aboutsummaryrefslogtreecommitdiff
path: root/clang/lib/Frontend/CompilerInvocation.cpp
diff options
context:
space:
mode:
authorArthur Eubanks <aeubanks@google.com>2020-05-28 15:00:17 -0700
committerArthur Eubanks <aeubanks@google.com>2020-06-08 12:08:49 -0700
commitc07339c6754e1faf4078d3c592c0ae28455503cd (patch)
treea59d3ae11c03f57a41259965591098c9ded76a00 /clang/lib/Frontend/CompilerInvocation.cpp
parent60cde7bbb719a0dc110c8390555dbd9c814aabf1 (diff)
downloadllvm-c07339c6754e1faf4078d3c592c0ae28455503cd.zip
llvm-c07339c6754e1faf4078d3c592c0ae28455503cd.tar.gz
llvm-c07339c6754e1faf4078d3c592c0ae28455503cd.tar.bz2
Move *San module passes later in the NPM pipeline
Summary: This fixes pr33372.cpp under the new pass manager. ASan adds padding to globals. For example, it will change a {i32, i32, i32} to a {{i32, i32, i32}, [52 x i8]}. However, when loading from the {i32, i32, i32}, InstCombine may (after various optimizations) end up loading 16 bytes instead of 12, likely because it thinks the [52 x i8] padding is ok to load from. But ASan checks that padding should not be loaded from. Ultimately this is an issue of *San passes wanting to be run after all optimizations. This change moves the module passes right next to the corresponding function passes. Also remove comment that's no longer relevant, this is the last ASan/MSan/TSan failure under the NPM (hopefully...). As mentioned in https://reviews.llvm.org/rG1285e8bcac2c54ddd924ffb813b2b187467ac2a6, NPM doesn't support LTO + sanitizers, so modified some tests that test for that. Reviewers: leonardchan, vitalybuka Subscribers: cfe-commits Tags: #clang Differential Revision: https://reviews.llvm.org/D81323
Diffstat (limited to 'clang/lib/Frontend/CompilerInvocation.cpp')
0 files changed, 0 insertions, 0 deletions