Abstract | ||
---|---|---|
We present the design and implementation of a universal, single-bit stream library for accelerating matrix-vector multiplication using FPGAs. Our library handles multiple matrix encodings ranging from dense to multiple sparse formats. A key novelty in our approach is the introduction of a hardware-optimized sparse matrix representation called Compressed Variable-Length Bit Vector (CVBV), which reduces the storage and bandwidth requirements up to 43% (on average 25%) compared to compressed sparse row (CSR) across all the matrices from the University of Florida Sparse Matrix Collection. Our hardware incorporates a runtime-programmable decoder that performs on-the-fly-decoding of various formats such as Dense, COO, CSR, DIA, and ELL. The flexibility and scalability of our design is demonstrated across two FPGA platforms: (1) the BEE3 (Virtex-5 LX155T with 16GB of DRAM) and (2) ML605 (Virtex-6 LX240T with 2GB of DRAM). For dense matrices, our approach scales to large data sets with over 1 billion elements, and achieves robust performance independent of the matrix aspect ratio. For sparse matrices, our approach using a compressed representation reduces the overall bandwidth while also achieving comparable efficiency relative to state-of-the-art approaches. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1109/FCCM.2012.12 | FCCM |
Keywords | Field | DocType |
multiple sparse format,state-of-the-art approach,approach scale,sparse matrix,dense matrix,matrix aspect ratio,universal fpga matrix-vector multiplication,multiple matrix,hardware-optimized sparse matrix representation,sparse row,bandwidth requirement,matrix multiplication,fpga,reconfigurable computing,field programmable gate arrays | Dram,Computer science,Matrix (mathematics),Parallel computing,Multiplication,Bit array,Matrix multiplication,Sparse matrix,Scalability,Reconfigurable computing | Conference |
Citations | PageRank | References |
22 | 1.36 | 16 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Srinidhi Kestur | 1 | 137 | 9.47 |
John D. Davis | 2 | 1110 | 54.37 |
Eric S. Chung | 3 | 647 | 38.01 |