6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-01-14 00:32:55 +00:00
Code Issues Projects Releases Wiki Activity

Fix a bug about generating undef operand when optimising shuffle vector and insert element in instruction combine.

Browse Source 
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@198730 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Hao Liu 2014-01-08 03:06:15 +00:00
parent 476136e951
commit 9e0fd27ce7
2 changed files with 20 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
lib/Transforms/InstCombine/InstCombineVectorOps.cpp
View File

@ -763,9 +763,10 @@ InstCombiner::EvaluateInDifferentElementOrder(Value *V, ArrayRef<int> Mask) {
}
}
// If element is not in Mask, no need to handle the operand 1 (element to
// be inserted). Just evaluate values in operand 0 according to Mask.
if (!Found)
return UndefValue::get(
VectorType::get(V->getType()->getScalarType(), Mask.size()));
return EvaluateInDifferentElementOrder(I->getOperand(0), Mask);
Value *V = EvaluateInDifferentElementOrder(I->getOperand(0), Mask);
return InsertElementInst::Create(V, I->getOperand(1),

17
test/Transforms/InstCombine/vec_shuffle.ll
View File

@ -228,3 +228,20 @@ define <4 x float> @test15b(<4 x float> %LHS, <4 x float> %RHS) {
ret <4 x float> %tmp5
}
define <1 x i32> @test16a(i32 %ele) {
; CHECK-LABEL: @test16a(
; CHECK-NEXT: ret <1 x i32> <i32 2>
%tmp0 = insertelement <2 x i32> <i32 1, i32 undef>, i32 %ele, i32 1
%tmp1 = shl <2 x i32> %tmp0, <i32 1, i32 1>
%tmp2 = shufflevector <2 x i32> %tmp1, <2 x i32> undef, <1 x i32> <i32 0>
ret <1 x i32> %tmp2
}
define <4 x i8> @test16b(i8 %ele) {
; CHECK-LABEL: @test16b(
; CHECK-NEXT: ret <4 x i8> <i8 2, i8 2, i8 2, i8 2>
%tmp0 = insertelement <8 x i8> <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 undef, i8 1>, i8 %ele, i32 6
%tmp1 = shl <8 x i8> %tmp0, <i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1, i8 1>
%tmp2 = shufflevector <8 x i8> %tmp1, <8 x i8> undef, <4 x i32> <i32 1, i32 2, i32 3, i32 4>
ret <4 x i8> %tmp2
}