|
所在平台: Udemy |
课程主页: https://www.udemy.com/course/cuda-parallel-programming-on-nvidia-gpus-hw-and-sw/
课程评论：没有评论
**课程名称：** CUDA GPU 并行编程（硬件与软件） **课程概述：** 本课程是一门实践性课程，旨在教授学员如何利用 CUDA 释放现代 GPU 巨大的并行处理能力。课程将从 GPU 硬件基础知识入手，回顾历代旗舰架构（Fermi → Pascal → Volta → Ampere → Hopper）的演进，并通过代码实践实验，教授学员如何编写、剖析和优化高性能的 CUDA 内核（kernels）。 **您将掌握的技能：** * **GPU 与 CPU 基础对比：** 理解 GPU 在数据并行工作负载中的优势。 * **架构设计演进：** 了解对 GPU 性能至关重要的硬件特性。 * **CUDA 工具包安装：** 掌握在 Windows、Linux 和 WSL（Windows Subsystem for Linux）上安装 CUDA 工具包，并进行初步的功能检查。 * **CUDA 核心概念：** 通过矢量加法等实验，深入理解线程（threads）、块（blocks）、网格（grids）以及内存层次结构。 * **使用 Nsight Compute / nvprof 进行剖析与调优：** 学习如何衡量占用率（occupancy）、隐藏延迟（hide latency）和解决性能瓶颈。 * **矩阵二维索引：** 学习编写高效的 CUDA 内核以应对实际的线性代数任务。 * **优化策略：** 掌握处理非二的幂次方数据、利用共享内存（shared memory）、最大化内存带宽（bandwidth）以及最小化 warp 发散（warp divergence）等优化技巧。 * **健壮的调试与错误处理：** 学会使用运行时 API 检查来编写生产级代码。 **课程目标：** 课程结束后，学员将能够设计、分析和微调在当前 GPU 上高效运行的 CUDA 内核，为应对苛刻的科学、工程和人工智能工作负载做好准备。 **重要提示：** 本课程为独立的培训资源，与 NVIDIA 公司无任何赞助、认可或关联关系。"CUDA"、"Nsight" 及架构代号仅用于事实性引用。
This hands-on course teaches you how to unlock the huge parallel-processing power of modern GPUs with CUDA. You'll start with the fundamentals of GPU hardware, trace the evolution of flagship architectures (Fermi → Pascal → Volta → Ampere → Hopper), and learn-through code-along labs-how to write, profile, and optimize high-performance kernels.This is an independent training resource. It is not sponsored by, endorsed by, or otherwise affiliated with NVIDIA Corporation. "CUDA", "Nsight", and the architecture codenames are trademarks of NVIDIA and are used here only as factual references.What you'll masterGPU vs. CPU fundamentals - why GPUs dominate data-parallel workloads.Generational design advances - the hardware features that matter most for performance.CUDA toolkit installation - Windows, Linux, and WSL, plus first-run sanity checks.Core CUDA concepts - threads, blocks, grids, and the memory hierarchy, built up with labs such as vector addition.Profiling & tuning with Nsight Compute / nvprof - measure occupancy, hide latency, and break bottlenecks.2-D indexing for matrices - write efficient kernels for real-world linear-algebra tasks.Optimization playbook - handle non-power-of-two data, leverage shared memory, maximize bandwidth, and minimize warp divergence.Robust debugging & error handling - use runtime-API checks to ship production-ready code.By the end, you'll be able to design, analyze, and fine-tune CUDA kernels that run efficiently on today's GPUs-equipping you to tackle demanding scientific, engineering, and AI workloads.
