静态随机存取存储器
计算机科学
并行计算
人工神经网络
二进制数
内存处理
计算机硬件
算法
嵌入式系统
人工智能
搜索引擎
算术
情报检索
数学
Web搜索查询
按示例查询
作者
Win-San Khwa,Jiajing Chen,Jiafang Li,Xin Si,En-Yu Yang,Xiaoyu Sun,Rui Liu,Pai-Yu Chen,Qiang Li,Shimeng Yu,Meng‐Fan Chang
出处
期刊:
日期:2018-02-01
被引量:218
标识
DOI:10.1109/isscc.2018.8310401
摘要
For deep-neural-network (DNN) processors [1-4], the product-sum (PS) operation predominates the computational workload for both convolution (CNVL) and fully-connect (FCNL) neural-network (NN) layers. This hinders the adoption of DNN processors to on the edge artificial-intelligence (AI) devices, which require low-power, low-cost and fast inference. Binary DNNs [5-6] are used to reduce computation and hardware costs for AI edge devices; however, a memory bottleneck still remains. In Fig. 31.5.1 conventional PE arrays exploit parallelized computation, but suffer from inefficient single-row SRAM access to weights and intermediate data. Computing-in-memory (CIM) improves efficiency by enabling parallel computing, reducing memory accesses, and suppressing intermediate data. Nonetheless, three critical challenges remain (Fig. 31.5.2), particularly for FCNL. We overcome these problems by co-optimizing the circuits and the system. Recently, researches have been focusing on XNOR based binary-DNN structures [6]. Although they achieve a slightly higher accuracy, than other binary structures, they require a significant hardware cost (i.e. 8T-12T SRAM) to implement a CIM system. To further reduce the hardware cost, by using 6T SRAM to implement a CIM system, we employ binary DNN with 0/1-neuron and ±1-weight that was proposed in [7]. We implemented a 65nm 4Kb algorithm-dependent CIM-SRAM unit-macro and in-house binary DNN structure (focusing on FCNL with a simplified PE array), for cost-aware DNN AI edge processors. This resulted in the first binary-based CIM-SRAM macro with the fastest (2.3ns) PS operation, and the highest energy-efficiency (55.8TOPS/W) among reported CIM macros [3-4].
科研通智能强力驱动
Strongly Powered by AbleSci AI