[DAGCombine] Permit combining of shuffles of equivalent splat BUILD_VECTORs

combineShuffleOfScalars is very conservative about shuffled BUILD_VECTORs that can be combined together.

This patch adds one additional case - if both BUILD_VECTORs represent splats of the same scalar value but with different UNDEF elements, then we should create a single splat BUILD_VECTOR, sharing only the UNDEF elements defined by the shuffle mask.

Differential Revision: https://reviews.llvm.org/D38696

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@316331 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
index 73b90666c568625b91f06537bfd9b853bee98b6b..b79ff7f146d1fe4d086c922d0c9590c31e234151 100644 (file)
--- a/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
+++ b/lib/CodeGen/SelectionDAG/DAGCombiner.cpp
@@ -15453,7 +15453,7 @@ static SDValue partitionShuffleOfConcats(SDNode *N, SelectionDAG &DAG) {
 //
 // To deal with this, we currently use a bunch of mostly arbitrary heuristics.
 // We don't fold shuffles where one side is a non-zero constant, and we don't
-// fold shuffles if the resulting BUILD_VECTOR would have duplicate
+// fold shuffles if the resulting (non-splat) BUILD_VECTOR would have duplicate
 // non-constant operands. This seems to work out reasonably well in practice.
 static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
                                        SelectionDAG &DAG,
@@ -15477,6 +15477,15 @@ static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
       return SDValue();
   }
 
+  // If both inputs are splats of the same value then we can safely merge this
+  // to a single BUILD_VECTOR with undef elements based on the shuffle mask.
+  bool IsSplat = false;
+  auto *BV0 = dyn_cast<BuildVectorSDNode>(N0);
+  auto *BV1 = dyn_cast<BuildVectorSDNode>(N1);
+  if (BV0 && BV1)
+    if (SDValue Splat0 = BV0->getSplatValue())
+      IsSplat = (Splat0 == BV1->getSplatValue());
+
   SmallVector<SDValue, 8> Ops;
   SmallSet<SDValue, 16> DuplicateOps;
   for (int M : SVN->getMask()) {
@@ -15495,11 +15504,12 @@ static SDValue combineShuffleOfScalars(ShuffleVectorSDNode *SVN,
       }
     }
 
-    // Don't duplicate a non-constant BUILD_VECTOR operand; semantically, this is
-    // fine, but it's likely to generate low-quality code if the target can't
-    // reconstruct an appropriate shuffle.
+    // Don't duplicate a non-constant BUILD_VECTOR operand unless we're
+    // generating a splat; semantically, this is fine, but it's likely to
+    // generate low-quality code if the target can't reconstruct an appropriate
+    // shuffle.
     if (!Op.isUndef() && !isa<ConstantSDNode>(Op) && !isa<ConstantFPSDNode>(Op))
-      if (!DuplicateOps.insert(Op).second)
+      if (!IsSplat && !DuplicateOps.insert(Op).second)
         return SDValue();
 
     Ops.push_back(Op);

diff --git a/test/CodeGen/X86/avx-vbroadcast.ll b/test/CodeGen/X86/avx-vbroadcast.ll
index 65e856c03c8031bd0cb3bf853f5cfaee9d272b75..5dcc5a70529aaef15aa2dddb3c8c52c7913594f1 100644 (file)
--- a/test/CodeGen/X86/avx-vbroadcast.ll
+++ b/test/CodeGen/X86/avx-vbroadcast.ll
@@ -853,14 +853,12 @@ define <4 x double> @broadcast_shuffle1032(double* %p) {
 ; X32-LABEL: broadcast_shuffle1032:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
-; X32-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; X32-NEXT:    vbroadcastsd (%eax), %ymm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: broadcast_shuffle1032:
 ; X64:       ## BB#0:
-; X64-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
-; X64-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; X64-NEXT:    vbroadcastsd (%rdi), %ymm0
 ; X64-NEXT:    retq
   %1 = load double, double* %p
   %2 = insertelement <2 x double> undef, double %1, i32 1