This shows you the differences between two versions of the page.
| Next revision | Previous revision | ||
|
cuda [2015/07/19 10:31] volker created |
cuda [2015/07/19 10:35] (current) volker |
||
|---|---|---|---|
| Line 8: | Line 8: | ||
| where XX is the Compute Capability of the cards the code will run on. For cards available at the ICS, use the following. | where XX is the Compute Capability of the cards the code will run on. For cards available at the ICS, use the following. | ||
| - | |||
| ^Slurm Partition^Card^Compute Capability^ | ^Slurm Partition^Card^Compute Capability^ | ||
| - | |tasna|Geforce GTX 590|20| | + | |tasna|GeForce GTX 590|20| |
| - | |ceres|Geforce GTX 680|30| | + | |ceres|GeForce GTX 680|30| |
| - | |vesta|Tesla K80|37| | + | |vesta|Tesla K80X|37| |
| + | :!: **You should compile on nodes of the partition you are running on. To do so, launch an interactive job as described on the [[slurm|SLURM Scheduler]] page.** :!: | ||
| + | Note that the GTX 680 cards have gimped double precision performance compared to the GTX 590. Do not be surprised if your code runs slower than you would expect. | ||