Accelerating Gravitational $N$-Body Simulations Using the RISC-V-Based Tenstorrent Wormhole

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Almerol, Jenny Lynn, Boella, Elisabetta, Spera, Mario, Gregori, Daniele
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909802662199296
author Almerol, Jenny Lynn
Boella, Elisabetta
Spera, Mario
Gregori, Daniele
author_facet Almerol, Jenny Lynn
Boella, Elisabetta
Spera, Mario
Gregori, Daniele
contents Although originally developed primarily for artificial intelligence workloads, RISC-V-based accelerators are also emerging as attractive platforms for high-performance scientific computing. In this work, we present our approach to accelerating an astrophysical $N$-body code on the RISC-V-based Wormhole n300 card developed by Tenstorrent. Our results show that this platform can be highly competitive for astrophysical simulations employing this class of algorithms, delivering more than a $2 \times$ speedup and approximately $2 \times$ energy savings compared to a highly optimized CPU implementation of the same code.
format Preprint
id arxiv_https___arxiv_org_abs_2509_19294
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Accelerating Gravitational $N$-Body Simulations Using the RISC-V-Based Tenstorrent Wormhole
Almerol, Jenny Lynn
Boella, Elisabetta
Spera, Mario
Gregori, Daniele
Distributed, Parallel, and Cluster Computing
Instrumentation and Methods for Astrophysics
D.1.3; J.2
Although originally developed primarily for artificial intelligence workloads, RISC-V-based accelerators are also emerging as attractive platforms for high-performance scientific computing. In this work, we present our approach to accelerating an astrophysical $N$-body code on the RISC-V-based Wormhole n300 card developed by Tenstorrent. Our results show that this platform can be highly competitive for astrophysical simulations employing this class of algorithms, delivering more than a $2 \times$ speedup and approximately $2 \times$ energy savings compared to a highly optimized CPU implementation of the same code.
title Accelerating Gravitational $N$-Body Simulations Using the RISC-V-Based Tenstorrent Wormhole
topic Distributed, Parallel, and Cluster Computing
Instrumentation and Methods for Astrophysics
D.1.3; J.2
url https://arxiv.org/abs/2509.19294