The next-generation Pawsey’s Supercomputing System (PSS) will replace Magnus and Galaxy through the Pawsey Capital Refresh project. The system will power future high-impact Australian research projects by delivering 30 times more compute power than predecessor systems Magnus and Galaxy.
To find out more – Powering the next generation of Australian research with HPE
Achieving sustainable scalability on the PSS will create a direct pathway to achieve superior scale on next-generation supercomputers. Pawsey’s Centre for Extreme scale Readiness (PaCER) is Pawsey’s response to that unique opportunity.
The main purpose of PaCER is to prepare Australian computational researchers for the next era of supercomputing. The focus of the PaCER program is on both extreme scale research (algorithms design, code optimisation, application and workflow readiness) and using the computational infrastructure to facilitate research for producing world-class scientific outcomes.
PaCER is not another allocation scheme, it is a partnership for collaboration between researchers and Pawsey Supercomputing Centre supercomputing specialists using the latest infrastructure provided by the PSS. It is built upon the past experience of Pawsey and other supercomputing facilities from running similar programs in past few years: Pawsey’s Petascale Pioneers and Athena Early Adopters programs, NERSC’s NESAP program and ORNL’s CAAR.
PaCER provides researchers an opportunity to optimise their codes and workflows suitable for next-generation supercomputers. It is designed as a minimum 3-year partnership for collaboration with Pawsey and HPC vendors by providing early access to supercomputing tools and infrastructure, training and exclusive hackathons focused on HPC performance at scale.
PaCER projects will have an opportunity to create new PhD or postdoctoral positions working on technical aspects of the project in relation to new advanced architectures. The new positions can be co-funded by PaCER. This co-investment model will serve as a tool to develop and grow competencies in supercomputing and computational sciences in Australia.
PaCER projects will demonstrate:
- Significant performance improvement between existing Australian supercomputers and Pawsey’s next-generation supercomputer,
- Significant power efficiency improvement (performance per watt),
- Superior capability improvement for the whole scientific domain and ability to achieve previously unavailable computational, data processing and visualisation scales.
Information for applicants
Full details are provided in the PACER_Information_for_Applicants, including assessment criteria, application process and eligibility rules. Applicants are strongly advised to read this information carefully before applying.
Call for Projects
The call for PaCER projects is now open. Completed forms should be submitted in PDF format by emailing email@example.com
Call for Projects Deadline: 29th November 2020
|Call Opens||26th October 2020|
|Call Closes||29th November 2020|
|Proposals Assessment||29th November 2020 – 3rd January 2021|
|Shortlisting and Program Committee Meetings *||3rd January – 22nd January 2021|
|Applicants Notified||End of January 2021|
* At this stage shortlisted Applicants might be contacted and asked to provide additional information e.g. in relation to co-funding and collaboration proposal.
The “Information for Applicants” document discusses that PaCER is at least 3-year collaboration project, however the co-funding is only available for up to 2 years. Is that correct?
Yes, the co-funding is linked to Pawsey Capital Refresh project and there is a deadline for when it needs to be spent. PaCER will be a longer collaboration to make sure that technical outcomes of the project can be efficiently used to support science and generate research outcomes on the PSS.
What is the expected co-funding level?
This will depend on the number of projects and their proposed co-funding model. We are expecting to support max. 0.5 postdoctoral FTE for up to 2 years.
How many projects will be supported within ** PaCER?
We are expecting to co-fund around 6 projects, but the final number will depend on the quality of proposals and their co-funding model.
We already have a group member/s (PhD or postdoc) working on the technical aspect of our simulations. Can we still apply for PaCER ** if we are not looking for co-funding a new position but would like the current group member to work on PaCER?
Yes, the details of collaboration and co-funding model needs to be defined by applicants and will be subject to a separate review. We allow applicants to repurpose existing positions to work for PaCER.
Can we apply for co-funding within PaCER without a secured funds from the institution side, e.g. apply for PaCER first and then for additional funding through a separate grant/program?
The preferred co-funding model agreed with Pawsey Procurement Board and Pawsey Board is that applicants have secured funding for PaCER within their institution. We acknowledge that this might be challenging for institutions and applicants and for that reason we have pre-announced the program back in July 2020 (https://pawsey.org.au/pacer-preannouncement/). However, applicants are encouraged to describe their proposed co-funding and collaboration model in details, especially if any constraints apply. This will be assessed through a separate review.
What allocation is available within PaCER?
PaCER is not an allocation scheme, it is a partnership for collaboration between researchers and Pawsey Supercomputing Centre supercomputing specialists. The allocation size will be flexible to achieve goals defined in PaCER project proposals. An allocation of maximum 1M Service Units (SUs) per year will be granted for PaCER projects with additional dedicated Early Access to Phase 2 system for the purpose of running Grand Challenge Problems.
Is converting a large-scale CPU code to GPU architecture in scope of PaCER?
Yes, converting your code and learning how to scale on GPU resources that will be made available in next-generation Pawsey’s supercomputer is within the scope of PaCER.