[all-commits] [llvm/llvm-project] 89086d: [SPIR-V] Allow bfloat vector atomics lowering with...

[Dmitry Sidorov via All-commits]

  Branch: refs/heads/main
  Home:   https://github.com/llvm/llvm-project
  Commit: 89086dbe073123f1a6507c74681d82f674250dcb
      https://github.com/llvm/llvm-project/commit/89086dbe073123f1a6507c74681d82f674250dcb
  Author: Dmitry Sidorov <Dmitry.Sidorov at amd.com>
  Date:   2026-06-09 (Tue, 09 Jun 2026)

  Changed paths:
    M llvm/lib/Target/SPIRV/SPIRVModuleAnalysis.cpp
    A llvm/test/CodeGen/SPIRV/extensions/SPV_NV_shader_atomic_fp16_vector/atomicrmw_vector_bfloat16_amd.ll

  Log Message:
  -----------
  [SPIR-V] Allow bfloat vector atomics lowering without scalarization (#202083)

This is a workaround only for AMD triple - to use
SPV_NV_shader_atomic_fp16_vector for this lowering.



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