[PATCH] D125997: [AMDGPU] Instruction Type Pipeline
Austin Kerbow via Phabricator via llvm-commits
llvm-commits at lists.llvm.org
Thu May 19 13:09:38 PDT 2022
kerbowa added a comment.
Can you name these files something so that it is clear that it is a DAG mutation involving MFMA? I'm also not sure pipeline is the correct terminology here? I know that library folks have been calling it that.
Will we eventually be able to specify the order of the pipeline types and the size of each InstructionClass cluster?
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSchedPipeline.cpp:34
+
+static cl::opt<unsigned> PipelineStageMaxSize(
+ "amdgpu-pipeline-stage-size", cl::init(20), cl::Hidden,
----------------
This should be abstracted by instruction type.
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSchedPipeline.cpp:44
+ const IsInstructionType isInstructionClass;
+ const bool IsSized;
+
----------------
I'm not sure I understand what `IsSized` means?
================
Comment at: llvm/lib/Target/AMDGPU/AMDGPUSchedPipeline.cpp:51
+class SchedPipelineDAGMutation : public ScheduleDAGMutation {
+ // const SIInstrInfo *TII;
+ // ScheduleDAGMI *DAG;
----------------
Remove commented code.
Repository:
rG LLVM Github Monorepo
CHANGES SINCE LAST ACTION
https://reviews.llvm.org/D125997/new/
https://reviews.llvm.org/D125997
More information about the llvm-commits
mailing list