summaryrefslogtreecommitdiffstats
path: root/llvm/test
diff options
context:
space:
mode:
authorHal Finkel <hfinkel@anl.gov>2014-10-14 22:59:49 +0000
committerHal Finkel <hfinkel@anl.gov>2014-10-14 22:59:49 +0000
commit1a600faba0329f5cde0aab1ce7bbff2f09252eff (patch)
tree0b9e37ad779b27a1e4d7abfa607f001420aed0e3 /llvm/test
parentadfd7f6ef4599f3a3477125eb267f9de59c0946f (diff)
downloadbcm5719-llvm-1a600faba0329f5cde0aab1ce7bbff2f09252eff.tar.gz
bcm5719-llvm-1a600faba0329f5cde0aab1ce7bbff2f09252eff.zip
[LoopVectorize] Ignore @llvm.assume for cost estimates and legality
A few minor changes to prevent @llvm.assume from interfering with loop vectorization. First, treat @llvm.assume like the lifetime intrinsics, which are scalarized (but don't otherwise interfere with the legality checking). Second, ignore the cost of ephemeral instructions in the loop (these will go away anyway during CodeGen). Alignment assumptions and other uses of @llvm.assume can often end up inside of loops that should be vectorized (this is not uncommon for assumptions generated by __attribute__((align_value(n))), for example). llvm-svn: 219741
Diffstat (limited to 'llvm/test')
-rw-r--r--llvm/test/Transforms/LoopVectorize/X86/assume.ll100
1 files changed, 100 insertions, 0 deletions
diff --git a/llvm/test/Transforms/LoopVectorize/X86/assume.ll b/llvm/test/Transforms/LoopVectorize/X86/assume.ll
new file mode 100644
index 00000000000..a94e24dd7e9
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/X86/assume.ll
@@ -0,0 +1,100 @@
+; RUN: opt < %s -loop-vectorize -mtriple=x86_64-apple-macosx10.8.0 -mcpu=corei7 -S | FileCheck %s
+target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
+target triple = "x86_64-unknown-linux-gnu"
+
+; Function Attrs: nounwind uwtable
+define void @test1(float* noalias nocapture %a, float* noalias nocapture readonly %b) #0 {
+entry:
+ br label %for.body
+
+; CHECK-LABEL: @test1
+; CHECK: vector.body:
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: for.body:
+; CHECK: ret void
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ %arrayidx = getelementptr inbounds float* %b, i64 %indvars.iv
+ %0 = load float* %arrayidx, align 4
+ %cmp1 = fcmp ogt float %0, 1.000000e+02
+ tail call void @llvm.assume(i1 %cmp1)
+ %add = fadd float %0, 1.000000e+00
+ %arrayidx5 = getelementptr inbounds float* %a, i64 %indvars.iv
+ store float %add, float* %arrayidx5, align 4
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %exitcond = icmp eq i64 %indvars.iv, 1599
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+}
+
+; Function Attrs: nounwind
+declare void @llvm.assume(i1) #1
+
+attributes #0 = { nounwind uwtable }
+attributes #1 = { nounwind }
+
+%struct.data = type { float*, float* }
+
+; Function Attrs: nounwind uwtable
+define void @test2(%struct.data* nocapture readonly %d) #0 {
+entry:
+ %b = getelementptr inbounds %struct.data* %d, i64 0, i32 1
+ %0 = load float** %b, align 8
+ %ptrint = ptrtoint float* %0 to i64
+ %maskedptr = and i64 %ptrint, 31
+ %maskcond = icmp eq i64 %maskedptr, 0
+ %a = getelementptr inbounds %struct.data* %d, i64 0, i32 0
+ %1 = load float** %a, align 8
+ %ptrint2 = ptrtoint float* %1 to i64
+ %maskedptr3 = and i64 %ptrint2, 31
+ %maskcond4 = icmp eq i64 %maskedptr3, 0
+ br label %for.body
+
+; CHECK-LABEL: @test2
+; CHECK: vector.body:
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: @llvm.assume
+; CHECK: for.body:
+; CHECK: ret void
+
+for.body: ; preds = %for.body, %entry
+ %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
+ tail call void @llvm.assume(i1 %maskcond)
+ %arrayidx = getelementptr inbounds float* %0, i64 %indvars.iv
+ %2 = load float* %arrayidx, align 4
+ %add = fadd float %2, 1.000000e+00
+ tail call void @llvm.assume(i1 %maskcond4)
+ %arrayidx5 = getelementptr inbounds float* %1, i64 %indvars.iv
+ store float %add, float* %arrayidx5, align 4
+ %indvars.iv.next = add nuw nsw i64 %indvars.iv, 1
+ %exitcond = icmp eq i64 %indvars.iv, 1599
+ br i1 %exitcond, label %for.end, label %for.body
+
+for.end: ; preds = %for.body
+ ret void
+}
+
OpenPOWER on IntegriCloud