101010.pl

statquant<a href="https://mastodon.social/tags/rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#rstats</a> people do anyone know of an example to send jobs to <a href="https://mastodon.social/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> using the <a href="https://mastodon.social/tags/mirai" class="mention hashtag" rel="nofollow noopener" target="_blank">#mirai</a> package?

WorteksVous cherchez à optimiser vos ressources informatiques pour vos projets de science de la donnée et d'IA ? Découvrez comment <a href="https://mastodon.social/tags/Slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#Slurm</a>, un outil Open Source puissant, peut vous aider !<a href="https://mastodon.social/tags/Slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#Slurm</a> est un système très évolutif qui permet la gestion de clusters et l'ordonnancement des tâches. Retrouvez sur notre blog comment exploiter au maximum les performances de vos clusters grâce à lui. 🔗 <a href="https://www.worteks.com/blog/comment-utiliser-slurm/" rel="nofollow noopener" translate="no" target="_blank">https://www.worteks.com/blog/comment-utiliser-slurm/</a><a href="https://fosstodon.org/@ow2" class="u-url mention" rel="nofollow noopener" target="_blank">@ow2</a> <a href="https://social.openinfra.dev/@OpenInfra" class="u-url mention" rel="nofollow noopener" target="_blank">@OpenInfra</a> <a href="https://mastodon.social/@fsfe" class="u-url mention" rel="nofollow noopener" target="_blank">@fsfe</a><a href="https://mastodon.social/tags/DataScience" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataScience</a> <a href="https://mastodon.social/tags/IA" class="mention hashtag" rel="nofollow noopener" target="_blank">#IA</a> <a href="https://mastodon.social/tags/AI" class="mention hashtag" rel="nofollow noopener" target="_blank">#AI</a> <a href="https://mastodon.social/tags/FreeSoftware" class="mention hashtag" rel="nofollow noopener" target="_blank">#FreeSoftware</a> <a href="https://mastodon.social/tags/OpenSource" class="mention hashtag" rel="nofollow noopener" target="_blank">#OpenSource</a> <a href="https://mastodon.social/tags/LogicielLibre" class="mention hashtag" rel="nofollow noopener" target="_blank">#LogicielLibre</a>

Krzysztof Sakrejda<a href="https://bayes.club/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> Cluster based on redhat <a href="https://bayes.club/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#Linux</a> running <a href="https://bayes.club/tags/Nix" class="mention hashtag" rel="nofollow noopener" target="_blank">#Nix</a> through <a href="https://bayes.club/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a>... surely no one will regret that!

Michael Sumner<a href="https://rstats.me/tags/rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#rstats</a> future_map in <a href="https://rstats.me/tags/furrr" class="mention hashtag" rel="nofollow noopener" target="_blank">#furrr</a> on <a href="https://rstats.me/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> has stopped being my friend ... multicore or multisession, both take way longer than normal - tested on small sets with 6 cores, smallish sets with 24, and the real job with 128 coresparallel::parLapply works fine in the small or all 128 coresany ideas?

Tyler SmithA very niche post on using <a href="https://ottawa.place/tags/emacs" class="mention hashtag" rel="nofollow noopener" target="_blank">#emacs</a> and <a href="https://ottawa.place/tags/orgmode" class="mention hashtag" rel="nofollow noopener" target="_blank">#orgmode</a> to manage <a href="https://ottawa.place/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> job submission scripts:<a href="https://plantarum.ca/2025/01/10/slurm-yasnippet/" rel="nofollow noopener" translate="no" target="_blank">https://plantarum.ca/2025/01/10/slurm-yasnippet/</a><a href="https://ottawa.place/tags/bioinformatics" class="mention hashtag" rel="nofollow noopener" target="_blank">#bioinformatics</a>

TOVOn Linux, Slurm is also a command-line network monitoring tool in real time. This tool lets you monitor traffic on your network and display the statistics with an ASCII graph. Three different types of graphs are available on this tool.<a href="https://fosstodon.org/tags/Linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#Linux</a> <a href="https://fosstodon.org/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> <a href="https://fosstodon.org/tags/network" class="mention hashtag" rel="nofollow noopener" target="_blank">#network</a> <a href="https://fosstodon.org/tags/monitor" class="mention hashtag" rel="nofollow noopener" target="_blank">#monitor</a>

