CSU33014 - Concurrent Systems
Course Notes: Hilary Term 2020 (in order of topics covered)
1. Background
2. Taxonomy
3. Locality and arrays
4. Introduction to OpenMP
5. Parallel sorting
6. Multithreaded architecture
7. SSE Programming
8. More SSE programming
9. Instruction-Level Parallelism
and
remaining slides
10. Very Long Instruction Word (VLIW)
11. Lock algorithms/implementation
12. MPI 1
,
MPI 2
, and
example
Deep neural network convolution for the CSU33014 lab. (See videos of lectures on Blackboard).
14. Distributed memory multiprocessor machines
(See online lecture on Blackboard)
15. Shared memory multiprocessor machines
(See online lecture on Blackboard)
16. GPU introduction
(See online lectures on Blackboard)
17. Conclusions
Course Notes not covered in CSU33014 in academic year 2019/2020
Memory Hierarchy
More Open MP
Open MP 3.0
Open MP under the hood
Instruction level parallelism
More instruction level parallelism
Superscalar
Dynamic instruction scheduling
Very long instruction word
Multithreaded architecture
Vector architectures
SIMD Multimedia
Vector Programming
mean.c
The Mandelbrot set
Intel multi-core presentation
Multiprocesor architectures
Introduction to multiprocesors
Network multiprocessor machines
Atomic instructions and locks
Cell Processor
IBM PowerEN processor
Network multiprocessor machines
MPI 1
MPI 2
More MPI
Locality and arrays
GPU 1
GPU 2
16. GPU programming in OpenCL
and
extra slides
Radix sort
Conclusions
Module Readings
Future of Microprocessors