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

[X86][AVX] lowerShuffleAsLanePermuteAndPermute - fully populate the lane shuffle mask (PR40730) 

As detailed on PR40730, we are not correctly filling in the lane shuffle mask (D53148/rL344446) - we fill in for the correct src lane but don't add it to the correct mask element, so any reference to the correct element is likely to see an UNDEF mask index.

This allows constant folding to propagate UNDEFs prior to the lane mask being (correctly) lowered to vperm2f128.

This patch fixes the issue by fully populating the lane shuffle mask - this is more than is necessary (if we only filled in the required mask elements we might be able to match other shuffle instructions - broadcasts etc.), but its the most cautious approach as this needs to be cherrypicked into the 8.0.0 release branch.

Differential Revision: https://reviews.llvm.org/D58237

llvm-svn: 354117
This commit is contained in:
Simon Pilgrim 2019-02-15 11:39:21 +00:00
parent 0446b40b63
commit 6ce08672fb
2 changed files with 12 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
llvm/lib/Target/X86/X86ISelLowering.cpp
View File

@ -14081,7 +14081,6 @@ static SDValue lowerShuffleAsLanePermuteAndPermute(
int NumEltsPerLane = NumElts / NumLanes;
SmallVector<int, 4> SrcLaneMask(NumLanes, SM_SentinelUndef);
SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef);
SmallVector<int, 16> PermMask(NumElts, SM_SentinelUndef);
for (int i = 0; i != NumElts; ++i) {
@ -14096,10 +14095,20 @@ static SDValue lowerShuffleAsLanePermuteAndPermute(
return SDValue();
SrcLaneMask[DstLane] = SrcLane;
LaneMask[i] = (SrcLane * NumEltsPerLane) + (i % NumEltsPerLane);
PermMask[i] = (DstLane * NumEltsPerLane) + (M % NumEltsPerLane);
}
// Make sure we set all elements of the lane mask, to avoid undef propagation.
SmallVector<int, 16> LaneMask(NumElts, SM_SentinelUndef);
for (int DstLane = 0; DstLane != NumLanes; ++DstLane) {
int SrcLane = SrcLaneMask[DstLane];
if (0 <= SrcLane)
for (int j = 0; j != NumEltsPerLane; ++j) {
LaneMask[(DstLane * NumEltsPerLane) + j] =
(SrcLane * NumEltsPerLane) + j;
}
}
// If we're only shuffling a single lowest lane and the rest are identity
// then don't bother.
// TODO - isShuffleMaskInputInPlace could be extended to something like this.

2
llvm/test/CodeGen/X86/pr40730.ll
View File

@ -19,7 +19,7 @@ define <8 x i32> @shuffle_v8i32_0dcd3f14(<8 x i32> %a, <8 x i32> %b) {
; CHECK: .LCPI1_0:
; CHECK-NEXT: .quad 60129542157
; CHECK-NEXT: .quad 60129542157
; CHECK-NEXT: .zero 8
; CHECK-NEXT: .quad 68719476736
; CHECK-NEXT: .quad 60129542157
define <8 x i32> @shuffle_v8i32_0dcd3f14_constant(<8 x i32> %a0) {