news 2026/5/9 14:23:03

CANN/pto-isa内存操作(GM <-> Tile)

作者头像

张小明

前端开发工程师

1.2k 24
文章封面图
CANN/pto-isa内存操作(GM <-> Tile)

Memory (GM <-> Tile)

【免费下载链接】pto-isaParallel Tile Operation (PTO) is a virtual instruction set architecture designed by Ascend CANN, focusing on tile-level operations. This repository offers high-performance, cross-platform tile operations across Ascend platforms.项目地址: https://gitcode.com/cann/pto-isa

This document describes memory operations between global memory and tiles.

Total Operations:6


Operations

TLOAD

For detailed instruction documentation, see isa/TLOAD

AS Level 1 (SSA):

%dst = pto.tload %mem : !pto.partition_tensor_view<MxNxdtype> -> !pto.tile<loc, dtype, rows, cols, blayout, slayout, fractal, pad>

AS Level 2 (DPS):

pto.tload ins(%mem : !pto.partition_tensor_view<MxNxdtype>) outs(%dst : !pto.tile_buf<...>)

TPREFETCH

For detailed instruction documentation, see isa/TPREFETCH

AS Level 1 (SSA):

%dst = pto.tprefetch %src : !pto.global<...> -> !pto.tile<...>

AS Level 2 (DPS):

pto.tprefetch ins(%src : !pto.global<...>) outs(%dst : !pto.tile_buf<...>)

TSTORE

For detailed instruction documentation, see isa/TSTORE

AS Level 1 (SSA):

pto.tstore %src, %mem : (!pto.tile<...>, !pto.partition_tensor_view<MxNxdtype>) -> ()

AS Level 2 (DPS):

pto.tstore ins(%src : !pto.tile_buf<...>) outs(%mem : !pto.partition_tensor_view<MxNxdtype>)

TSTORE_FP

For detailed instruction documentation, see isa/TSTORE_FP

AS Level 1 (SSA):

pto.tstore.fp %src, %fp, %mem : (!pto.tile<...>, !pto.tile<...>, !pto.partition_tensor_view<MxNxdtype>) -> ()

AS Level 2 (DPS):

pto.tstore.fp ins(%src, %fp : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%mem : !pto.partition_tensor_view<MxNxdtype>)

MGATHER

For detailed instruction documentation, see isa/MGATHER

AS Level 1 (SSA):

%dst = pto.mgather %mem, %idx : (!pto.partition_tensor_view<MxNxdtype>, pto.tile<...>) -> !pto.tile<loc, dtype, rows, cols, blayout, slayout, fractal, pad>

AS Level 2 (DPS):

pto.mgather ins(%mem, %idx : !pto.partition_tensor_view<MxNxdtype>, !pto.tile_buf<...>) outs(%dst : !pto.tile_buf<...>)

MSCATTER

For detailed instruction documentation, see isa/MSCATTER

AS Level 1 (SSA):

pto.mscatter %src, %idx, %mem : (!pto.tile<...>, !pto.tile<...>, !pto.partition_tensor_view<MxNxdtype>) -> ()

AS Level 2 (DPS):

pto.mscatter ins(%src, %idx : !pto.tile_buf<...>, !pto.tile_buf<...>) outs(%mem : !pto.partition_tensor_view<MxNxdtype>)

【免费下载链接】pto-isaParallel Tile Operation (PTO) is a virtual instruction set architecture designed by Ascend CANN, focusing on tile-level operations. This repository offers high-performance, cross-platform tile operations across Ascend platforms.项目地址: https://gitcode.com/cann/pto-isa

创作声明:本文部分内容由AI辅助生成(AIGC),仅供参考

版权声明: 本文来自互联网用户投稿,该文观点仅代表作者本人,不代表本站立场。本站仅提供信息存储空间服务,不拥有所有权,不承担相关法律责任。如若内容造成侵权/违法违规/事实不符,请联系邮箱:809451989@qq.com进行投诉反馈,一经查实,立即删除!
网站建设 2026/5/9 14:21:38

探索率如何驱动多智能体Q学习中的自发合作行为

1. 项目概述&#xff1a;当AI学会“社交”&#xff0c;探索与合作的微妙平衡最近在复现一个多智能体强化学习的实验时&#xff0c;我遇到了一个非常有趣的现象&#xff1a;几个原本各自为战、只追求自身奖励最大化的AI智能体&#xff0c;在没有任何显式通信或中央协调的情况下&…

作者头像 李华
网站建设 2026/5/9 14:20:41

CANN/metadef动态算子自动映射

AutoMappingByOpFnDynamic 【免费下载链接】metadef Ascend Metadata Definition 项目地址: https://gitcode.com/cann/metadef 函数功能 动态输入/输出算子的自动映射回调函数。 函数原型 Status AutoMappingByOpFnDynamic(const ge::Operator &op_src, ge::Ope…

作者头像 李华
网站建设 2026/5/9 14:19:33

无监督模型评估新范式:可靠性-完整性曲线与AURCC指标详解

1. 项目概述&#xff1a;当模型评估遇上“无米之炊”在机器学习项目的落地过程中&#xff0c;我们总会遇到一个经典的“鸡生蛋还是蛋生鸡”的困境&#xff1a;要评估一个模型的性能好坏&#xff0c;你需要有高质量的标注数据&#xff1b;但很多时候&#xff0c;获取这些标注数据…

作者头像 李华
网站建设 2026/5/9 14:18:04

CANN社区新建仓与仓开放操作指引

CANN社区新建仓与仓开放操作指引 【免费下载链接】community 本项目是CANN开源社区的核心管理仓库&#xff0c;包含社区的治理章程、治理组织、通用操作指引及流程规范等基础信息 项目地址: https://gitcode.com/cann/community 本指引结合TSC、PMC会议时间&#xff0c;为…

作者头像 李华
网站建设 2026/5/9 14:17:23

基于AI的CAD/CFD自动化形状优化:Anvil工具实战指南

1. 项目概述&#xff1a;当CAD遇上CFD&#xff0c;如何用AI实现自动化形状优化&#xff1f;在工程设计与仿真领域&#xff0c;CAD&#xff08;计算机辅助设计&#xff09;和CFD&#xff08;计算流体动力学&#xff09;是工程师手中不可或缺的两把利器。前者负责构建和修改产品的…

作者头像 李华
网站建设 2026/5/9 14:15:29

2025届学术党必备的五大AI写作神器实际效果

Ai论文网站排名&#xff08;开题报告、文献综述、降aigc率、降重综合对比&#xff09; TOP1. 千笔AI TOP2. aipasspaper TOP3. 清北论文 TOP4. 豆包 TOP5. kimi TOP6. deepseek 依托自然语言处理跟学术知识图谱技术的AI开题报告工具&#xff0c;有着强大功能&#xff0c…

作者头像 李华