Michael Sumnerand so, do I have any other <a href="https://rstats.me/tags/Pawsey" class="mention hashtag" rel="nofollow noopener" target="_blank">#Pawsey</a> or <a href="https://rstats.me/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> users in <a href="https://rstats.me/tags/RStats" class="mention hashtag" rel="nofollow noopener" target="_blank">#RStats</a> who've been through the wringer with <a href="https://rstats.me/tags/targets" class="mention hashtag" rel="nofollow noopener" target="_blank">#targets</a>?? so far the crew.cluster issues tab, and the minimal tests is my friend3/2

Philipp BayerI wrote down my notes on getting RStudio Server to run on a SLURM instance via Singularity - it's as fiddly as it sounds<a href="https://philippbayer.github.io/blerg/posts/2024_09_06_running_rstudio_server_on_singularity/" rel="nofollow noopener" translate="no" target="_blank">https://philippbayer.github.io/blerg/posts/2024_09_06_running_rstudio_server_on_singularity/</a><a href="https://genomic.social/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> <a href="https://genomic.social/tags/singularity" class="mention hashtag" rel="nofollow noopener" target="_blank">#singularity</a> <a href="https://genomic.social/tags/rstudio" class="mention hashtag" rel="nofollow noopener" target="_blank">#rstudio</a>

Christian MeestersJust released the <a href="https://fediscience.org/tags/Snakemake" class="mention hashtag" rel="nofollow noopener" target="_blank">#Snakemake</a> plugin for the <a href="https://fediscience.org/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> batch system, v0.10.0.The main difference: Now, it should be possible to work within a SLURM job, too.Before, just the entire environment got exported to the job. Seemed like a good idea (most needs to be exported, for how else, can the program find all its path??). Now, the SLURM environment is stripped away, avoiding clashes. (For details, I would need to write a macro blog post.)What vexes me?1/3

Christian MeestersJust released a new version of the <a href="https://fediscience.org/tags/Snakemake" class="mention hashtag" rel="nofollow noopener" target="_blank">#Snakemake</a> plugin for <a href="https://fediscience.org/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> (<a href="https://fediscience.org/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a>).The default time to check for the job status has been 40 seconds. As productive runs on a cluster really should be in the order of minutes or bigger, this is a sensible default. However, it hindered quick development. Because during development of workflows, things break, and you do not want to wait a minute to know your bug.Now, this is configurable via the command line. And similar features are on the horizon!

Oliver Stueker<a href="https://mast.hpc.social/@AlanSill" class="u-url mention" rel="nofollow noopener" target="_blank">@AlanSill</a> <a href="https://fediscience.org/@rupdecat" class="u-url mention" rel="nofollow noopener" target="_blank">@rupdecat</a> There’s also the NEWS file in the repo that contains changes of <a href="https://mast.hpc.social/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> releases. <a href="https://github.com/SchedMD/slurm/blob/master/NEWS" rel="nofollow noopener" translate="no" target="_blank">https://github.com/SchedMD/slurm/blob/master/NEWS</a>

Christian Meesters<a href="https://fediscience.org/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> sometimes drives me crazy. Does anyone know a place to find old changelogs?<a href="https://fediscience.org/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a>

Tyler Smith<a href="https://ottawa.place/tags/Bioinformatics" class="mention hashtag" rel="nofollow noopener" target="_blank">#Bioinformatics</a> question: does <a href="https://ottawa.place/tags/snakemake" class="mention hashtag" rel="nofollow noopener" target="_blank">#snakemake</a> actually do anything that can't be done with a well-structured <a href="https://ottawa.place/tags/bash" class="mention hashtag" rel="nofollow noopener" target="_blank">#bash</a> script? Or, in my case, with a single <a href="https://ottawa.place/tags/emacs" class="mention hashtag" rel="nofollow noopener" target="_blank">#emacs</a> <a href="https://ottawa.place/tags/orgmode" class="mention hashtag" rel="nofollow noopener" target="_blank">#orgmode</a> file that contains all my scripts, <a href="https://ottawa.place/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> submissions and <a href="https://ottawa.place/tags/rstats" class="mention hashtag" rel="nofollow noopener" target="_blank">#rstats</a> analysis, interleaved with discussion and links to sources?Our <a href="https://ottawa.place/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> cluster folks seem to think <a href="https://ottawa.place/tags/snakemake" class="mention hashtag" rel="nofollow noopener" target="_blank">#snakemake</a> is 'next level' for reproducibility, but I'm starting to think that's because they don't realize how much you can do with existing tools like Bash and Emacs.

