Abstract | ||
---|---|---|
Many models of spiking neural networks heavily rely on exponential waveforms. On neuromorphic multiprocessor systems like SpiNNaker, they have to be approximated by dedicated algorithms, often dominating the processing load. Here we present a processor extension for fast calculation of exponentials, aimed at integration in the next-generation SpiNNaker system. Our implementation achieves single-LSB precision in a 32bit fixed-point format and 250Mexp/s throughput at 0.44nJ/exp for nominal supply (1.0V), or 0.21nJ/exp at 0.7V supply and 77Mexp/s, demonstrating a throughput multiplication of almost 50 and 98% energy reduction at 2% area overhead per processor on a 28nm CMOS chip. |
Year | Venue | Keywords |
---|---|---|
2017 | 2017 IEEE INTERNATIONAL SYMPOSIUM ON CIRCUITS AND SYSTEMS (ISCAS) | MPSoC, neuromorphic computing, SpiNNaker, exponential function |
Field | DocType | ISSN |
Exponential function,Computer science,Parallel computing,Neuromorphic engineering,Multiprocessing,Multiplication,Fixed point,Throughput,Spiking neural network,MPSoC | Conference | 0271-4302 |
Citations | PageRank | References |
2 | 0.35 | 10 |
Authors | ||
7 |
Name | Order | Citations | PageRank |
---|---|---|---|
Johannes Partzsch | 1 | 89 | 14.56 |
Sebastian Höppner | 2 | 76 | 14.19 |
Matthias Eberlein | 3 | 2 | 0.35 |
René Schüffny | 4 | 133 | 24.49 |
Christian Mayr | 5 | 72 | 15.71 |
David R. Lester | 6 | 220 | 21.00 |
Steve Furber | 7 | 5 | 1.82 |