We develop new algorithms and architectures for matrix multiplication on configurable devices. These designs significantly reduce the energy dissipation and latency compared with the state-of-the-art FPGA-based designs. We derive functions to represent the impact of algorithmic level design choices on the system-wide energy dissipation, latency, and area by capturing algorithm and architecture details including features of the target FPGA. The functions are used to optimize energy performance under latency and area constraints for a family of candidate algorithms and architectures. As a result, our designs improve the energy performance of the optimized design from the recent Xilinx library by 32% to 88% without any increase in area-latency product. In terms of comprehensive metrics such as EAT (Energy-Area-Time) and E/AT (Energy/Area-Time), our designs offer superior performance compared with the Xilinx design by 50%-79% and 13%-44%, respectively. We also address how to exploit further increases in density of future FPGA devices for asymptotic improvement in latency and energy dissipation for multiplication of larger size matrices.
[1]
Wayne Luk,et al.
A Reconfigurable Engine for Real-Time Video Processing
,
1998,
FPL.
[2]
Abbes Amira,et al.
Accelerating Matrix Product on Reconfigurable Hardware for Signal Processing
,
2001,
FPL.
[3]
Bevan M. Baas,et al.
A low-power, high-performance, 1024-point FFT processor
,
1999,
IEEE J. Solid State Circuits.
[4]
Neil W. Bergmann,et al.
Reconfigurable Computing in Remote and Harsh Environments
,
1999,
FPL.
[5]
Viktor K. Prasanna,et al.
On Synthesizing Optimal Family of Linear Systolic Arrays for Matrix Multiplication
,
1991,
IEEE Trans. Computers.
[6]
P. J. Green,et al.
Probability and Statistical Inference
,
1978
.