summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Target
diff options
context:
space:
mode:
authorAndrea Di Biagio <Andrea_DiBiagio@sn.scee.net>2015-03-13 17:29:49 +0000
committerAndrea Di Biagio <Andrea_DiBiagio@sn.scee.net>2015-03-13 17:29:49 +0000
commit510feca1b86530f4c48fb69180a612cdb47fcaf2 (patch)
treee78d72aa78597f7524f29d25665ddf70bf5837ca /llvm/lib/Target
parent76e37aa334f72d842e779b5014d1b1875f2d21a7 (diff)
downloadbcm5719-llvm-510feca1b86530f4c48fb69180a612cdb47fcaf2.tar.gz
bcm5719-llvm-510feca1b86530f4c48fb69180a612cdb47fcaf2.zip
[X86][AVX] Fix wrong lowering of v4x64 shuffles into concat_vector plus extract_subvector nodes.
This patch fixes a bug in the shuffle lowering logic implemented by function 'lowerV2X128VectorShuffle'. The are few cases where function 'lowerV2X128VectorShuffle' wrongly expands a shuffle of two v4X64 vectors into a CONCAT_VECTORS of two EXTRACT_SUBVECTOR nodes. The problematic expansion only occurs when the shuffle mask M has an 'undef' element at position 2, and M is equivalent to mask <0,1,4,5>. In that case, the algorithm propagates the wrong vector to one of the two new EXTRACT_SUBVECTOR nodes. Example: ;; define <4 x double> @test(<4 x double> %A, <4 x double> %B) { entry: %0 = shufflevector <4 x double> %A, <4 x double> %B, <4 x i32><i32 undef, i32 1, i32 undef, i32 5> ret <4 x double> %0 } ;; Before this patch, llc (-mattr=+avx) generated: vinsertf128 $1, %xmm0, %ymm0, %ymm0 With this patch, llc correctly generates: vinsertf128 $1, %xmm1, %ymm0, %ymm0 Added test lower-vec-shuffle-bug.ll Differential Revision: http://reviews.llvm.org/D8259 llvm-svn: 232179
Diffstat (limited to 'llvm/lib/Target')
-rw-r--r--llvm/lib/Target/X86/X86ISelLowering.cpp6
1 files changed, 3 insertions, 3 deletions
diff --git a/llvm/lib/Target/X86/X86ISelLowering.cpp b/llvm/lib/Target/X86/X86ISelLowering.cpp
index 0533afc59f6..167685ac2a8 100644
--- a/llvm/lib/Target/X86/X86ISelLowering.cpp
+++ b/llvm/lib/Target/X86/X86ISelLowering.cpp
@@ -9021,12 +9021,12 @@ static SDValue lowerV2X128VectorShuffle(SDLoc DL, MVT VT, SDValue V1,
VT.getVectorNumElements() / 2);
// Check for patterns which can be matched with a single insert of a 128-bit
// subvector.
- if (isShuffleEquivalent(V1, V2, Mask, {0, 1, 0, 1}) ||
- isShuffleEquivalent(V1, V2, Mask, {0, 1, 4, 5})) {
+ bool OnlyUsesV1 = isShuffleEquivalent(V1, V2, Mask, {0, 1, 0, 1});
+ if (OnlyUsesV1 || isShuffleEquivalent(V1, V2, Mask, {0, 1, 4, 5})) {
SDValue LoV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT, V1,
DAG.getIntPtrConstant(0));
SDValue HiV = DAG.getNode(ISD::EXTRACT_SUBVECTOR, DL, SubVT,
- Mask[2] < 4 ? V1 : V2, DAG.getIntPtrConstant(0));
+ OnlyUsesV1 ? V1 : V2, DAG.getIntPtrConstant(0));
return DAG.getNode(ISD::CONCAT_VECTORS, DL, VT, LoV, HiV);
}
if (isShuffleEquivalent(V1, V2, Mask, {0, 1, 6, 7})) {
OpenPOWER on IntegriCloud