[all-commits] [llvm/llvm-project] c246b7: [AMDGPU] Only count global-to-global as indirect a...

[Jay Foad via All-commits]

  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