|
News
Aitken's Milan Nodes Are Now Available
17 Jun, 2024
Aitken's 512 new Milan nodes are now available for production use. Each Milan node has two Milan CPU processors. You can submit PBS jobs to the new nodes by accessing an Aitken-Milan front end (AFE), and specifying the following model type and...
Dedicated Time for All Systems Wed., June 26
14 Jun, 2024
There will be a suspend/resume for Pleiades, Electra, and Aitken, Cabeus, and all enclave service nodes, on Wednesday, June 26, from 8:00 a.m. to 11:59 p.m. Pacific Time (PT) to facilitate kernel patching and file system maintenance. The following...
Update: GPU Hackathon Application Deadline Extended to June 16
03 Jun, 2024
If you’re thinking about porting to Graphics Processing Units (GPUs) or if your NASA application is already using GPUs and you could use help getting to that next level of performance, consider applying to participate in the 2024 NASA GPU Hackathon...
Brief Downtime for LFEs, pfe23 on June 6
29 May, 2024
There will be a brief downtime for pfe23 and the Lou front ends, lfe[5-8], from 6:00 - 7:00 p.m. (Pacific Time) on Thursday, June 6, 2024 for configuration changes required to ensure enclave security. We apologize for any impact to your work. If...
Reminder: Virtual User Meeting May 22
21 May, 2024
NAS will host our second 2024 virtual user meeting on Wednesday, May 22 to provide an overview of the High-End Computing Capability portfolio component, including services and resources available to you and what’s in store for the future. Get...
Update: Emergency Downtime for PBS Server Completed
10 Apr, 2024
The PBS downtime has been completed. Original Notification PBS will be taken offline today from 3:00 – 3:30 p.m. (Pacific Time) for critical patching and restart. We anticipate minimal impact to users. During this time jobs cannot be...
Training Materials Now Available for the Cabeus NAS User Training Webinars
20 Mar, 2024
The training materials from the two-part user webinars "Overview of the New Cabeus Cluster" and “Programming and Building HPC Applications for Running on One Nvidia GPU,” held on March 12 and March 13, 2024, are now available in the Past Webinars...
New GPU Queues Now Available for A100 Nodes
18 Mar, 2024
in response to feedback from the Cabeus user community to balance the demands from both development and production workloads on these limited resources, we are instituting new queue structures. The new GPU queues for the AMD Milan A100 GPU nodes...
Dedicated Time for All Systems Wed., March 20
08 Mar, 2024
There will be a suspend/resume for all Pleiades, Electra, Aitken, and Cabeus cluster service nodes, on Wednesday, March 20, from 10:00 a.m. to 11:59 p.m. PT to facilitate system upgrades and file system maintenance. The following services will be...
User Training Webinar, "Introduction to Cabeus" on March 12 and March 13
29 Feb, 2024
The NAS Application and Performance Productivity (APP) team will conduct Cabeus user training sessions to be delivered in two separate Teams meetings scheduled for March 12 and 13 at 11:00 a.m. Pacific Time. Part 1 gives an overview of Cabeus -...
Suspend/Resume for All NAS Systems on Feb. 21 for Upgrades
05 Feb, 2024
There will be a suspend/resume for Pleiades, Electra, Aitken, Cabeus, and all Enclave service nodes, on Wednesday, February 21, from 10:00 a.m. to 11:59 p.m. (Pacific Time) to facilitate system upgrades and file system maintenance. The following...
License Servers Unavailable on February 1
26 Jan, 2024
The NAS license servers will be patched on Thursday, February 1 from 9:00 a.m. to 6:00 p.m. (Pacific Time) to facilitate installation of critical patches. The service is not expected to be unavailable at any point during this maintenance window,...
Results of the 2023 User Survey Now Available
26 Jan, 2024
In Fall of 2023, 233 users participated in a survey that addressed 12 HECC service areas. A summary of the survey results is now available, including information on key areas targeted for improvement over the next year: System Reliability Job...
UPDATE: Containers Enabled on PFEs, Disabled on Compute Nodes
26 Jan, 2024
Containers are temporarily disabled on all compute nodes inside the NAS secure enclave. This is due to a vulnerability that was discovered on all systems that use containers and run Lustre 2.12 and later. A Lustre patch that addresses the...
Upcoming Lou Outages Starting Jan. 31
19 Jan, 2024
There will be several upcoming outages on Lou in the next few weeks for patching and system upgrades. See below for dates and systems impacted: January 31, 1:00 p.m. to 7:00 p.m. (PT): All Lou front ends (LFEs) and Lou Data Analysis Nodes...
Suspend/Resume on January 17 for All NAS Systems
08 Jan, 2024
There will be a suspend/resume for Aitken, Cabeus, Electra, and Pleiades on Wednesday, January 17, 2024 from 10:00 a.m. to 11:59 p.m. (Pacific Time) to facilitate system upgrades and filesystem maintenance. The following services will be affected: ...
New Cabeus GPU System Is Now Available
27 Dec, 2023
The new 128-node Cabeus GPU system is now available for production use. Each Cabeus GPU node has four NVIDIA A100 GPUs, for a total of 512 virtual nodes (vnodes). You can use the new nodes by accessing a Cabeus front end (CFE) system, and...
Cancelled: Suspend/Resume for All NAS Systems on Dec. 19 for Patching
11 Dec, 2023
UPDATE: The suspend/resume originally scheduled for Dec. 19 has been cancelled. A new date will be set for this patching work. There will be a suspend/resume for Pleiades, Electra, and Aitken on Tuesday, December 19, 2023 from 10:00 a.m. to...
Suspend/Resume for All NAS Systems on November 21 for Network Upgrade
13 Nov, 2023
There will be a suspend/resume for all systems on Tuesday, November 21, from 8:00 a.m. to 8:00 p.m. (Pacific Time) to facilitate network hardware upgrades. The following services will be affected: Pleiades, Electra, Aitken, and all systems...
License Server Patching on Nov. 14 May Affect Some Jobs
10 Nov, 2023
NAS license servers will be patched on Tuesday, November 14, 2023 from 4:45 - 5:45 p.m. (Pacific Time). PBS jobs that rely on some NAS-provided scientific software products may fail, if an unexpected downtime results from the patching activity....
|
