Don't vectorize when the attribute NoImplicitFloat is used.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@187340 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Transforms/Vectorize/SLPVectorizer.cpp b/lib/Transforms/Vectorize/SLPVectorizer.cpp
index db1a91ec9e349dd26b6c611d331c782ec0c53a38..8f23a976f9f75a6c3c20b33aca1531d393577d8c 100644 (file)
--- a/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -1557,6 +1557,11 @@ struct SLPVectorizer : public FunctionPass {
     if (!DL)
       return false;
 
+    // Don't vectorize when the attribute NoImplicitFloat is used.
+    if (F.getAttributes().hasAttribute(AttributeSet::FunctionIndex,
+                                       Attribute::NoImplicitFloat))
+      return false;
+
     DEBUG(dbgs() << "SLP: Analyzing blocks in " << F.getName() << ".\n");
 
     // Use the bollom up slp vectorizer to construct chains that start with

diff --git a/test/Transforms/SLPVectorizer/X86/implicitfloat.ll b/test/Transforms/SLPVectorizer/X86/implicitfloat.ll
new file mode 100644 (file)
index 0000000..f63f268
--- /dev/null
+++ b/test/Transforms/SLPVectorizer/X86/implicitfloat.ll
@@ -0,0 +1,25 @@
+; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s
+
+target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64-S128"
+target triple = "x86_64-apple-macosx10.8.0"
+
+; Don't vectorize when noimplicitfloat is used.
+; CHECK: test1
+; CHECK-NOT: store <2 x double>
+; CHECK: ret
+define void @test1(double* %a, double* %b, double* %c) noimplicitfloat { ; <------ noimplicitfloat attribute here!
+entry:
+  %i0 = load double* %a, align 8
+  %i1 = load double* %b, align 8
+  %mul = fmul double %i0, %i1
+  %arrayidx3 = getelementptr inbounds double* %a, i64 1
+  %i3 = load double* %arrayidx3, align 8
+  %arrayidx4 = getelementptr inbounds double* %b, i64 1
+  %i4 = load double* %arrayidx4, align 8
+  %mul5 = fmul double %i3, %i4
+  store double %mul, double* %c, align 8
+  %arrayidx5 = getelementptr inbounds double* %c, i64 1
+  store double %mul5, double* %arrayidx5, align 8
+  ret void
+}
+