diff options
| author | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-06-26 09:50:11 +0000 |
|---|---|---|
| committer | Simon Pilgrim <llvm-dev@redking.me.uk> | 2019-06-26 09:50:11 +0000 |
| commit | 3845a4f849309eab5dabecf1b0b6320af60b3dea (patch) | |
| tree | 104fff75e6e3fa81aecda8775d186a07afc6a785 /llvm/test/CodeGen/X86/bitcast-setcc-512.ll | |
| parent | 1a0810407edcff9791a5354d762ef8b4e7c07287 (diff) | |
| download | bcm5719-llvm-3845a4f849309eab5dabecf1b0b6320af60b3dea.tar.gz bcm5719-llvm-3845a4f849309eab5dabecf1b0b6320af60b3dea.zip | |
[X86][AVX] truncateVectorWithPACK - avoid bitcasted shuffles
truncateVectorWithPACK is often used in conjunction with ComputeNumSignBits which struggles when peeking through bitcasts.
This fix tries to avoid bitcast(shuffle(bitcast())) patterns in the 256-bit 64-bit sublane shuffles so we can still see through at least until lowering when the shuffles will need to be bitcasted to widen the shuffle type.
llvm-svn: 364401
Diffstat (limited to 'llvm/test/CodeGen/X86/bitcast-setcc-512.ll')
| -rw-r--r-- | llvm/test/CodeGen/X86/bitcast-setcc-512.ll | 3 |
1 files changed, 0 insertions, 3 deletions
diff --git a/llvm/test/CodeGen/X86/bitcast-setcc-512.ll b/llvm/test/CodeGen/X86/bitcast-setcc-512.ll index 177be1fd6a6..9f5097bab3c 100644 --- a/llvm/test/CodeGen/X86/bitcast-setcc-512.ll +++ b/llvm/test/CodeGen/X86/bitcast-setcc-512.ll @@ -624,9 +624,6 @@ define void @bitcast_8i64_store(i8* %p, <8 x i64> %a0) { ; ; AVX2-LABEL: bitcast_8i64_store: ; AVX2: # %bb.0: -; AVX2-NEXT: vpxor %xmm2, %xmm2, %xmm2 -; AVX2-NEXT: vpcmpgtq %ymm1, %ymm2, %ymm1 -; AVX2-NEXT: vpcmpgtq %ymm0, %ymm2, %ymm0 ; AVX2-NEXT: vpackssdw %ymm1, %ymm0, %ymm0 ; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,2,1,3] ; AVX2-NEXT: vmovmskps %ymm0, %eax |
