This document serves as a knowledge base for properly managing and diagnosing threading issues in user jobs. It focuses on OpenMP, Intel Math Kernel Library (MKL), and common thread-related misuse at OSC.
Intel MKL is widely used in HPC for linear algebra, FFTs, and statistical routines. MKL is multithreaded by default, which can significantly improve performance but only when correctly configured.
osc-seff is a command developed at OSC for use on OSC's systems and provides a the CPU resource data of the seff command with the GPU resource data of gpu-seff.
gpu-seff is a command developed at OSC for use on OSC's systems and is similar providing GPU resource data, similar to the CPU resource data reported by the seff command.
It is strongly suggested to consider the memory use to the available per-core memory when users request OSC resources for their jobs.
The following are technical specifications for Cardinal.
378 nodes
756 (2 sockets/node for all nodes)
39,312
104 cores/node for all nodes (96 usable)
This page includes a summary of differences to keep in mind when migrating jobs from other clusters to Ascend.
| Ascend (PER NODE) | Pitzer (PER NODE) | ||
|---|---|---|---|
| Regular compute node | n/a |
40 cores and 192GB of RAM 48 cores and 192GB of RAM | |
In October 2022, OSC retires the Data Direct Networks (DDN) GRIDScaler system deployed in 2016 and expands the IBM Elastic Storage System (ESS) for both Project and global Scratch services. This expands the total capacity of Project and Scratch storage at OSC to ~16 petabytes with better performance.
In December 2021 OSC updated its firewall to enhance security. As a result, SSH sessions are being closed more quickly than they used to be. It is very easy to modify your SSH options in the client you use to connect to OSC to keep your connection open.
In ~/.ssh/config (use the command touch ~/.ssh/config to create it if there is no exisitng one), you can set 3 options:
