Accelerating Gravitational $N$-Body Simulations Using the RISC-V-Based Tenstorrent Wormhole
By: Jenny Lynn Almerol , Elisabetta Boella , Mario Spera and more
Potential Business Impact:
Speeds up space simulations and saves energy.
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.
Similar Papers
Exploring Fast Fourier Transforms on the Tenstorrent Wormhole
Distributed, Parallel, and Cluster Computing
Makes supercomputers use less power for math.
Assessing Tenstorrent's RISC-V MatMul Acceleration Capabilities
Performance
Makes AI run faster and use less power.
Hardware vs. Software Implementation of Warp-Level Features in Vortex RISC-V GPU
Hardware Architecture
Makes computer graphics run much faster.