Ben CardoenWestgrid's <a href="https://mstdn.science/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> training sessions (workshops, courses, slides, code) are posted publicly & free <a href="https://training.westdri.ca/tools/rdm/#dvc" rel="nofollow noopener" translate="no" target="_blank">https://training.westdri.ca/tools/rdm/#dvc</a> Great resource to get up to speed quickly with topics ranging from intro to <a href="https://mstdn.science/tags/bash" class="mention hashtag" rel="nofollow noopener" target="_blank">#bash</a> all the way to <a href="https://mstdn.science/tags/chapel" class="mention hashtag" rel="nofollow noopener" target="_blank">#chapel</a> , <a href="https://mstdn.science/tags/julia" class="mention hashtag" rel="nofollow noopener" target="_blank">#julia</a> , <a href="https://mstdn.science/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#slurm</a> , <a href="https://mstdn.science/tags/deeplearning" class="mention hashtag" rel="nofollow noopener" target="_blank">#deeplearning</a> and hard to master topics such as scientific visualization on computing clusters

vsochA poll is underway! For anyone interested in <a href="https://mastodon.social/tags/Kubernetes" class="mention hashtag" rel="nofollow noopener" target="_blank">#Kubernetes</a> batch: workload managers, scheduling, and perhaps that includes @FluxFramework <a href="https://mastodon.social/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> in <a href="https://mastodon.social/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> or <a href="https://mastodon.social/tags/ConvergedComputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#ConvergedComputing</a> please help us find a time for an Americas/APAC meeting. 👉 <a href="https://groups.google.com/a/kubernetes.io/g/wg-batch/c/TeN95370Ibg/m/h9NQSe8HAgAJ" rel="nofollow noopener" translate="no" target="_blank">https://groups.google.com/a/kubernetes.io/g/wg-batch/c/TeN95370Ibg/m/h9NQSe8HAgAJ</a>Re: this post <a href="https://mastodon.social/@vsoch/111535008970787376" rel="nofollow noopener" translate="no" target="_blank">https://mastodon.social/@vsoch/111535008970787376</a>. Thanks a bunch!

Jason NucciaroneThe 2023 Ubuntu Summit has been living in my head rent free... especially now that it is only two weeks away 😏If you want to get ahead on your summit game, be sure to check out the posted timetable here: <a href="https://events.canonical.com/event/31/ngtimetable/" rel="nofollow noopener" translate="no" target="_blank">https://events.canonical.com/event/31/ngtimetable/</a>. We have excellent talks and workshops across nine different tracks ranging from using <a href="https://mast.hpc.social/tags/Ubuntu" class="mention hashtag" rel="nofollow noopener" target="_blank">#Ubuntu</a> on <a href="https://mast.hpc.social/tags/ARM" class="mention hashtag" rel="nofollow noopener" target="_blank">#ARM</a>-based laptops to using <a href="https://mast.hpc.social/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> with <a href="https://mast.hpc.social/tags/Kubernetes" class="mention hashtag" rel="nofollow noopener" target="_blank">#Kubernetes</a> for efficient <a href="https://mast.hpc.social/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> job scheduling.Hope to see you there, whether it be via a WiFi 🌐 or IRL 🤙 connection!

