November 2025
Intermediate to advanced
1060 pages
14h 20m
Chinese
Content preview from 人工智能系统性能工程 (Chinese Edition)Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.
索引
符号
- #pragma unroll、指令级并行性暴露、循环展开、交错编译与编译器提示
- 展开过多迭代器，分析寄存器压力并采取缓解措施
- 百兆参数模型，迈向百兆参数模型
- NVIDIA机架式超级计算机，NVIDIA的"机架式AI超级计算机"
- 讨论缘由，迈向百兆参数模型
- 向 千万级GPU集群与百兆参数模型扩展-向千万级GPU集群与百兆参数模型扩展
- 3FS（参见萤火虫文件系统（3FS；DeepSeek））
- <<< >>>（箭头语法）
- __global__，CUDA编程复习
- __launch_bounds__，通过有界调整占用率-通过有界调整占用率， 占用率调优技术
- 占用率优化，编译器优化占用率的提示
- __ldg()，只读数据缓存
- __shared__区域，分布式共享内存
- __shfl_sync， 波段洗牌内置函数：避免共享内存和显式同步-波段洗牌内置函数：避免共享内存和显式同步
- __syncthreads() ，协作组
- ~6800亿参数模型，DeepSeek在中美硬件出口限制下仍可扩展至~6800亿参数模型-DeepSeek在中美硬件出口限制下仍可扩展至~6800亿参数模型
A
- 实现占用率，保持高占用率和GPU利用率，检查实现的占用率和GPU利用率
- 检查，检查实现的占用率和GPU利用率-优化内核，基于原子工作队列的动态调度
- 内核计算吞吐量与GPU浮点运算性能对比，内核计算吞吐量与峰值GPU浮点运算性能对比
- 内核内存吞吐量与HBM对比， 内核内存吞吐量与峰值HBM内存带宽对比
- 提升并行度，维持高占用率与GPU利用率
- 检查，检查实现的占用率和GPU利用率-优化内核，基于原子工作队列的动态调度
- 激活检查点机制，基于内存节省的激活检查点机制
- FSDP自动检查点机制，FSDP自动检查点机制与任务卸载
- 自适应分批处理，自适应分批处理与分块 预填充调度
- 自适应路由，自适应专家路由与实时监控 ，基于GPUDirect RDMA的多节点多机架通信
- 接入控制（参见早期拒绝）
- 自我进化的AI代理，自我进化的AI代理（AI未来项目）-自我进化的AI代理（AI未来项目）
- 基于NVL72构建模块的AI工厂，共封装光学器件：网络硬件的未来
- AI未来计划， 自我进化AI代理（AI未来计划）-自我进化AI代理（AI未来计划）
- AI优化AI系统， AI辅助实时系统优化与集群运维-AI辅助实时系统优化与集群运维
- 机架式AI超级计算机（NVIDIA），NVIDIA的" 机架式AI超级计算机"
- 关于，AI系统硬件概述
- 缓存一致性，CPU与GPU超级芯片
- CPU + GPU超级芯片，CPU和GPU超级芯片-流式多处理器、线程和线程组
- GPU张量核心与Transformer引擎， NVIDIA GPU张量核心与Transformer引擎-NVIDIA GPU张量核心与Transformer引擎
- 多GPU合一，超大规模网络将多GPU视为一体-共封装光学：网络硬件的未来
- 多GPU编程，多GPU编程-多GPU编程
- 多机架与存储通信，多机架与存储通信
- NVIDIA Blackwell 双晶片GPU ，NVIDIA Blackwell “双晶片”GPU-NVIDIA Blackwell “双晶片” GPU
- NVIDIA Grace CPU
- NVL72，超大规模网络将多GPU视为一体
- NVLink与NVSwitch，N VLink与NVSwitch-NVLink与NVSwitch
- SHARP用于网络聚合，基于NVIDIA SHARP的网络聚合-基于NVIDIA SHARP的网络聚合
- 流式多处理器、线程、波段 ，流式多处理器、线程和波段-流式多处理器、线程和波段
- AI系统性能工程师，AI系统性能工程师
- 基准 测试 ...
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Read now
Unlock full access
More than 5,000 organizations count on O’Reilly
O’Reilly covers everything we've got, with content to help us build a world-class technology community, upgrade the capabilities and competencies of our teams, and improve overall team performance as well as their engagement.Julian F.
I wanted to learn C and C++, but it didn't click for me until I picked up an O'Reilly book. When I went on the O’Reilly platform, I was astonished to find all the books there, plus live events and sandboxes so you could play around with the technology.Addison B.
I’ve been on the O’Reilly platform for more than eight years. I use a couple of learning platforms, but I'm on O'Reilly more than anybody else. When you're there, you start learning. I'm never disappointed.Amir M.
I'm always learning. So when I got on to O'Reilly, I was like a kid in a candy store. There are playlists. There are answers. There's on-demand training. It's worth its weight in gold, in terms of what it allows me to do.