[PATCH] D31426: [DAGCombine] Combine shuffle of splat with multiple uses

[Zvi Rackover via Phabricator via llvm-commits]

zvi created this revision.

Add a combine for shuffle_vector(shuffle_splat(V), undef) for when the shuffle-splat has more than one use.

Fixes pr32449


Repository:
  rL LLVM

https://reviews.llvm.org/D31426

Files:
  lib/CodeGen/SelectionDAG/DAGCombiner.cpp
  test/CodeGen/X86/shuffle-of-splat-multiuses.ll


Index: test/CodeGen/X86/shuffle-of-splat-multiuses.ll
===================================================================
--- test/CodeGen/X86/shuffle-of-splat-multiuses.ll
+++ 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 <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 @@
 ; 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>
Index: lib/CodeGen/SelectionDAG/DAGCombiner.cpp
===================================================================
--- lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -14920,6 +14920,16 @@
     return DAG.getVectorShuffle(VT, SDLoc(N), SV0, SV1, Mask);
   }
 
+  // shuffle(shuffle_splat(A), u) -> shuffle_splat(A)
+  // The case where the shuffle-splat has a single use should have been handled
+  // previously, so here the shuffle being visited is not the only use of the
+  // splat-shuffle.
+  if (auto Shuf = dyn_cast<ShuffleVectorSDNode>(N0))
+    if (N1->isUndef() && Shuf->isSplat()) {
+      assert(!N->isOnlyUserOf(Shuf) &&
+             "Single use of splat-shuffle should have already been visited");
+      return N0;
+    }
   return SDValue();
 }
 


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D31426.93258.patch
Type: text/x-patch
Size: 2915 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170328/fd6b541c/attachment.bin>