45 lines
1.5 KiB
Markdown
45 lines
1.5 KiB
Markdown
# Exercise 2b
|
|
|
|
Execute numpy code with multiple threads.
|
|
|
|
```NOTE``` Remember to use `htop` in your terminal to track what the CPUs are doing.
|
|
|
|
## First
|
|
|
|
Use the script `heavy_computation.py` with different numbers of threads.
|
|
|
|
`OMP_NUM_THREADS` can be used to override the number of threads used:
|
|
```
|
|
OMP_NUM_THREADS=7 python heavy_computation.py
|
|
```
|
|
|
|
The script will save the timing results into a `timings/` folder as `.txt` files.
|
|
|
|
> What happens if `OMP_NUM_THREADS` is not set? How many threads are there? Why?
|
|
|
|
|
|
## Second
|
|
|
|
Plot the timing results from the first part, we wrote the IO for you in `timing_plot.py`.
|
|
|
|
1. Plot a graph of execution duration vs. the number of threads
|
|
2. Plot the execution speedup with respect to running a single-threaded process
|
|
|
|
Open a PR with your plotting code and post your plots in the conversation, don't upload binaries to the Git remote!
|
|
|
|
> What does the result tell us about the optimum number of threads? Why?
|
|
|
|
> Does it take the same time as your colleagues to run? Why?
|
|
|
|
## Extra
|
|
|
|
Investigate the runtime variability. Systematically run multiple instances with the same number of threads by modifying `heavy_computation.py`.
|
|
|
|
### Extra extra
|
|
|
|
How is the runtime affected when the problem becomes bigger? Is the optimum number of threads always the same?
|
|
|
|
How is the runtime affected when the memory is almost full? You can fill it up by creating a separate (unused) large numpy array.
|
|
|
|
How about running on battery vs having your laptop plugged in?
|