...
Computing resources on Ares are assigned based on PLGrid computing grants (more information can be found here: Obliczenia w PLGrid). To perform computations on Ares you need to obtain a computing grant and also apply for Ares access , service through the PLGrid portal (https://aplikacje.plgrid.pl/service/dostep-do-klastra-ares-w-osrodku-cyfronet/).
If your grant is active, and you have applied for the service access, the request should be accepted in about half an hour, please . Please report any issues through the helpdesk.
...
Partition | Number of nodes | CPU | RAM | Proportional RAM /for one CPU | Proportional RAM /for one GPU | Proportional CPU/CPUs for one GPU | Accelerator |
---|---|---|---|---|---|---|---|
plgrid (includes plgrid-long) | 532 + 256 (if not used by plgrid-bigmem) | 48 cores, Intel(R) Xeon(R) Platinum 8268 CPU @ 2.90GHz | 192GB | 3850MB | n/a | n/a | |
plgrid-bigmem | 256 | 48 cores, Intel(R) Xeon(R) Platinum 8268 CPU @ 2.90GHz | 384GB | 7700MB | n/a | n/a | |
plgrid-gpu-v100 | 9 | 32 cores, Intel(R) Xeon(R) Gold 6242 CPU @ 2.80GHz | 384GB | n/a | 46000M | 4 | 8x Tesla V100-SXM2 |
...
Name | Timelimit | Resource type (account suffix) | Access requirements | Description |
---|---|---|---|---|
plgrid | 72h | -cpu | Generally available. | Standard partition. |
plgrid-testing | 1h | -cpu | Generally available. | High priority, testing jobs, limited to 3 running jobs1 running job and 2 nodes. |
plgrid-now | 12h | -cpu | Generally available. | The highest priority, interactive jobs, limited to 1 running or queued job, and 1 node. |
plgrid-long | 168h | -cpu | Requires a grant with a maximum job runtime of 168h. | Used for jobs with extended runtime. |
plgrid-bigmem | 72h | -cpu-bigmem | Requires a grant with CPU-BIGMEM resources. | Resources used for jobs requiring an extended amount of memory. |
plgrid-gpu-v100 | 48h | -gpu | Requires a grant with GPGPU resources. | GPU partition. |
If you are unsure of how to properly configure your job on Ares please consult this guide: Job configuration
Accounts and computing grants
Ares uses a new naming scheme for CPU and GPU computing accounts, which are supplied by the -A parameter in sbatch command. Before, the account name was the same as the grant name. Currently, plain CPU accounts are named in the following manner:
Resource | account name |
---|---|
CPU | grantname-cpu |
CPU bigmem nodes | grantname-cpu-bigmem |
GPU | grantname-gpu |
Please mind that sbatch -A grantname
won't work on its own. You need to add the -cpu, -cpu-bigmem, or -gpu suffix! Available computing grants, with respective account names (allocations), can be viewed using the hpc-grants
command.
Resource allocated on Ares doesn't use normalization, which was used on Prometheus and previous clusters. 1 hour of CPU time equals 1 hour spent on a computing core with the default a proportional amount of memory (consult the table above). The billing system accounts for jobs where with more memory was used than the default valueproportional amount. If the job uses more memory for each allocated CPU than the proportional amount (consult the table above), then the job , it will be billed as it would have used more CPUs. Jobs on CPU partitions are always billed in CPU hours. The amount billed The billed amount can be calculated by dividing the used memory used by the proportional memory per core and rounding the result to the closest and larger integer. Jobs on CPU partitions are always billed in CPU hours.
The same principle was applied to GPU resources, where the GPU-hour is a billing unit, while and there are default values for proportional memory per GPU and proportional CPUs per GPU defined (consult the table above).
For example, for a typical CPU job if it uses the default amount of memory per core, or less, then the job is billed simply for the time spent using CPUs. If the job used more memory than the default amount, the The cost can be expressed as a simple algorithm for CPUs:
Code Block |
---|
cost_cpu = job_cpus_used * job_duration cost_memory = ceil(job_memory_used/memory_per_cpu) * job_duration final_cost = max(cost_cpu, cost_memory) |
and for GPUs, where a GPU has the respective amount of memory per GPU and CPUs per GPU, respectively:
Code Block |
---|
cost_gpu = job_gpus_used * job_duration cost_cpu = ceil(job_cpus_used/cpus_per_gpu) * job_duration cost_memory = ceil(job_memory_used/memory_per_gpu) * job_duration final_cost = max(cost_gpu, cost_cpu, cost_memory) |
...
and the environment can be purged by:
module purge
Sample job scripts
Example job scripts are available on this page: Sample scripts
More information
Ares is following Prometheus' configuration and usage patterns. Prometheus documentation can be found here: https://kdm.cyfronet.pl/portal/Prometheus:Basics