diff options
| author | Justin Hibbits <jrh29@alumni.cwru.edu> | 2020-04-18 23:09:30 -0500 |
|---|---|---|
| committer | Justin Hibbits <jrh29@alumni.cwru.edu> | 2020-05-12 17:19:43 -0500 |
| commit | 0138cc012506d5195ba2a3cf8a98ceb84c5aeffa (patch) | |
| tree | 6b4811254a82fde4101890181472fa9e91575dd5 /llvm/lib/Support/VirtualFileSystem.cpp | |
| parent | 293c6d382128a0e52a144cec901932d71e072760 (diff) | |
| download | llvm-0138cc012506d5195ba2a3cf8a98ceb84c5aeffa.zip llvm-0138cc012506d5195ba2a3cf8a98ceb84c5aeffa.tar.gz llvm-0138cc012506d5195ba2a3cf8a98ceb84c5aeffa.tar.bz2 | |
PowerPC: Treat llvm.fma.f* intrinsic as using CTR with SPE
Summary:
The SPE doesn't have a 'fma' instruction, so the intrinsic becomes a
libcall. It really should become an expansion to two instructions, but
for some reason the compiler doesn't think that's as optimal as a
branch. Since this lowering is done after CTR is allocated for loops,
tell the optimizer that CTR may be used in this case. This prevents a
"Invalid PPC CTR loop!" assertion in the case that a fma() function call
is used in a C/C++ file, and clang converts it into an intrinsic.
Reviewed By: shchenz
Differential Revision: https://reviews.llvm.org/D78668
Diffstat (limited to 'llvm/lib/Support/VirtualFileSystem.cpp')
0 files changed, 0 insertions, 0 deletions