[all-commits] [llvm/llvm-project] f1961c: [AMDGPU][GFX1250] Insert S_WAIT_XCNT for SMEM and ...

[Christudasan Devadasan via All-commits]

  Branch: refs/heads/users/cdevadas/implement_s_wait_xcnt_insertion_gfx1250
  Home:   https://github.com/llvm/llvm-project
  Commit: f1961c829cddd705d95613977584b4938499c7ca
      https://github.com/llvm/llvm-project/commit/f1961c829cddd705d95613977584b4938499c7ca
  Author: Christudasan Devadasan <Christudasan.Devadasan at amd.com>
  Date:   2025-06-24 (Tue, 24 Jun 2025)

  Changed paths:
    M llvm/lib/Target/AMDGPU/SIInsertWaitcnts.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp
    M llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.h
    A llvm/test/CodeGen/AMDGPU/global-load-xcnt.ll
    A llvm/test/CodeGen/AMDGPU/wait-xcnt.mir

  Log Message:
  -----------
  [AMDGPU][GFX1250] Insert S_WAIT_XCNT for SMEM and VMEM load-stores

This patch tracks the register operands of both VMEM (FLAT, MUBUF,
MTBUF) and SMEM load-store operations and inserts a S_WAIT_XCNT
instruction with sufficient wait-count before potentially redefining
them. For VMEM instructions, XNACK is returned in the same order as
they were issued and hence non-zero counter values can be inserted.
However, SMEM execution is out-of-order and so is their XNACK reception.
Thus, only zero counter value can be inserted to capture SMEM dependencies.



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