The following is OCTOPUS job class table. Please note that the job classes differ depending on your usage.
General Purpose CPU nodes
| Usage | Job Class | Maximum Elapsed Time | Maximum Number of Cores | Maximum Size of Memory | Maximum Number of Nodes | Remarks |
|---|---|---|---|---|---|---|
| Shared Use | OCT | 120 hours | 32,768 cores (256 cores/node) | 92.75 TiB (742 GiB/node) | 128 nodes | Dedicated use within nodes |
| OCT-H | 120 hours | 32,768 cores (256 cores/node) | 92.75 TiB (742 GiB/node) | 128 nodes | Dedicated use within nodes High Priority(*1) |
|
| OCT-S | 120 hours | 128 cores | 371 GiB | 1 node | Allows multiple jobs to be assigned to a single node.(*2) | |
| DBG | 10 minutes | 512 cores (256 cores/node) | 1,484 GiB (742 GiB/node) | 2 nodes | For debug use | |
| INT | 10 minutes | 512 cores (256 cores/node) | 1,484 GiB (742 GiB/node) | 2 nodes | For interactive use | |
| VA | 120 hours | 256 cores | 742 GiB | 1 node | For pseudo-quantum annealing | |
| DPS | 120 hours | 32,768 cores (256 cores/node) | 92.5 TiB (740 GiB/node) | 128 nodes | For collection of provenance information (*3) | |
| Dedicated Use | myOCT | Unlimited | 256 cores × number of dedicated nodes | 742 GiB × number of dedicated nodes | number of dedicated nodes | Apply separately |
*1 Jobs submitted to the high-priority queue are more likely to be selected as the next job to run when the system is congested and execution wait queues are formed, which can help reduce waiting time. They do not replace or preempt jobs whose scheduled start times have already been determined (i.e., jobs for which a scheduled start time is displayed by the qstat command). Please note that the high-priority queue has a higher consumption coefficient than the normal queue, and therefore consumes more points when executed. For details, please refer to this page.
*2: Allows resource sharing with other jobs within one node. A queue that allows resource sharing within a single node with other jobs. As shown below, point consumption decreases depending on the computation scale, but your job may be affected by other jobs.
| Jobs with 128 cores or fewer and 371 GB of memory or less | Apply the Share (1/2) consumption factor |
|---|---|
| Jobs with 64 cores or fewer and 185 GB of memory or less | Apply the Share (1/4) consumption factor |
*3: Executes a job and collects its provenance using DPS4H. The limits other than the memory limit and the priority are the same as for the OCT queue.
Resource Limitations
For each queue, there are limits on elapsed time, number of CPUs, size of memory, and number of nodes.
When describing them in a job script, it is necessary to specify that the limits are not exceeded.
