Deming Chen, Alaa Youssef, et al.
arXiv
Power ISA™ Version 3.1 has introduced a new family of matrix math instructions, collectively known as the Matrix-Multiply Assist (MMA) facility. The instructions in this facility implement numerical linear algebra operations on small matrices and are meant to accelerate computation-intensive kernels, such as matrix multiplication, convolution and discrete Fourier transform. These instructions have led to a power- and area-efficient implementation of a high throughput math engine in the future POWER10 processor. Performance per core is 4 times better, at constant frequency, than the previous generation POWER9 processor. We also advocate the use of compiler built-ins as the preferred way of leveraging these instructions, which we illustrate through case studies covering matrix multiplication and convolution.
Deming Chen, Alaa Youssef, et al.
arXiv
Jovan Stojkovic, Tianyin Xu, et al.
HPCA 2023
Shiqiang Wang, Mingyue Ji
NeurIPS 2022
Elaine Palmer
OCP Global Summit 2020