Skip to content
CUDA 中文指南
搜索文档
K
Main Navigation
阅读指南
全部章节
学习笔记
外观
章节目录
返回顶部
本页小节
3.2 Advanced Kernel Programming
待翻译
本节已建立目录框架,正文尚未翻译。
3.2.1 Using PTX
3.2.2 Hardware Implementation
3.2.2.1 SIMT Execution Model
3.2.2.1.1 Independent Thread Scheduling
3.2.2.2 Hardware Multithreading
3.2.2.3 Asynchronous Execution Features
3.2.2.3.1 Async Thread and Async Proxy
3.2.3 Thread Scopes
3.2.4 Advanced Synchronization Primitives
3.2.4.1 Scoped Atomics
3.2.4.1.1 Thread Scope and Memory Ordering
3.2.4.1.2 Performance Considerations
3.2.4.2 Asynchronous Barriers
3.2.4.3 Pipelines
3.2.5 Asynchronous Data Copies
3.2.6 Configuring L1/Shared Memory Balance