OmpSs@FPGA framework for high performance FPGA computing
Authors:
- 2 June 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Computers
- Vol. 70 (00189340) , 1
Abstract
This article presents the new features of the OmpSs@FPGA framework. OmpSs is a data-flow programming model that supports task nesting and dependencies to target asynchronous parallelism and heterogeneity. OmpSs@FPGA is the extension of the programming model addressed specifically to FPGAs. OmpSs environment is built on top of Mercurium source to source compiler and Nanos++ runtime system. To address FPGA specifics Mercurium compiler implements several FPGA related features as local variable caching, wide memory accesses or accelerator replication. In addition, part of the Nanos++ runtime has been ported to hardware. Driven by the compiler this new hardware runtime adds new features to FPGA codes, such as task creation and dependence management, providing both performance increases and ease of programming. To demonstrate these new capabilities, different high performance benchmarks have been evaluated over different FPGA platforms using the OmpSs programming model. The results demonstrate that programs that use the OmpSs programming model achieve very competitive performance with low to moderate porting effort compared to other FPGA implementations.Keywords
Funding Information
- European Unions Horizon 2020 Research and Innovation Programme (754337)
- Generalitat de Catalunya (2017-SGR-1328, 2017-SGR-1414)
- Spanish Government (BES-2016-078046, PID2019-107255GB, SEV2015-0493)
This publication has 15 references indexed in Scilit:
- RapidWright: Enabling Custom Crafted Implementations for FPGAs2018
- OpenMP device offloading to FPGA accelerators2017
- FPGA-based Stream Computing for High-Performance N-Body Simulation using Floating-Point DSP Blocks2017
- Automating the Design of Processor/Accelerator Embedded Systems with LegUp High-Level Synthesis2014
- LegUpACM Transactions on Embedded Computing Systems, 2013
- FPGA code accelerators - the compiler perspective2013
- Compressed sensing and Cholesky decomposition on FPGAs and GPUsParallel Computing, 2012
- OmpSs: A PROPOSAL FOR PROGRAMMING HETEROGENEOUS MULTI-CORE ARCHITECTURESParallel Processing Letters, 2011
- Designing Modular Hardware Accelerators in C with ROCCC 2.02010
- OpenMP extensions for FPGA accelerators2009