[x86] Fix assertion failure caused by a wrong combine of PSHUFD nodes with different types.
When combining a sequence of two PSHUFD dag nodes into a single PSHUFD, make sure that we assign the correct type to the resulting PSHUFD. X86ISD::PSHUFD dag nodes can be either MVT::v4i32 or MVT::v4f32. Before this change, an assertion failure was triggered in method 'DAGCombinerInfo::CombineTo' when trying to combine the shuffles from the test below into a single PSHUFD. define <4 x float> @test1(<4 x float> %V) { %1 = shufflevector <4 x float> %V, <4 x float> undef, <4 x i32> <i32 3, i32 0, i32 2, i32 1> %2 = shufflevector <4 x float> %1, <4 x float> undef, <4 x i32> <i32 3, i32 0, i32 2, i32 1> ret <4 x float> %2 } llvm-svn: 212498
This commit is contained in:
parent
5c53298c1e
commit
2620b877b6
|
@ -18510,7 +18510,7 @@ static bool combineRedundantDWordShuffle(SDValue N, MutableArrayRef<int> Mask,
|
||||||
SmallVector<int, 4> VMask = getPSHUFShuffleMask(V);
|
SmallVector<int, 4> VMask = getPSHUFShuffleMask(V);
|
||||||
for (int &M : Mask)
|
for (int &M : Mask)
|
||||||
M = VMask[M];
|
M = VMask[M];
|
||||||
V = DAG.getNode(X86ISD::PSHUFD, DL, MVT::v4i32, V.getOperand(0),
|
V = DAG.getNode(X86ISD::PSHUFD, DL, V.getValueType(), V.getOperand(0),
|
||||||
getV4X86ShuffleImm8ForMask(Mask, DAG));
|
getV4X86ShuffleImm8ForMask(Mask, DAG));
|
||||||
|
|
||||||
// It is possible that one of the combinable shuffles was completely absorbed
|
// It is possible that one of the combinable shuffles was completely absorbed
|
||||||
|
|
|
@ -0,0 +1,14 @@
|
||||||
|
; RUN: llc < %s -march=x86-64 -mcpu=corei7 -debug
|
||||||
|
|
||||||
|
; REQUIRES: asserts
|
||||||
|
|
||||||
|
; Test that the dag combiner doesn't assert if we try to replace a sequence of two
|
||||||
|
; v4f32 X86ISD::PSHUFD nodes with a single PSHUFD.
|
||||||
|
|
||||||
|
|
||||||
|
define <4 x float> @test(<4 x float> %V) {
|
||||||
|
%1 = shufflevector <4 x float> %V, <4 x float> undef, <4 x i32> <i32 3, i32 0, i32 2, i32 1>
|
||||||
|
%2 = shufflevector <4 x float> %1, <4 x float> undef, <4 x i32> <i32 3, i32 0, i32 2, i32 1>
|
||||||
|
ret <4 x float> %2
|
||||||
|
}
|
||||||
|
|
Loading…
Reference in New Issue