The Community for Technology Leaders
Green Image
Issue No. 02 - February (2009 vol. 58)
ISSN: 0018-9340
pp: 208-219
Stephanie Chan , Numerica Corp., Loveland
Karl Papadantonakis , Myricom, Arcadia
André DeHon , University of Pennsylvania, Philadelphia
Nachiket Kapre , CALTECH, Pasadena
ABSTRACT
Aggressive pipelining and spatial parallelism allow integrated circuits (e.g., custom VLSI, ASICs, and FPGAs) to achieve high throughput on many Digital Signal Processing applications. However, cyclic data dependencies in the computation can limit parallelism and reduce the efficiency and speed of an implementation. Saturated accumulation is an important example where such a cycle limits the throughput of signal processing applications. We show how to reformulate saturated addition as an associative operation so that we can use a parallel-prefix calculation to perform saturated accumulation at any data rate supported by the device. This allows us, for example, to design a 16-bit saturated accumulator which can operate at 280 MHz on a Xilinx Spartan-3 (XC3S-5000-4) FPGA, the maximum frequency supported by the component's DCM.
INDEX TERMS
High-speed arithmetic, pipeline and parallel arithmetic and logic structures, saturated arithmetic, accumulation, parallel prefix.
CITATION
Stephanie Chan, Karl Papadantonakis, André DeHon, Nachiket Kapre, "Pipelining Saturated Accumulation", IEEE Transactions on Computers, vol. 58, no. , pp. 208-219, February 2009, doi:10.1109/TC.2008.110
114 ms
(Ver 3.3 (11022016))