[all-commits] [llvm/llvm-project] 2224e1: [AMDGPU][CodeGen] Allow remat with multiple users ...

[Lucas Ramirez via All-commits]

  Branch: refs/heads/users/lucas-rami/rematerialize-multiple-regions
  Home:   https://github.com/llvm/llvm-project
  Commit: 2224e146314bc6226d066a8fe53b48dc371dc032
      https://github.com/llvm/llvm-project/commit/2224e146314bc6226d066a8fe53b48dc371dc032
  Author: Lucas Ramirez <lucas.rami at proton.me>
  Date:   2026-09-08 (Tue, 08 Sep 2026)

  Changed paths:
    M llvm/lib/Target/AMDGPU/GCNSchedStrategy.cpp
    M llvm/lib/Target/AMDGPU/GCNSchedStrategy.h
    M llvm/test/CodeGen/AMDGPU/gfx-callable-argument-types.ll
    M llvm/test/CodeGen/AMDGPU/machine-scheduler-sink-trivial-remats.mir
    M llvm/test/CodeGen/AMDGPU/sched-assert-dead-def-subreg-use-other-subreg.mir
    M llvm/test/CodeGen/AMDGPU/sched_mfma_rewrite_copies.mir
    M llvm/test/CodeGen/AMDGPU/sched_mfma_rewrite_cost.mir
    M llvm/test/CodeGen/AMDGPU/sched_mfma_rewrite_diff_types.mir

  Log Message:
  -----------
  [AMDGPU][CodeGen] Allow remat with multiple users in multiple regions

This relaxes one of the constraints on rematerialization candidates in
the scheduler's `PreRARematStage`. The current implementation only allows
rematerializing a register if it has users in a single region. This
allows it when a register has multiple users in multiple regions.

In such cases the register is rematerialized as many times as there are
using regions, just before the first user in each using region. The cost
model for assessing rematerialization opportunities now takes into
account that mutliple new instructions may be created for each candidate.



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