Sparse Matrix-Vector Multiplication on a Small Linear Array
نویسندگان
چکیده
A data-driven algorithm to compute a matrix-vector product on a linear array of processing elements is presented. This algorithm is based on an eecient construction that covers the nonzero entries of the matrix with staircases. The number of processing elements required equals the size of a minimal staircase cover of the matrix. The algorithm is shown to be superior to the algorithm of Melhem in terms of hardware requirements, while using exactly the same number of time steps. A question posed by Melhem is answered through a precise characterization of the number of time steps required for a particular matrix. Many problems from numerical linear algebra are eeciently solved on systolic, or data-driven, networks. EEcient systolic algorithms have been developed for a wide range of applications and VLSI implementations of such algorithms are of considerable importance in signal processing, relational query processing, and other real-time applications.
منابع مشابه
Run - Time Optimization of Sparse Matrix - Vector Multiplication onSIMD
Sparse matrix-vector multiplication forms the heart of iterative linear solvers used widely in scientiic computations (e.g., nite element methods). In such solvers, the matrix-vector product is computed repeatedly, often thousands of times, with updated values of the vector until convergence is achieved. In an SIMD architecture, each processor has to fetch the updated oo-processor vector elemen...
متن کاملRun-Time Optimization of Sparse Matrix-Vector Multiplication on SIMD Machines
Sparse matrix-vector multiplication forms the heart of iterative linear solvers used widely in scientific computations (e.g., finite element methods). In such solvers, the matrix-vector product is computed repeatedly, often thousands of times, with updated values of the vector until convergence is achieved. In an SIMD architecture, each processor has to fetch the updated off-processor vector el...
متن کاملSparse Matrix Multiplication on CAM Based Accelerator
Sparse matrix multiplication is an important component of linear algebra computations. In this paper, an architecture based on Content Addressable Memory (CAM) and Resistive Content Addressable Memory (ReCAM) is proposed for accelerating sparse matrix by sparse vector and matrix multiplication in CSR format. Using functional simulation, we show that the proposed ReCAM-based accelerator exhibits...
متن کاملHigh performance sparse matrix-vector multiplication on FPGA
This paper presents the design and implementation of a high performance sparse matrix-vector multiplication (SpMV) on fieldprogrammable gate array (FPGA). By proposing a new storage format to compress the indexes of non-zero elements by exploiting the substructure of the sparse matrix, our SpMV implementation on a reconfigurable computing platform with a multi-channel memory subsystem is capabl...
متن کاملA New Format for the Sparse Matrix-vector Multiplication
Algorithms for the sparse matrix-vector multiplication (shortly SpMV) are important building blocks in solvers of sparse systems of linear equations. Due to matrix sparsity, the memory access patterns are irregular and the utilization of a cache suffers from low spatial and temporal locality. To reduce this effect, the register blocking formats were designed. This paper introduces a new combine...
متن کامل