llvm/llvm-project

AMDGPU should handle SimplifyDemandedVectorElts for more trivial intrinsics

Open

#131,734 创建于 2025年3月18日

在 GitHub 查看
 (9 评论) (0 反应) (1 负责人)C++ (10,782 fork)batch import
backend:AMDGPUgood first issuemissed-optimization

仓库指标

Star
 (26,378 star)
PR 合并指标
 (平均合并 1天 2小时) (30 天内合并 1,000 个 PR)

描述

As a follow up to https://github.com/llvm/llvm-project/pull/128647, more intrinsics should be handled in SimplifyDemandedVectorElts.

This includes: Intrinsic::amdgcn_readlane, Intrinsic::amdgcn_update_dpp, Intrinsic::amdgcn_permlane16, Intrinsic::amdgcn_permlanex16, Intrinsic::amdgcn_permlane64 and Intrinsic::amdgcn_mov_dpp8

This is mostly a matter of adding the intrinsics to the switch, some boilerplate to keep the other immediate operands as they are, and adding tests similar to the ones added in #128647

贡献者指南