maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[DAG] foldShuffleOfConcatUndefs - ensure shuffles of upper (undef) subvector elements is undef (PR50609) 

shuffle(concat(x,undef),concat(y,undef)) -> concat(shuffle(x,y),shuffle(x,y))

If the original shuffle references any of the upper (undef) subvector elements, ensure the split shuffle masks uses undef instead of an out-of-bounds value.

Fixes PR50609
This commit is contained in:
Simon Pilgrim 2021-06-08 15:49:27 +01:00
parent dee1f0cb34
commit 61a2d6bfe4
2 changed files with 45 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -20427,6 +20427,9 @@ static SDValue foldShuffleOfConcatUndefs(ShuffleVectorSDNode *Shuf,
for (unsigned i = 0; i != NumElts; ++i) {
if (Mask[i] == -1)
continue;
// If we reference the upper (undef) subvector then the element is undef.
if ((Mask[i] % NumElts) >= HalfNumElts)
continue;
int M = Mask[i] < (int)NumElts ? Mask[i] : Mask[i] - (int)HalfNumElts;
if (i < HalfNumElts)
Mask0[i] = M;

42
llvm/test/CodeGen/X86/pr50609.ll Normal file
View File

@ -0,0 +1,42 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=sandybridge | FileCheck %s
define void @PR50609(float* noalias nocapture %RET, float* noalias %aFOO, <16 x i32> %__mask) nounwind {
; CHECK-LABEL: PR50609:
; CHECK: # %bb.0: # %allocas
; CHECK-NEXT: leal 40(%rsi), %eax
; CHECK-NEXT: vmovq %rsi, %xmm2
; CHECK-NEXT: vmovd %eax, %xmm3
; CHECK-NEXT: vpsubq %xmm2, %xmm3, %xmm2
; CHECK-NEXT: vpsrad $31, %xmm2, %xmm3
; CHECK-NEXT: vpsrld $30, %xmm3, %xmm3
; CHECK-NEXT: vpaddd %xmm3, %xmm2, %xmm2
; CHECK-NEXT: vpsrad $2, %xmm2, %xmm2
; CHECK-NEXT: vcvtdq2ps %ymm2, %ymm2
; CHECK-NEXT: vpermilps {{.*#+}} xmm2 = xmm2[0,0,0,0]
; CHECK-NEXT: vinsertf128 $1, %xmm2, %ymm2, %ymm2
; CHECK-NEXT: vmaskmovps %ymm2, %ymm0, (%rdi)
; CHECK-NEXT: vmaskmovps %ymm2, %ymm1, 32(%rdi)
; CHECK-NEXT: vzeroupper
; CHECK-NEXT: retq
allocas:
%aFOO_load_ptr2int = ptrtoint float* %aFOO to i64
%aFOO_load_ptr2int_broadcast = insertelement <16 x i64> undef, i64 %aFOO_load_ptr2int, i32 0
%aFOO_load4_offset = getelementptr float, float* %aFOO, i64 10
%c_load_ptr2int = ptrtoint float* %aFOO_load4_offset to i64
%c_load_ptr2int_broadcast = insertelement <16 x i64> undef, i64 %c_load_ptr2int, i32 0
%0 = sub <16 x i64> %c_load_ptr2int_broadcast, %aFOO_load_ptr2int_broadcast
%1 = trunc <16 x i64> %0 to <16 x i32>
%2 = sdiv <16 x i32> %1, <i32 4, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
%3 = sitofp <16 x i32> %2 to <16 x float>
%ptr.i.i = bitcast float* %RET to i8*
%val0.i.i = shufflevector <16 x float> %3, <16 x float> undef, <8 x i32> zeroinitializer
%mask0.i.i = shufflevector <16 x i32> %__mask, <16 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
%mask1.i.i = shufflevector <16 x i32> %__mask, <16 x i32> undef, <8 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
call void @llvm.x86.avx.maskstore.ps.256(i8* %ptr.i.i, <8 x i32> %mask0.i.i, <8 x float> %val0.i.i) #1
%ptr1.i.i16 = getelementptr float, float* %RET, i64 8
%ptr1.i.i = bitcast float* %ptr1.i.i16 to i8*
call void @llvm.x86.avx.maskstore.ps.256(i8* %ptr1.i.i, <8 x i32> %mask1.i.i, <8 x float> %val0.i.i) #1
ret void
}
declare void @llvm.x86.avx.maskstore.ps.256(i8*, <8 x i32>, <8 x float>)