Divergence analysis for GPU programs

Summary:
Some optimizations such as jump threading and loop unswitching can negatively
affect performance when applied to divergent branches. The divergence analysis
added in this patch conservatively estimates which branches in a GPU program
can diverge. This information can then help LLVM to run certain optimizations
selectively.

Test Plan: test/Analysis/DivergenceAnalysis/NVPTX/diverge.ll

Reviewers: resistor, hfinkel, eliben, meheff, jholewinski

Subscribers: broune, bjarke.roune, madhur13490, tstellarAMD, dberlin, echristo, jholewinski, llvm-commits

Differential Revision: http://reviews.llvm.org/D8576

llvm-svn: 234567

1 files changed, 1 insertions, 0 deletions

diff --git a/llvm/lib/Analysis/Analysis.cpp b/llvm/lib/Analysis/Analysis.cpp
index 4549c1e969f..842ff0a14e2 100644
--- a/llvm/lib/Analysis/Analysis.cpp
+++ b/llvm/lib/Analysis/Analysis.cpp
@@ -37,6 +37,7 @@ void llvm::initializeAnalysis(PassRegistry &Registry) {
   initializeCFLAliasAnalysisPass(Registry);
   initializeDependenceAnalysisPass(Registry);
   initializeDelinearizationPass(Registry);
+  initializeDivergenceAnalysisPass(Registry);
   initializeDominanceFrontierPass(Registry);
   initializeDomViewerPass(Registry);
   initializeDomPrinterPass(Registry);