Stanford CS149, Fall 2023
PARALLEL COMPUTING
From smart phones, to multi-core CPUs and GPUs, to the world's largest supercomputers and web sites, parallel processing is ubiquitous in modern computing. The goal of this course is to provide a deep understanding of the fundamental principles and engineering trade-offs involved in designing modern parallel computing systems as well as to teach parallel programming techniques necessary to effectively utilize these machines. Because writing good parallel programs requires an understanding of key machine performance characteristics, this course will cover both parallel hardware and software design.
Basic Info
Time: Tues/Thurs 10:30-11:50am
Location: NVIDIA Auditorium
Instructors: Kayvon Fatahalian and Kunle Olukotun
See the course info page for more info on policies and logistics.
Fall 2023 Schedule
Sep 26 |
|
Challenges of parallelizing code, motivations for parallel chips, processor basics
|
Sep 28 |
|
Forms of parallelism: multi-core, SIMD, and multi-threading
|
Oct 03 |
|
Finish up multi-threaded and latency vs. bandwidth. ISPC programming, abstraction vs. implementation
|
Oct 05 |
|
Ways of thinking about parallel programs, thought process of parallelizing a program in data parallel and shared address space models
|
Oct 10 |
|
Achieving good work distribution while minimizing overhead, scheduling Cilk programs with work stealing
|
Oct 12 |
|
Message passing, async vs. blocking sends/receives, pipelining, increasing arithmetic intensity, avoiding contention
|
Oct 17 |
|
CUDA programming abstractions, and how they are implemented on modern GPUs
|
Oct 19 |
|
Data-parallel operations like map, reduce, scan, prefix sum, groupByKey
|
Oct 24 |
|
Producer-consumer locality, RDD abstraction, Spark implementation and scheduling
|
Oct 26 |
|
Efficiently scheduling DNN layers, mapping convs to matrix-multiplication, transformers, layer fusion
|
Oct 31 |
|
Definition of memory coherence, invalidation-based coherence using MSI and MESI, false sharing
|
Nov 02 |
|
Relaxed consistency models and their motivation, acquire/release semantics
|
Nov 07 |
|
Democracy Day (no class)
Take time to volunteer/educate yourself/take action!
|
Nov 09 |
|
Fine-grained synchronization via locks, basics of lock-free programming: single-reader/writer queues, lock-free stacks, the ABA problem, hazard pointers
|
Nov 14 |
|
Midterm Review
The midterm will be an evening midterm on Nov 15th. We will use the class period as a review period.
|
Nov 16 |
|
Performance/productivity motivations for DSLs, case studies on several DSLs
|
Nov 28 |
|
Motivation for transactions, design space of transactional memory implementations.
|
Nov 30 |
|
Finishing up transactional memory focusing on implementations of STM and HTM.
|
Dec 05 |
|
Energy-efficient computing, motivation for heterogeneous processing, fixed-function processing, FPGAs, mobile SoCs
|
Dec 07 |
|
How DRAM works, suggestions for post-cs149 topics
|
Dec 14 |
|
Final Exam
Held at 3:30pm. Location TBD
|
Programming Assignments
Written Assignments
Oct 10 | Written Assignment 1 |
Oct 26 | Written Assignment 2 |
Nov 3 | Written Assignment 3 |
Nov 11 | Written Assignment 4 |
Dec 6 | Written Assignment 5 |