Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revisionPrevious revision
Next revision		Previous revision
Next revisionBoth sides next revision
en:services:application_services:high_performance_computing:running_jobs_slurm [2023/06/21 10:14] – [GPU selection] skreyen:services:application_services:high_performance_computing:running_jobs_slurm [2023/06/21 10:15] – [GPU selection] skrey
Line 290: Line 290:
 <code> <code>
 v100: Nvidia Tesla V100 v100: Nvidia Tesla V100
-rtx500: Nvidia Quadro RTX5000+rtx5000: Nvidia Quadro RTX5000
 gtx1080 : GeForce GTX 1080  gtx1080 : GeForce GTX 1080 
 gtx980  : GeForce GTX 980 (only in the interactive partition gpu-int) gtx980  : GeForce GTX 980 (only in the interactive partition gpu-int)
 </code> </code>
  
-Most GPUs are optimized for single precision calculations. If you need double precision performance, or error correcting memory (ECC RAM), you can select the data center (Tesla) GPUs with+Most GPUs are optimized for single precision (or lower) calculations. If you need double precision performance, tensor units or error correcting memory (ECC RAM), you can select the data center (Tesla) GPUs with
 <code> <code>
 #SBATCH -p gpu #SBATCH -p gpu