RPCSX/llvm
1
0
Fork 0
mirror of https://github.com/RPCSX/llvm.git synced 2025-03-02 18:06:17 +00:00
Code Issues Actions Packages Projects Releases Wiki Activity

[DAGCombiner] Fix fold (or (shuf A, V_0, MA), (shuf B, V_0, MB)) -> (shuf A, B, Mask) to explicitly ensure that only one of the inputs of each shuffle is a zero vector.

Browse Source 
This can only happen when we have a mix of zero and undef elements and the two vectors have a different arrangement of zeros/undefs. The shuffle should eventually be constant folded to all zeros.

Fixes PR32484.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@299291 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Craig Topper 2017-04-01 04:26:20 +00:00
parent 2a400a79a2
commit 0c554b7eb1
2 changed files with 33 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
lib/CodeGen/SelectionDAG/DAGCombiner.cpp
View File

@ -4082,7 +4082,7 @@ SDValue DAGCombiner::visitOR(SDNode *N) {
bool ZeroN10 = ISD::isBuildVectorAllZeros(N1.getOperand(0).getNode());
bool ZeroN11 = ISD::isBuildVectorAllZeros(N1.getOperand(1).getNode());
// Ensure both shuffles have a zero input.
if ((ZeroN00 || ZeroN01) && (ZeroN10 || ZeroN11)) {
if ((ZeroN00 != ZeroN01) && (ZeroN10 != ZeroN11)) {
assert((!ZeroN00 || !ZeroN01) && "Both inputs zero!");
assert((!ZeroN10 || !ZeroN11) && "Both inputs zero!");
const ShuffleVectorSDNode *SV0 = cast<ShuffleVectorSDNode>(N0);

32
test/CodeGen/X86/pr32484.ll Normal file
View File

@ -0,0 +1,32 @@
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -O0 -mtriple=x86_64-unknown-linux-gnu < %s | FileCheck %s
define void @foo() {
; CHECK-LABEL: foo:
; CHECK: # BB#0:
; CHECK-NEXT: # implicit-def: %RAX
; CHECK-NEXT: jmpq *%rax
; CHECK-NEXT: .LBB0_1:
; CHECK-NEXT: # implicit-def: %RAX
; CHECK-NEXT: xorps %xmm0, %xmm0
; CHECK-NEXT: pcmpeqd %xmm1, %xmm1
; CHECK-NEXT: movdqu %xmm1, (%rax)
; CHECK-NEXT: movaps %xmm0, -{{[0-9]+}}(%rsp) # 16-byte Spill
; CHECK-NEXT: .LBB0_2:
; CHECK-NEXT: retq
indirectbr i8* undef, [label %9, label %1]
; <label>:1: ; preds = %0
%2 = shufflevector <16 x i8> zeroinitializer, <16 x i8> <i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef>, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
%3 = shufflevector <16 x i8> <i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 undef, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0, i8 0>, <16 x i8> zeroinitializer, <16 x i32> <i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23>
%4 = or <16 x i8> %3, %2
%5 = shufflevector <16 x i8> %4, <16 x i8> undef, <16 x i32> <i32 8, i32 5, i32 1, i32 13, i32 15, i32 10, i32 14, i32 0, i32 3, i32 2, i32 7, i32 4, i32 6, i32 9, i32 11, i32 12>
%6 = bitcast <16 x i8> %5 to <2 x i64>
%7 = xor <2 x i64> %6, zeroinitializer
%8 = xor <2 x i64> %7, <i64 -1, i64 -1>
store <2 x i64> %8, <2 x i64>* undef, align 1
unreachable
; <label>:9: ; preds = %0
ret void
}