6502/llvm-6502
1
0
Fork 0
mirror of https://github.com/c64scene-ar/llvm-6502.git synced 2025-02-23 05:29:23 +00:00
Code Issues Projects Releases Wiki Activity

[X86][SSE] Fix for getScalarValueForVectorElement to detect scalar sources requiring truncation.

Browse Source 
The fix ensures that scalar sources inserted into a vector are the correct bit size.

Integer scalar sources from BUILD_VECTOR and SCALAR_TO_VECTOR nodes may require truncation that this function doesn't currently support.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235281 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Simon Pilgrim 2015-04-19 22:16:49 +00:00
parent e398eb753a
commit ca3e6fafc8
2 changed files with 23 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
lib/Target/X86/X86ISelLowering.cpp
View File

@ -6918,8 +6918,13 @@ static SDValue getScalarValueForVectorElement(SDValue V, int Idx,
return SDValue();
if (V.getOpcode() == ISD::BUILD_VECTOR ||
(Idx == 0 && V.getOpcode() == ISD::SCALAR_TO_VECTOR))
return DAG.getNode(ISD::BITCAST, SDLoc(V), EltVT, V.getOperand(Idx));
(Idx == 0 && V.getOpcode() == ISD::SCALAR_TO_VECTOR)) {
// Ensure the scalar operand is the same size as the destination.
// FIXME: Add support for scalar truncation where possible.
SDValue S = V.getOperand(Idx);
if (EltVT.getSizeInBits() == S.getSimpleValueType().getSizeInBits())
return DAG.getNode(ISD::BITCAST, SDLoc(V), EltVT, S);
}
return SDValue();
}

16
test/CodeGen/X86/fold-vector-shuffle-crash.ll Normal file
View File

@ -0,0 +1,16 @@
; RUN: llc < %s -mtriple=x86_64-unknown -mcpu=corei7
define void @autogen_SD13708(i32) {
BB:
%Shuff7 = shufflevector <8 x i32> zeroinitializer, <8 x i32> zeroinitializer, <8 x i32> <i32 8, i32 10, i32 12, i32 14, i32 undef, i32 2, i32 4, i32 undef>
br label %CF
CF:
%Tr = trunc <8 x i64> zeroinitializer to <8 x i32>
%Shuff20 = shufflevector <8 x i32> %Shuff7, <8 x i32> %Tr, <8 x i32> <i32 13, i32 15, i32 1, i32 3, i32 5, i32 7, i32 undef, i32 11>
br i1 undef, label %CF, label %CF247
CF247:
%I171 = insertelement <8 x i32> %Shuff20, i32 %0, i32 0
br i1 undef, label %CF, label %CF247
}