forked from OSchip/llvm-project
[X86] Fold ANDNP(undef,x)/ANDNP(x,undef) -> 0
Matches the fold in DAGCombiner::visitANDLike.
This commit is contained in:
parent
d5ee20fcc9
commit
2d7f0b1c22
|
@ -50665,6 +50665,11 @@ static SDValue combineAndnp(SDNode *N, SelectionDAG &DAG,
|
|||
SDValue N1 = N->getOperand(1);
|
||||
MVT VT = N->getSimpleValueType(0);
|
||||
|
||||
// ANDNP(undef, x) -> 0
|
||||
// ANDNP(x, undef) -> 0
|
||||
if (N0.isUndef() || N1.isUndef())
|
||||
return DAG.getConstant(0, SDLoc(N), VT);
|
||||
|
||||
// ANDNP(0, x) -> x
|
||||
if (ISD::isBuildVectorAllZeros(N0.getNode()))
|
||||
return N1;
|
||||
|
|
|
@ -1,33 +1,20 @@
|
|||
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
||||
; RUN: llc < %s -mtriple=x86_64-linux -opaque-pointers -mcpu=ivybridge -mattr=+avx2 | FileCheck %s --check-prefixes=IVB
|
||||
; RUN: llc < %s -mtriple=x86_64-linux -opaque-pointers -mcpu=haswell | FileCheck %s --check-prefixes=HSW
|
||||
; RUN: llc < %s -mtriple=x86_64-linux -opaque-pointers -mcpu=ivybridge -mattr=+avx2 | FileCheck %s
|
||||
; RUN: llc < %s -mtriple=x86_64-linux -opaque-pointers -mcpu=haswell | FileCheck %s
|
||||
|
||||
define <2 x i64> @PR55158(ptr %0) {
|
||||
; IVB-LABEL: PR55158:
|
||||
; IVB: # %bb.0:
|
||||
; IVB-NEXT: vmovdqa 64(%rdi), %xmm0
|
||||
; IVB-NEXT: vmovdqa 128(%rdi), %xmm1
|
||||
; IVB-NEXT: vpmovsxbd (%rdi), %xmm2
|
||||
; IVB-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm1
|
||||
; IVB-NEXT: vphsubw %xmm0, %xmm0, %xmm0
|
||||
; IVB-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
||||
; IVB-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; IVB-NEXT: vpsrlvq %xmm1, %xmm2, %xmm1
|
||||
; IVB-NEXT: vpunpckhqdq {{.*#+}} xmm0 = xmm1[1],xmm0[1]
|
||||
; IVB-NEXT: retq
|
||||
;
|
||||
; HSW-LABEL: PR55158:
|
||||
; HSW: # %bb.0:
|
||||
; HSW-NEXT: vmovdqa 64(%rdi), %xmm0
|
||||
; HSW-NEXT: vmovdqa 128(%rdi), %xmm1
|
||||
; HSW-NEXT: vpmovsxbd (%rdi), %xmm2
|
||||
; HSW-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm1
|
||||
; HSW-NEXT: vphsubw %xmm0, %xmm0, %xmm0
|
||||
; HSW-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
||||
; HSW-NEXT: vpandn {{\.?LCPI[0-9]+_[0-9]+}}(%rip), %xmm0, %xmm2
|
||||
; HSW-NEXT: vpsrlvq %xmm1, %xmm2, %xmm1
|
||||
; HSW-NEXT: vpunpckhqdq {{.*#+}} xmm0 = xmm1[1],xmm0[1]
|
||||
; HSW-NEXT: retq
|
||||
; CHECK-LABEL: PR55158:
|
||||
; CHECK: # %bb.0:
|
||||
; CHECK-NEXT: vmovdqa 64(%rdi), %xmm0
|
||||
; CHECK-NEXT: vmovdqa 128(%rdi), %xmm1
|
||||
; CHECK-NEXT: vpmovsxbd (%rdi), %xmm2
|
||||
; CHECK-NEXT: vpcmpgtd %xmm2, %xmm1, %xmm1
|
||||
; CHECK-NEXT: vphsubw %xmm0, %xmm0, %xmm0
|
||||
; CHECK-NEXT: vpmovzxdq {{.*#+}} xmm1 = xmm1[0],zero,xmm1[1],zero
|
||||
; CHECK-NEXT: vpxor %xmm2, %xmm2, %xmm2
|
||||
; CHECK-NEXT: vpsrlvq %xmm1, %xmm2, %xmm1
|
||||
; CHECK-NEXT: vpunpckhqdq {{.*#+}} xmm0 = xmm1[1],xmm0[1]
|
||||
; CHECK-NEXT: retq
|
||||
%2 = load <16 x i8>, ptr %0, align 16
|
||||
%3 = getelementptr inbounds i32, ptr %0, i64 16
|
||||
%4 = load <8 x i16>, ptr %3, align 16
|
||||
|
|
Loading…
Reference in New Issue