 (fabs (fsub V128:$Rn, V128:$Rm))),
|
||||
(FABDv4f32 V128:$Rn, V128:$Rm)>;
|
||||
def : Pat<(v2f64 (fabs (fsub V128:$Rn, V128:$Rm))),
|
||||
(FABDv2f64 V128:$Rn, V128:$Rm)>;
|
||||
|
||||
def : Pat<(AArch64bsl (v8i8 V64:$Rd), V64:$Rn, V64:$Rm),
|
||||
(BSLv8i8 V64:$Rd, V64:$Rn, V64:$Rm)>;
|
||||
def : Pat<(AArch64bsl (v4i16 V64:$Rd), V64:$Rn, V64:$Rm),
|
||||
@ -3083,11 +3049,6 @@ defm UQXTN : SIMDTwoScalarMixedBHS<1, 0b10100, "uqxtn", int_aarch64_neon_scalar
|
||||
defm USQADD : SIMDTwoScalarBHSDTied< 1, 0b00011, "usqadd",
|
||||
int_aarch64_neon_usqadd>;
|
||||
|
||||
def : Pat<(f32 (fabs (fsub FPR32:$Rn, FPR32:$Rm))),
|
||||
(FABD32 FPR32:$Rn, FPR32:$Rm)>;
|
||||
def : Pat<(f64 (fabs (fsub FPR64:$Rn, FPR64:$Rm))),
|
||||
(FABD64 FPR64:$Rn, FPR64:$Rm)>;
|
||||
|
||||
def : Pat<(AArch64neg (v1i64 V64:$Rn)), (NEGv1i64 V64:$Rn)>;
|
||||
|
||||
def : Pat<(v1i64 (int_aarch64_neon_fcvtas (v1f64 FPR64:$Rn))),
|
||||
|
||||
@ -1,170 +0,0 @@
|
||||
; RUN: llc -mtriple=aarch64-none-linux-gnu < %s | FileCheck %s
|
||||
target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
|
||||
target triple = "aarch64--linux-gnu"
|
||||
|
||||
; CHECK: testv4i32
|
||||
; CHECK: sabd v0.4s, v0.4s, v1.4s
|
||||
define void @testv4i32(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c){
|
||||
%1 = bitcast i32* %b to <4 x i32>*
|
||||
%2 = load <4 x i32>* %1, align 4
|
||||
%3 = bitcast i32* %c to <4 x i32>*
|
||||
%4 = load <4 x i32>* %3, align 4
|
||||
%5 = sub nsw <4 x i32> %2, %4
|
||||
%6 = icmp sgt <4 x i32> %5, <i32 -1, i32 -1, i32 -1, i32 -1>
|
||||
%7 = sub <4 x i32> zeroinitializer, %5
|
||||
%8 = select <4 x i1> %6, <4 x i32> %5, <4 x i32> %7
|
||||
%9 = bitcast i32* %a to <4 x i32>*
|
||||
store <4 x i32> %8, <4 x i32>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: testv2i32
|
||||
; CHECK: sabd v0.2s, v0.2s, v1.2s
|
||||
define void @testv2i32(i32* noalias nocapture %a, i32* noalias nocapture readonly %b, i32* noalias nocapture readonly %c){
|
||||
%1 = bitcast i32* %b to <2 x i32>*
|
||||
%2 = load <2 x i32>* %1, align 4
|
||||
%3 = bitcast i32* %c to <2 x i32>*
|
||||
%4 = load <2 x i32>* %3, align 4
|
||||
%5 = sub nsw <2 x i32> %2, %4
|
||||
%6 = icmp sgt <2 x i32> %5, <i32 -1, i32 -1>
|
||||
%7 = sub <2 x i32> zeroinitializer, %5
|
||||
%8 = select <2 x i1> %6, <2 x i32> %5, <2 x i32> %7
|
||||
%9 = bitcast i32* %a to <2 x i32>*
|
||||
store <2 x i32> %8, <2 x i32>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: testv8i16
|
||||
; CHECK: sabd v0.8h, v0.8h, v1.8h
|
||||
define void @testv8i16(i16* noalias nocapture %a, i16* noalias nocapture readonly %b, i16* noalias nocapture readonly %c){
|
||||
%1 = bitcast i16* %b to <8 x i16>*
