Programming Novel AI Accelerators for Scientific Computing
Monday, June 22, 2026 2:00 PM to 6:00 PM · 4 hr. (Europe/Berlin)
Hall X11 - 1st Floor
Tutorial
Emerging Computing TechnologiesHeterogeneous System ArchitecturesHW and SW Design for Scalable Machine LearningML Systems and Frameworks
Information
Scientific applications are increasingly adopting Artificial Intelligence (AI) techniques to advance
science. There exist specialized hardware accelerators designed to run AI applications efficiently.
With a wide diversity in the hardware architectures and software stacks of these systems, it is
challenging to understand the differences between these accelerators, their capabilities,
programming approaches, and how they perform, particularly for scientific applications.
In this tutorial, we will cover an overview of the AI accelerators deployed at ALCF: SambaNova,
Cerebras, and Tenstorrent systems along with the architectural features and details of their
software stacks. Through hands-on exercises, attendees will gain practical experience in refactoring
code and running models on these systems, focusing on use cases of pre-training and fine-tuning
open-source Large Language Models (LLMs) and deploying AI inference solutions relevant to
scientific contexts. Additionally, the sessions will cover the low-level software stack of these
accelerators using simple HPC kernels. The tutorial will provide the attendees with an understanding
of the key capabilities of emerging AI accelerators and their performance implications for scientific
applications.
science. There exist specialized hardware accelerators designed to run AI applications efficiently.
With a wide diversity in the hardware architectures and software stacks of these systems, it is
challenging to understand the differences between these accelerators, their capabilities,
programming approaches, and how they perform, particularly for scientific applications.
In this tutorial, we will cover an overview of the AI accelerators deployed at ALCF: SambaNova,
Cerebras, and Tenstorrent systems along with the architectural features and details of their
software stacks. Through hands-on exercises, attendees will gain practical experience in refactoring
code and running models on these systems, focusing on use cases of pre-training and fine-tuning
open-source Large Language Models (LLMs) and deploying AI inference solutions relevant to
scientific contexts. Additionally, the sessions will cover the low-level software stack of these
accelerators using simple HPC kernels. The tutorial will provide the attendees with an understanding
of the key capabilities of emerging AI accelerators and their performance implications for scientific
applications.
Format
on-site
Targeted Audience
Researchers and system architects who would benefit from running ML workloads to evaluate existing HPC systems or to guide the design of future systems and deploy the AI components onto these accelerators. Participants are expected to have a basic understanding of ML, HPC, and at least one deep learning framework.
Beginner Level
50%
Intermediate Level
50%
Prerequesites
The attendees would need
a laptop to view the presentation slides to follow the material closely with the speakers. For
the hands-on session, the attendees will be provided instructions on using the ALCF AI
Testbed systems. There will be a few sessions on the remote cloud servers to run inference
examples, the instructions to set up accounts will be available in the GitHub repository.
