HybridOS: Runtime Support for Reconfigurable Accelerators

被引:0
|
作者
Kelm, John H. [1 ]
Lumetta, Steven S. [1 ]
机构
[1] Univ Illinois, Dept Elect & Comp Engn, Urbana, IL 61801 USA
关键词
CPU/Accelerator Architecture; Operating System;
D O I
暂无
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
We present HybridOS, a set of operating system extensions for supporting fine-grained reconfigurable accelerators integrated with general-purpose computing, platforms. HybridOS specifically taracts the application integration, data movement and communication overheads for a CPU/accelerator model when running a commodity operating system. HybridOS provides a simple API for applications and a well-defined hardware interface for reconfigurable accelerators. The goal is to reduce the difficulty in mapping applications into a CPU/accelerator model compared to an unrestrained FPGA platform while achieving whole-application speedups. HybridOS is integrated into a full Linux distribution running on the embedded processor of an FPGA. Application-specific accelerators are implemented in the reconfigurable fabric of the FPGA that are allocated to user applications running on Linux. We have developed and evaluated four methods for accessing the data buffers required by hardware-accelerated applications using our prototype. The results of our work show the feasibility of our system for a case study, JPEG encoding with two accelerators, and an evaluation of HybridOS for varying data movement requirements that can be used as a guide for future applications developers.
引用
收藏
页码:212 / 221
页数:10
相关论文
共 50 条
  • [1] Synthesis of Application Accelerators on Runtime Reconfigurable Hardware
    Alle, Mythri
    Varadarajan, Keshavan
    Reddy, Ramesh
    Joseph, Nimmy
    Fell, Alexander
    Rao, Adarsha
    Nandy, S. K.
    Narayan, Ranjani
    [J]. 2008 INTERNATIONAL CONFERENCE ON APPLICATION-SPECIFIC SYSTEMS, ARCHITECTURES AND PROCESSORS, 2008, : 13 - +
  • [2] Approximate Accelerators: A Case Study using Runtime Reconfigurable Processors
    Lesniak, Fabian
    Harbaum, Tanja
    Becker, Juergen
    [J]. 2023 IEEE 36TH INTERNATIONAL SYSTEM-ON-CHIP CONFERENCE, SOCC, 2023, : 244 - 249
  • [3] Runtime support for reconfigurable real-time embedded systems
    Papp, Z
    [J]. IMTC/2001: PROCEEDINGS OF THE 18TH IEEE INSTRUMENTATION AND MEASUREMENT TECHNOLOGY CONFERENCE, VOLS 1-3: REDISCOVERING MEASUREMENT IN THE AGE OF INFORMATICS, 2001, : 2111 - 2116
  • [4] Runtime Filesystem Support for Reconfigurable FPGA Hardware Processes in BORPH
    So, Hayden Kwok-Hay
    Brodersen, Robert
    [J]. PROCEEDINGS OF THE SIXTEENTH IEEE SYMPOSIUM ON FIELD-PROGRAMMABLE CUSTOM COMPUTING MACHINES, 2008, : 285 - +
  • [5] Runtime reconfigurable routing
    Brebner, G
    Donlin, A
    [J]. PARALLEL AND DISTRIBUTED PROCESSING, 1998, 1388 : 25 - 30
  • [6] Runtime Support for Multiple Offload-Based Programming Models on Clustered Manycore Accelerators
    Capotondi, Alessandro
    Marongiu, Andrea
    Benini, Luca
    [J]. IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING, 2018, 6 (03) : 330 - 342
  • [7] Runtime Behavior Comparison of Modern Accelerators and Coprocessors
    Tarakji, Ayman
    Salscheider, Niels Ole
    [J]. PROCEEDINGS OF 2014 IEEE INTERNATIONAL PARALLEL & DISTRIBUTED PROCESSING SYMPOSIUM WORKSHOPS (IPDPSW), 2014, : 97 - 111
  • [8] Reconfigurable accelerators for combinatorial problems
    Platzner, M
    [J]. COMPUTER, 2000, 33 (04) : 58 - +
  • [9] Elastic Management of Reconfigurable Accelerators
    Grigoras, Paul
    Tottenham, Max
    Niu, Xinyu
    Coutinho, Jose G. F.
    Luk, Wayne
    [J]. 2014 IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS (ISPA), 2014, : 174 - 181
  • [10] Designing a Virtual Runtime for FPGA Accelerators in the Cloud
    Asiatici, Mikhail
    George, Nithin
    Vipin, Kizheppau
    Fahmy, Suhaib A.
    Ienne, Paolo
    [J]. 2016 26TH INTERNATIONAL CONFERENCE ON FIELD PROGRAMMABLE LOGIC AND APPLICATIONS (FPL), 2016,