[all-commits] [llvm/llvm-project] 1d9f8d: [AMDGPU] Introduce ABI occupancy for object linking

[Shilei Tian via All-commits]

  Branch: refs/heads/users/shiltian/object-linking-occupancy-abi
  Home:   https://github.com/llvm/llvm-project
  Commit: 1d9f8de543d58daa0f84b68f6f4c269e2b4e6075
      https://github.com/llvm/llvm-project/commit/1d9f8de543d58daa0f84b68f6f4c269e2b4e6075
  Author: Shilei Tian <i at tianshilei.me>
  Date:   2026-05-29 (Fri, 29 May 2026)

  Changed paths:
    M llvm/docs/AMDGPUUsage.rst
    M llvm/include/llvm/Support/AMDGPUObjLinkingInfo.h
    M llvm/lib/Target/AMDGPU/AMDGPUAsmPrinter.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUMCResourceInfo.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUSubtarget.cpp
    M llvm/lib/Target/AMDGPU/AMDGPUSubtarget.h
    M llvm/lib/Target/AMDGPU/AsmParser/AMDGPUAsmParser.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.cpp
    M llvm/lib/Target/AMDGPU/GCNSubtarget.h
    M llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.cpp
    M llvm/lib/Target/AMDGPU/MCTargetDesc/AMDGPUTargetStreamer.h
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-device-no-attr.ll
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-flat-workgroup-lower.ll
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-flat-workgroup-reject-override.ll
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-kernel-no-attr.ll
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-override.ll
    A llvm/test/CodeGen/AMDGPU/object-linking-abi-occupancy-preserves-attr.ll
    A llvm/test/Linker/amdgpu-abi-waves-per-eu-module-flag.ll
    M llvm/test/MC/AMDGPU/amdgpu-info-roundtrip.s

  Log Message:
  -----------
  [AMDGPU] Introduce ABI occupancy for object linking

This PR introduces ABI occupancy as the contract used to compile functions under
object linking. The default is derived from the occupancy needed for a 1024
workitem workgroup, can be overridden with `-amdgpu-abi-waves-per-eu`, and can
be overridden per function by `amdgpu-flat-work-group-size` or tightened by an
accepted `amdgpu-waves-per-eu` hint.

The backend emits the selected occupancy in `.amdgpu.info` and uses it to
enforce the object linking register budget.



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