Efficient FPGA-Based Sparse Matrix-Vector Multiplication With Data Reuse-Aware Compression
Journal article, Peer reviewed
Accepted version
![Thumbnail](/ntnu-xmlui/bitstream/handle/11250/3136451/TCAD_SpMV.pdf.jpg?sequence=5&isAllowed=y)
View/ Open
Date
2023Metadata
Show full item recordCollections
Original version
IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems. 2023, 42 (12), 4606-4617. 10.1109/TCAD.2023.3281715Abstract
Sparse matrix–vector multiplication (SpMV) on FPGAs has gained much attention. The performance of SpMV is mainly determined by the number of multiplications between nonzero matrix elements and the corresponding vector values per cycle. On the one side, the off-chip memory bandwidth limits the number of nonzero matrix elements transferred from the off-chip DDR to the FPGA chip per cycle. On the other side, the irregular vector access pattern poses challenges to fetch the corresponding vector values. Besides, the read-after-write (RAW) dependency in the accumulation process shall be solved to enable a fully pipelined design. In this work, we propose an efficient FPGA-based SpMV accelerator with data reuse-aware compression. The key observation is that repeated accesses to a vector value can be omitted by reusing the fetched data. Based on the observation, we propose a reordering algorithm to manually exploit the data reuse of fetched vector values. Further, we propose a novel compressed format called data reuse-aware compressed (DRC) to take full advantage of the data reuse and a fast format conversion algorithm to shorten the preprocessing time. Meanwhile, we propose an HLS-friendly accumulator to solve the RAW dependency. Finally, we implement and evaluate our proposed design on the Xilinx Zynq-UltraScale ZCU106 platform with a set of sparse matrices from the SuiteSparse matrix collection. Our proposed design achieves an average 1.18× performance speedup without the DRC format and an average 1.57× performance speedup with the DRC format w.r.t. the state-of-the-art work, respectively.