PAR Class 1, Thurs 2019-01-10
Table of contents
1 Material
- Read the syllabus.
- Read https://computing.llnl.gov/tutorials/parallel_comp/ for an intro to parallel computing.
- Some points:
- Parallel computing is decades old; there were commercial machines in the 1980s. However, then, clocks speeds were increasing so serial machines were more interesting.
- Now: physics limits to processor speed.
- History of Nvidia.
- Intel CPUs vs Nvidia CUDA cores.
- Advantages and disadvantages of shared memory.
- OpenMP vs CUDA.
- Rate-limiting cost usually I/O not computation.
- Think about these questions for next week.
- Answer the following questions.
- Why have machine cycle speeds stopped increasing?
- What architectures do the top 3 machines on the Top 500 list use?
- Which one of the following 4 choices are most GPUs: SISD, SIMD, MISD, MIMD.
- Which one of the following 4 choices are most current multicore CPUs: SISD, SIMD, MISD, MIMD.
- Per Amdahl's law, if a program is 10% sequential and 90% parallelizable, what is the max speed up that can be obtained with an infinite number of parallel processors?
- Answer the following questions.
2 Computer
- parallel.ecse accounts
- I'll try to set yours up in class today.
- Play with them. I recomend connecting with ssh.
- Intel Xeon Phi coprocessor
- Parallel.ecse has one.
- This tech was dropped by Intel, so I don't intend to cover it in class.
- If anyone is interested, tell me today. Otherwise it may stop working when I upgrade the system from Ubuntu 16.04 to 18.xx
3 My research
I do parallel geometry algorithms on large problems for CAD and GIS. See my home page. If this is interesting, talk to me.