Vector ISA Extension for Sparse Matrix-Vector Multiplication
نویسندگان
چکیده
In this paper we introduce a vector ISA extension to facilitate sparse matrix manipulation on vector processors (VPs). First we introduce a new Block Based Compressed Storage (BBCS) format for sparse matrix representation and a Block-wise Sparse Matrix-Vector Multiplication approach. Additionally, we propose two vector instructions, Multiple Inner Product and Accumulate (MIPA) and LoaD Section (LDS), specially tuned to increase the VP performance when executing sparse matrix-vector multiplications.
منابع مشابه
Transposition Mechanism for Sparse Matrices on Vector Processors
Many scientific applications involve operations on sparse matrices. However, due to irregularities induced by the sparsity patterns, many operations on sparse matrices execute inefficiently on traditional scalar and vector architectures. To tackle this problem a scheme has been proposed consisting of two parts: (a) An extension to a vector architecture to support sparse matrix-vector multiplica...
متن کاملSparse Matrix-vector Multiplication on Nvidia Gpu
In this paper, we present our work on developing a new matrix format and a new sparse matrix-vector multiplication algorithm. The matrix format is HEC, which is a hybrid format. This matrix format is efficient for sparse matrix-vector multiplication and is friendly to preconditioner. Numerical experiments show that our sparse matrix-vector multiplication algorithm is efficient on
متن کاملTwo-dimensional cache-oblivious sparse matrix-vector multiplication
In earlier work, we presented a one-dimensional cache-oblivious sparse matrix–vector (SpMV) multiplication scheme which has its roots in one-dimensional sparse matrix partitioning. Partitioning is often used in distributed-memory parallel computing for the SpMV multiplication, an important kernel in many applications. A logical extension is to move towards using a two-dimensional partitioning. ...
متن کاملSubdivision Surface Evaluation as Sparse Matrix-Vector Multiplication
We present an interpretation of subdivision surface evaluation in the language of linear algebra. Specifically, the vector of surface points can be computed by left-multiplying the vector of control points by a sparse subdivision matrix. This “matrix-driven” interpretation applies to any level of subdivision, holds for many common subdivision schemes (including Catmull-Clark and Loop), supports...
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 کامل