diff options
| author | Andrew Trick <atrick@apple.com> | 2011-12-09 06:19:40 +0000 |
|---|---|---|
| committer | Andrew Trick <atrick@apple.com> | 2011-12-09 06:19:40 +0000 |
| commit | 5d73448bb7f3d326f310e6f35030821b103b1cdb (patch) | |
| tree | 559f8f027346d2270472463686fa54187721d8d5 /test/Transforms/LoopUnroll/runtime-loop2.ll | |
| parent | 9c181a92d8bc7af36839520c3e145bf11a6193fa (diff) | |
| download | llvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.gz llvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.bz2 llvm-5d73448bb7f3d326f310e6f35030821b103b1cdb.tar.xz | |
Add -unroll-runtime for unrolling loops with run-time trip counts.
Patch by Brendon Cahoon!
This extends the existing LoopUnroll and LoopUnrollPass. Brendon
measured no regressions in the llvm test suite with -unroll-runtime
enabled. This implementation works by using the existing loop
unrolling code to unroll the loop by a power-of-two (default 8). It
generates an if-then-else sequence of code prior to the loop to
execute the extra iterations before entering the unrolled loop.
git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@146245 91177308-0d34-0410-b5e6-96231b3b80d8
Diffstat (limited to 'test/Transforms/LoopUnroll/runtime-loop2.ll')
| -rw-r--r-- | test/Transforms/LoopUnroll/runtime-loop2.ll | 31 |
1 files changed, 31 insertions, 0 deletions
diff --git a/test/Transforms/LoopUnroll/runtime-loop2.ll b/test/Transforms/LoopUnroll/runtime-loop2.ll new file mode 100644 index 0000000000..cbc7af58ff --- /dev/null +++ b/test/Transforms/LoopUnroll/runtime-loop2.ll @@ -0,0 +1,31 @@ +; RUN: opt < %s -S -loop-unroll -unroll-threshold=50 -unroll-runtime -unroll-count=8 | FileCheck %s + +; Choose a smaller, power-of-two, unroll count if the loop is too large. +; This test makes sure we're not unrolling 'odd' counts + +; CHECK: unr.cmp: +; CHECK: for.body.unr: +; CHECK: for.body: +; CHECK: br i1 %exitcond.3, label %for.end.loopexit{{.*}}, label %for.body +; CHECK-NOT: br i1 %exitcond.4, label %for.end.loopexit{{.*}}, label %for.body + +define i32 @test(i32* nocapture %a, i32 %n) nounwind uwtable readonly { +entry: + %cmp1 = icmp eq i32 %n, 0 + br i1 %cmp1, label %for.end, label %for.body + +for.body: ; preds = %for.body, %entry + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body ], [ 0, %entry ] + %sum.02 = phi i32 [ %add, %for.body ], [ 0, %entry ] + %arrayidx = getelementptr inbounds i32* %a, i64 %indvars.iv + %0 = load i32* %arrayidx, align 4 + %add = add nsw i32 %0, %sum.02 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %n + br i1 %exitcond, label %for.end, label %for.body + +for.end: ; preds = %for.body, %entry + %sum.0.lcssa = phi i32 [ 0, %entry ], [ %add, %for.body ] + ret i32 %sum.0.lcssa +} |