X86: Do not select X86 custom vector nodes if operand types don't match

X86ISD::ADDSUB, X86ISD::(F)HADD, X86ISD::(F)HSUB should not be selected
if the operand types do not match the result type because vector type
legalization cannot deal with this for custom nodes.

Testcase X86ISD::ADDSUB is attached. I could not create a testcase for
the FHADD/FHSUB cases because of: https://llvm.org/bugs/show_bug.cgi?id=23296

Differential Revision: http://reviews.llvm.org/D9120

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@235367 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Matthias Braun 2015-04-21 01:13:41 +00:00
parent 9b56994421
commit 6fbedc4cfd
2 changed files with 30 additions and 5 deletions

View File

@ -5269,11 +5269,17 @@ static bool isHorizontalBinOp(const BuildVectorSDNode *N, unsigned Opcode,
unsigned I1 = cast<ConstantSDNode>(Op1.getOperand(1))->getZExtValue();
if (i * 2 < NumElts) {
if (V0.getOpcode() == ISD::UNDEF)
if (V0.getOpcode() == ISD::UNDEF) {
V0 = Op0.getOperand(0);
if (V0.getValueType() != VT)
return false;
}
} else {
if (V1.getOpcode() == ISD::UNDEF)
if (V1.getOpcode() == ISD::UNDEF) {
V1 = Op0.getOperand(0);
if (V1.getValueType() != VT)
return false;
}
if (i * 2 == NumElts)
ExpectedVExtractIdx = BaseIdx;
}
@ -5423,10 +5429,16 @@ static SDValue matchAddSub(const BuildVectorSDNode *BV, SelectionDAG &DAG,
SubFound = true;
// Update InVec0 and InVec1.
if (InVec0.getOpcode() == ISD::UNDEF)
if (InVec0.getOpcode() == ISD::UNDEF) {
InVec0 = Op0.getOperand(0);
if (InVec1.getOpcode() == ISD::UNDEF)
if (InVec0.getValueType() != VT)
return SDValue();
}
if (InVec1.getOpcode() == ISD::UNDEF) {
InVec1 = Op1.getOperand(0);
if (InVec1.getValueType() != VT)
return SDValue();
}
// Make sure that operands in input to each add/sub node always
// come from a same pair of vectors.

View File

@ -315,4 +315,17 @@ define <4 x float> @test16(<4 x float> %A, <4 x float> %B) {
; CHECK-NOT: addsubps
; CHECK: ret
define <2 x float> @test_v2f32(<2 x float> %v0, <2 x float> %v1) {
%v2 = extractelement <2 x float> %v0, i32 0
%v3 = extractelement <2 x float> %v1, i32 0
%v4 = extractelement <2 x float> %v0, i32 1
%v5 = extractelement <2 x float> %v1, i32 1
%sub = fsub float %v2, %v3
%add = fadd float %v5, %v4
%res0 = insertelement <2 x float> undef, float %sub, i32 0
%res1 = insertelement <2 x float> %res0, float %add, i32 1
ret <2 x float> %res1
}
; CHECK-LABEL: test_v2f32
; CHECK: addsubps %xmm1, %xmm0
; CHECK-NEXT: retq