3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories
3D-aCortex: An Ultra-Compact Energy-Efficient Neurocomputing Platform Based on Commercial 3D-NAND Flash Memories
复制标题
DOI：
10.1088/2634-4386/ac0775
复制
发表时间：
2019-08
期刊：
影响因子：
--
通讯作者：
Mohammad Bavandpour;Shubham Sahay;M. Mahmoodi;D. Strukov
中科院分区：
文献类型：
--
作者：
Mohammad Bavandpour;Shubham Sahay;M. Mahmoodi;D. Strukov
本文的第一个贡献是基于现有的3D-NAND闪存块开发了极其密集、节能的混合信号矢量矩阵乘法（VMM）电路，而无需对其进行任何修改。这种兼容性是使用时域编码VMM设计实现的。我们的详细模拟表明，例如，采用55纳米技术节点设计的64层栅极全通面型3D-NAND存储块，200元矢量的5位VMM可以提供前所未有的0.14 um2/byte的面积效率和~10 fJ/Op的能量效率，包括输入/输出和其他外围电路开销。我们的第二个主要贡献是3D-aCortex的开发，这是一种多用途的神经形态推理处理器，利用提出的3D-VMM模块作为其核心处理单元。我们在电路和系统层面对这种处理器进行了严格的性能模拟，考虑到非理想情况，如漏极诱导的阻挡降低、电容耦合、电荷注入、寄生、工艺变化和噪声。我们对3D-aCortex进行了几次最先进的神经形态网络基准测试，结果表明，它可以提供创纪录的4.34 MB/mm2的存储效率，70.43 TOps/J的峰值能量效率，以及高达10.66 TOps/s的计算吞吐量。通过积极共享VMM外围电路，存储效率可以进一步提高7倍，但代价是能量效率和吞吐量略有下降。
The first contribution of this paper is the development of extremely dense, energy-efficient mixed-signal vector-by-matrix-multiplication (VMM) circuits based on the existing 3D-NAND flash memory blocks, without any need for their modification. Such compatibility is achieved using time-domain-encoded VMM design. Our detailed simulations have shown that, for example, the 5-bit VMM of 200-element vectors, using the commercially available 64-layer gate-all-around macaroni-type 3D-NAND memory blocks designed in the 55-nm technology node, may provide an unprecedented area efficiency of 0.14 um2/byte and energy efficiency of ~10 fJ/Op, including the input/output and other peripheral circuitry overheads. Our second major contribution is the development of 3D-aCortex, a multi-purpose neuromorphic inference processor that utilizes the proposed 3D-VMM blocks as its core processing units. We have performed rigorous performance simulations of such a processor on both circuit and system levels, taking into account non-idealities such as drain-induced barrier lowering, capacitive coupling, charge injection, parasitics, process variations, and noise. Our modeling of the 3D-aCortex performing several state-of-the-art neuromorphic-network benchmarks has shown that it may provide the record-breaking storage efficiency of 4.34 MB/mm2, the peak energy efficiency of 70.43 TOps/J, and the computational throughput up to 10.66 TOps/s. The storage efficiency can be further improved seven-fold by aggressively sharing VMM peripheral circuits at the cost of slight decrease in energy efficiency and throughput.