EricMostly remote (>95%) position available in St. Louis, MO, USA area. (Washington University in St. Louis)"User Support Manager Technical Services Manage support operations, project implementation, and staff positions in the Research Infrastructure Services group which is responsible for providing services such as high-performance computing, distributed storage, and common applications to the research community. Works independently and as a team to lead operations functions including staff supervision, functional area management, client relationship management, project coordination and implementation, issue analysis, and resolution....This position is a primarily remote position (>95%) but required to be available for onsite meetings and training when necessary approximately two to three times per month."<a href="https://wustl.wd1.myworkdayjobs.com/External/job/Remote---Missouri/Manager-Technical-Services---WUIT_JR77650" rel="nofollow noopener" target="_blank">Job Posting</a><a href="https://geldmacher.io/tags/getfedihired" class="mention hashtag" rel="nofollow noopener" target="_blank">#GetFediHired</a> <a href="https://geldmacher.io/tags/jobposting" class="mention hashtag" rel="nofollow noopener" target="_blank">#JobPosting</a> <a href="https://geldmacher.io/tags/remotework" class="mention hashtag" rel="nofollow noopener" target="_blank">#RemoteWork</a> <a href="https://geldmacher.io/tags/hpc" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> <a href="https://geldmacher.io/tags/datascience" class="mention hashtag" rel="nofollow noopener" target="_blank">#DataScience</a> <a href="https://geldmacher.io/tags/researchcomputing" class="mention hashtag" rel="nofollow noopener" target="_blank">#ResearchComputing</a> <a href="https://geldmacher.io/tags/linux" class="mention hashtag" rel="nofollow noopener" target="_blank">#linux</a> <a href="https://geldmacher.io/tags/docker" class="mention hashtag" rel="nofollow noopener" target="_blank">#docker</a> <a href="https://geldmacher.io/tags/lsf" class="mention hashtag" rel="nofollow noopener" target="_blank">#LSF</a> <a href="https://geldmacher.io/tags/slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> <a href="https://geldmacher.io/tags/git" class="mention hashtag" rel="nofollow noopener" target="_blank">#git</a> <a href="https://geldmacher.io/tags/python" class="mention hashtag" rel="nofollow noopener" target="_blank">#python</a> <a href="https://geldmacher.io/tags/mpi" class="mention hashtag" rel="nofollow noopener" target="_blank">#MPI</a> <a href="https://geldmacher.io/tags/sql" class="mention hashtag" rel="nofollow noopener" target="_blank">#SQL</a>

Aalto Scientific ComputingOn a <a href="https://fosstodon.org/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> cluster, array jobs let you parallelize things without parallelizing your code - parallelize an easy script instead. For many tasks, this is enough! The basic idea is same code, slightly different data, and <a href="https://fosstodon.org/tags/ShellScript" class="mention hashtag" rel="nofollow noopener" target="_blank">#ShellScript</a>:s connect it all. Our array tutorial explains the concepts and provides copy-and-paste examples, and works on any <a href="https://fosstodon.org/tags/Slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#Slurm</a> cluster. <a href="https://fosstodon.org/tags/RSEng" class="mention hashtag" rel="nofollow noopener" target="_blank">#RSEng</a> <a href="https://fosstodon.org/tags/SciComp" class="mention hashtag" rel="nofollow noopener" target="_blank">#SciComp</a> <a href="https://fosstodon.org/tags/tip" class="mention hashtag" rel="nofollow noopener" target="_blank">#tip</a><a href="https://scicomp.aalto.fi/triton/tut/array/" rel="nofollow noopener" target="_blank">https://scicomp.aalto.fi/triton/tut/array/</a>

Thomas ArildsenI am involved in managing a <a href="https://fosstodon.org/tags/GPU" class="mention hashtag" rel="nofollow noopener" target="_blank">#GPU</a> cluster (<a href="https://aicloud-docs.claaudia.aau.dk/" rel="nofollow noopener" target="_blank">https://aicloud-docs.claaudia.aau.dk/</a>) we have at Aalborg University. I often find myself digging tediously through the output of <a href="https://fosstodon.org/tags/Slurm" class="mention hashtag" rel="nofollow noopener" target="_blank">#Slurm</a>'s `scontrol show node` to get an idea how occupied the cluster is. I ended up enjoying my Friday evening writing a simple little <a href="https://fosstodon.org/tags/Python" class="mention hashtag" rel="nofollow noopener" target="_blank">#Python</a> tool for summarising and displaying the utilisation of the nodes in the cluster: <a href="https://git.its.aau.dk/CLAAUDIA/aicloud-tools" rel="nofollow noopener" target="_blank">https://git.its.aau.dk/CLAAUDIA/aicloud-tools</a> (I may migrate it to GitHub).

Christian Meesters<a href="https://fosstodon.org/@johanneskoester" class="u-url mention" rel="nofollow noopener" target="_blank">@johanneskoester</a> Thank you. I think this is important for two reasons:- <a href="https://fediscience.org/tags/HPC" class="mention hashtag" rel="nofollow noopener" target="_blank">#HPC</a> sites usually have issues with regard to life science support. Now, with native <a href="https://fediscience.org/tags/SLURM" class="mention hashtag" rel="nofollow noopener" target="_blank">#SLURM</a> support, users have a much more intuitive approach (let alone the option to provide curated workflows with resource settings for a given cluster) - every kW not used is the best kW. Using a workflow system will ensure less waste in biological data science.

Recent searches

Search options

Administered by:

Server stats:

#slurm