[all-commits] [llvm/llvm-project] ddd92c: [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: ddd92c7e901af48724de940b65be9946b8df048e
      https://github.com/llvm/llvm-project/commit/ddd92c7e901af48724de940b65be9946b8df048e
  Author: Shilei Tian <i at tianshilei.me>
  Date:   2026-04-17 (Fri, 17 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
    M llvm/test/CodeGen/AMDGPU/lds-link-time-codegen-indirect.ll
    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 via
`.amdgpu.info`, 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