[InstCombine] shrink truncated splat shuffle (2nd try)

This was committed at r297155 and reverted at r297166 because of an
over-reaching clang test. That should be fixed with r297189.

This is one part of solving a recent bug report:
http://lists.llvm.org/pipermail/llvm-dev/2017-February/110293.html

This keeps with our general approach: changing arbitrary shuffles is off-limts,
but changing splat is ok. The transform is very similar to the existing
shrinkBitwiseLogic() canonicalization.

Differential Revision: https://reviews.llvm.org/D30123

llvm-svn: 297232

2 files changed, 24 insertions, 6 deletions

diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
index e60687fa7ad..a1ac64dda35 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCasts.cpp
@@ -463,6 +463,23 @@ Instruction *InstCombiner::shrinkBitwiseLogic(TruncInst &Trunc) {
   return BinaryOperator::Create(LogicOp->getOpcode(), NarrowOp0, NarrowC);
 }
 
+/// Try to narrow the width of a splat shuffle. This could be generalized to any
+/// shuffle with a constant operand, but we limit the transform to avoid
+/// creating a shuffle type that targets may not be able to lower effectively.
+static Instruction *shrinkSplatShuffle(TruncInst &Trunc,
+                                       InstCombiner::BuilderTy &Builder) {
+  auto *Shuf = dyn_cast<ShuffleVectorInst>(Trunc.getOperand(0));
+  if (Shuf && Shuf->hasOneUse() && isa<UndefValue>(Shuf->getOperand(1)) &&
+      Shuf->getMask()->getSplatValue()) {
+    // trunc (shuf X, Undef, SplatMask) --> shuf (trunc X), Undef, SplatMask
+    Constant *NarrowUndef = UndefValue::get(Trunc.getType());
+    Value *NarrowOp = Builder.CreateTrunc(Shuf->getOperand(0), Trunc.getType());
+    return new ShuffleVectorInst(NarrowOp, NarrowUndef, Shuf->getMask());
+  }
+
+  return nullptr;
+}
+
 Instruction *InstCombiner::visitTrunc(TruncInst &CI) {
   if (Instruction *Result = commonCastTransforms(CI))
     return Result;
@@ -554,6 +571,9 @@ Instruction *InstCombiner::visitTrunc(TruncInst &CI) {
   if (Instruction *I = shrinkBitwiseLogic(CI))
     return I;
 
+  if (Instruction *I = shrinkSplatShuffle(CI, *Builder))
+    return I;
+
   if (Src->hasOneUse() && isa<IntegerType>(SrcTy) &&
       shouldChangeType(SrcTy, DestTy)) {
     // Transform "trunc (shl X, cst)" -> "shl (trunc X), cst" so long as the
diff --git a/llvm/test/Transforms/InstCombine/trunc.ll b/llvm/test/Transforms/InstCombine/trunc.ll
index 581e990df0f..ba72908d3c4 100644
--- a/llvm/test/Transforms/InstCombine/trunc.ll
+++ b/llvm/test/Transforms/InstCombine/trunc.ll
@@ -478,13 +478,12 @@ define <4 x i8> @wide_shuf(<4 x i32> %x) {
   ret <4 x i8> %trunc
 }
 
-; FIXME:
 ; trunc (shuffle X, undef, SplatMask) --> shuffle (trunc X), undef, SplatMask
 
 define <4 x i8> @wide_splat1(<4 x i32> %x) {
 ; CHECK-LABEL: @wide_splat1(
-; CHECK-NEXT:    [[SHUF:%.*]] = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
-; CHECK-NEXT:    [[TRUNC:%.*]] = trunc <4 x i32> [[SHUF]] to <4 x i8>
+; CHECK-NEXT:    [[TMP1:%.*]] = trunc <4 x i32> %x to <4 x i8>
+; CHECK-NEXT:    [[TRUNC:%.*]] = shufflevector <4 x i8> [[TMP1]], <4 x i8> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
 ; CHECK-NEXT:    ret <4 x i8> [[TRUNC]]
 ;
   %shuf = shufflevector <4 x i32> %x, <4 x i32> undef, <4 x i32> <i32 2, i32 2, i32 2, i32 2>
@@ -492,14 +491,13 @@ define <4 x i8> @wide_splat1(<4 x i32> %x) {
   ret <4 x i8> %trunc
 }
 
-; FIXME:
 ; Test weird types.
 ; trunc (shuffle X, undef, SplatMask) --> shuffle (trunc X), undef, SplatMask
 
 define <3 x i31> @wide_splat2(<3 x i33> %x) {
 ; CHECK-LABEL: @wide_splat2(
-; CHECK-NEXT:    [[SHUF:%.*]] = shufflevector <3 x i33> %x, <3 x i33> undef, <3 x i32> <i32 1, i32 1, i32 1>
-; CHECK-NEXT:    [[TRUNC:%.*]] = trunc <3 x i33> [[SHUF]] to <3 x i31>
+; CHECK-NEXT:    [[TMP1:%.*]] = trunc <3 x i33> %x to <3 x i31>
+; CHECK-NEXT:    [[TRUNC:%.*]] = shufflevector <3 x i31> [[TMP1]], <3 x i31> undef, <3 x i32> <i32 1, i32 1, i32 1>
 ; CHECK-NEXT:    ret <3 x i31> [[TRUNC]]
 ;
   %shuf = shufflevector <3 x i33> %x, <3 x i33> undef, <3 x i32> <i32 1, i32 1, i32 1>