|
||||
%2 = load <8 x i16>* %1, align 4
|
||||
%3 = bitcast i16* %c to <8 x i16>*
|
||||
%4 = load <8 x i16>* %3, align 4
|
||||
%5 = sub nsw <8 x i16> %2, %4
|
||||
%6 = icmp sgt <8 x i16> %5, <i16 -1, i16 -1,i16 -1, i16 -1,i16 -1, i16 -1,i16 -1, i16 -1>
|
||||
%7 = sub <8 x i16> zeroinitializer, %5
|
||||
%8 = select <8 x i1> %6, <8 x i16> %5, <8 x i16> %7
|
||||
%9 = bitcast i16* %a to <8 x i16>*
|
||||
store <8 x i16> %8, <8 x i16>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: testv4i16
|
||||
; CHECK: sabd v0.4h, v0.4h, v1.4h
|
||||
define void @testv4i16(i16* noalias nocapture %a, i16* noalias nocapture readonly %b, i16* noalias nocapture readonly %c){
|
||||
%1 = bitcast i16* %b to <4 x i16>*
|
||||
%2 = load <4 x i16>* %1, align 4
|
||||
%3 = bitcast i16* %c to <4 x i16>*
|
||||
%4 = load <4 x i16>* %3, align 4
|
||||
%5 = sub nsw <4 x i16> %2, %4
|
||||
%6 = icmp sgt <4 x i16> %5, <i16 -1, i16 -1,i16 -1, i16 -1>
|
||||
%7 = sub <4 x i16> zeroinitializer, %5
|
||||
%8 = select <4 x i1> %6, <4 x i16> %5, <4 x i16> %7
|
||||
%9 = bitcast i16* %a to <4 x i16>*
|
||||
store <4 x i16> %8, <4 x i16>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
|
||||
; CHECK: testv16i8
|
||||
; CHECK: sabd v0.16b, v0.16b, v1.16b
|
||||
define void @testv16i8(i8* noalias nocapture %a, i8* noalias nocapture readonly %b, i8* noalias nocapture readonly %c){
|
||||
%1 = bitcast i8* %b to <16 x i8>*
|
||||
%2 = load <16 x i8>* %1, align 4
|
||||
%3 = bitcast i8* %c to <16 x i8>*
|
||||
%4 = load <16 x i8>* %3, align 4
|
||||
%5 = sub nsw <16 x i8> %2, %4
|
||||
%6 = icmp sgt <16 x i8> %5, <i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1>
|
||||
%7 = sub <16 x i8> zeroinitializer, %5
|
||||
%8 = select <16 x i1> %6, <16 x i8> %5, <16 x i8> %7
|
||||
%9 = bitcast i8* %a to <16 x i8>*
|
||||
store <16 x i8> %8, <16 x i8>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: testv8i8
|
||||
; CHECK: sabd v0.8b, v0.8b, v1.8b
|
||||
define void @testv8i8(i8* noalias nocapture %a, i8* noalias nocapture readonly %b, i8* noalias nocapture readonly %c){
|
||||
%1 = bitcast i8* %b to <8 x i8>*
|
||||
%2 = load <8 x i8>* %1, align 4
|
||||
%3 = bitcast i8* %c to <8 x i8>*
|
||||
%4 = load <8 x i8>* %3, align 4
|
||||
%5 = sub nsw <8 x i8> %2, %4
|
||||
%6 = icmp sgt <8 x i8> %5, <i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1,i8 -1, i8 -1>
|
||||
%7 = sub <8 x i8> zeroinitializer, %5
|
||||
%8 = select <8 x i1> %6, <8 x i8> %5, <8 x i8> %7
|
||||
%9 = bitcast i8* %a to <8 x i8>*
|
||||
store <8 x i8> %8, <8 x i8>* %9, align 4
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: test_v4f32
|
||||
; CHECK: fabd v0.4s, v0.4s, v1.4s
