Week | Date | Slide set | Topic | Remarks |
34 | 21.08 | 01, 01b | Introduction | |
22.08 | 02 | The von Neumann computer | ||
35 | 28.08 | 03,04 | Caches and virtual memory Instruction-level parallelism | Cache performance example code |
29.08 | 05 | Flynn's taxonomy Shared and distributed memory, interconnects | ||
36 | 04.09 | 06,07 | Speedup and efficiency The advection equation | Sequential advection equation solvers |
05.09 | 08 | Concepts of MPI | ||
37 | 11.09 | 09,10 | Six-function MPI with point-to-point communication | Six-function MPI examples |
12.09 | 11 | MPI: Collective operations | Reduction example | |
38 | 18.09 | 12,13 | MPI: Communication modes, timing, scattering and gathering data | |
19.09 | 14 | MPI: Derived data types | ||
39 | 25.09 | 15,16 | MPI: Communicators, Parallel I/O | Communicator examples Parallel I/O example |
26.09 | 17 | Pthreads introduction | ||
40 | 02.10 | 18,19 | Pthreads operations | Pthreads examples |
03.10 | 20 | OpenMP introduction | OpenMP introductory examples | |
41 | 09.10 | 21,22 | OpenMP: atomicity OpenMP: worksharing directives | OpenMP atomicity examples OpenMP worksharing examples |
10.10 | 23 | OpenMP: loop schedules | OpenMP schedule examples | |
42 | 16.10 | 24,25 | Cache coherence Loop tiling and vector operations | Tiling and vectorization examples: x86 SSE2 version ARM neon version |
17.10 | 26 | OpenMP: tasks | Task example | |
43 | 23.10 | 27,28 | Roofline analysis Application classes | |
24.10 | 29 | Loose ends: SMT, superlinear speedup, load balancing, and hybrid programming | ||
44 | 30.10 | 30 | CUDA: The GPU and U | |
31.10 | 31 | CUDA: Cooperation organisation | ||
45 | 06.11 | 32 | CUDA: Shuffle shenanigans | |
07.11 | 33 | CUDA: Thread lightly | ||
46 | 13.11 | ARM guest lecture | Slide set | |
14.11 | Canceled due to travel | |||
47 | 20.11 | Summary | Summary pt.1 | |
21.11 | Summary | Summary pt.2 Exam notes |
Slide set 01
Slide set 01b
Slide set 02
Slide set 03
Slide set 04
Slide set 05
Slide set 06
Slide set 07
Slide set 08
Slide set 09
Slide set 10
Slide set 11
Slide set 12
Slide set 13
Slide set 14
Slide set 15
Slide set 16
Slide set 17
Slide set 18
Slide set 19
Slide set 20
Slide set 21
Slide set 22
Slide set 23
Slide set 24
Slide set 25
Slide set 26
Slide set 27
Slide set 28
Slide set 29
Slide set 30
Slide set 31
Slide set 32
Slide set 33