Lin-Analyzer: A High-level Performance Analysis Tool for FPGA-based Accelerators

被引:69
|
作者
Zhong, Guanwen [1 ]
Prakash, Alok [1 ]
Liang, Yun [2 ]
Mitra, Tulika [1 ]
Niar, Smail [3 ]
机构
[1] Natl Univ Singapore, Sch Comp, Singapore, Singapore
[2] Peking Univ, Sch EECS, Ctr Energy Efficient Comp & Applicat, Beijing, Peoples R China
[3] Univ Valenciennes, LAMIH, Valenciennes, France
关键词
D O I
10.1145/2897937.2898040
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
The increasing complexity of FPGA-based accelerators, coupled with time-to-market pressure, makes high-level synthesis (HLS) an attractive solution to improve designer productivity by abstracting the programming effort above register-transfer level (RTL). HLS offers various architectural design options with different trade-offs via pragmas (loop unrolling, loop pipelining, array partitioning). However, non-negligible HLS runtime renders manual or automated HLS-based exhaustive architectural exploration practically infeasible. To address this challenge, we present Lin-Analyzer, a high-level accurate performance analysis tool that enables rapid design space exploration with various pragmas for FPGA-based accelerators without requiring RTL implementations.
引用
收藏
页数:6
相关论文
共 50 条
  • [41] Fast Design Exploration for Performance, Power and Accuracy Tradeoffs in FPGA-Based Accelerators
    Ulusel, Onur
    Nepal, Kumud
    Bahar, R. Iris
    Reda, Sherief
    ACM TRANSACTIONS ON RECONFIGURABLE TECHNOLOGY AND SYSTEMS, 2014, 7 (01)
  • [42] High performance FPGA-based image correlation
    Almudena Lindoso
    Luis Entrena
    Journal of Real-Time Image Processing, 2007, 2 : 223 - 233
  • [43] FPGA-based spectrum analyzer with high area efficiency by Goertzel algorithm
    Lin, Min-Chuan
    Tsai, Guo-Ruey
    Tu, Yung-Chin
    Chang, Tai-Hsiung
    Lin, Ching-Hui
    CISP 2008: FIRST INTERNATIONAL CONGRESS ON IMAGE AND SIGNAL PROCESSING, VOL 1, PROCEEDINGS, 2008, : 157 - 159
  • [44] Build Fast, Trade Fast: FPGA-based High-Frequency Trading using High-Level Synthesis
    Boutros, Andrew
    Grady, Brett
    Abbas, Mustafa
    Chow, Paul
    2017 INTERNATIONAL CONFERENCE ON RECONFIGURABLE COMPUTING AND FPGAS (RECONFIG), 2017,
  • [45] FPGA acceleration analysis of LibSVM predictors based on high-level synthesis
    Lucas Leiva
    Martín Vázquez
    Jordina Torrents-Barrena
    The Journal of Supercomputing, 2022, 78 : 14137 - 14163
  • [46] HLScope: High-Level Performance Debugging for FPGA Designs
    Choi, Young-Kyu
    Cong, Jason
    2017 IEEE 25TH ANNUAL INTERNATIONAL SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES (FCCM 2017), 2017, : 125 - 128
  • [47] FPGA acceleration analysis of LibSVM predictors based on high-level synthesis
    Leiva, Lucas
    Vazquez, Martin
    Torrents-Barrena, Jordina
    JOURNAL OF SUPERCOMPUTING, 2022, 78 (12): : 14137 - 14163
  • [48] High throughput edit distance computation on FPGA-based accelerators using HLS
    Schifano, Sebastiano Fabio
    Reggiani, Marco
    Calore, Enrico
    Micheloni, Rino
    Marelli, Alessia
    Zambelli, Cristian
    FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE, 2025, 164
  • [49] FPGA-Based Evaluation and Implementation of an Automotive RADAR Signal Processing System using High-Level Synthesis
    Luthra, Siddhant
    Khalid, Mohammed A. S.
    Oninda, Mohammad Abdul Moin
    2020 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING (CCECE), 2020,
  • [50] Implementation of an FPGA-Based 3D Shape Measurement System Using High-Level Synthesis
    Kim, Tae-Hyeon
    Lee, Hyunki
    Ok, Seung-Ho
    ELECTRONICS, 2024, 13 (16)