[all-commits] [llvm/llvm-project] 06d91c: [AMDGPU] Report only local per-function resource u...

[Shilei Tian via All-commits]

  Branch: refs/heads/users/shiltian/object-linking-local-resource-only
  Home:   https://github.com/llvm/llvm-project
  Commit: 06d91cf77a309dffe5190e0b2de656e1b34941f2
      https://github.com/llvm/llvm-project/commit/06d91cf77a309dffe5190e0b2de656e1b34941f2
  Author: Shilei Tian <i at tianshilei.me>
  Date:   2026-04-18 (Sat, 18 Apr 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.h
    M llvm/lib/Target/AMDGPU/AMDGPUResourceUsageAnalysis.cpp
    A llvm/test/CodeGen/AMDGPU/object-linking-local-resources.ll

  Log Message:
  -----------
  [AMDGPU] Report only local per-function resource usage when object linking is enabled

With object linking the linker aggregates resource usage across TUs, so
compile-time pessimism and call-graph propagation duplicate the linker's work or
pollute its inputs.

In this mode, skip the per-callsite conservative bumps in
`AMDGPUResourceUsageAnalysis` and assign each resource symbol in
`AMDGPUMCResourceInfo` a concrete local constant instead of building call-graph
`max`/`or` expressions.



To unsubscribe from these emails, change your notification settings at https://github.com/llvm/llvm-project/settings/notifications