CUTIE：超越PetaOp/s/W的三元DNN推理加速，能效优于二元
CUTIE: Beyond PetaOp/s/W Ternary DNN Inference Acceleration with Better-than-Binary Energy Efficiency
摘要：
提出了一种用于三值神经网络的3.1 POp/s/W全数字硬件加速器。CUTIE，完全展开的三进制推理引擎，专注于最大限度地减少非计算能量和切换活动，以便最大限度地减少存储（本地或全局）中间结果所花费的动态功率。这是通过以下方式实现的：1）在特征图和滤波器维度中完全展开的数据路径架构，以通过在迭代计算上支持静默并最大化数据重用来减少切换活动，2）瞄准三元神经网络，其与二进制NN相比，允许减少切换活动的稀疏权重，以及3）引入用于滤波器权重的更高稀疏性的优化训练方法，导致开关活动的进一步减少。与最先进的加速器相比，CUTIE实现了更高或相等的准确性，同时将总体核心推理能量成本降低了4.8倍至21倍。
英文摘要：
We present a 3.1 POp/s/W fully digital hardware accelerator for ternary neural networks. CUTIE, the Completely Unrolled Ternary Inference Engine, focuses on minimizing non-computational energy and switching activity so that dynamic power spent on storing (locally or globally) intermediate results is minimized. This is achieved by 1) a data path architecture completely unrolled in the feature map and filter dimensions to reduce switching activity by favoring silencing over iterative computation and maximizing data re-use, 2) targeting ternary neural networks which, in contrast to binary NNs, allow for sparse weights which reduce switching activity, and 3) introducing an optimized training method for higher sparsity of the filter weights, resulting in a further reduction of the switching activity. Compared with state-of-the-art accelerators, CUTIE achieves greater or equal accuracy while decreasing the overall core inference energy cost by a factor of 4.8x-21x.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
