projects / platform / upstream / llvm.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: ce6aff8) | patch
[AMDGPU] Add GCNMaxILPSchedStrategy
authorAustin Kerbow <Austin.Kerbow@amd.com>
Sat, 30 Jul 2022 14:40:11 +0000 (07:40 -0700)
committerAustin Kerbow <Austin.Kerbow@amd.com>
Tue, 2 Aug 2022 20:21:24 +0000 (13:21 -0700)
commitd7100b398b76318300dd536e72219af9a82caec6
tree0b6db0073d2bbfdc71b11737cce6eba86e44a40dtree | snapshot
parentce6aff8d13894bdb6ec492858a66e8f8ab42c33bcommit | diff
[AMDGPU] Add GCNMaxILPSchedStrategy

Creates a new scheduling strategy that attempts to maximize ILP for a single
wave.

Reviewed By: rampitec

Differential Revision: https://reviews.llvm.org/D130869
llvm/lib/Target/AMDGPU/AMDGPUTargetMachine.cpp diff | blob | history
llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp diff | blob | history
llvm/lib/Target/AMDGPU/GCNSchedStrategy.h diff | blob | history
llvm/test/CodeGen/AMDGPU/schedule-ilp.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/schedule-regpressure-limit.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/schedule-regpressure-limit2.ll diff | blob | history
llvm/test/CodeGen/AMDGPU/schedule-regpressure-limit3.ll diff | blob | history
Domain: System / Toolchain;