NextAccel'26:

International Workshop on Next-generation Accelerators For HPC, Data, and AI

July 06, 2pm-5:30pm, Belfast, UK

Introduction | Topics | Dates | Organizers | Program Committee | Submission | Program

held in conjunction with ICS’26 and in cooperation with ACM

2:00PM - 5:30PM, July 06, 2026

Meeting room 7, Assembly Buildings Conference Centre

Introduction

As the scaling limits of traditional general-purpose processors become increasingly apparent, heterogeneous computing has emerged as a central paradigm for sustaining performance growth, improving energy efficiency, and enabling new classes of computation in the post-Moore era. Modern and future computing systems are rapidly evolving toward extreme heterogeneity, integrating a diverse set of accelerators and execution substrates, ranging from AI accelerators, neuromorphic and analog computing devices, near- and in-memory accelerators, RISC-V custom processors, CGRAs, to emerging quantum processing units (QPUs).

This architectural diversity enables extreme specialization, allowing algorithms to be mapped onto the most suitable hardware substrates, thereby reducing data movement, improving performance-per-watt, and enabling scalable parallelism across a wide spectrum of workloads. These systems are already reshaping domains such as machine learning, data analytics, scientific simulation, and real-time decision making. At the same time, they introduce profound challenges in programmability, performance portability, system software, and end-to-end co-design. This workshop aims to provide a focused forum to examine the rapidly expanding design space of heterogeneous computing and the opportunities it offers for future high-performance and sustainable systems.

By bringing together researchers and practitioners spanning applications, algorithms, programming systems, middleware, and hardware platforms, NextAccel seeks to promote cross-layer interaction and informed exchange across traditionally siloed communities. The workshop will serve as a venue for critically assessing the current state-of-the-art, distilling key architectural and software challenges, and identifying realistic technology paths and co-design approaches that can shape the next generation of accelerator-rich computing systems.

Topics of Interest

The topics of interest include, but are not limited to:

Important Dates

Submission and Review Process

Submission is Open. Submissions must use the ACM template at https://www.acm.org/publications/proceedings-template (use \documentclass[sigconf,screen,final]{acmart} in the ACM LaTeX template). Submitted manuscripts may not exceed eight (8) pages in length for regular papers and at least (4) pages for short papers, excluding references. Submitted papers must represent original unpublished research that is not currently under review for any other conference or journal. Papers will be evaluated based on novelty, technical soundness, clarity of presentation, and impact.

Accepted papers can be included in the ACM proceedings. ACM is transitioning in 2026 to 100% Open Access. Full/short papers require the open access fee unless corresponding authors are from participating institutions at https://libraries.acm.org/acmopen/open-participants. For more details, please visit https://www.acm.org/publications/openaccess

2:00 - 5:30: TBD

Program Committee

Organizers