[PATCH] D36244: [LoopVectorize] Fix assertion failure in Fcmp vectorization

[Anna Thomas via Phabricator via llvm-commits]

anna updated this revision to Diff 110199.
anna marked 2 inline comments as done.
anna added a comment.

Addressed review comments.


https://reviews.llvm.org/D36244

Files:
  lib/Transforms/Vectorize/LoopVectorize.cpp
  test/Transforms/LoopVectorize/fcmp-vectorize.ll


Index: test/Transforms/LoopVectorize/fcmp-vectorize.ll
===================================================================
--- /dev/null
+++ test/Transforms/LoopVectorize/fcmp-vectorize.ll
@@ -0,0 +1,25 @@
+; RUN: opt -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 -S %s | FileCheck %s
+
+; Avoid crashing while trying to vectorize fcmp that can be folded to vector of
+; i1 true.
+define void @test1() {
+; CHECK-LABEL: test1(
+; CHECK-LABEL: vector.body:
+; CHECK-NEXT:    %index = phi i32 [ 0, %vector.ph ], [ %index.next, %vector.body ]
+; CHECK-NEXT:    %broadcast.splatinsert = insertelement <4 x i32> undef, i32 %index, i32 0
+; CHECK:         %induction = add <4 x i32> %broadcast.splat, <i32 0, i32 1, i32 2, i32 3>
+; CHECK:         %index.next = add i32 %index, 4
+
+entry:
+  br label %loop
+
+loop:                                              ; preds = %loop, %entry
+  %iv = phi i32 [ 0, %entry ], [ %ivnext, %loop ]
+  %fcmp = fcmp uno float 0.000000e+00, 0.000000e+00
+  %ivnext = add nsw i32 %iv, 1
+  %cnd = icmp sgt i32 %iv, 142
+  br i1 %cnd, label %exit, label %loop
+
+exit:                                              ; preds = %loop
+  ret void
+}
Index: lib/Transforms/Vectorize/LoopVectorize.cpp
===================================================================
--- lib/Transforms/Vectorize/LoopVectorize.cpp
+++ lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -4863,8 +4863,10 @@
       Value *B = getOrCreateVectorValue(Cmp->getOperand(1), Part);
       Value *C = nullptr;
       if (FCmp) {
+        // Propagate fast math flags.
+        IRBuilder<>::FastMathFlagGuard FMFG(Builder);
+        Builder.setFastMathFlags(Cmp->getFastMathFlags());
         C = Builder.CreateFCmp(Cmp->getPredicate(), A, B);
-        cast<FCmpInst>(C)->copyFastMathFlags(Cmp);
       } else {
         C = Builder.CreateICmp(Cmp->getPredicate(), A, B);
       }


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D36244.110199.patch
Type: text/x-patch
Size: 1892 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20170808/ed22ca02/attachment.bin>