A matrix math facility for Power ISA(TM) processors

04/07/2021
by   José E. Moreira, et al.
0

Power ISA(TM) 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.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 11

05/20/2017

Sparse Matrix Multiplication On An Associative Processor

Sparse matrix multiplication is an important component of linear algebra...
03/26/2019

Matrix multiplication and universal scalability of the time on the Intel Scalable processors

Matrix multiplication is one of the core operations in many areas of sci...
04/06/2017

Parallel Multi Channel Convolution using General Matrix Multiplication

Convolutional neural networks (CNNs) have emerged as one of the most suc...
08/30/2020

Low-Depth Parallel Algorithms for the Binary-Forking Model without Atomics

The binary-forking model is a parallel computation model, formally defin...
01/17/2019

Supporting mixed-datatype matrix multiplication within the BLIS framework

We approach the problem of implementing mixed-datatype support within th...
08/03/2020

High Throughput Matrix-Matrix Multiplication between Asymmetric Bit-Width Operands

Matrix multiplications between asymmetric bit-width operands, especially...
05/13/2020

High Performance and Portable Convolution Operators for ARM-based Multicore Processors

The considerable impact of Convolutional Neural Networks on many Artific...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.