[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

1 files changed, 41 insertions, 0 deletions

diff --git a/llvm/test/CodeGen/X86/lower-vec-shuffle-bug.ll b/llvm/test/CodeGen/X86/lower-vec-shuffle-bug.ll
new file mode 100644
index 00000000000..5918e8045f6
--- /dev/null
+++ b/llvm/test/CodeGen/X86/lower-vec-shuffle-bug.ll
@@ -0,0 +1,41 @@
+; RUN: llc -mtriple=x86_64-unknown-unknown -mattr=+avx < %s | FileCheck %s
+
+define <4 x double> @test1(<4 x double> %A, <4 x double> %B) {
+; CHECK-LABEL: test1:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; CHECK-NEXT:    retq
+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
+}
+
+define <4 x double> @test2(<4 x double> %A, <4 x double> %B) {
+; CHECK-LABEL: test2:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; CHECK-NEXT:    retq
+entry:
+  %0 = shufflevector <4 x double> %A, <4 x double> %B, <4 x i32> <i32 undef, i32 1, i32 undef, i32 1>
+  ret <4 x double> %0
+}
+
+define <4 x double> @test3(<4 x double> %A, <4 x double> %B) {
+; CHECK-LABEL: test3:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; CHECK-NEXT:    retq
+entry:
+  %0 = shufflevector <4 x double> %A, <4 x double> %B, <4 x i32> <i32 0, i32 1, i32 undef, i32 5>
+  ret <4 x double> %0
+}
+
+define <4 x double> @test4(<4 x double> %A, <4 x double> %B) {
+; CHECK-LABEL: test4:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; CHECK-NEXT:    retq
+entry:
+  %0 = shufflevector <4 x double> %A, <4 x double> %B, <4 x i32> <i32 0, i32 1, i32 undef, i32 1>
+  ret <4 x double> %0
+}