Accelerating parallel data processing using optically tightly coupled FPGAs
- 31 January 2022
- journal article
- research article
- Published by Optica Publishing Group in Journal of Optical Communications and Networking
- Vol. 14 (2) , A166-A179
Abstract
A cutting-edge field programmable gate array (FPGA) card can be equipped with high-bandwidth inputs and outputs by high-density optical integration, e.g., onboard Si-photonics transceivers or co-packaged optics. It is possible to implement highly parallel data processing by using tightly coupled FPGAs. We previously proposed a lightweight, fully connected inter-FPGA network called OPTWEB for efficient collective communications. OPTWEB discards the traditional packet communication mechanism and introduces dedicated memory processing to minimize communication overhead. In this paper, we provide the design guidelines for a parallel data application on FPGAs connected by OPTWEB. We then present a generalized diameter-two hypercube network topology for connecting multiple FPGAs, which enables larger applications. In the guidelines, data to be exchanged should be directly processed by the dedicated memory on each FPGA, and parallelism should be implemented to match the collective communications provided by OPTWEB. We illustrate two case studies, one on parallel counting sort and the other on sharing averaged parameters, on eight custom Stratix10 MX2100 FPGA cards with 800 Gbps network bandwidth. The parallel counting sort operates up to 5.3 times faster than a comparable CPU cluster with the conventional InfiniBand network, and with sharing averaged parameters, up to 250 times faster operation is achieved. The two applications utilize a total of 80.1% and 60.6% of the adaptive logic modules of the FPGA, respectively.Keywords
Funding Information
- New Energy and Industrial Technology Development Organization (JPNP13004)
This publication has 13 references indexed in Scilit:
- Wavelength-routing interconnect "Optical Hub" for parallel computing systems2020
- BlueConnect: Decomposing all-reduce for deep learning on heterogeneous network hierarchyIBM Journal of Research and Development, 2019
- Toward FPGA-Based HPC: Advancing Interconnect TechnologiesIEEE Micro, 2019
- In-memory database acceleration on FPGAs: a surveyThe VLDB Journal, 2019
- Evaluating Modern GPU Interconnect: PCIe, NVLink, NV-SLI, NVSwitch and GPUDirectIEEE Transactions on Parallel and Distributed Systems, 2019
- Darwin: A Genomics CoprocessorIEEE Micro, 2019
- Fingertip-Size Optical Module, “Optical I/O Core”, and Its Application in FPGAIEICE Transactions on Electronics, 2019
- Novo-G#: Large-scale reconfigurable computing with direct and programmable interconnects2016
- A Reconfigurable Fabric for Accelerating Large-Scale Datacenter ServicesIEEE Micro, 2015
- Generalized Hypercube and Hyperbus Structures for a Computer NetworkIEEE Transactions on Computers, 1984