Title | ||
---|---|---|
Double MAC: Doubling the performance of convolutional neural networks on modern FPGAs. |
Abstract | ||
---|---|---|
This paper presents a novel method to double the computation rate of convolutional neural network (CNN) accelerators by packing two multiply-and-accumulate (MAC) operations into one DSP block of off-the-shelf FPGAs (called Double MAC). While a general SIMD MAC using a single DSP block seems impossible, our solution is tailored for the kind of MAC operations required for a convolution layer. Our preliminary evaluation shows that not only can our Double MAC approach increase the computation throughput of a CNN layer by twice with essentially the same resource utilization, the network level performance can also be improved by 14∼84% over a highly optimized state-of-the-art accelerator solution depending on the CNN hyper-parameters. |
Year | Venue | Field |
---|---|---|
2017 | DATE | Network level,Digital signal processing,Convolutional neural network,Convolution,Computer science,Parallel computing,Field-programmable gate array,SIMD,Throughput,Computation |
DocType | ISSN | Citations |
Conference | 1530-1591 | 3 |
PageRank | References | Authors |
0.41 | 8 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Dong Nguyen | 1 | 682 | 49.92 |
Daewoo Kim | 2 | 8 | 1.24 |
Jongeun Lee | 3 | 429 | 33.71 |