| Date |
Topic |
Assignment |
|
Notes
- The exact topics of the lectures are subject to change.
- We do not anticipate changing any of the other dates (exams, assignments, etc.)
- To watch the lecture videos, sign in to YouTube using your andrew.cmu.edu account.
|
Jan |
17 |
Why parallelism?
(slides
, video
) |
|
|
Jan |
19 |
Modern multicore processors
(slides
, video
) |
Assignment 1 out |
|
|
Jan |
22 |
Parallel programming models
(slides
, video
) |
|
Jan |
24 |
Graphic processing units and CUDA (slides ,
video (part 1),
video (part 2))
|
|
Jan |
26 |
Parallel programming basics (slides
, video
) |
|
|
|
Jan |
29 |
Work distribution and scheduling (slides
, video
) |
Assignment 1 due, assignment 2 out |
|
Jan |
31 |
Locality, communication, and contention
(slides
, video
) |
|
|
Feb |
2 |
Application case studies
(slides
, video
) |
|
|
|
Feb |
5 |
Workload-driven performance evaluation
(slides
,video (part 1), video (part 2), video (part 3)
) |
|
|
Feb |
7 |
Interconnection networks (slides<,
video (part 1),
video (part 2)) |
)
|
|
Feb |
9 |
Performance Measurement and Tuning (slides. video (part 1),
video (part 2))
|
|
|
|
Feb |
12 |
Snooping-based cache coherence (slides, video (part 1),
video (part 2),
video (part 3)) |
Assignment 2 due, Assignment 3 out |
|
Feb |
14 |
Directory-based cache coherence (slides, video (part 1),
video (part 2)
)
|
|
|
Feb |
16 |
Snooping implementation (slides,
video (part 1),
video (part 2)) |
|
|
|
Feb |
19 |
Prefetching + Exam Review
(slides
,
exam review slides,
video,
exam review video (NOTE: ignore the discussion of exam logistics - it is outdated)
)
|
|
|
Feb |
21 |
Exam 1 |
|
|
Feb |
23 |
Memory consistency
(slides
, video
) |
|
|
|
Feb |
26 |
Implementing synchronization (slides,
video (part 1),
video (part 2),
video (part 3)) |
Assignment 3 due (2/27), Assignment 4 out |
|
Feb |
28 |
Fine-grained synchronization, lock-free programming
(slides,
video (part 1),
video (part 2),
video (part 3)) |
|
|
Mar |
1 |
Transactional memory (slides,
video (part 1),
video (part 2),
video (part 3)) |
|
|
|
Mar |
11 |
Under the Hood: Message Passing and Parallel Run-Time Implementations
(slides,
slides (p2)
, video, video pt 2
)
| |
|
Mar |
13 |
Heterogenous parallelism (slides,
video (part 1),
video (part 2),
video (part 3)) |
|
|
Mar |
15 |
Parallel Application Case Study: Earthquake Simulation (guest lecture: Prof. Dave O'Hallaron)
(
slides,
Tech Report) |
|
|
|
Mar |
18 |
Domain-specific programming languages
(slides
, video
) |
|
|
Mar |
20 |
Domain-specific programming on graphs
(slides
, video
) |
Assignment 4 due |
|
Mar |
22 |
Parallel Deep Learning: Part 1
(slides
, video
) |
|
|
|
|
Mar |
25 |
Project Idea Meetings |
|
|
Mar |
27 |
Parallel Deep Learning: Part 2
(slides
,
video for data parallelism,
video for model parallelism,
video for pipeline parallelism (watch parts matching the slides)
) |
|
|
|
|
Apr |
1 |
Exam Review for Exam 2
(slides) |
|
|
Apr |
3 |
Exam 2 |
|
|
|
Apr |
19 |
ML accelerators at Amazon (guest lecture by Sheng Xu) |
|