Sparse Matrix to Matrix Multiplication: A Representation and Architecture for Acceleration (long version)

06/02/2019
by   Pareesa Ameneh Golnari, et al.
0

Accelerators for sparse matrix multiplication are important components in emerging systems. In this paper, we study the main challenges of accelerating Sparse Matrix Multiplication (SpMM). For the situations that data is not stored in the desired order (row/column order), we propose a compact high performance sparse format, which allows for random access to a dataset with low memory access overhead. We show that using this format results in a 14-49 times speedup for SpMM. Next, we propose a high performance systolic architecture for SpMM, which uses a mesh of comparators to locate the useful (non-zero) computation. This design maximizes data reuse by sharing the input data among a row/column of the mesh. We also show that, with similar memory access assumptions, the proposed architecture results in a 9-30 times speedup in comparison with the state of the art.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
05/28/2017

Sparse Matrix Multiplication on CAM Based Accelerator

Sparse matrix multiplication is an important component of linear algebra...
research
03/22/2018

Design Principles for Sparse Matrix Multiplication on the GPU

We implement two novel algorithms for sparse-matrix dense-matrix multipl...
research
03/26/2023

Common Subexpression-based Compression and Multiplication of Sparse Constant Matrices

In deep learning inference, model parameters are pruned and quantized to...
research
03/02/2022

Sparse matrix multiplication in the low-bandwidth model

We study matrix multiplication in the low-bandwidth model: There are n c...
research
06/14/2022

Accelerating CPU-Based Sparse General Matrix Multiplication With Binary Row Merging

Sparse general matrix multiplication (SpGEMM) is a fundamental building ...
research
02/20/2020

SpArch: Efficient Architecture for Sparse Matrix Multiplication

Generalized Sparse Matrix-Matrix Multiplication (SpGEMM) is a ubiquitous...
research
07/08/2023

Rosko: Row Skipping Outer Products for Sparse Matrix Multiplication Kernels

We propose Rosko – row skipping outer products – for deriving sparse mat...

Please sign up or login with your details

Forgot password? Click here to reset