[PATCH] D98423: Fix the trunc instruction insertion problem in SLP pass

[Bu Le via Phabricator via llvm-commits]

bule updated this revision to Diff 330492.
bule added a comment.

add -U9999 diff patch and the change after the pre-commit patch


CHANGES SINCE LAST ACTION
  https://reviews.llvm.org/D98423/new/

https://reviews.llvm.org/D98423

Files:
  llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
  llvm/test/Transforms/SLPVectorizer/AArch64/trunc-insertion.ll


Index: llvm/test/Transforms/SLPVectorizer/AArch64/trunc-insertion.ll
===================================================================
--- llvm/test/Transforms/SLPVectorizer/AArch64/trunc-insertion.ll
+++ llvm/test/Transforms/SLPVectorizer/AArch64/trunc-insertion.ll
@@ -12,7 +12,7 @@
 ; CHECK-NEXT:  bb:
 ; CHECK-NEXT:    br label [[BB1:%.*]]
 ; CHECK:       bb1:
-; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[BB:%.*]] ], [ [[TMP12:%.*]], [[BB25:%.*]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = phi <2 x i16> [ undef, [[BB:%.*]] ], [ [[TMP11:%.*]], [[BB25:%.*]] ]
 ; CHECK-NEXT:    br i1 undef, label [[BB3:%.*]], label [[BB11:%.*]]
 ; CHECK:       bb3:
 ; CHECK-NEXT:    [[TMP4:%.*]] = zext i1 undef to i32
@@ -32,12 +32,12 @@
 ; CHECK:       bb25:
 ; CHECK-NEXT:    [[TMP28:%.*]] = phi i32 [ [[TMP12]], [[BB11]] ], [ [[TMP4]], [[BB3]] ]
 ; CHECK-NEXT:    [[TMP10:%.*]] = phi <2 x i32> [ [[TMP9]], [[BB11]] ], [ [[TMP3]], [[BB3]] ]
-; CHECK-NEXT:    [[TMP11:%.*]] = trunc <2 x i32> [[TMP10]] to <2 x i8>
-; CHECK-NEXT:    [[TMP12]] = phi <2 x i16> [ [[TMP4]], [[BB11]] ], [ [[TMP1]], [[BB3]] ]
-; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x i8> [[TMP11]], i32 0
+; CHECK-NEXT:    [[TMP11]] = phi <2 x i16> [ [[TMP4]], [[BB11]] ], [ [[TMP1]], [[BB3]] ]
+; CHECK-NEXT:    [[TMP12:%.*]] = trunc <2 x i32> [[TMP10]] to <2 x i8>
+; CHECK-NEXT:    [[TMP13:%.*]] = extractelement <2 x i8> [[TMP12]], i32 0
 ; CHECK-NEXT:    [[TMP14:%.*]] = zext i8 [[TMP13]] to i32
 ; CHECK-NEXT:    [[TMP31:%.*]] = and i32 undef, [[TMP14]]
-; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x i8> [[TMP11]], i32 1
+; CHECK-NEXT:    [[TMP15:%.*]] = extractelement <2 x i8> [[TMP12]], i32 1
 ; CHECK-NEXT:    [[TMP16:%.*]] = zext i8 [[TMP15]] to i32
 ; CHECK-NEXT:    [[TMP32:%.*]] = and i32 [[TMP31]], [[TMP16]]
 ; CHECK-NEXT:    [[TMP33:%.*]] = and i32 [[TMP32]], [[TMP28]]
Index: llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
===================================================================
--- llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -4909,8 +4909,14 @@
   // sign extend the extracted values below.
   auto *ScalarRoot = VectorizableTree[0]->Scalars[0];
   if (MinBWs.count(ScalarRoot)) {
-    if (auto *I = dyn_cast<Instruction>(VectorRoot))
-      Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
+    if (auto *I = dyn_cast<Instruction>(VectorRoot)) {
+      // If current instr is a phi and not the last phi, insert it after the
+      // last phi node.
+      if (dyn_cast<PHINode>(I))
+        Builder.SetInsertPoint(&*I->getParent()->getFirstInsertionPt());
+      else
+        Builder.SetInsertPoint(&*++BasicBlock::iterator(I));
+    }
     auto BundleWidth = VectorizableTree[0]->Scalars.size();
     auto *MinTy = IntegerType::get(F->getContext(), MinBWs[ScalarRoot].first);
     auto *VecTy = FixedVectorType::get(MinTy, BundleWidth);


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D98423.330492.patch
Type: text/x-patch
Size: 2916 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210314/24baead2/attachment.bin>