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

[X86] Fixes bug in build_vector v4x32 lowering 

r222375 made some improvements to build_vector lowering of v4x32 and v4xf32 into an insertps, but it missed a case where:

1. A single extracted element is used twice.
2. The lower of the two non-zero indexes should be preserved, and the higher should be used for the dest mask.

This caused a crash, since the source value for the insertps ends-up uninitialized.

Differential Revision: http://reviews.llvm.org/D6377

llvm-svn: 222635
This commit is contained in:
Michael Kuperstein 2014-11-23 13:09:06 +00:00
parent 8c5128bf1b
commit 9ef90647b9
2 changed files with 23 additions and 3 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

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

@ -5771,7 +5771,8 @@ static SDValue LowerBuildVectorv4x32(SDValue Op, SelectionDAG &DAG,
// We only know how to deal with build_vector nodes where elements are either
// zeroable or extract_vector_elt with constant index.
SDValue FirstNonZero;
for (int i=0; i < 4; ++i) {
unsigned FirstNonZeroIdx;
for (unsigned i=0; i < 4; ++i) {
if (Zeroable[i])
continue;
SDValue Elt = Op->getOperand(i);
@ -5782,8 +5783,10 @@ static SDValue LowerBuildVectorv4x32(SDValue Op, SelectionDAG &DAG,
MVT VT = Elt.getOperand(0).getSimpleValueType();
if (!VT.is128BitVector())
return SDValue();
if (!FirstNonZero.getNode())
if (!FirstNonZero.getNode()) {
FirstNonZero = Elt;
FirstNonZeroIdx = i;
}
}
assert(FirstNonZero.getNode() && "Unexpected build vector of all zeros!");
@ -5822,7 +5825,7 @@ static SDValue LowerBuildVectorv4x32(SDValue Op, SelectionDAG &DAG,
return SDValue();
SDValue V2 = Elt.getOperand(0);
if (Elt == FirstNonZero)
if (Elt == FirstNonZero && EltIdx == FirstNonZeroIdx)
V1 = SDValue();
bool CanFold = true;

17
llvm/test/CodeGen/X86/sse41.ll
View File

@ -1145,6 +1145,23 @@ entry:
ret <4 x float> %vecinit3
}
define <4 x float> @insertps_10(<4 x float> %A)
{
; X32-LABEL: insertps_10:
; X32: ## BB#0:
; X32-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
; X32-NEXT: retl
;
; X64-LABEL: insertps_10:
; X64: ## BB#0:
; X64-NEXT: insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
; X64-NEXT: retq
%vecext = extractelement <4 x float> %A, i32 0
%vecbuild1 = insertelement <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %vecext, i32 0
%vecbuild2 = insertelement <4 x float> %vecbuild1, float %vecext, i32 2
ret <4 x float> %vecbuild2
}
define <4 x float> @build_vector_to_shuffle_1(<4 x float> %A) {
; X32-LABEL: build_vector_to_shuffle_1:
; X32: ## BB#0: