When FPGA Meets Cloud: A First Look at Performance

   @ARTICLE {9086121,
       author = {X. Wang and Y. Niu and F. Liu and Z. Xu},
       journal = {IEEE Transactions on Cloud Computing},
       title = {When FPGA Meets Cloud: A First Look at Performance},
       year = {2022},
       volume = {10},
       number = {02},
       issn = {2168-7161},
       pages = {1344-1357},
       abstract = {Cloud service providers promote their new field programmable gate array (FPGA) infrastructure as a service (IaaS) as the new era of cloud product. This FPGA IaaS wraps virtualized compute resources with FPGA boards, e.g., Amazon AWS F1, and reserves acceleration capability for specific applications. Though this acceleration technique sounds promising, questions like real world performance, best-fit scenarios, portability, etc., still need further clarification. In this article, we present one of the first few empirical studies that take a close look at FPGA clouds from the tenants’ perspective. We have conducted measurement studies on Amazon AWS, Alibaba, and Huawei clouds for over one year. The experimental results show that: (1) Tenants experience severe performance-cost imbalance on FPGA IaaS platforms; (2) The inter-communication performance in FPGA clouds is tightly constrained by hardware drivers, e.g., small optimization of DMA drivers for PCIe can harvest significant performance gain; (3) The virtualized FPGA clouds are far from mature, e.g., small-sized jobs can greatly degrade the performance of FPGA clouds due to underutilized PCIe bandwidth. Our study not only provides useful hints to help tenants with FPGA service selection, but also sheds some lights for cloud providers to improve the performance of FPGA clouds.},
       keywords = {field programmable gate arrays;cloud computing;acceleration;performance evaluation;bandwidth;throughput},
       doi = {10.1109/TCC.2020.2992548},
       publisher = {IEEE Computer Society},
       address = {Los Alamitos, CA, USA},
       month = {apr}
   }