Abstract
Hardware-accelerated cloud computing systems based on FPGA chips (FPGA cloud) or ASIC chips (ASIC cloud) have emerged as a new technology trend for power-efficient acceleration of various software applications. However, the operating systems and hypervisors currently used in cloud computing will lead to power, performance, and scalability problems in an exascale cloud computing environment. Consequently, the present study proposes a parallel hardware hypervisor system that is implemented entirely in special-purpose hardware, and that virtualizes application-specific multi-chip supercomputers, to enable virtual supercomputers to share available FPGA and ASIC resources in a cloud system. In addition to the virtualization of multi-chip supercomputers, the system’s other unique features include simultaneous migration of multiple communicating hardware tasks, and on-demand increase or decrease of hardware resources allocated to a virtual supercomputer. Partitioning the flat hardware design of the proposed hypervisor system into multiple partitions and applying the chip unioning technique to its partitions, the present study introduces a cloud building block chip that can be used to create FPGA or ASIC clouds as well. Single-chip and multi-chip verification studies have been done to verify the functional correctness of the hypervisor system, which consumes only a fraction of (10%) hardware resources.
- [1] . 2019. Cloud-based FPGA custom computing machines for streaming applications. IEEE Access 7 (2019), 38009–38019. https://doi.org/10.1109/ACCESS.2019.2906910Google Scholar
Cross Ref
- [2] . 2017. Virtualized execution runtime for FPGA accelerators in the cloud. IEEE Access 5 (2017), 1900–1910. https://doi.org/10.1109/ACCESS.2017.2661582Google Scholar
Cross Ref
- [3] . 2018. A manifesto for future generation cloud computing: Research directions for the next decade. Comput. Surv. 51, 5 (2018). Google Scholar
Digital Library
- [4] . 2014. FPGAs in the cloud: Booting virtualized hardware accelerators with OpenStack. In Proceedings of the 22nd International Symposium on Field Programmable Custom Computing Machines. 109–116. https://doi.org/10.1109/FCCM.2014.42 Google Scholar
Digital Library
- [5] . 2016. A cloud-scale acceleration architecture. In Proceedings of the International Symposium on Microarchitecture (MICRO’16). 1–13. https://doi.org/10.1109/MM.2017.51 Google Scholar
Digital Library
- [6] . 2014. Enabling FPGAs in the cloud. In Proceedings of the 11th ACM Conference on Computing Frontiers. ACM Press, New York, NY, 1–10. https://doi.org/10.1145/2597917.2597929 Google Scholar
Digital Library
- [7] . 2021. A parallel hardware hypervisor for hardware accelerated cloud computingAccepted for Publication in Concurrency and Computation: Practice and Experience. http://doi.org/10.1002/cpe.6554.Google Scholar
- [8] . 2020. Getting Started Guide for Linux. The Linux Foundation Projects. Retrieved May 31, 2021 from https://www.dpdk.org.Google Scholar
- [9] . 2016. Parallel hardware hypervisor for virtualizing application-specific supercomputers.
US Patent 9,465,632, application date 4 February 2012, grant date 11 October 2016. Google Scholar - [10] . 2015. Method and system for converting a single-threaded software program into an application-specific supercomputer.
US Patent 8.966,457, application date 15 November 2011, grant date 24 February 2015. Google Scholar - [11] . 1999. FPGA viruses. In Proceedings of the 9th International Workshop on Field Programmable Logic and Applications. Springer-Verlag, Berlin, 291–300. https://doi.org/10.1007/978-3-540-48302-1_30 Google Scholar
Digital Library
- [12] . 2017. In-datacenter performance analysis of a tensor processing unit. In Proceedings of the 44th International Symposium on Computer Architecture (ISCA’17). ACM Press, New York, NY, 1–12. https://doi.org/10.1145/3079856.3080246 Google Scholar
Digital Library
- [13] . 2016. A survey on reconfigurable accelerators for cloud computing. In Proceedings of the 26th International Conference on Field Programmable Logic and Applications (FPL’16). 1–10. https://doi.org/10.1109/FPL.2016.7577381Google Scholar
Cross Ref
- [14] . 2018. FPGAs and the cloud—An endless tale of virtualization, elasticity and efficiency. Int. J. Adv. Syst. Meas. 11, 3 & 4 (2018), 230–249.Google Scholar
- [15] . 2017. Migration of long-running tasks between reconfigurable resources using virtualization. SIGARCH Comput. Arch. News 44, 4 (2017), 56–61. https://doi.org/10.1145/3039902.3039913 Google Scholar
Digital Library
- [16] . 2014. DOE ASCAC subcommittee report: Top ten exascale research challenges.
