[DAGCombine] A shuffle of a splat is always the splat itself

Summary:
Add a simplification:
shuffle (splat-shuffle), undef, M --> splat-shuffle

Fixes pr32449

Patch by Sanjay Patel

Reviewers: eli.friedman, RKSimon, spatel

Reviewed By: spatel

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D31426

llvm-svn: 299047

diff --git a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 922947a..ce485a9 100644 (file)
--- a/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/llvm/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14643,6 +14643,12 @@ SDValue DAGCombiner::visitVECTOR_SHUFFLE(SDNode *N) {
       return DAG.getVectorShuffle(VT, SDLoc(N), N0, N1, NewMask);
   }
 
+  // A shuffle of a splat is always the splat itself:
+  // shuffle (splat-shuffle), undef, M --> splat-shuffle
+  if (auto *N0Shuf = dyn_cast<ShuffleVectorSDNode>(N0))
+    if (N1.isUndef() && N0Shuf->isSplat())
+      return N0;
+
   // If it is a splat, check if the argument vector is another splat or a
   // build_vector.
   if (SVN->isSplat() && SVN->getSplatIndex() < (int)NumElts) {

diff --git a/llvm/test/CodeGen/X86/shuffle-of-splat-multiuses.ll b/llvm/test/CodeGen/X86/shuffle-of-splat-multiuses.ll
index 38d45ca..e7011df 100644 (file)
--- a/llvm/test/CodeGen/X86/shuffle-of-splat-multiuses.ll
+++ b/llvm/test/CodeGen/X86/shuffle-of-splat-multiuses.ll
@@ -5,9 +5,8 @@
 define <2 x double> @foo2(<2 x double> %v, <2 x double> *%p) nounwind {
 ; AVX2-LABEL: foo2:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,1]
-; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm1[1,0]
-; AVX2-NEXT:    vmovapd %xmm1, (%rdi)
+; AVX2-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,1]
+; AVX2-NEXT:    vmovapd %xmm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <2 x double> %v, <2 x double> undef, <2 x i32> <i32 1, i32 1>
   %res1 = shufflevector<2 x double> %res, <2 x double> undef, <2 x i32> <i32 1, i32 undef>
@@ -18,9 +17,8 @@ define <2 x double> @foo2(<2 x double> %v, <2 x double> *%p) nounwind {
 define <4 x double> @foo4(<4 x double> %v, <4 x double> *%p) nounwind {
 ; AVX2-LABEL: foo4:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,2,2]
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm1[2,0,2,3]
-; AVX2-NEXT:    vmovapd %ymm1, (%rdi)
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,2]
+; AVX2-NEXT:    vmovapd %ymm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <4 x double> %v, <4 x double> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
   %res1 = shufflevector<4 x double> %res, <4 x double> undef, <4 x i32> <i32 2, i32 0, i32 undef, i32 undef>
@@ -32,10 +30,8 @@ define <8 x float> @foo8(<8 x float> %v, <8 x float> *%p) nounwind {
 ; AVX2-LABEL: foo8:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vmovshdup {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
-; AVX2-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,2,2]
-; AVX2-NEXT:    vmovaps {{.*#+}} ymm0 = <2,0,u,u,5,1,3,7>
-; AVX2-NEXT:    vpermps %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vmovapd %ymm1, (%rdi)
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,2]
+; AVX2-NEXT:    vmovapd %ymm0, (%rdi)
 ; AVX2-NEXT:    retq
   %res = shufflevector <8 x float> %v, <8 x float> undef, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5, i32 5>
   %res1 = shufflevector<8 x float> %res, <8 x float> undef, <8 x i32> <i32 2, i32 0, i32 undef, i32 undef, i32 5, i32 1, i32 3, i32 7>