期刊
IEEE TRANSACTIONS ON VERY LARGE SCALE INTEGRATION (VLSI) SYSTEMS
卷 25, 期 8, 页码 2220-2233出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TVLSI.2017.2688340
关键词
Computation pattern; deep convolutional neural networks (DCNNs); neural network accelerator; reconfigurable architecture; scheduling framework
资金
- China Major ST Project [013ZX01033001-001-003]
- National High-Tech R&D Program of China [2015AA016601]
- NNSF of China [61274131]
Deep convolutional neural networks (DCNNs) have been successfully used in many computer vision tasks. Previous works on DCNN acceleration usually use a fixed computation pattern for diverse DCNN models, leading to imbalance between power efficiency and performance. We solve this problem by designing a DCNN acceleration architecture called deep neural architecture (DNA), with reconfigurable computation patterns for different models. The computation pattern comprises a data reuse pattern and a convolution mapping method. For massive and different layer sizes, DNA reconfigures its data paths to support a hybrid data reuse pattern, which reduces total energy consumption by 5.9 similar to 8.4 times over conventional methods. For various convolution parameters, DNA reconfigures its computing resources to support a highly scalable convolution mapping method, which obtains 93% computing resource utilization on modern DCNNs. Finally, a layer-based scheduling framework is proposed to balance DNA's power efficiency and performance for different DCNNs. DNA is implemented in the area of 16 mm(2) at 65 nm. On the benchmarks, it achieves 194.4 GOPS at 200 MHz and consumes only 479 mW. The system-level power efficiency is 152.9 GOPS/W (considering DRAM access power), which outperforms the state-of-the-art designs by one to two orders.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据