LoopVectorizer - skip 'bitcast' between GEP and load.

[oota-llvm.git] / test / Transforms / LoopVectorize / X86 / metadata-enable.ll

diff --git a/test/Transforms/LoopVectorize/X86/metadata-enable.ll b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
index e98a4acddea5c96034bdd928d9f443fa74f13c09..74c0c16086fedb84a5d54c3d378460615605b1a4 100644 (file)
--- a/test/Transforms/LoopVectorize/X86/metadata-enable.ll
+++ b/test/Transforms/LoopVectorize/X86/metadata-enable.ll
@@ -1,16 +1,17 @@
-; RUN: opt < %s -mcpu=corei7 -O1 -S | FileCheck %s --check-prefix=O1
-; RUN: opt < %s -mcpu=corei7 -O2 -S | FileCheck %s --check-prefix=O2
-; RUN: opt < %s -mcpu=corei7 -O3 -S | FileCheck %s --check-prefix=O3
-; RUN: opt < %s -mcpu=corei7 -Os -S | FileCheck %s --check-prefix=Os
-; RUN: opt < %s -mcpu=corei7 -Oz -S | FileCheck %s --check-prefix=Oz
-; RUN: opt < %s -mcpu=corei7 -O1 -vectorize-loops -S | FileCheck %s --check-prefix=O1VEC
-; RUN: opt < %s -mcpu=corei7 -Oz -vectorize-loops -S | FileCheck %s --check-prefix=OzVEC
-; RUN: opt < %s -mcpu=corei7 -O1 -loop-vectorize -S | FileCheck %s --check-prefix=O1VEC2
-; RUN: opt < %s -mcpu=corei7 -Oz -loop-vectorize -S | FileCheck %s --check-prefix=OzVEC2
-; RUN: opt < %s -mcpu=corei7 -O3 -disable-loop-vectorization -S | FileCheck %s --check-prefix=O3DIS
+; RUN: opt < %s -mcpu=corei7 -O1 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1
+; RUN: opt < %s -mcpu=corei7 -O2 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O2
+; RUN: opt < %s -mcpu=corei7 -O3 -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O3
+; RUN: opt < %s -mcpu=corei7 -Os -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=Os
+; RUN: opt < %s -mcpu=corei7 -Oz -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=Oz
+; RUN: opt < %s -mcpu=corei7 -O1 -vectorize-loops -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1VEC
+; RUN: opt < %s -mcpu=corei7 -Oz -vectorize-loops -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=OzVEC
+; RUN: opt < %s -mcpu=corei7 -O1 -loop-vectorize -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O1VEC2
+; RUN: opt < %s -mcpu=corei7 -Oz -loop-vectorize -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=OzVEC2
+; RUN: opt < %s -mcpu=corei7 -O3 -disable-loop-vectorization -S -unroll-allow-partial=0 | FileCheck %s --check-prefix=O3DIS
 
-; This file tests the llvm.vectorizer.pragma forcing vectorization even when
-; optimization levels are too low, or when vectorization is disabled.
+; This file tests the llvm.loop.vectorize.enable metadata forcing
+; vectorization even when optimization levels are too low, or when
+; vectorization is disabled.
 
 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-unknown-linux-gnu"
@@ -53,17 +54,17 @@ entry:
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
-  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  %exitcond = icmp eq i64 %indvars.iv.next, 64
   br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !0
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
@@ -104,17 +105,17 @@ entry:
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
-  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  %exitcond = icmp eq i64 %indvars.iv.next, 64
   br i1 %exitcond, label %for.end, label %for.body
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
@@ -155,21 +156,21 @@ entry:
 
 for.body:                                         ; preds = %for.body, %entry
   %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %arrayidx = getelementptr inbounds i32* %b, i64 %indvars.iv
-  %0 = load i32* %arrayidx, align 4
+  %arrayidx = getelementptr inbounds i32, i32* %b, i64 %indvars.iv
+  %0 = load i32, i32* %arrayidx, align 4
   %add = add nsw i32 %0, %N
-  %arrayidx2 = getelementptr inbounds i32* %a, i64 %indvars.iv
+  %arrayidx2 = getelementptr inbounds i32, i32* %a, i64 %indvars.iv
   store i32 %add, i32* %arrayidx2, align 4
   %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
-  %exitcond = icmp eq i64 %indvars.iv.next, 32
+  %exitcond = icmp eq i64 %indvars.iv.next, 64
   br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !2
 
 for.end:                                          ; preds = %for.body
-  %1 = load i32* %a, align 4
+  %1 = load i32, i32* %a, align 4
   ret i32 %1
 }
 
-!0 = metadata !{metadata !0, metadata !1}
-!1 = metadata !{metadata !"llvm.vectorizer.enable", i1 1}
-!2 = metadata !{metadata !2, metadata !3}
-!3 = metadata !{metadata !"llvm.vectorizer.enable", i1 0}
+!0 = !{!0, !1}
+!1 = !{!"llvm.loop.vectorize.enable", i1 1}
+!2 = !{!2, !3}
+!3 = !{!"llvm.loop.vectorize.enable", i1 0}