diff options
| author | Michael Zolotukhin <mzolotukhin@apple.com> | 2016-05-18 21:20:12 +0000 |
|---|---|---|
| committer | Michael Zolotukhin <mzolotukhin@apple.com> | 2016-05-18 21:20:12 +0000 |
| commit | d2268a73bc8b505fa5d124e9b95e9cfe50698b14 (patch) | |
| tree | cdb8f8b0ac64d91adacff191fea2f7325f023f48 /llvm/lib/Transforms | |
| parent | 6989ebf6619711a6dcb04fd5dc4fabf175d9207a (diff) | |
| download | bcm5719-llvm-d2268a73bc8b505fa5d124e9b95e9cfe50698b14.tar.gz bcm5719-llvm-d2268a73bc8b505fa5d124e9b95e9cfe50698b14.zip | |
[LoopUnrollAnalyzer] Take into account cost of instructions controlling branches, along with their operands.
Previously, we didn't add their and their operands cost, which could've
resulted in unrolling loops for no actual benefit.
llvm-svn: 269985
Diffstat (limited to 'llvm/lib/Transforms')
| -rw-r--r-- | llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp index 034cb04dc50..d167c44c19c 100644 --- a/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp +++ b/llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp @@ -506,6 +506,7 @@ analyzeLoopUnrollCost(const Loop *L, unsigned TripCount, DominatorTree &DT, BBWorklist.insert(Succ); else ExitWorklist.insert({BB, Succ}); + AddCostRecursively(*TI, Iteration); } // If we found no optimization opportunities on the first iteration, we |
