Merging r339166:

------------------------------------------------------------------------
r339166 | abataev | 2018-08-07 21:21:05 +0200 (Tue, 07 Aug 2018) | 12 lines

[SLP] Fix insert point for reused extract instructions.

Summary:
Reworked the previously committed patch to insert shuffles for reused
extract element instructions in the correct position. Previous logic was
incorrect, and might lead to the crash with PHIs and EH instructions.

Reviewers: efriedma, javed.absar

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D50143
------------------------------------------------------------------------


git-svn-id: https://llvm.org/svn/llvm-project/llvm/branches/release_70@339853 91177308-0d34-0410-b5e6-96231b3b80d8

2 files changed, 96 insertions, 7 deletions

diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 5c2efe885e2..32df6d58157 100644
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -3109,14 +3109,8 @@ Value *BoUpSLP::vectorizeTree(TreeEntry *E) {
         }
         if (NeedToShuffleReuses) {
           // TODO: Merge this shuffle with the ReorderShuffleMask.
-          if (!E->ReorderIndices.empty())
+          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");
         }
diff --git a/test/Transforms/SLPVectorizer/AArch64/PR38339.ll b/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
index 1ab4a13260e..1a981a32804 100644
--- a/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
+++ b/test/Transforms/SLPVectorizer/AArch64/PR38339.ll
@@ -27,3 +27,98 @@ define void @f1(<2 x i16> %x, i16* %a) {
   store i16 %t2, i16* %ptr3
   ret void
 }
+
+define void @f2(<2 x i16> %x, i16* %a) {
+; CHECK-LABEL: @f2(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[CONT:%.*]]
+; CHECK:       cont:
+; CHECK-NEXT:    [[XX:%.*]] = phi <2 x i16> [ [[X:%.*]], [[ENTRY:%.*]] ], [ undef, [[CONT]] ]
+; CHECK-NEXT:    [[AA:%.*]] = phi i16* [ [[A:%.*]], [[ENTRY]] ], [ undef, [[CONT]] ]
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <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:    [[TMP0:%.*]] = extractelement <4 x i16> [[SHUFFLE]], i32 0
+; CHECK-NEXT:    store i16 [[TMP0]], i16* [[A]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[PTR0]] to <4 x i16>*
+; CHECK-NEXT:    store <4 x i16> [[SHUFFLE]], <4 x i16>* [[TMP1]], align 2
+; CHECK-NEXT:    [[A_VAL:%.*]] = load i16, i16* [[A]], align 2
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i16 [[A_VAL]], 0
+; CHECK-NEXT:    br i1 [[CMP]], label [[CONT]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %cont
+
+cont:                                           ; preds = %entry, %cont
+  %xx = phi <2 x i16> [ %x, %entry ], [ undef, %cont ]
+  %aa = phi i16* [ %a, %entry ], [ undef, %cont ]
+  %t2 = extractelement <2 x i16> %xx, i32 0
+  %t3 = extractelement <2 x i16> %xx, 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
+  %a_val = load i16, i16* %a, align 2
+  %cmp = icmp eq i16 %a_val, 0
+  br i1 %cmp, label %cont, label %exit
+
+exit:                                           ; preds = %cont
+  ret void
+}
+
+define void @f3(<2 x i16> %x, i16* %a) {
+; CHECK-LABEL: @f3(
+; CHECK-NEXT:  entry:
+; CHECK-NEXT:    br label [[CONT:%.*]]
+; CHECK:       cont:
+; CHECK-NEXT:    [[XX:%.*]] = phi <2 x i16> [ [[X:%.*]], [[ENTRY:%.*]] ], [ undef, [[CONT]] ]
+; CHECK-NEXT:    [[AA:%.*]] = phi i16* [ [[A:%.*]], [[ENTRY]] ], [ undef, [[CONT]] ]
+; CHECK-NEXT:    [[REORDER_SHUFFLE:%.*]] = shufflevector <2 x i16> [[XX]], <2 x i16> undef, <2 x i32> <i32 1, i32 0>
+; CHECK-NEXT:    [[SHUFFLE:%.*]] = shufflevector <2 x i16> [[REORDER_SHUFFLE]], <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:    [[TMP0:%.*]] = extractelement <4 x i16> [[SHUFFLE]], i32 0
+; CHECK-NEXT:    store i16 [[TMP0]], i16* [[A]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i16* [[PTR0]] to <4 x i16>*
+; CHECK-NEXT:    store <4 x i16> [[SHUFFLE]], <4 x i16>* [[TMP1]], align 2
+; CHECK-NEXT:    [[A_VAL:%.*]] = load i16, i16* [[A]], align 2
+; CHECK-NEXT:    [[CMP:%.*]] = icmp eq i16 [[A_VAL]], 0
+; CHECK-NEXT:    br i1 [[CMP]], label [[CONT]], label [[EXIT:%.*]]
+; CHECK:       exit:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %cont
+
+cont:                                           ; preds = %entry, %cont
+  %xx = phi <2 x i16> [ %x, %entry ], [ undef, %cont ]
+  %aa = phi i16* [ %a, %entry ], [ undef, %cont ]
+  %t2 = extractelement <2 x i16> %xx, i32 0
+  %t3 = extractelement <2 x i16> %xx, 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 %t3, i16* %a
+  store i16 %t3, i16* %ptr0
+  store i16 %t2, i16* %ptr1
+  store i16 %t2, i16* %ptr2
+  store i16 %t3, i16* %ptr3
+  %a_val = load i16, i16* %a, align 2
+  %cmp = icmp eq i16 %a_val, 0
+  br i1 %cmp, label %cont, label %exit
+
+exit:                                           ; preds = %cont
+  ret void
+}