VWA: Hardware Efficient Vectorwise Accelerator for Convolutional Neural Network
檔案
本條目沒有附加檔案。
日期
2020-01-01
類型
系所
期刊名稱
IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS
卷期與頁次
第 67 卷第 1 期,頁 145–154
ISSN
1549-8328
語言
英文
摘要
Hardware accelerators for convolution neural networks (CNNs) enable real-time applications of artificial intelligence technology. However, most of the existing designs suffer from low hardware utilization or high area cost due to complex data flow. This paper proposes a hardware efficient vectorwise CNN accelerator that adopts a $3\times 3$ filter optimized systolic array using 1-D broadcast data flow to generate partial sum. This enables easy reconfiguration for different kinds of kernels with interleaved input or elementwise input data flow. This simple and regular data flow results in low area cost while attains high hardware utilization. The presented design achieves 99, 97, 93.7, and 94 hardware utilization for VGG-16, ResNet-34, GoogLeNet, and Mobilenet, respectively. Hardware implementation with TSMC 40nm technology takes 266.9K NAND gate count and 191KB SRAM to support 168GOPS throughput while consumes only 154.98mW when running at 500MHz operating frequency, which has superior area and power efficiency than other designs.
所屬典藏
期刊論文引用此條目
Chang, K.-W., & Chang, T.-S. (2020). VWA: Hardware Efficient Vectorwise Accelerator for Convolutional Neural Network. IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS, 67(1), 145–154. https://doi.org/10.1109/TCSI.2019.2942529
引用文字依 APA 第 7 版格式自動產生,使用前請再核對。
分享
永久網址:https://ir.lib.nycu.edu.tw/handle/11536/153564