Lehigh ISE / COR@L Lab Wiki

User Tools

Site Tools

Trace: • Navigation • COR@L and COR@L Resources
coral_lab

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision 		Previous revision
coral_lab [2014/12/02 18:18]
aykutbulut 		coral_lab [2025/07/22 08:50] (current)
mjm519 [K80 GPGPU Support]
Line 1: Line 1:
 ====== COR@L Lab ====== ====== COR@L Lab ======
  
-COR@L Lab is the computational software system in Lehigh University Industrial and Systems Engineering Department. See [[http://coral.ie.lehigh.edu/coral-resources/]|coral resources page] for a detailed introduction.+COR@L Lab is the computational software system in Lehigh University Industrial and Systems Engineering Department. 
  
 ===== Hardware ===== ===== Hardware =====
  
-^ Sl. No. ^Name ^Memory (MB)^CPU ^Scratch^Remarks ^ +^ Sl. No.  ^ Name           ^ Memory (MB)  ^ CPU                             ^ Scratch  ^ Operating System        ^ Remarks                                                      ^ 
-| 01|coral |4000|Intel Xeon 3.0GHz (x2)|46GB|webserver, mailman, bugzilla, mysql, trac, subversion. 64 bit | +| 01       | coral          | 4000         | Intel Xeon 3.10GHz (4 cores)    | --       | Debian 10      | webserver, mailman, bugzilla, mysql, trac, subversion. 64 bit  | 
-|02|piranha|2000|Pentium Xeon 3.0 GHz (x2)|58GB |64 bit architecture | +| 02       | polyp1 (polyps)  | 32000      | AMD Opteron 2.0 GHz (16 cores)  | 761GB    | Debian 12      | 64 bit architecture, head node / login node                         | 
-|03|[[polyps|polyps]] (1-12)|32000 |AMD Opteron 2.0 GHz (x16)|781GB|64 bit architecture, head node: polyp1| +| 03       | polyps (2-15)  | 32000        | AMD Opteron 2.0 GHz (16 cores)  | 761GB    | Debian 12      | 64 bit architecture, head node: polyp1   | 
-|04|[[polyps|polyps]] (13-32)|2000|AMD Opteron Processor 244 1.8 GHz (x2)|9GB|64 bit architecture, head node: polyp1| +| 04       | polyps (30)    | 128000       | Intel Xeon 2.4GHz (24 cores)    | 92GB     | Debian 12      | 64 bit architecture, Tesla K80 GPGPU, head node: polyp1        | 
-|05|shark|2000|Intel Xeon 2.4GHz (x2)|250GB|Software licences.|+| 05       | beluga         | 11000        | Intel Xeon 3.2GHz (4 cores)     | --       | Debian 8       | 64 bit architecture, storage node, exports home, software, and globalscratch directories        | 
 +| 06       | shark          | 2000         | Intel Xeon 2.4GHz (2 cores)     | 250GB    | Ubuntu 14.04   | Software licences.                                             |
  
 ===== Software ===== ===== Software =====
  
 +====== Polyp30 ======
 +Access to polyp30 is accessible via PBS. Please use an interactive job to (qsub -I) to gain access to its resources. Once you have a job, you can submit your batch job to that node. It has Nvidia Tesla K80 GPGPU. Currently it has in /usr/local the following versions of cuda installed:
 +
 +<code>user@polyp30:~$ cd /usr/local
 +user@polyp30:/usr/local$ ls -al |grep cuda
 +drwxr-sr-x 17 root   staff 4.0K Jun 26  2016 cuda-7.5
 +drwxr-sr-x  8 root   staff 4.0K Oct 10  2017 cuda-8.0
 +drwxr-sr-x 19 root   staff 4.0K Mar 26  2018 cuda-9.1
 +drwxr-sr-x 18 root   staff 4.0K Mar 27  2018 cuda-9.0
 +drwxr-sr-x 18 root   staff 4.0K Dec 16  2024 cuda-10.2
 +lrwxrwxrwx  1 root   staff   21 Jul 22 08:06 cuda -> /usr/local/cuda-11.4/
 +drwxr-sr-x 16 root   staff 4.0K Jul 22 08:08 cuda-11.4</code>
 +
 +Please update your PATH (echo $PATH) and any other variables to utilize the version you need. (LD_LIBRARY_PATH, PYTHONPATH).
 +
 +===== K80 GPGPU Support =====
 +nVidia ended Cuda support for the K80 GPGPU with Cuda 11.4. Newer versions will not function with this GPGPU. 
 +
 +[[ https://developer.nvidia.com/cuda-legacy-gpus|nVidia Legacy GPGPU matrix]]
 +
 +<code>Support for the following compute capabilities are deprecated in the CUDA 11.0 Toolkit:
 +    sm_35 (Kepler)
 +    ► sm_37 (Kepler) ◄
 +    sm_50 (Maxwell)
 +
 +See matrix link above
 +</code>
 +
 +* [[https://docs.nvidia.com/cuda/archive/11.0/cuda-toolkit-release-notes|CUDA Toolkit v11.0.3 Release Notes]]
 +
 +* [[https://docs.nvidia.com/cuda/archive/11.4.4/cuda-toolkit-release-notes/index.html|CUDA Toolkit v11.4.4 Release Notes]]
 +
 +* [[https://docs.nvidia.com/cuda/archive/11.4.4/cuda-toolkit-release-notes/index.html|Tesla K80 and discontinued driver support for Kepler]]
 +
 +  
 +===== Hints =====
 +1. Due to the heavy usage of the login node (polyps / polyp1), it is recommended you launch an interactive job on a compute node. This will provide you the dedicated resources you request rather than running on a shared node.
  
 ===== Administrators ===== ===== Administrators =====
-  * Aykut Bulut (ayb211) + 
-  * Alireza Yektamaram (sey212)+  * Cor@l admin mail-list: coral-admin-list [at] lehigh.edu 
 + 
 +  * Mark Motsko (mjm519 [at] lehigh.edu) 
 +  * Suresh Bolusani (bsuresh [at] lehigh.edu)
coral_lab.1417562290.txt.gz · Last modified: 1998/12/03 12:11 (external edit)

Page Tools

Except where otherwise noted, content on this wiki is licensed under the following license: CC Attribution-Share Alike 4.0 International
CC Attribution-Share Alike 4.0 International Donate Powered by PHP Valid HTML5 Valid CSS Driven by DokuWiki