|
||||
declare <4 x float> @llvm.fabs.v4f32(<4 x float>)
|
||||
define void @test_v4f32(float* noalias nocapture %a, float* noalias nocapture readonly %b, float* noalias nocapture readonly %c){
|
||||
%1 = bitcast float* %b to <4 x float>*
|
||||
%2 = load <4 x float>* %1
|
||||
%3 = bitcast float* %c to <4 x float>*
|
||||
%4 = load <4 x float>* %3
|
||||
%5 = fsub <4 x float> %2, %4
|
||||
%6 = call <4 x float> @llvm.fabs.v4f32(<4 x float> %5)
|
||||
%7 = bitcast float* %a to <4 x float>*
|
||||
store <4 x float> %6, <4 x float>* %7
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: test_v2f32
|
||||
; CHECK: fabd v0.2s, v0.2s, v1.2s
|
||||
declare <2 x float> @llvm.fabs.v2f32(<2 x float>)
|
||||
define void @test_v2f32(float* noalias nocapture %a, float* noalias nocapture readonly %b, float* noalias nocapture readonly %c){
|
||||
%1 = bitcast float* %b to <2 x float>*
|
||||
%2 = load <2 x float>* %1
|
||||
%3 = bitcast float* %c to <2 x float>*
|
||||
%4 = load <2 x float>* %3
|
||||
%5 = fsub <2 x float> %2, %4
|
||||
%6 = call <2 x float> @llvm.fabs.v2f32(<2 x float> %5)
|
||||
%7 = bitcast float* %a to <2 x float>*
|
||||
store <2 x float> %6, <2 x float>* %7
|
||||
ret void
|
||||
}
|
||||
|
||||
; CHECK: test_v2f64
|
||||
; CHECK: fabd v0.2d, v0.2d, v1.2d
|
||||
declare <2 x double> @llvm.fabs.v2f64(<2 x double>)
|
||||
define void @test_v2f64(double* noalias nocapture %a, double* noalias nocapture readonly %b, double* noalias nocapture readonly %c){
|
||||
%1 = bitcast double* %b to <2 x double>*
|
||||
%2 = load <2 x double>* %1
|
||||
%3 = bitcast double* %c to <2 x double>*
|
||||
%4 = load <2 x double>* %3
|
||||
%5 = fsub <2 x double> %2, %4
|
||||
%6 = call <2 x double> @llvm.fabs.v2f64(<2 x double> %5)
|
||||
%7 = bitcast double* %a to <2 x double>*
|
||||
store <2 x double> %6, <2 x double>* %7
|
||||
ret void
|
||||
}
|
||||
|
||||
@a = common global float 0.000000e+00
|
||||
declare float @fabsf(float)
|
||||
; CHECK: test_fabd32
|
||||
; CHECK: fabd s0, s0, s1
|
||||
define void @test_fabd32(float %b, float %c) {
|
||||
%1 = fsub float %b, %c
|
||||
%fabsf = tail call float @fabsf(float %1) #0
|
||||
store float %fabsf, float* @a
|
||||
ret void
|
||||
}
|
||||
|
||||
@d = common global double 0.000000e+00
|
||||
declare double @fabs(double)
|
||||
; CHECK: test_fabd64
|
||||
; CHECK: fabd d0, d0, d1
|
||||
define void @test_fabd64(double %b, double %c) {
|
||||
%1 = fsub double %b, %c
|
||||
%2 = tail call double @fabs(double %1) #0
|
||||
store double %2, double* @d
|
||||
ret void
|
||||
}
|
||||
|
||||
attributes #0 = { nounwind readnone}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user