The Ookami team is pleased to announce the addition of two NVIDIA Grace CPU Superchips (144 Arm Neoverse V2 CPU cores with Scalable Vector Extensions (SVE2)).

The new nodes are now available to all Ookami users.  If you are interested in using them, get an allocation on Ookami. 

Read more

The ACM SIGHPC Education Chapter is seeking nominations for candidates for the 2024 Educational Award For Outstanding Contribution to Computational Science Education.  

We are seeking candidates who have led projects or programs that have made significant contributions to computational science education defined broadly to include all disciplines and all education levels.  The executive committee of the SIGHPC Education Chapter (Chair, Vice-chair, and Secretary-treasurer) and SIGHPC are not eligible for this award.

Nominations will be evaluated based on these criteria:

Join NVIDIA’s Deep Learning Institute (DLI) this February for a series of free, virtual instructor-led workshops providing hands-on experience with GPU-accelerated servers in the cloud to complete end-to-end projects in the areas of Generative AI and Large Language Models (LLMs). Each of these workshops are led by a DLI Certified Instructor and offer an opportunity to earn an industry-recognized certificate of competency based on assessments to support your career growth.

Learn more about the Ookami cluster (CPU only)

Whether you need computational resources and consider getting an account,  you are a new user just getting familiar with the system, or a longtime user, who wants to optimize their usage, this webinar is for you!
It will cover the basics of the system, what it's best suited for, a lot of tips and tricks on how to use it efficiently, and instructions on how to get an account. 

The ByteBoost team is thrilled to announce the launch of the ByteBoost Cybertraining Program. This groundbreaking program is driven by the imperative to enhance researchers' proficiency and productivity when navigating cutting-edge, specialized computing technologies. By offering experiential learning opportunities on modern computing technologies, ByteBoost will empower researchers to make the best computing choices in the ever-changing landscape of computational technology.

On 01/31/2024 at 4pm, the queues for Stampede2 closed permanently. 

Jobs that are already in the queue will complete their runs. No new jobs will be accepted. 

Stampede2 login nodes will remain up so that you may continue to transfer data to Stampede3: https://docs.tacc.utexas.edu/hpc/stampede3/#migrating

If you would like to request an allocation on Stampede3, you may do so here: https://allocations.access-ci.org/

We are thrilled to announce the launch of the ByteBoost Cybertraining Program. This groundbreaking program is driven by the imperative to enhance researchers' proficiency and productivity when navigating cutting-edge, specialized computing technologies. By offering experiential learning opportunities on modern computing technologies, ByteBoost will empower researchers to make the best computing choices in the ever-changing landscape of computational technology.

 Hello all,

We are pleased to announce we have opened up the login nodes for the new Stampede3 system, to allow you to begin the migration process.

At this time functionality is still limited; the new storage system and updated software stack are now available, but the only compute nodes available for running jobs are a few of the old Stampede2 “SKX” and “ICX” nodes (the login nodes do have the new Sapphire Rapids chip).

Purdue Research Computing personnel will observe the university winter break beginning on December 22nd, 2023, and will resume normal business hours on January 2nd.  During this time, Research Computing services will continue to be available, but all staff will be on leave. 

Critical system outages will be dealt with should they occur during this time. Other support needs will be handled when the University re-opens on January 3rd. 

Have a wonderful break, everyone, and we look forward to great things in the new year!

The PEARC Steering Committee is now accepting nominations for steering committee members at large as well as the 2025 conference general chair. Please consider who you might nominate for these roles and help us spread the word within your communities!

New ML Benchmarks for Scientific Discovery

Pittsburgh Supercomputing Center (PSC) is soliciting the next round of proposals for computer time on Anton 2, a special-purpose supercomputer for molecular dynamics (MD) simulation designed by D. E. Shaw Research (DESRES). Anton 2 enables biomolecular simulations running nearly 100 times faster than the state of the art on traditional supercomputers. Anton 2 is made available without cost by DESRES and supported by NIH for non-commercial research use by universities and other not-for-profit institutions. Proposals are due on Thursday June 29, 2023.

For researchers with the largest-scale computational, analysis, and storage needs, requests for Maximize ACCESS allocations can be submitted during the period of March 15 - April 15. Approved allocations will begin or renew on July 1, 2023. 

Rosen Center for Advanced Computing personnel will observe Purdue University's winter break from 5:00pm EST on Thursday, December 22nd, 2022, and will resume normal business hours on Tuesday, January 3rd, 2023.

During this time, Anvil services will continue to be available, but all staff will be on leave.

DELTA Resource Users,

We apologize for any duplication.

We are happy to announce that the National Science Foundation approved the transition of DELTA to full production. The official start date of production will be September 19th, 2022. Please be aware that computational usage by jobs on DELTA ending after Noon (Central Time) Monday, 9/19/22 will be charged against your allocations.

Note that ACCESS awards can be managed on DELTA at https://allocations.access-ci.org/requests.

Update 1

SDSC is seeking a small number of researchers interested in exploring the NSF-funded AI supercomputer, Voyager, which is currently in the testbed phase at the San Diego Supercomputer Center. Voyager is based on Intel’s Habana Lab AI processors and provides a unique opportunity to use AI focused hardware for exploring AI in science and engineering.

Parallel Computing Concepts
Wednesday, September 14, 2022
11:00 AM – 12:00 PM PDT
Instructor: Robert Sinkovits, Director of Scientific Computing Applications, SDSC

Please register at https://na.eventscloud.com/2022-09-parallel-computing-concepts

Update 1

The following sentence in our recent announcement needs clarification:

• "XSEDE support for Globus and Grid Community Toolkit client software, including the myproxy, gsi-openssh, and globus-url-copy commands, will end. "

XSEDE will no longer support the Globus Toolkit client software, and the Grid Community Toolkit client software, which provide the legacy commands myproxy-init, myproxy-logon, gsi-openssh, and globus-url-copy.