Mapping Sparse Matrix-Vector Multiplication on FPGAs

Conference · Mon Jan 01 04:00:00 EST 2007

OSTI ID:931886

Sun, Junqing ^[1]; Peterson, Greg D ^[1]; Storaasli, Olaf O ^[1]

---

1. ORNL

Higher peak performance on Field Programmable Gate Arrays (FPGAs) than on microprocessors was shown for sparse matrix vector multiplication (SpMxV) accelerator designs. However due to the frequent memory movement in SpMxV, system performance is heavily affected by memory bandwidth and overheads in real applications. In this paper, we introduce an innovative SpMxV Solver, designed for FPGAs, SSF. Besides high computational throughput, system performance is optimized by minimizing and overlapping I/O operations, reducing initialization time and overhead, and increasing scalability. The potential of using mixed (64-bit, 32-bit) data formats to increase system performance is also explored. SSF accepts any matrix size and easily adapts to different data formats. SSF minimizes resource costs and uses concise control logic by taking advantage of the data flow via innovative floating point accumulation logic. To analyze the performance, a performance model is defined for SpMxV on FPGAs. Compared to microprocessors, SSF has speedups up to 20x and depends less on the sparsity structure.

• Research Organization: Oak Ridge National Laboratory (ORNL), Oak Ridge, TN (United States)
• Sponsoring Organization: ORNL LDRD Director's R&D
• DOE Contract Number: AC05-00OR22725
• OSTI ID: 931886
• Country of Publication: United States
• Language: English

Related Subjects

Field Programmable Gate Array FPGA HPC Reconfigurable Supercomputer DNA human Genome Opteron