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-loop3.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-loop3.ll')
-rw-r--r-- | test/Transforms/LoopUnroll/runtime-loop3.ll | 44 |
1 files changed, 44 insertions, 0 deletions
diff --git a/test/Transforms/LoopUnroll/runtime-loop3.ll b/test/Transforms/LoopUnroll/runtime-loop3.ll new file mode 100644 index 0000000000..55cf22373e --- /dev/null +++ b/test/Transforms/LoopUnroll/runtime-loop3.ll @@ -0,0 +1,44 @@ +; RUN: opt < %s -disable-output -stats -loop-unroll -unroll-runtime -unroll-threshold=400 -info-output-file - | FileCheck %s --check-prefix=STATS + +; Test that nested loops can be unrolled. We need to increase threshold to do it + +; STATS: 2 loop-unroll - Number of loops unrolled (completely or otherwise) + +define i32 @nested(i32* nocapture %a, i32 %n, i32 %m) nounwind uwtable readonly { +entry: + %cmp11 = icmp sgt i32 %n, 0 + br i1 %cmp11, label %for.cond1.preheader.lr.ph, label %for.end7 + +for.cond1.preheader.lr.ph: ; preds = %entry + %cmp28 = icmp sgt i32 %m, 0 + br label %for.cond1.preheader + +for.cond1.preheader: ; preds = %for.inc5, %for.cond1.preheader.lr.ph + %indvars.iv16 = phi i64 [ 0, %for.cond1.preheader.lr.ph ], [ %indvars.iv.next17, %for.inc5 ] + %sum.012 = phi i32 [ 0, %for.cond1.preheader.lr.ph ], [ %sum.1.lcssa, %for.inc5 ] + br i1 %cmp28, label %for.body3, label %for.inc5 + +for.body3: ; preds = %for.cond1.preheader, %for.body3 + %indvars.iv = phi i64 [ %indvars.iv.next, %for.body3 ], [ 0, %for.cond1.preheader ] + %sum.19 = phi i32 [ %add4, %for.body3 ], [ %sum.012, %for.cond1.preheader ] + %0 = add nsw i64 %indvars.iv, %indvars.iv16 + %arrayidx = getelementptr inbounds i32* %a, i64 %0 + %1 = load i32* %arrayidx, align 4 + %add4 = add nsw i32 %1, %sum.19 + %indvars.iv.next = add i64 %indvars.iv, 1 + %lftr.wideiv = trunc i64 %indvars.iv.next to i32 + %exitcond = icmp eq i32 %lftr.wideiv, %m + br i1 %exitcond, label %for.inc5, label %for.body3 + +for.inc5: ; preds = %for.body3, %for.cond1.preheader + %sum.1.lcssa = phi i32 [ %sum.012, %for.cond1.preheader ], [ %add4, %for.body3 ] + %indvars.iv.next17 = add i64 %indvars.iv16, 1 + %lftr.wideiv18 = trunc i64 %indvars.iv.next17 to i32 + %exitcond19 = icmp eq i32 %lftr.wideiv18, %n + br i1 %exitcond19, label %for.end7, label %for.cond1.preheader + +for.end7: ; preds = %for.inc5, %entry + %sum.0.lcssa = phi i32 [ 0, %entry ], [ %sum.1.lcssa, %for.inc5 ] + ret i32 %sum.0.lcssa +} + |