Abstract: It is well-known that the all-pairs shortest paths problem has a similar algorithmic characteristic to the classical matrix-matrix multiply-add (MMA) problem, one of the differences between ...

This directory contains a benchmark harness for testing different implementations of vector-matrix multiply (VMM) for varying problem sizes. The main code is benchmark.cpp, which sets up the problem, ...

Abstract: We present optimizations for sparse matrix-vector multiply SpMV and its generalization to multiple vectors, SpMM, when the matrix is symmetric: (1) symmetric storage, (2) register blocking, ...

import glsl; [shader("fragment")] void fragment_main() { mat4 matrix = mat4(1.0); vec4 vector = vec4(1.0); vec4 result0 = matrix * vector; vec4 result1 = matrix ...

A novel AI-acceleration paper presents a method to optimize sparse matrix multiplication for machine learning models, particularly focusing on structured sparsity. Structured sparsity involves a ...