The Intel Center of Excellence in collaboration with Argonne Leadership Computing Facility is hosting a workshop for Argonne's upcoming exascale system, Aurora. In this workshop we will provide access to most recent Intel GPU hardware and software along with time for hands-on work and individual discussions.
This is an invitation-only workshop for researchers participating in the ALCF's Aurora Early Science Program and DOE's Exascale Computing Project. Please note that your institution must have an CNDA or RSNDA agreement with Intel for you to be allowed to attend the workshop. Attendees need to have an active JLSE accounts with access to Arcticus and Florentia to be able to participate in the hands-on portions.
A broad range of topics will be covered in short presentations to provide attendees with essential information and help to maximize hands-on time and interactions between workshop participants. Some high-level topics follow.
Aurora system update:
- Overview and updates on Aurora hardware
- Overview and updates on Aurora software
Aurora applications:
- Survey of approaches to Aurora readiness
- Performance and portability across multiple GPU platforms
- Preparing applications to use multiple GPUs on a node
Breakout sessions:
- Using Intel VTune
- Using Intel Advisor
- OpenMP Target Offload
- DPC++ and SYCL
- AI frameworks and software
REGISTRATION DEADLINE: June 1st.
For questions please email us at [email protected]
