[llvm] r338380 - [SLP] Fix PR38339: Instruction does not dominate all uses!

[Alexey Bataev via llvm-commits]

Author: abataev
Date: Tue Jul 31 07:02:43 2018
New Revision: 338380

URL: http://llvm.org/viewvc/llvm-project?rev=338380&view=rev
Log:
[SLP] Fix PR38339: Instruction does not dominate all uses!

Summary:
If the ExtractElement instructions can be optimized out during the
vectorization and we need to reshuffle the parent vector, this
ShuffleInstruction may be inserted in the wrong place causing compiler
to produce incorrect code.

Reviewers: spatel, RKSimon, mkuper, hfinkel, javed.absar

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D49928

Added:
    llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
Modified:
    llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp

Modified: llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp?rev=338380&r1=338379&r2=338380&view=diff
==============================================================================
--- llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp (original)
+++ llvm/trunk/lib/Transforms/Vectorize/SLPVectorizer.cpp Tue Jul 31 07:02:43 2018
@@ -3111,6 +3111,12 @@ Value *BoUpSLP::vectorizeTree(TreeEntry
           // TODO: Merge this shuffle with the ReorderShuffleMask.
           if (!E->ReorderIndices.empty())
             Builder.SetInsertPoint(VL0);
+          else if (auto *I = dyn_cast<Instruction>(V))
+            Builder.SetInsertPoint(I->getParent(),
+                                   std::next(I->getIterator()));
+          else
+            Builder.SetInsertPoint(&F->getEntryBlock(),
+                                   F->getEntryBlock().getFirstInsertionPt());
           V = Builder.CreateShuffleVector(V, UndefValue::get(VecTy),
                                           E->ReuseShuffleIndices, "shuffle");
         }

Added: llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll?rev=338380&view=auto
==============================================================================
--- llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll (added)
+++ llvm/trunk/test/Transforms/SLPVectorizer/AArch64/PR38339.ll Tue Jul 31 07:02:43 2018
@@ -0,0 +1,29 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt -slp-vectorizer -S -mtriple=aarch64-apple-ios -mcpu=cyclone -o - %s | FileCheck %s
+
+define void @f1(<2 x i16> %x, i16* %a) {
+; CHECK-LABEL: @f1(
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[X:%.*]], <2 x i16> undef, <4 x i32> <i32 0, i32 1, i32 1, i32 0>
+; CHECK-NEXT:    [[PTR0:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 0
+; CHECK-NEXT:    [[PTR1:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 1
+; CHECK-NEXT:    [[PTR2:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 2
+; CHECK-NEXT:    [[PTR3:%.*]] = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 3
+; CHECK-NEXT:    [[TMP1:%.*]] = extractelement <4 x i16> [[SHUFFLE]], i32 0
+; CHECK-NEXT:    store i16 [[TMP1]], i16* [[A:%.*]]
+; CHECK-NEXT:    [[TMP2:%.*]] = bitcast i16* [[PTR0]] to <4 x i16>*
+; CHECK-NEXT:    store <4 x i16> [[SHUFFLE]], <4 x i16>* [[TMP2]], align 2
+; CHECK-NEXT:    ret void
+;
+  %t2 = extractelement <2 x i16> %x, i32 0
+  %t3 = extractelement <2 x i16> %x, i32 1
+  %ptr0 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 0
+  %ptr1 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 1
+  %ptr2 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 2
+  %ptr3 = getelementptr inbounds [4 x i16], [4 x i16]* undef, i16 0, i16 3
+  store i16 %t2, i16* %a
+  store i16 %t2, i16* %ptr0
+  store i16 %t3, i16* %ptr1
+  store i16 %t3, i16* %ptr2
+  store i16 %t2, i16* %ptr3
+  ret void
+}