Lecture | Date | Topic (notes) | Comments |
---|---|---|---|
1 | 8/24 | Introduction | |
2 | 8/29 | Locality in CPUs | |
3 | 8/31 | Cache-aware and oblivious SW | Reading |
9/5 | NO CLASS (Labor Day) | ||
4 | 9/7 | Parallelism in HW | |
5 | 9/12 | Overview of Graphics | |
6 | 9/14 | GPUs I | |
7 | 9/19 | GPGPU execution model | |
8 | 9/21 | CUDA | |
9 | 9/26 | CUDA wrapup + Optimizations | |
10 | 9/28 | Parallelism in SW I | |
11 | 10/3 | Parallelism in SW II | |
12 | 10/5 | Parallelism in SW III | |
13 | 10/10 | Parallelism in SW IV + GPU uarch | |
14 | 10/12 | GPUs in system (OS) context | |
15 | 10/17 | Software engineering concepts | |
16 | 10/19 | Intel Xeon Phi I | |
17 | 10/24 | Intel Xeon Phi II | |
18 | 10/26 | Intel Xeon Phi III | |
19 | 10/31 | Xeon Phi + GPU Microarch discussion | |
20 | 11/2 | GPU uarch 2 | |
21 | 11/7 | GPU uarch 3 | |
22 | 11/9 | More hardware | |
23 | 11/14 | DNNs on GPUs | |
24 | 11/16 | Quiz (includes reading) | Reading! |
25 | 11/21 | Wires | Reading due |
11/23 | Thanksgiving Break | ||
26 | 11/28 | Programming systems (Sequoia and Legion) | Reading |
27 | 11/30 | Resilience | Reading |
28 | 12/5 | Wrapup |