MaxTracker: Continuously Tracking the Maximum Computation Progress for Energy Harvesting ReRAM-based CNN Accelerators
MaxTracker: Continuously Tracking the Maximum Computation Progress for Energy Harvesting ReRAM-based CNN Accelerators
复制标题
MaxTracker：持续跟踪基于 ReRAM 的能量收集 CNN 加速器的最大计算进度
DOI：
10.1145/3477009
复制
发表时间：
2021-09
影响因子：
2
通讯作者：
Vijaykrishnan Narayanan
中科院分区：
文献类型：
--
作者：
Keni Qiu;Nicholas Jao;Kunyu Zhou;Yongpan Liu;Jack Sampson;Mahmut Taylan K;emir;Vijaykrishnan Narayanan
在许多物联网场景中，越来越多地将推理任务（如CNN）卸载到边缘设备是一种持续的趋势。由于能量收集是一种有吸引力的物联网电源，最近基于ReRAM的CNN加速器被设计用于收集能量的操作。当解决所收集的能量的不稳定性问题时，现有的优化技术通常假设负载是固定的，忽略了输入功率、计算负载和电路效率之间的密切相互作用，或者在没有中间能量存储的简单收集架构下调整动态负载以匹配即时输入功率。针对配备能量存储和能量输送模块的更高效的收集架构，本文首次针对基于ReRAM的能量收集加速器的整个系统的端到端效率。首先，我们对ReRAM负载功率、DC-DC转换器效率和电源故障开销之间的关系进行建模。然后，提出了一种最大计算进度跟踪方案（MaxTracker），通过调整基于ReRAM的加速器的负载功率来实现整个系统的联合优化。具体而言，MaxTracker可适应连续和间歇计算方案，并根据收获场景提供动态ReRAM负载。我们评估MaxTracker在四个输入功率的情况下，实验结果显示平均加速比为38.4%/40.3%（高达51.3%/84.4%），在一个完整的激活计划（与能量存储）和数量级的加速比最近提出的（能量存储）ResiRCA技术。此外，我们还探索MaxTracker与Capybara可重构电容器方法相结合，以提供更灵活的调谐器，从而进一步提高系统性能。
There is an ongoing trend to increasingly offload inference tasks, such as CNNs, to edge devices in many IoT scenarios. As energy harvesting is an attractive IoT power source, recent ReRAM-based CNN accelerators have been designed for operation on harvested energy. When addressing the instability problems of harvested energy, prior optimization techniques often assume that the load is fixed, overlooking the close interactions among input power, computational load, and circuit efficiency, or adapt the dynamic load to match the just-in-time incoming power under a simple harvesting architecture with no intermediate energy storage. Targeting a more efficient harvesting architecture equipped with both energy storage and energy delivery modules, this paper is the first effort to target whole system, end-to-end efficiency for an energy harvesting ReRAM-based accelerator. First, we model the relationships among ReRAM load power, DC-DC converter efficiency, and power failure overhead. Then, a maximum computation progress tracking scheme (MaxTracker) is proposed to achieve a joint optimization of the whole system by tuning the load power of the ReRAM-based accelerator. Specifically, MaxTracker accommodates both continuous and intermittent computing schemes and provides dynamic ReRAM load according to harvesting scenarios. We evaluate MaxTracker over four input power scenarios, and the experimental results show average speedups of 38.4%/40.3% (up to 51.3%/84.4%), over a full activation scheme (with energy storage) and order-of-magnitude speedups over the recently proposed (energy storage-less) ResiRCA technique. Furthermore, we also explore MaxTracker in combination with the Capybara reconfigurable capacitor approach to offer more flexible tuners and thus further boost the system performance.
登录
查看更多内容
DOI：
10.1145/3373376.3378473
发表时间：
2020-03
期刊：
Proceedings of the Twenty-Fifth International Conference on Architectural Support for Programming Languages and Operating Systems
影响因子：
--
作者：
Bradley Denby;Brandon Lucia
通讯作者：
Bradley Denby;Brandon Lucia
DOI：
10.1109/hpca47549.2020.00034
发表时间：
2020-02
期刊：
2020 IEEE International Symposium on High Performance Computer Architecture (HPCA)
影响因子：
--
作者：
Keni Qiu;N. Jao;Mengying Zhao;Cyan Subhra Mishra;Gulsum Gudukbay;Sethu Jose;Jack Sampson;M. Kandemir
通讯作者：
Keni Qiu;N. Jao;Mengying Zhao;Cyan Subhra Mishra;Gulsum Gudukbay;Sethu Jose;Jack Sampson;M. Kandemir
DOI：
10.1109/iccad.2015.7372634
发表时间：
2015-11
期刊：
2015 IEEE/ACM International Conference on Computer-Aided Design (ICCAD)
影响因子：
--
作者：
Kaisheng Ma;Xueqing Li;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
通讯作者：
Kaisheng Ma;Xueqing Li;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
DOI：
10.1109/aspdac.2017.7858402
发表时间：
2017
期刊：
2017 22nd Asia and South Pacific Design Automation Conference (ASP-DAC)
影响因子：
--
作者：
Kaisheng Ma;Xueqing Li;S. Srinivasa;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
通讯作者：
Kaisheng Ma;Xueqing Li;S. Srinivasa;Yongpan Liu;Jack Sampson;Yuan Xie;N. Vijaykrishnan
DOI：
10.1145/3297858.3304011
发表时间：
2018-09
期刊：
Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Systems
影响因子：
--
作者：
Graham Gobieski;Nathan Beckmann;Brandon Lucia
通讯作者：
Graham Gobieski;Nathan Beckmann;Brandon Lucia