diff options
| author | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-02-08 21:22:03 +0000 |
|---|---|---|
| committer | Stanislav Mekhanoshin <Stanislav.Mekhanoshin@amd.com> | 2017-02-08 21:22:03 +0000 |
| commit | 4a24705dd61e583c489349a4e2a87008ca68d16b (patch) | |
| tree | 328b825abe1e41889156deaf1b25a581311a963b /llvm/lib/MC/MCDisassembler/MCDisassembler.cpp | |
| parent | 401d3693286103fd76d622ee9cd8f8a7df934bdd (diff) | |
| download | llvm-4a24705dd61e583c489349a4e2a87008ca68d16b.zip llvm-4a24705dd61e583c489349a4e2a87008ca68d16b.tar.gz llvm-4a24705dd61e583c489349a4e2a87008ca68d16b.tar.bz2 | |
[AMDGPU] Implement register pressure callbacks
Implement getRegPressureLimit and getRegPressureSetLimit callbacks in
SIRegisterInfo.
This makes standard converge scheduler to behave almost the same as
GCNScheduler, sometime slightly better sometimes a bit worse.
In gerenal that is also possible to switch GCNScheduler to use these
callbacks instead of getMaxWaves(), which also makes GCNScheduler
slightly better on some tests and slightly worse on another. A big
win is behavior with converge scheduler.
Note, these are used not only by scheduling, but in places like
MachineLICM.
Differential Revision: https://reviews.llvm.org/D29700
llvm-svn: 294518
Diffstat (limited to 'llvm/lib/MC/MCDisassembler/MCDisassembler.cpp')
0 files changed, 0 insertions, 0 deletions