论文标题
雷神 - 具有7.29g tsop $^2 $/mm $^2 $ JS能量通量效率的神经形态处理器
THOR -- A Neuromorphic Processor with 7.29G TSOP$^2$/mm$^2$Js Energy-Throughput Efficiency
论文作者
论文摘要
使用具有生物学启发的尖峰神经网络（SNN）的神经形态计算是满足边缘计算设备所需的能量通量（ET）效率的有前途的解决方案。已经提出，在模拟模拟/混合信号域中模仿SNN的神经形态硬件体系结构已提出比全数字架构更高的能量效率，但以有限的可扩展性，对噪声，复杂验证和差异差的敏感性为代价。另一方面，最新的数字神经形态体系结构着重于实现高能量效率（焦耳/突触操作（SOP））或吞吐量效率（SOP/秒/区域），从而导致ET效率较差。在这项工作中，我们介绍了Thor，这是一个具有新颖的记忆层次结构和神经元更新体系结构的全数字神经形态处理器，可解决能源消耗和吞吐量瓶颈。我们在28nM FDSOI CMOS技术中实施了Thor，我们的层后结果表明，ET的效率为7.29g $ \ text {tsop}^2/\ text {mm}^2 \ text^2 \ text {js} $在0.9V，400 MHz，400 MHz，代表A 3 x的状态neuromormoromormormoromormormoromormoromormormoromormormoromormoromormoromormoromormormoromormormoromormoromormoromormoromormoromormormoromormoromormoromormoromormoromormoromormormoromormoromor phise
Neuromorphic computing using biologically inspired Spiking Neural Networks (SNNs) is a promising solution to meet Energy-Throughput (ET) efficiency needed for edge computing devices. Neuromorphic hardware architectures that emulate SNNs in analog/mixed-signal domains have been proposed to achieve order-of-magnitude higher energy efficiency than all-digital architectures, however at the expense of limited scalability, susceptibility to noise, complex verification, and poor flexibility. On the other hand, state-of-the-art digital neuromorphic architectures focus either on achieving high energy efficiency (Joules/synaptic operation (SOP)) or throughput efficiency (SOPs/second/area), resulting in poor ET efficiency. In this work, we present THOR, an all-digital neuromorphic processor with a novel memory hierarchy and neuron update architecture that addresses both energy consumption and throughput bottlenecks. We implemented THOR in 28nm FDSOI CMOS technology and our post-layout results demonstrate an ET efficiency of 7.29G $\text{TSOP}^2/\text{mm}^2\text{Js}$ at 0.9V, 400 MHz, which represents a 3X improvement over state-of-the-art digital neuromorphic processors.
