Job queues

NameHardwareLimit per accountWalltime max.Details
cpucourtIntel Xeon Gold 6248 (2×20 cores) or AMD Epyc 7302 (2×16 cores)400 cores72 hchoice of processor type
cpulongIntel Xeon Gold 6248 (2×20 cores) or AMD Epyc 7302 (2×16 cores)128 cores15 dayschoice of processor type
visuQuadro RTX 600052 cores24 huser guide
smpIntel Xeon Gold 5220 (4×18 cores) – 1 TB RAM72 cores15 daysaccess upon request
gpuNvidia V100 32 Gb or A100 80 Gb6 GPUs (incl. a max. of 2 A100)36 haccess upon request and low-priority for A100s

Information

The queues refer to the partition parameter when defining a Slurm job.

Access to the GPU and/or SMP queues is only authorized for certain projects requiring GPU computing and/or nodes with high memory (after submission of a request to the scientific committee). The other queues are available for everyone.

The amount of CPU cores per account corresponds to the maximum number of cores that members of a same Slurm account can use simultaneously. Beyond this limit, jobs are pending.

Walltime: corresponds to the maximum duration of your job before it is automatically stopped by Slurm.

Priority among some queues: see this page.

Checkpoints strongly recommended for jobs, especially long jobs. For example, see DMTCP.

Specific targeted campaigns (major challenges, jobs longer than a week, etc.) may take place at certain times of the year, for certain users or on ad hoc request.