[all-commits] [llvm/llvm-project] c246b7: [AMDGPU] Only count global-to-global as indirect a...
Jay Foad via All-commits
all-commits at lists.llvm.org
Fri Apr 1 05:51:12 PDT 2022
Branch: refs/heads/main
Home: https://github.com/llvm/llvm-project
Commit: c246b7bd4a5191d48f68ce12b50e03bfadd2a0b5
https://github.com/llvm/llvm-project/commit/c246b7bd4a5191d48f68ce12b50e03bfadd2a0b5
Author: Jay Foad <jay.foad at amd.com>
Date: 2022-04-01 (Fri, 01 Apr 2022)
Changed paths:
M llvm/lib/Target/AMDGPU/AMDGPUPerfHintAnalysis.cpp
M llvm/test/CodeGen/AMDGPU/perfhint.ll
M llvm/test/CodeGen/AMDGPU/schedule-regpressure-limit2.ll
Log Message:
-----------
[AMDGPU] Only count global-to-global as indirect accesses
Previously any load (global, local or constant) feeding into a
global load or store would be counted as an indirect access. This
patch only counts global loads feeding into a global load or store.
The rationale is that the latency for global loads is generally
much larger than the other kinds.
As a side effect this makes it easier to write small kernels test
cases that are not counted as having indirect accesses, despite
the fact that arguments to the kernel are accessed with an SMEM
load.
Differential Revision: https://reviews.llvm.org/D122804
More information about the All-commits
mailing list