2019 · 31 citations · 21 references
ComputingComputer ScienceHigh-performance ComputingDistributed SystemsMessage PassingReconfigurable ComputingDistributed Memory ParallelismDistributed Memory ProgrammingDistributed Memory SystemsInterconnect ArchitectureInterprocess CommunicationReconfigurable AcceleratorsDistributed MemoryDistributed Memory CommunicationHigh-performance Computing SystemsMessage Passing InterfacePipelined CommunicationReconfigurable Hardware ArchitectureStreaming ComputationStreaming Programming Models
Distributed memory programming is the established paradigm used in high-performance computing (HPC) systems, requiring explicit communication between nodes and devices. When FPGAs are deployed in distributed settings, communication is typically handled either by going through the host machine, sacrificing performance, or by streaming across fixed device-to-device connections, sacrificing flexibility. We present Streaming Message Interface (SMI), a communication model and API that unifies explicit message passing with a hardware-oriented programming model, facilitating minimal-overhead, flexible, and productive inter-FPGA communication. Instead of bulk transmission, messages are streamed across the network during computation, allowing communication to be seamlessly integrated into pipelined designs. We present a high-level synthesis implementation of SMI targeting a dedicated FPGA interconnect, exposing runtime-configurable routing with support for arbitrary network topologies, and implement a set of distributed memory benchmarks. Using SMI, programmers can implement distributed, scalable HPC programs on reconfigurable hardware, without deviating from best practices for hardware design.
21
Serving DNNs in Real Time at Datacenter Scale with Project Brainwave
Eric S. Chung, Jeremy Fowers, Kalin Ovtcharov et al. · IEEE Micro · 2018 · 338 citations
From opencl to high-performance hardware on FPGAS
Tomasz Czajkowski, Utku Aydonat, Dmitry Denisenko et al. · 2012 · 239 citations
Engineering, Computer Science, High-performance Computing +15