yale-som-hpc
Official@yale-som-hpc
High-performance computing resource management and distributed data processing for academic research environments using Slurm and GPFS infrastructure.
Agent Skills by yale-som-hpc
Showing 15 vetted skills indexed across 1 GitHub repositories.
yale-som-hpcmanaging-jobs
Manage Slurm jobs on the Yale SOM HPC cluster with sbatch, squeue, sacct, scancel, and scontrol.
yale-som-hpcusing-gpus
Align GPU allocations with active CUDA workloads on SLURM clusters.
yale-som-hpcrunning-r
Execute R scripts on the Yale SOM HPC cluster with Slurm and renv.
yale-som-hpcworking-with-large-data
Process terabyte-scale datasets out-of-core with Parquet, DuckDB, Polars, and Arrow.
yale-som-hpcstarting-a-new-project
Create a reproducible project skeleton with code, data, and logs on the Yale HPC cluster.
yale-som-hpcinstalling-software
Install and configure software on the Yale SOM HPC cluster using modules, uv, and Apptainer.
yale-som-hpcaccelerating-python
Profile Python Slurm jobs to identify bottlenecks and guide acceleration.
yale-som-hpcself-diagnosing-resource-use
Diagnose Slurm job CPU, memory, and GPU utilization using sacct, seff, and nvidia-smi.
yale-som-hpcacquiring-data
Fetch WRDS data, query REST APIs, and scrape sources on the Yale SOM HPC cluster with secure credentials.
yale-som-hpcparallel-python
Guide Python parallelism worker sizing for Slurm HPC workloads.
yale-som-hpcrunning-stata
Run Stata MP batch jobs on the Yale SOM HPC cluster via Slurm sbatch scripts.
yale-som-hpcusing-the-filesystem
Guide data placement and write patterns on GPFS for HPC environments.
yale-som-hpcrunning-python
Run resumable Python jobs on the Yale SOM HPC cluster via Slurm and uv environments.
yale-som-hpcoverview
Define a mental model for Yale SOM HPC cluster login and compute nodes.
yale-som-hpcconnecting-securely
Configure SSH keys, agents, and jump hosts to connect to the Yale SOM HPC cluster.
Frequently Asked Questions About yale-som-hpc
FAQPage SchemaWhat specific tasks can researchers perform on the Yale SOM HPC cluster?▼
Researchers can manage batch jobs via Slurm, execute parallelized R and Stata MP processes, and perform out-of-core data analysis on terabyte-scale datasets. The environment supports GPU-accelerated workloads, containerized software deployment via Apptainer, and optimized data placement on GPFS filesystems for high-throughput research requirements.
Which personas are the primary users of these HPC resources?▼
The primary users are quantitative researchers, data scientists, and academic faculty requiring high-performance compute power for complex statistical modeling. These users typically work with large-scale financial or social science datasets that exceed the processing capacity of standard local workstations and require distributed cluster environments.
What are the prerequisites for accessing and running jobs on the cluster?▼
Access requires institutional credentials and the configuration of SSH keys for secure connection to jump hosts. Users must define project structures, manage software dependencies through modules or environment managers, and utilize Slurm directives to request specific CPU, memory, and GPU allocations before executing batch processes.