CMU 15-418 并行体系结构与编程（Parallel Computer Architecture and Programming）2016春
转自<https://www.youtube.com/playlist?list=PLpIxOj-HnDsO4Atvrp86c-4La9Mq3kMQZ>
CMU 15-418《并行体系结构与编程》2016春季课程录像
课程主页：<https://www.cs.cmu.edu/~418/>
封面图与内容无关（
视频选集
（1/29）
自动连播
Lecture 01 Why Parallelism? Why Efficiency?
01:10:52
Lecture 02 A Modern Multi Core Processor
01:25:38
Lecture 03 Parallel Programing Abstractions
01:15:39
Lecture 04 Parallel Programing Basics
01:20:53
Lecture 05 GPU Architecture and CUDA Programming
01:22:32
Lecture 06 Performance Optimization 1 Work Distribution and Scheduling
01:23:06
Lecture 07 Performance Optimization II
01:21:13
Lecture 08 Parallel Programming Case Studies
01:17:36
Lecture 09 Workload Driven Performance Evaluation
01:15:54
Lecture 10 Snooping Based Cache Coherence
01:23:26
Lecture 11 Directory Based Cache Coherence
01:15:04
Lecture 12 Basic Snooping Based Multiprocessor Implementation
01:24:13
Lecture 13 Memory Consistency + Exam 1 Review
01:20:05
Lecture 14 Scaling a Website
01:09:10
Lecture 15 Interconnection Networks
01:12:45
Lecture 16 Implementing Synchronization
01:16:49
Lecture 17 Fine Grained Sync and Lock Free Programming
01:20:02
Lecture 18 Transactional Memory
01:18:21
Lecture 19 Heterogeneous Parallelism and Hardware Specialization
01:20:50
Lecture 20 Domain Specific Parallel Programming Systems
01:21:37
Lecture 21 Domain Specific Programming on Graphs
01:18:01
Lecture 22 Spark
01:24:02
Lecture 23 Addressing the Memory Wall
01:14:47
Lecture 24 The Future of High Performance Computing
01:08:36
Lecture 25 Efficiently Evaluating Deep Networks
01:21:05
Lecture 26 Parallel Deep Network Training
01:15:46
Lecture 27 Parallelizing the Graphics Pipeline
01:16:13
Lecture 28 Course Wrap up and Project Presentations
01:05:18
Student Presentations
02:34:41
顶部