[InstCombine] limit extracting shuffle transform based on uses

As discussed in D53037, this can lead to worse codegen, and we
don't generally expect the backend to be able to optimize
arbitrary shuffles. If there's only one use of the 1st shuffle,
that means it's getting removed, so that should always be
safe.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@353235 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/InstCombine/InstCombineVectorOps.cpp b/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
index abc2297f346fc8304a724d8e72638e00084f014c..6889cd9189ce13f4db56899046ac6c714387c8d6 100644 (file)
--- a/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
+++ b/lib/Transforms/InstCombine/InstCombineVectorOps.cpp
@@ -1498,6 +1498,11 @@ static Instruction *foldIdentityExtractShuffle(ShuffleVectorInst &Shuf) {
   if (!match(Op0, m_ShuffleVector(m_Value(X), m_Value(Y), m_Constant(Mask))))
     return nullptr;
 
+  // Be conservative with shuffle transforms. If we can't kill the 1st shuffle,
+  // then combining may result in worse codegen.
+  if (!Op0->hasOneUse())
+    return nullptr;
+
   // We are extracting a subvector from a shuffle. Remove excess elements from
   // the 1st shuffle mask to eliminate the extract.
   //

diff --git a/test/Transforms/InstCombine/vec_shuffle.ll b/test/Transforms/InstCombine/vec_shuffle.ll
index 401bcee4991148eb4fa79b74d9edd383befa0ce0..aae337d0de3f8d12db38df2422a9ef8e361191b7 100644 (file)
--- a/test/Transforms/InstCombine/vec_shuffle.ll
+++ b/test/Transforms/InstCombine/vec_shuffle.ll
@@ -195,7 +195,7 @@ define <4 x i8> @extract_subvector_of_shuffle_undefs_types(<2 x i8> %x, <2 x i8>
   ret <4 x i8> %extract_subv
 }
 
-; FIXME: Extra uses are not ok - we should only do the transform when we can eliminate an instruction.
+; Extra uses are not ok - we only do the transform when we can eliminate an instruction.
 
 declare void @use_v5i8(<5 x i8>)
 
@@ -203,7 +203,7 @@ define <4 x i8> @extract_subvector_of_shuffle_extra_use(<2 x i8> %x, <2 x i8> %y
 ; CHECK-LABEL: @extract_subvector_of_shuffle_extra_use(
 ; CHECK-NEXT:    [[SHUF:%.*]] = shufflevector <2 x i8> [[X:%.*]], <2 x i8> [[Y:%.*]], <5 x i32> <i32 undef, i32 2, i32 0, i32 1, i32 0>
 ; CHECK-NEXT:    call void @use_v5i8(<5 x i8> [[SHUF]])
-; CHECK-NEXT:    [[EXTRACT_SUBV:%.*]] = shufflevector <2 x i8> [[X]], <2 x i8> [[Y]], <4 x i32> <i32 undef, i32 2, i32 0, i32 undef>
+; CHECK-NEXT:    [[EXTRACT_SUBV:%.*]] = shufflevector <5 x i8> [[SHUF]], <5 x i8> undef, <4 x i32> <i32 0, i32 1, i32 2, i32 undef>
 ; CHECK-NEXT:    ret <4 x i8> [[EXTRACT_SUBV]]
 ;
   %shuf = shufflevector <2 x i8> %x, <2 x i8> %y, <5 x i32> <i32 undef, i32 2, i32 0, i32 1, i32 0>