Fortran High-Level Synthesis: Reducing the barriers to accelerating HPC codes on FPGAs

被引:0
|
作者
Rodriguez-Canal, Gabriel [1 ]
Brown, Nick [1 ]
Dykes, Tim [2 ]
Jones, Jess [2 ]
Haus, Utz-Uwe [2 ]
机构
[1] Univ Edinburgh, EPCC, Edinburgh, Midlothian, Scotland
[2] Hewlett Packard Enterprise, HPC AI EMEA Res Lab, Spring, TX USA
关键词
FPGAs; Fortran; High Level Synthesis; HPC;
D O I
10.1109/FPL60245.2023.00010
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In recent years the use of FPGAs to accelerate scientific applications has grown, with numerous applications demonstrating the benefit of FPGAs for high performance workloads. However, whilst High Level Synthesis (HLS) has significantly lowered the barrier to entry in programming FPGAs by enabling programmers to use C++, a major challenge is that most often these codes are not originally written in C++. Instead, Fortran is the lingua franca of scientific computing and-so it requires a complex and time consuming initial step to convert into C++ even before considering the FPGA. In this paper we describe work enabling Fortran for AMD Xilinx FPGAs by connecting the LLVM Flang front end to AMD Xilinx's LLVM back end. This enables programmers to use Fortran as a first-class language for programming FPGAs, and as we demonstrate enjoy all the tuning and optimisation opportunities that HLS C++ provides. Furthermore, we demonstrate that certain language features of Fortran make it especially beneficial for programming FPGAs compared to C++. The result of this work is a lowering of the barrier to entry in using FPGAs for scientific computing, enabling programmers to leverage their existing codebase and language of choice on the FPGA directly.
引用
收藏
页码:10 / 18
页数:9
相关论文
共 50 条
  • [1] High-Level Synthesis-Based Approach for Accelerating Scientific Codes on FPGAs
    Venkatakrishnan, Ramshankar
    Misra, Ashish
    Kindratenko, Volodymyr
    COMPUTING IN SCIENCE & ENGINEERING, 2020, 22 (04) : 104 - 108
  • [2] A Parametrizable High-Level Synthesis Library for Accelerating Neural Networks on FPGAs
    Lester Kalms
    Pedram Amini Rad
    Muhammad Ali
    Arsany Iskander
    Diana Göhringer
    Journal of Signal Processing Systems, 2021, 93 : 513 - 529
  • [3] A Parametrizable High-Level Synthesis Library for Accelerating Neural Networks on FPGAs
    Kalms, Lester
    Rad, Pedram Amini
    Ali, Muhammad
    Iskander, Arsany
    Goehringer, Diana
    JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY, 2021, 93 (05): : 513 - 529
  • [4] Development of Multiobjective High-Level Synthesis for FPGAs
    Reyes Fernandez de Bulnes, Darian
    Maldonado, Yazmin
    Trujillo, Leonardo
    SCIENTIFIC PROGRAMMING, 2020, 2020
  • [5] High-Level Modeling and Synthesis for Embedded FPGAs
    Chen, Xiaolin
    Li, Shuai
    Schleifer, Jochen
    Coenen, Thomas
    Chattopadhyay, Anupam
    Ascheid, Gerd
    Noll, Tobias G.
    DESIGN, AUTOMATION & TEST IN EUROPE, 2013, : 1565 - 1570
  • [6] HIGH-LEVEL SYNTHESIS UNLOCKS POTENTIAL OF FPGAS
    TUCK, B
    COMPUTER DESIGN, 1991, 30 (07): : 50 - &
  • [7] Improving Performance of HPC Kernels on FPGAs Using High-Level Resource Management
    Filgueras, Antonio
    Vidal, Miquel
    Jimenez-Gonzalez, Daniel
    Alvarez, Carlos
    Martorell, Xavier
    2023 IEEE 31ST ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES, FCCM, 2023, : 213 - 213
  • [8] Improved Synthesis of Compressor Trees on FPGAs in High-level Synthesis
    Tu, Le
    Yuan, Yuelai
    Huang, Kan
    Zhang, Xiaoqiang
    Wang, Zixin
    Chen, Dihu
    2017 IEEE 25TH ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2017), 2017, : 25 - 25
  • [9] Challenges Designing for FPGAs Using High-Level Synthesis
    Faber, Clayton J.
    Harris, Steven D.
    Xiao, Zhili
    Chamberlain, Roger D.
    Cabrera, Anthony M.
    2022 IEEE HIGH PERFORMANCE EXTREME COMPUTING VIRTUAL CONFERENCE (HPEC), 2022,
  • [10] SOFF: An OpenCL High-Level Synthesis Framework for FPGAs
    Jo, Gangwon
    Kim, Heehoon
    Lee, Jeesoo
    Lee, Jaejin
    2020 ACM/IEEE 47TH ANNUAL INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE (ISCA 2020), 2020, : 295 - 308