Internet Streaming SIMD Extensions
Computer
Reduced Power Dissipation Through Truncated Multiplication
VOLTA '99 Proceedings of the IEEE Alessandro Volta Memorial Workshop on Low-Power Design
Discrete-Time Signal Processing
Discrete-Time Signal Processing
Multipliers for floating-point double precision and beyond on FPGAs
ACM SIGARCH Computer Architecture News
Floating-Point Exponentiation Units for Reconfigurable Computing
ACM Transactions on Reconfigurable Technology and Systems (TRETS)
Hi-index | 0.00 |
Significant reductions in FPGA resources, delay, and power can be achieved using truncated multipliers instead of standard parallel multipliers when the full precision of the standard multiplier is not required. With truncated multiplication, the less significant columns of the multiplication matrix are eliminated and correction terms are added to keep the total error to less than one unit in the last place. The truncated multiplication techniques presented in this paper are applied to FPGA parallel multipliers, and can be used in conjunction with a number of other performance enhancing techniques, such as pipelining, Booth encoding, and device specific optimizations to increase the effectiveness of device mapping, placing, and routing.