This shows you the differences between two versions of the page.
Both sides previous revision Previous revision Next revision | Previous revision | ||
matlab [2022/06/05 15:28] root |
matlab [2022/06/05 19:44] (current) root |
||
---|---|---|---|
Line 11: | Line 11: | ||
</ | </ | ||
- | ==GPU computing== | + | ==Benchmarks== |
- | Matlab in recent years has recently added a number of modern features such as GPU support, big data analysis and machine learning. | + | Matlab in recent years has recently added a number of modern features such as GPU support, big data analysis and machine learning. |
< | < | ||
Line 22: | Line 22: | ||
b = eig(a); | b = eig(a); | ||
toc; | toc; | ||
- | quit() | ||
$ matlab -nodesktop -nosplash < eigcpu.m | $ matlab -nodesktop -nosplash < eigcpu.m | ||
</ | </ | ||
- | This requires about 2700 seconds | + | This requires about 2700 sec on 32-core Intel nodes and 5300 sec on 64-core AMD nodes. |
- | The GPU version is selected in code, commands are the same. Initializing the first array as gpuArray is sufficient to use the available GPU functions, see [[https:// | + | < |
+ | module load mkl/19.0.5 matlab/ | ||
+ | </ | ||
+ | |||
+ | Matlab doesn' | ||
+ | |||
+ | < | ||
+ | MKL_DEBUG_CPU_TYPE=5 | ||
+ | </ | ||
+ | |||
+ | which improves the performance on AMD of MKL versions less than 20, which correspond to Matlab versions less than 2020. | ||
+ | |||
+ | ==GPU computing== | ||
+ | |||
+ | The GPU version is selected in code, commands are the same. Initializing the first array as gpuArray is sufficient to use the available GPU functions, see [[https:// | ||
< | < | ||
Line 37: | Line 50: | ||
b = eig(a); | b = eig(a); | ||
toc; | toc; | ||
- | quit() | ||
$ matlab -nodesktop -nosplash < eiggpu.m | $ matlab -nodesktop -nosplash < eiggpu.m | ||
</ | </ | ||
Line 50: | Line 62: | ||
[[https:// | [[https:// | ||
+ | |||
+ | [[https:// |