maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

[IRCE] Avoid computing potentially unnecessary analyses. NFC 

IRCE is a function pass that operates on loops. If there are no loops in
the function (as seen through LI), we should avoid computing the
remaining expensive analyses (such as BPI). Reordered the analyses
requests and early return if there are no loops. This is an NFC with
compile time improvement.

The same will be done in a follow-up patch for the loop vectorizer.

Reviewed-By: nikic
Differential Revision: https://reviews.llvm.org/D124478
This commit is contained in:
Anna Thomas 2022-04-26 17:15:48 -04:00
parent 70dbb5abd3
commit c515b2f39e
1 changed files with 6 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
llvm/lib/Transforms/Scalar/InductiveRangeCheckElimination.cpp
View File

@ -1761,10 +1761,14 @@ IntersectUnsignedRange(ScalarEvolution &SE,
}
PreservedAnalyses IRCEPass::run(Function &F, FunctionAnalysisManager &AM) {
auto &SE = AM.getResult<ScalarEvolutionAnalysis>(F);
auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
auto &BPI = AM.getResult<BranchProbabilityAnalysis>(F);
LoopInfo &LI = AM.getResult<LoopAnalysis>(F);
// There are no loops in the function. Return before computing other expensive
// analyses.
if (LI.empty())
return PreservedAnalyses::all();
auto &SE = AM.getResult<ScalarEvolutionAnalysis>(F);
auto &BPI = AM.getResult<BranchProbabilityAnalysis>(F);
// Get BFI analysis result on demand. Please note that modification of
// CFG invalidates this analysis and we should handle it.