NAWQ-SR：一种混合精度NPU引擎，用于高效的设备上超分辨率
NAWQ-SR: A Hybrid-Precision NPU Engine for Efficient On-Device Super-Resolution
摘要：
近年来，图像和视频传输系统已经开始集成深度学习超分辨率（SR）方法，利用其前所未有的视觉增强功能，同时减少对网络条件的依赖。然而，在移动设备上部署这些解决方案仍然是一个积极的挑战，因为SR模型在工作负载和内存占用方面要求过高。尽管最近在设备上的SR框架上取得了进展，但现有的系统要么惩罚视觉质量，导致过度的能量消耗，要么对可用资源的利用效率低下。这项工作提出了NAWQ-SR，SR模型的有效的设备上执行的一种新的框架。通过一种新的混合精度量化技术和一种运行时神经图像编解码器，NAWQ-SR利用现代移动NPU的多精度功能，以最大限度地减少延迟，同时满足用户指定的质量约束。此外，NAWQ-SR在运行时间选择性地调整算法精度，以使SR DNN的层具有更广泛的代表性，从而提高视觉质量，超越以前在NPU上可能达到的效果。总的来说，NAWQ-SR实现了7.9倍，3倍和1.91倍的平均速度比最先进的设备上的SR系统，分别使用异构处理器（ARMSR），CPU（SplitSR）和NPU（XLSR）。此外，NAWQ-SR提供了平均3.2倍的加速比和0.39 dB的PSNR高出现状的INT 8 NPU设计，但最重要的是减轻了量化对视觉质量的负面影响，设置了一个新的国家的最先进的可达到的质量的NPU为基础的SR。
英文摘要：
In recent years, image and video delivery systems have begun integrating deep learning super-resolution (SR) approaches, leveraging their unprecedented visual enhancement capabilities while reducing reliance on networking conditions. Nevertheless, deploying these solutions on mobile devices still remains an active challenge as SR models are excessively demanding with respect to workload and memory footprint. Despite recent progress on on-device SR frameworks, existing systems either penalize visual quality, lead to excessive energy consumption or make inefficient use of the available resources. This work presents NAWQ-SR, a novel framework for the efficient on-device execution of SR models. Through a novel hybrid-precision quantization technique and a runtime neural image codec, NAWQ-SR exploits the multi-precision capabilities of modern mobile NPUs in order to minimize latency, while meeting user-specified quality constraints. Moreover, NAWQ-SR selectively adapts the arithmetic precision at run time to equip the SR DNN's layers with wider representational power, improving visual quality beyond what was previously possible on NPUs. Altogether, NAWQ-SR achieves an average speedup of 7.9x, 3x and 1.91x over the state-of-the-art on-device SR systems that use heterogeneous processors (MobiSR), CPU (SplitSR) and NPU (XLSR), respectively. Furthermore, NAWQ-SR delivers an average of 3.2x speedup and 0.39 dB higher PSNR over status-quo INT8 NPU designs, but most importantly mitigates the negative effects of quantization on visual quality, setting a new state-of-the-art in the attainable quality of NPU-based SR.
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。