Technical Report . U.S. Department of Energy. Retrieved May 31, 2021 from https://www.osti.gov/biblio/1222713-doe-advanced-scientific-computing-advisory-subcommittee-ascac-report-top-ten-exascale-research-challenges.Google Scholar - [17] . 2016. ASIC clouds: Specializing the datacenter. In Proceedings of the 43rd Annual International Symposium on Computer Architecture (ISCA’16). 178–190. https://doi.org/10.1109/ISCA.2016.25 Google Scholar
Digital Library
- [18] 2004. Run-time support for heterogeneous multitasking on reconfigurable SoCs. Integration 38, 1 (2004), 107–130. https://doi.org/10.1016/j.vlsi.2004.03.002 Google Scholar
Digital Library
- [19] . 2016. A survey and evaluation of FPGA high-level synthesis tools. IEEE Trans. Comput.-Aid. Des. Integr. Circ. Syst. 35, 10 (2016), 1591–1604. https://doi.org/10.1109/TCAD.2015.2513673 Google Scholar
Digital Library
- [20] . 2014. A reconfigurable fabric for accelerating large-scale datacenter services. In Proceedings of the 41st International Symposium on Computer Architecture (ISCA’14). IEEE Press, 14–18. https://doi.org/10.1109/ISCA.2014.6853195 Google Scholar
Digital Library
- [21] . 2015. Exascale computing and big data: The next frontier. Commun. ACM 58, 7 (2015), 56–68. Google Scholar
Digital Library
- [22] . 2019. System architecture for network-attached FPGAs in the cloud using partial reconfiguration. In Proceedings of the 29th International Conference on Field Programmable Logic and Applications. 293–300. https://doi.org/10.1109/FPL.2019.00054Google Scholar
Cross Ref
- [23] . 2020. Amazon Web Services (AWS) Elastic Compute Cloud (EC2) F1 instances. Retrieved May 31, 2021 from https://aws.amazon.com/ec2/instance-types/f1.Google Scholar
- [24] . 2020. User Guide for Linux Instances. Retrieved May 31, 2021 from https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/placement-groups.html.Google Scholar
- [25] . 2020. Virtual Ethernet Application Guide. Retrieved May 31, 2021 from https://github.com/aws/aws-fpga/blob/master/sdk/apps/virtual-ethernet/doc/Virtual_Ethernet_Application_Guide.md.Google Scholar
- [26] . 2019. From FPGA to support cloud to cloud of FPGA: State of the art. Int. J. Reconfig. Comput. (2019), 17 pages. https://doi.org/10.1155/2019/8085461Google Scholar
- [27] . 2020. Verilator Manual. Retrieved May 31, 2021 from https://www.veripool.org.Google Scholar
- [28] . 2017. Enabling flexible network FPGA clusters in a heterogeneous cloud data center. In Proceedings of the ACM/SIGDA International Symposium on Field-Programmable Gate Arrays. ACM Press, New York, NY, 237–246. https://doi.org/10.1145/3020078.3021742 Google Scholar
Digital Library
- [29] . 2020. TOP500 Supercomputer List. Retrieved May 31, 2021 from https://www.top500.org/lists/top500/2020/11.Google Scholar
- [30] . 2018. A survey on FPGA virtualization. In Proceedings of the International Conference on Field-Programmable Logic and Applications. 131–138. https://doi.org/10.1109/FPL.2018.00031Google Scholar
Cross Ref
- [31] . 2015. Enabling FPGAs in hyperscale data centers. In Proceedings of the IEEE 12th International Conference on Ubiquitous Intelligence and Computing and the IEEE 12th International Conference on Autonomic and Trusted Computing, and the IEEE 15th International Conference on Scalable Computing and Communications and Its Associated Workshops (UIC-ATC-ScalCom’15). 1078–1086. https://doi.org/10.1109/UIC-ATC-ScalCom-CBDCom-IoP.2015.199Google Scholar
- [32] . 2016. Network-attached FPGAs for data center applications. In Proceedings of the International Conference on Field-Programmable Technology (FPT’16). 36–43. https://doi.org/10.1109/FPT.2016.7929186Google Scholar
Cross Ref
- [33] . 2020. Dynamic Function Exchange Controller: PG374 (v1.0). Retrieved May 31, 2021 from https://www.xilinx.com/support/documentation/ip_documentation/dfx_controller/v1_0/pg374-dfx-controller.pdf.Google Scholar
- [34] . 2017. The Feniks FPGA operating system for cloud computing. In Proceedings of the 8th Asia-Pacific Workshop on Systems. ACM Press, New York, NY, 1–7. https://doi.org/10.1145/3124680.3124743 Google Scholar
Digital Library
- [35] . 2018. FPGA-Based remote power side-channel attacks. In Proceedings of the IEEE Symposium on Security and Privacy (SP’18). 229–244. https://doi.org/10.1109/SP.2018.00049Google Scholar
Cross Ref
Index Terms
Cloud Building Block Chip for Creating FPGA and ASIC Clouds
Recommendations
ASIC clouds: specializing the datacenter
ISCA'16GPU and FPGA-based clouds have already demonstrated the promise of accelerating computing-intensive workloads with greatly improved power and performance.
In this paper, we examine the design of ASIC Clouds, which are purpose-built datacenters comprised ...
ASIC clouds: specializing the datacenter
ISCA '16: Proceedings of the 43rd International Symposium on Computer ArchitectureGPU and FPGA-based clouds have already demonstrated the promise of accelerating computing-intensive workloads with greatly improved power and performance.
In this paper, we examine the design of ASIC Clouds, which are purpose-built datacenters comprised ...
ASIC clouds: specializing the datacenter for planet-scale applications
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 ...






Comments