The goal of this workshop is to continue building the community of RISC-V in HPC, sharing the benefits of this technology with domain scientists, tool developers, and supercomputer operators. RISC-V is an open standard Instruction Set Architecture (ISA) which enables the royalty free development of CPUs and a common software ecosystem to be shared across them. Following this community driven ISA standard, a very diverse set of CPUs have been, and continue to be, developed which are suited to a range of workloads. Whilst RISC-V has become very popular already in some fields, and in 2022 the ten billionth RISC-V core was shipped, to date it has yet to gain traction in HPC.

However, there are numerous potential advantages that RISC-V can provide to HPC and, assuming the significant rate of growth of this technology to date continues, as we progress further into the decade it is highly likely that RISC-V will become more relevant and widespread for HPC workloads. Furthermore, recent advances in RISC-V make it a more realistic proposition for HPC workloads than ever before. An example of this is vectorisation extension which provides important performance advantages for HPC workloads but was only standardised in early 2022, and-so we are only now seeing mature CPUs that fully implement this.

The open and standardised nature of RISC-V means that the large, and growing community, can be involved in shaping the standard and tooling. This is important from two perspectives, firstly it is our opportunity in the HPC community to help shape the future of RISC-V to ensure that it is suitable for the next generation of supercomputers. Secondly, whilst there are a wide variety of RISC-V CPUs currently available, the standard nature of the tooling means that very often the same software ecosystem comprising the compiler, operating system, and libraries will run across these whilst requiring few changes.

This workshop aims to bring together those already looking to popularise RISC-V in the field of HPC with the supercomputing community at-large. By sharing benefits of the architecture, success stories, and techniques we hope to further popularise the technology and increase involvement by the community.

Submission Guidelines

Authors are invited to submit unpublished, original work, and accepted papers will appear in the workshop proceedings. Following the main HPCAsia paper guidelines, where manuscripts should be submitted for review in a single-column format and be at most 18 pages including figures and references, formatted according to the ACM Proceedings Style. The ACM templates for Word and LaTeX as well as further details can be found on the main HPCAsia CfP page.

List of Topics

• Example use-cases and case-studies that use RISC-V
• Lessons learnt from leveraging RISC-V in HPC
• Industry papers exploring the use of RISC-V
• The porting of codes to RISC-V
• Novel hardware and accelerators built upon RISC-V
• Tools and techniques to aid in the use of RISC-V for HPC
• Developments in HPC libraries to port them to RISC-V
• Enhancements to RISC-V to make the architecture more suited for HPC
• Compiler and runtime support for RISC-V
• The RISC-V ecosystem
• Future gazing how RISC-V might evolve the HPC community
• And anything else related to RISC-V and HPC!

Committees

Organizing committee

• Michael Wong (Codeplay)
• Nick Brown (EPCC at the University of Edinburgh)
• John Davis

Venue

The workshop will be co-located with HPC Asia, and run between 8:30 a.m. and noon on January 25th 2024 in Nagoya, Japan

Contact

All questions about submissions should be emailed to n.brown@epcc.ed.ac.uk