DASP: Specific Dense Matrix Multiply-Accumulate Units Accelerated General Sparse Matrix-Vector Multiplication
Yuechen Lu, Weifeng Liu
Abstract
Sparse matrix-vector multiplication (SpMV) plays a key role in computational science and engineering, graph processing, and machine learning applications. Much work on SpMV was devoted to resolving problems such as random access to the vector x and unbalanced load. However, we have experimentally found that the computation of inner products still occupies much overhead in the SpMV operation, which has been largely ignored in existing work.
Topics & Concepts
Computer scienceMultiplication (music)Sparse matrixParallel computingMatrix multiplicationComputationOverhead (engineering)Matrix (chemical analysis)Key (lock)GraphTheoretical computer scienceComputational scienceAlgorithmMathematicsProgramming languageQuantumQuantum mechanicsCombinatoricsPhysicsComputer securityMaterials scienceGaussianComposite materialParallel Computing and Optimization TechniquesInterconnection Networks and SystemsAdvanced Data Storage Technologies