Kraken: An Efficient Engine with a Uniform Dataflow for Deep Neural Networks

TL;DR

Kraken is a hardware accelerator for deep neural networks that uses a uniform dataflow to optimize data reuse, achieve high performance, and outperform existing ASIC architectures in efficiency and throughput.

Contribution

The paper introduces Kraken, a novel ASIC architecture with a uniform dataflow and simplified PE design for efficient DNN processing across various layers.

Findings

Achieves 537.6 Gops peak performance in 65-nm CMOS

Outperforms state-of-the-art ASICs in Gops/mm2 and Gops/W

Efficiently processes multiple DNN architectures like AlexNet, VGG-16, ResNet-50

Abstract

Deep neural networks (DNNs) have been successfully employed in a multitude of applications with remarkable performance. As such performance is achieved at a significant computational cost, several embedded applications demand fast and efficient hardware accelerators for DNNs. Previously proposed application specific integrated circuit (ASIC) architectures strive to utilize arrays of hundreds of processing elements (PEs) and reduce power-hungry DRAM accesses using multiple dataflows requiring complex PE architectures. These consume significant area and reduce the maximum clock frequency. This paper introduces the Kraken architecture, which optimally processes the convolutional layers, fully-connected layers, and matrix products of any DNN through a hardware-friendly uniform dataflow. This enables maximal data reuse of weights, inputs, and outputs, with a bare-bones PE design and on-the-fly dynamic reconfiguration. Kraken, implemented in 65-nm CMOS technology at 400 MHz, packs 672 PEs in 7.3 mm2, with a peak performance of 537.6 Gops. Kraken processes the convolutional layers of AlexNet, VGG-16, and ResNet-50 at 336.6, 17.5, and 64.2 frames/s, respectively, hence outperforming the state-of-the-art ASIC architectures in terms of overall performance efficiency, DRAM accesses, arithmetic intensity, and throughput, with 5.8x more Gops/mm2 and 1.6x more Gops/W.