论文标题
Braintta：35 FJ/OP编译器可编程的混合精液运输触发的NN SOC
BrainTTA: A 35 fJ/op Compiler Programmable Mixed-Precision Transport-Triggered NN SoC
论文作者
论文摘要
最近，由于其在很大程度上降低每次推断的能源成本的能力，因此使用低至1位的操作数宽度的极高量化深度神经网络（DNN）推断的加速器已获得流行。在本文中，提出了具有混合精确支持的灵活SOC。与固定数据加速器的当前趋势相反，该体系结构利用了基于运输触发的体系结构（TTA）的灵活数据路径。该体系结构是使用C的完全编程的。加速器的峰值能效率为35/67/405 FJ/OP（二进制，三元和8位精度），吞吐量为614/307/77 GOPS，这是用于可编程架构的前所未有的。
Recently, accelerators for extremely quantized deep neural network (DNN) inference with operand widths as low as 1-bit have gained popularity due to their ability to largely cut down energy cost per inference. In this paper, a flexible SoC with mixed-precision support is presented. Contrary to the current trend of fixed-datapath accelerators, this architecture makes use of a flexible datapath based on a Transport-Triggered Architecture (TTA). The architecture is fully programmable using C. The accelerator has a peak energy efficiency of 35/67/405 fJ/op (binary, ternary, and 8-bit precision) and a throughput of 614/307/77 GOPS, which is unprecedented for a programmable architecture.
