ASIC clouds
ASIC clouds
复制标题
ASIC 云
DOI：
--
复制
发表时间：
2020
影响因子：
22.7
通讯作者：
D. Richmond
中科院分区：
文献类型：
--
作者：
M. Taylor;Luis Vega;Moein Khazraee;Ikuo Magaki;S. Davidson;D. Richmond
全球规模的应用程序正在推动云的指数级增长，而数据中心专业化是这一趋势的关键推动者。基于 GPU 和 FPGA 的云已经被部署来加速计算密集型工作负载。随着云服务在全球范围内扩展，基于 ASIC 的云是一种自然演变。 ASIC 云是专门构建的数据中心，由大量 ASIC 加速器组成，可优化大型、高容量横向扩展计算的总拥有成本 (TCO)。从表面上看，由于 NRE 高且 ASIC 缺乏灵活性，ASIC 云似乎不太可能实现，但大规模 ASIC 云已经部署在比特币加密货币系统中。本文总结了这些比特币 ASIC 云的经验教训，并将其应用到其他大规模工作负载中，例如 YouTube 式视频转码和深度学习，显示出相对于 CPU 和 GPU 而言更优越的 TCO。它基于加速器特性，通过联合优化 ASIC 架构、DRAM、主板、供电、冷却和工作电压，衍生出帕累托最优 ASIC 云服务器。最后，作者研究了 ASIC NRE 的影响以及何时构建 ASIC 云有意义。
Planet-scale applications are driving the exponential growth of the Cloud, and datacenter specialization is the key enabler of this trend. GPU- and FPGA-based clouds have already been deployed to accelerate compute-intensive workloads. ASIC-based clouds are a natural evolution as cloud services expand across the planet. ASIC Clouds are purpose-built datacenters comprised of large arrays of ASIC accelerators that optimize the total cost of ownership (TCO) of large, high-volume scale-out computations. On the surface, ASIC Clouds may seem improbable due to high NREs and ASIC inflexibility, but large-scale ASIC Clouds have already been deployed for the Bitcoin cryptocurrency system. This paper distills lessons from these Bitcoin ASIC Clouds and applies them to other large scale workloads such as YouTube-style video-transcoding and Deep Learning, showing superior TCO versus CPU and GPU. It derives Pareto-optimal ASIC Cloud servers based on accelerator properties, by jointly optimizing ASIC architecture, DRAM, motherboard, power delivery, cooling, and operating voltage. Finally, the authors examine the impact of ASIC NRE and when it makes sense to build an ASIC Cloud.