summaryrefslogtreecommitdiffstats
path: root/llvm/lib/Transforms/Utils/CodeExtractor.cpp
diff options
context:
space:
mode:
authorVedant Kumar <vsk@apple.com>2019-02-15 18:46:44 +0000
committerVedant Kumar <vsk@apple.com>2019-02-15 18:46:44 +0000
commit47a0c9b69cd7aaebbbf9c9b6b86e37fa892a6191 (patch)
treecf08bd3da4f1dd73ef016414b2d9c16e990cd928 /llvm/lib/Transforms/Utils/CodeExtractor.cpp
parent360163f671f54b5f5a153db1e8dbe5c81dd18927 (diff)
downloadbcm5719-llvm-47a0c9b69cd7aaebbbf9c9b6b86e37fa892a6191.tar.gz
bcm5719-llvm-47a0c9b69cd7aaebbbf9c9b6b86e37fa892a6191.zip
[HotColdSplit] Schedule splitting late to fix perf regression
With or without PGO data applied, splitting early in the pipeline (either before the inliner or shortly after it) regresses performance across SPEC variants. The cause appears to be that splitting hides context for subsequent optimizations. Schedule splitting late again, in effect reversing r352080, which scheduled the splitting pass early for code size benefits (documented in https://reviews.llvm.org/D57082). Differential Revision: https://reviews.llvm.org/D58258 llvm-svn: 354158
Diffstat (limited to 'llvm/lib/Transforms/Utils/CodeExtractor.cpp')
0 files changed, 0 insertions, 0 deletions
OpenPOWER on IntegriCloud