期刊
ACM SIGPLAN NOTICES
卷 50, 期 4, 页码 223-238出版社
ASSOC COMPUTING MACHINERY
DOI: 10.1145/2775054.2694347
关键词
datacenters; warehouse scale computers; emerging workloads; intelligent personal assistants
资金
- ARM
- Defense Advanced Research Projects Agency (DARPA) [HR0011-13-2-000]
- National Science Foundation (NSF) [CCF-SHF-1302682, CNS-CSR-1321047]
As user demand scales for intelligent personal assistants (IPAs) such as Apple's Siri, Google's Google Now, and Microsoft's Cortana, we are approaching the computational limits of current datacenter architectures. It is an open question how future server architectures should evolve to enable this emerging class of applications, and the lack of an open-source IPA workload is an obstacle in addressing this question. In this paper, we present the design of Sirius, an open end-to-end IPA web-service application that accepts queries in the form of voice and images, and responds with natural language. We then use this workload to investigate the implications of four points in the design space of future accelerator-based server architectures spanning traditional CPUs, GPUs, manycore throughput co-processors, and FPGAs. To investigate future server designs for Sirius, we decompose Sirius into a suite of 7 benchmarks (Sirius Suite) comprising the computationally intensive bottlenecks of Sirius. We port Sirius Suite to a spectrum of accelerator platforms and use the performance and power trade-offs across these platforms to perform a total cost of ownership (TCO) analysis of various server design points. In our study, we find that accelerators are critical for the future scalability of IPA services. Our results show that GPU- and FPGA-accelerated servers improve the query latency on average by 10x and 16x. For a given throughput, GPU-and FPGAaccelerated servers can reduce the TCO of datacenters by 2.6x and 1.4x, respectively. [GRAPHICS] .
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据