diff options
| -rw-r--r-- | llvm/test/Transforms/SLPVectorizer/X86/hoist.ll | 34 |
1 files changed, 22 insertions, 12 deletions
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/hoist.ll b/llvm/test/Transforms/SLPVectorizer/X86/hoist.ll index 36c939b597e..7d0379eab90 100644 --- a/llvm/test/Transforms/SLPVectorizer/X86/hoist.ll +++ b/llvm/test/Transforms/SLPVectorizer/X86/hoist.ll @@ -1,3 +1,4 @@ +; NOTE: Assertions have been autogenerated by utils/update_test_checks.py ; RUN: opt < %s -basicaa -slp-vectorizer -dce -S -mtriple=i386-apple-macosx10.8.0 -mcpu=corei7-avx | FileCheck %s target datalayout = "e-p:32:32:32-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-f32:32:32-f64:32:64-v64:64:64-v128:128:128-a0:0:64-f80:128:128-n8:16:32-S128" @@ -12,19 +13,28 @@ target triple = "i386-apple-macosx10.9.0" ; } ;} -; preheader: -;CHECK: entry -;CHECK-NEXT: insertelement -;CHECK-NEXT: insertelement -;CHECK-NEXT: insertelement -;CHECK-NEXT: insertelement -; loop body: -;CHECK: phi -;CHECK: load <4 x i32> -;CHECK: add nsw <4 x i32> -;CHECK: store <4 x i32> -;CHECK: ret define i32 @foo(i32* nocapture %A, i32 %n, i32 %k) { +; CHECK-LABEL: @foo( +; CHECK-NEXT: entry: +; CHECK-NEXT: [[TMP0:%.*]] = insertelement <4 x i32> undef, i32 [[N:%.*]], i32 0 +; CHECK-NEXT: [[TMP1:%.*]] = insertelement <4 x i32> [[TMP0]], i32 [[K:%.*]], i32 1 +; CHECK-NEXT: [[TMP2:%.*]] = insertelement <4 x i32> [[TMP1]], i32 [[N]], i32 2 +; CHECK-NEXT: [[TMP3:%.*]] = insertelement <4 x i32> [[TMP2]], i32 [[K]], i32 3 +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_024:%.*]] = phi i32 [ 0, [[ENTRY:%.*]] ], [ [[ADD10:%.*]], [[FOR_BODY]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i32 [[I_024]] +; CHECK-NEXT: [[TMP4:%.*]] = bitcast i32* [[ARRAYIDX]] to <4 x i32>* +; CHECK-NEXT: [[TMP5:%.*]] = load <4 x i32>, <4 x i32>* [[TMP4]], align 4 +; CHECK-NEXT: [[TMP6:%.*]] = add nsw <4 x i32> [[TMP3]], [[TMP5]] +; CHECK-NEXT: [[TMP7:%.*]] = bitcast i32* [[ARRAYIDX]] to <4 x i32>* +; CHECK-NEXT: store <4 x i32> [[TMP6]], <4 x i32>* [[TMP7]], align 4 +; CHECK-NEXT: [[ADD10]] = add nsw i32 [[I_024]], 4 +; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[ADD10]], 10000 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_END:%.*]] +; CHECK: for.end: +; CHECK-NEXT: ret i32 undef +; entry: br label %for.body |
