{"id":139,"date":"2019-04-25T15:21:42","date_gmt":"2019-04-25T13:21:42","guid":{"rendered":"http:\/\/lptms.u-psud.fr\/computing\/?page_id=139"},"modified":"2026-04-01T16:10:11","modified_gmt":"2026-04-01T14:10:11","slug":"titan","status":"publish","type":"page","link":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/titan\/","title":{"rendered":"TITAN Cluster"},"content":{"rendered":"\n

Titan<\/a> cluster in LPTMS<\/a> is a Linux cluster composed of one head node and twenty-two compute nodes, it uses the scheduler “SLURM<\/a>” to to keep track of available resources, allowing job requests to be efficiently assigned to various compute resources (CPU and GPU). The cluster provides computational capacity for single and multi-processor jobs, it possess 2914 CPUs, 3 GPUs and 8 TB memory, the highest CPU count per node is 192 and the maximum memory size per node provided is 3TB.<\/p>\n\n\n\n

The head node is the server where you log in, compile code, assign tasks and coordinate jobs; the computing node is to perform the tasks through its memory and CPU. <\/p>\n\n\n\n

A partition represents a group of nodes in the cluster. There are several partitions:<\/p>\n\n\n\n

q-1heure     allows a maximum run time of 1 hour\nq-1jour*     allows a maximum run time of 1 day\nq-1sem       allows a maximum run time of 1 week\nq-2sem       allows a maximum run time of 2 weeks\nq-1mois      allows a maximum run time of 1 month\nq-2mois      allows a maximum run time of 2 month\nqbigmem      allows a maximum run time of 1 week, used for large memory work \nqopnmp       allows a maximum run time of 1 week, used for parallel jobs\ndebug        for the purpose of test<\/code><\/pre>\n\n\n\n
Using GPUs<\/h2>\n\n\n\n
Titan<\/a> cluster contains five GPUs (Tesla T4 and NVIDIA L4), the GPUs are located in a different compute nodes. In these nodes, the Nividia CUDA Toolkit<\/a> is installed and provides a compiler for NVIDIA GPUs, math libraries, and tools for debugging and optimizing the performance of applications.
Useful links: <\/em>
Introduction to CUDA C++<\/a>
PyCUDA<\/a>
Numba<\/a><\/p>\n\n\n\n
To demand the GPU resource for Python in the script:<\/em><\/p>\n\n\n\n
!\/bin\/bash\n#SBATCH --ntasks-per-node=1\n#SBATCH --partition=gpu\n#SBATCH --mem-per-cpu=10G\n#SBATCH --time=1:00:00\n#SBATCH --job-name=celloracle\n#SBATCH --output=celloracle-%J.log\n\nsrun conda<\/a> run -n tf python .\/load-tensor.py<\/code><\/pre>\n\n\n\n
Using programming languages<\/strong><\/p>\n\n\n\n
Different languages are installed in Titan Cluster, like Python, C\/C++, Fortran, Julia, etc. <\/p>\n\n\n\n
Using SLURM<\/strong><\/p>\n\n\n\n
User Guide<\/a><\/p>\n\n\n\n
Here is the detail<\/a> about Titan Cluster. <\/p>\n","protected":false},"excerpt":{"rendered":"
Titan cluster in LPTMS is a Linux cluster composed of one head node and twenty-two compute nodes, it uses the scheduler “SLURM” to to keep track of available resources, allowing job requests to be efficiently assigned to various compute resources … Continue reading →<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-139","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/pages\/139","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/comments?post=139"}],"version-history":[{"count":51,"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/pages\/139\/revisions"}],"predecessor-version":[{"id":1790,"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/pages\/139\/revisions\/1790"}],"wp:attachment":[{"href":"https:\/\/www.lptms.universite-paris-saclay.fr\/computing\/wp-json\/wp\/v2\/media?parent=139"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}