[all-commits] [llvm/llvm-project] 362f98: [GlobalISel] Add tablegen test for metadata operan...

[Sameer Sahasrabuddhe via All-commits]

  Branch: refs/heads/users/ssahasra/av-intrinsics
  Home:   https://github.com/llvm/llvm-project
  Commit: 362f9852ce3684eb6f288ede0d15a38af7d8045e
      https://github.com/llvm/llvm-project/commit/362f9852ce3684eb6f288ede0d15a38af7d8045e
  Author: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
  Date:   2026-04-22 (Wed, 22 Apr 2026)

  Changed paths:
    A llvm/test/TableGen/GlobalISelEmitter/metadata-operand.td

  Log Message:
  -----------
  [GlobalISel] Add tablegen test for metadata operand type skip

Verify that no operand predicate is emitted for metadata operands
matched via srcvalue in a PatFrag.

Assisted-By: Claude Opus 4.6 (1M context)


  Commit: 4d6a57525b5531a9accb7a8415a7794dcc1b5313
      https://github.com/llvm/llvm-project/commit/4d6a57525b5531a9accb7a8415a7794dcc1b5313
  Author: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
  Date:   2026-04-27 (Mon, 27 Apr 2026)

  Changed paths:
    M llvm/docs/AMDGPUUsage.rst

  Log Message:
  -----------
  simplify documentation


  Commit: a4597a7871e13e50de212d2b27e7e76147e7b6d2
      https://github.com/llvm/llvm-project/commit/a4597a7871e13e50de212d2b27e7e76147e7b6d2
  Author: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
  Date:   2026-04-27 (Mon, 27 Apr 2026)

  Changed paths:
    M llvm/docs/AMDGPUUsage.rst
    M llvm/include/llvm/IR/IntrinsicsAMDGPU.td
    M llvm/lib/IR/Verifier.cpp
    M llvm/lib/Target/AMDGPU/AMDGPURegisterBankInfo.cpp
    M llvm/lib/Target/AMDGPU/FLATInstructions.td
    M llvm/lib/Target/AMDGPU/SIISelLowering.cpp
    M llvm/test/CodeGen/AMDGPU/amdgcn-av-scopes.ll
    M llvm/test/Verifier/AMDGPU/intrinsics-av.ll

  Log Message:
  -----------
  [AMDGPU] Add flat variants of av.load/store.b128 intrinsics

Add llvm.amdgcn.av.flat.load.b128 and llvm.amdgcn.av.flat.store.b128
intrinsics using flat_ptr_ty, following the established flat_/global_
naming convention used by other AMDGPU intrinsics (e.g., flat_prefetch
vs global_prefetch, flat_load_monitor vs global_load_monitor).

These select to FLAT_LOAD_DWORDX4 / FLAT_STORE_DWORDX4 with the same
cache policy bits as the global variants.

Assisted-By: Claude Opus 4.6 (1M context)


  Commit: 800ea4d63e7b635344b0375e5f61a1cb4c9363ab
      https://github.com/llvm/llvm-project/commit/800ea4d63e7b635344b0375e5f61a1cb4c9363ab
  Author: Sameer Sahasrabuddhe <sameer.sahasrabuddhe at amd.com>
  Date:   2026-04-27 (Mon, 27 Apr 2026)

  Changed paths:
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.av.global.load.b128.ll
    M llvm/test/CodeGen/AMDGPU/llvm.amdgcn.av.global.store.b128.ll

  Log Message:
  -----------
  add comments to tests


Compare: https://github.com/llvm/llvm-project/compare/197707008f69...800ea4d63e7b

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