RPCS3/llvm-mirror
1
0
Fork 0
mirror of https://github.com/RPCS3/llvm-mirror.git synced 2024-11-29 22:30:33 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[X86] Emit a PACKUS instead of a VECTOR_SHUFFLE from LowerTRUNCATE for v16i16->v16i8.

Browse Source 
We can't guarantee that demanded bits passing through the vector shuffle won't cause the AND in front of this to be removed. This would prevent the PACKUS from being matched during shuffle lowering.

Unfortunately, this adds a packuswb to one of the vector-reduce-mul.ll tests since we were removing the shuffle via SimplifyDemandedVectorElts. We appear to have similar issues with vpmovwb on the same test case on other targets.

llvm-svn: 347361
This commit is contained in:
Craig Topper 2018-11-20 22:57:48 +00:00
parent e7be680ca1
commit 285da5c731
2 changed files with 3 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/Target/X86/X86ISelLowering.cpp
View File

@ -18100,19 +18100,14 @@ SDValue X86TargetLowering::LowerTRUNCATE(SDValue Op, SelectionDAG &DAG) const {
}
if (VT == MVT::v16i8 && InVT == MVT::v16i16) {
// Use an AND to force a PACKUS.
// Use an AND to zero uppper bits for PACKUS.
In = DAG.getNode(ISD::AND, DL, InVT, In, DAG.getConstant(255, DL, InVT));
SDValue InLo = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i16, In,
DAG.getIntPtrConstant(0, DL));
SDValue InHi = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, MVT::v8i16, In,
DAG.getIntPtrConstant(8, DL));
InLo = DAG.getBitcast(VT, InLo);
InHi = DAG.getBitcast(VT, InHi);
return DAG.getVectorShuffle(VT, DL, InLo, InHi,
{ 0, 2, 4, 6, 8, 10, 12, 14,
16, 18, 20, 22, 24, 26, 28, 30});
return DAG.getNode(X86ISD::PACKUS, DL, VT, InLo, InHi);
}
// Handle truncation of V256 to V128 using shuffles.

1
test/CodeGen/X86/vector-reduce-mul.ll
View File

@ -1576,6 +1576,7 @@ define i8 @test_v16i8(<16 x i8> %a0) {
; AVX2-NEXT: vpmovzxbw {{.*#+}} ymm1 = xmm1[0],zero,xmm1[1],zero,xmm1[2],zero,xmm1[3],zero,xmm1[4],zero,xmm1[5],zero,xmm1[6],zero,xmm1[7],zero,xmm1[8],zero,xmm1[9],zero,xmm1[10],zero,xmm1[11],zero,xmm1[12],zero,xmm1[13],zero,xmm1[14],zero,xmm1[15],zero
; AVX2-NEXT: vpmullw %xmm1, %xmm0, %xmm0
; AVX2-NEXT: vpand {{.*}}(%rip), %xmm0, %xmm0
; AVX2-NEXT: vpackuswb %xmm0, %xmm0, %xmm0
; AVX2-NEXT: vpextrb $0, %xmm0, %eax
; AVX2-NEXT: # kill: def $al killed $al killed $eax
; AVX2-NEXT: vzeroupper