Abstract
The sparse matrix – vector multiplication (SpMV) kernel is important for many scientific computing applications. Implementing SpMV in a way that best utilizes hardware resources is challenging due to input-dependent memory access patterns. FPGA-based accelerators that buffer the entire irregular-access part in on-chip memory enable highly efficient SpMV implementations, but are limited to smaller matrices due to on-chip memory limits. Conversely, conventional caches can work with large matrices, but cache misses can cause many stalls that decrease efficiency. In this paper, we explore the intersection between these approaches and attempt to combine the strengths of each. We propose a hardware-software caching scheme that exploits preprocessing to enable performant and area-effective SpMV acceleration. Our experiments with a set of large sparse matrices indicate that our scheme can achieve nearly stall-free execution with average 1.1 % stall time, with 70 % less on-chip memory compared to buffering the entire vector. The preprocessing step enables our scheme to offer up to 40 % higher performance compared to a conventional cache of same size by eliminating cold miss penalties.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Preview
Unable to display preview. Download preview PDF.
References
Taylor, M.B.: Is dark silicon useful?: harnessing the four horsemen of the coming dark silicon apocalypse. In: Proc. of the Design Automation Conference (2012)
Williams, S., Oliker, L., Vuduc, R., Shalf, J., Yelick, K., Demmel, J.: Optimization of sparse matrix-vector multiplication on emerging multicore platforms. Parallel Computing 35(3) (2009)
Davis, T.A., Hu, Y.: The University of Florida Sparse Matrix Collection. ACM Trans. Math. Softw. 38(1) (2011)
Gregg, D., Mc Sweeney, C., McElroy, C., Connor, F., McGettrick, S., Moloney, D., Geraghty, D.: FPGA based sparse matrix vector multiplication using commodity DRAM memory. In: Int. Conf. on Field Prog. Logic and Applications (2007)
Fowers, J., Ovtcharov, K., Strauss, K., Chung, E.S., Stitt, G.: A high memory bandwidth fpga accelerator for sparse matrix-vector multiplication. In: IEEE Int. Symp. on Field-Programmable Custom Computing Machines (2014)
Dorrance, R., Ren, F., Marković, D.: A scalable sparse matrix-vector multiplication kernel for energy-efficient sparse-BLAS on FPGAs. In: Proc. of the ACM/SIGDA Int. Symp. on FPGAs (2014)
Umuroglu, Y., Jahre, M.: An energy efficient column-major backend for FPGA SpMV accelerators. In: IEEE Int. Conf. on Computer Design (2014)
Temam, O., Jalby, W.: Characterizing the behavior of sparse algorithms on caches. In: Proc. of the ACM/IEEE Conf. on Supercomputing (1992)
Toledo, S.: Improving the memory-system performance of sparse-matrix vector multiplication. IBM Journal of Res. and Dev. 41(6) (1997)
Jouppi, N.P.: Improving direct-mapped cache performance by the addition of a small fully-associative cache and prefetch buffers. In: Proc. of the Int. Symp. on Computer Architecture (1990)
Bachrach, J., Vo, H., Richards, B., Lee, Y., Waterman, A., Avižienis, R., Wawrzynek, J., Asanović, K.: Chisel: constructing hardware in a scala embedded language. In: Proc. of the Design Automation Conference (2012)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Umuroglu, Y., Jahre, M. (2015). A Vector Caching Scheme for Streaming FPGA SpMV Accelerators. In: Sano, K., Soudris, D., Hübner, M., Diniz, P. (eds) Applied Reconfigurable Computing. ARC 2015. Lecture Notes in Computer Science(), vol 9040. Springer, Cham. https://doi.org/10.1007/978-3-319-16214-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-319-16214-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-16213-3
Online ISBN: 978-3-319-16214-0
eBook Packages: Computer ScienceComputer Science (R0)