aboutsummaryrefslogtreecommitdiffstats
path: root/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
diff options
context:
space:
mode:
authorStephen Hines <srhines@google.com>2014-05-29 02:49:00 -0700
committerStephen Hines <srhines@google.com>2014-05-29 02:49:00 -0700
commitdce4a407a24b04eebc6a376f8e62b41aaa7b071f (patch)
treedcebc53f2b182f145a2e659393bf9a0472cedf23 /test/Transforms/LoopVectorize/X86/vect.omp.force.ll
parent220b921aed042f9e520c26cffd8282a94c66c3d5 (diff)
downloadexternal_llvm-dce4a407a24b04eebc6a376f8e62b41aaa7b071f.zip
external_llvm-dce4a407a24b04eebc6a376f8e62b41aaa7b071f.tar.gz
external_llvm-dce4a407a24b04eebc6a376f8e62b41aaa7b071f.tar.bz2
Update LLVM for 3.5 rebase (r209712).
Change-Id: I149556c940fb7dc92d075273c87ff584f400941f
Diffstat (limited to 'test/Transforms/LoopVectorize/X86/vect.omp.force.ll')
-rw-r--r--test/Transforms/LoopVectorize/X86/vect.omp.force.ll93
1 files changed, 93 insertions, 0 deletions
diff --git a/test/Transforms/LoopVectorize/X86/vect.omp.force.ll b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
new file mode 100644
index 0000000..84ffb27
--- /dev/null
+++ b/test/Transforms/LoopVectorize/X86/vect.omp.force.ll
@@ -0,0 +1,93 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7-avx -debug-only=loop-vectorize -stats -S 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+; CHECK: LV: Loop hints: force=enabled
+; CHECK: LV: Loop hints: force=?
+; No more loops in the module
+; CHECK-NOT: LV: Loop hints: force=
+; CHECK: 2 loop-vectorize - Number of loops analyzed for vectorization
+; CHECK: 1 loop-vectorize - Number of loops vectorized
+
+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"
+
+;
+; The source code for the test:
+;
+; #include <math.h>
+; void foo(float* restrict A, float * restrict B, int size)
+; {
+; for (int i = 0; i < size; ++i) A[i] = sinf(B[i]);
+; }
+;
+
+;
+; This loop will be vectorized, although the scalar cost is lower than any of vector costs, but vectorization is explicitly forced in metadata.
+;
+
+define void @vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
+entry:
+ %cmp6 = icmp sgt i32 %size, 0
+ br i1 %cmp6, label %for.body.preheader, label %for.end
+
+for.body.preheader:
+ br label %for.body
+
+for.body:
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+ %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+ %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !1
+ %call = tail call float @llvm.sin.f32(float %0)
+ %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+ store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !1
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %size
+ br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !1
+
+for.end.loopexit:
+ br label %for.end
+
+for.end:
+ ret void
+}
+
+!1 = metadata !{metadata !1, metadata !2}
+!2 = metadata !{metadata !"llvm.vectorizer.enable", i1 true}
+
+;
+; This method will not be vectorized, as scalar cost is lower than any of vector costs.
+;
+
+define void @not_vectorized(float* noalias nocapture %A, float* noalias nocapture %B, i32 %size) {
+entry:
+ %cmp6 = icmp sgt i32 %size, 0
+ br i1 %cmp6, label %for.body.preheader, label %for.end
+
+for.body.preheader:
+ br label %for.body
+
+for.body:
+ %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %for.body.preheader ]
+ %arrayidx = getelementptr inbounds float* %B, i64 %indvars.iv
+ %0 = load float* %arrayidx, align 4, !llvm.mem.parallel_loop_access !3
+ %call = tail call float @llvm.sin.f32(float %0)
+ %arrayidx2 = getelementptr inbounds float* %A, i64 %indvars.iv
+ store float %call, float* %arrayidx2, align 4, !llvm.mem.parallel_loop_access !3
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %lftr.wideiv = trunc i64 %indvars.iv.next to i32
+ %exitcond = icmp eq i32 %lftr.wideiv, %size
+ br i1 %exitcond, label %for.end.loopexit, label %for.body, !llvm.loop !3
+
+for.end.loopexit:
+ br label %for.end
+
+for.end:
+ ret void
+}
+
+declare float @llvm.sin.f32(float) nounwind readnone
+
+; Dummy metadata
+!3 = metadata !{metadata !3}
+