Abstract | ||
---|---|---|
As a powerful unsupervised learning method, Generative Adversarial Network (GAN) plays an essential role in many domains. However, training a GAN imposes four more challenges: (1) intensive communication caused by complex train phases of GAN; (2) much more ineffectual computations caused by peculiar convolutions; (3) more frequent off-chip memory accesses for exchanging intermediate data between the generator and the discriminator; and (4) high energy consumption of unnecessary fine-grained MLC programming. In this article, we propose LrGAN, a PIM-based GAN accelerator, to address the challenges of training GAN. We first propose a zero-free data reshaping scheme for ReRAM-based PIM, which removes the zero-related computations. We then propose a 3D-connected PIM, which can reconfigure connections inside PIM dynamically according to dataflows of propagation and updating. After that, we propose an approximate weight update algorithm to avoid unnecessary fine-grain MLC programming. Finally, we propose LrGAN based on these three techniques, providing different levels of accelerating GAN for programmers. Experiments show that LrGAN achieves 47.2×, 21.42×, and 7.46× speedup over FPGA-based GAN accelerator, GPU platform, and ReRAM-based neural network accelerator respectively. Besides, LrGAN achieves 13.65×, 10.75×, and 1.34× energy saving on average over GPU platform, PRIME, and FPGA-based GAN accelerator, respectively. |
Year | DOI | Venue |
---|---|---|
2021 | 10.1109/TC.2020.3011122 | IEEE Transactions on Computers |
Keywords | DocType | Volume |
Processing in memory,generative adversarial network,approximate computing,non-volatile memory | Journal | 70 |
Issue | ISSN | Citations |
9 | 0018-9340 | 0 |
PageRank | References | Authors |
0.34 | 0 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Haiyu Mao | 1 | 9 | 1.81 |
Jiwu Shu | 2 | 709 | 72.71 |
Mingcong Song | 3 | 59 | 5.42 |
Tao Li | 4 | 761 | 47.52 |