A Sorting Library for FPGA Implementation in OpenCL Programming

A Sorting Library for FPGA Implementation in OpenCL Programming
复制标题

OpenCL 编程中用于 FPGA 实现的排序库

DOI:
10.1145/3468044.3468054
复制
发表时间:
2021
期刊:
Proceedings of the 11th International Symposium on Highly Efficient Accelerators and Reconfigurable Technologies (HEART '21)
影响因子:
--
通讯作者:
Amagasa Toshiyuki
Amagasa Toshiyuki
中科院分区:
--
文献类型:
--
作者:
Kobayashi Ryohei;Miura Kento;Fujita Norihisa;Boku Taisuke;Amagasa Toshiyuki

文献摘要

参考文献

被引文献

相似文献

在本研究中,我们关注数据排序,这是一个基本的算术运算,我们提出了一个排序库,可以与OpenCL编程模型一起用于现场可编程门阵列(fpga)。我们的排序库是通过组合三种硬件排序算法构建的。与为fpga的OpenCL编程模型重构的合并排序相比,它消耗的总硬件资源是前者的两倍多。然而,它的工作频率比基线高1.09倍,其分拣吞吐量比基线高3个数量级。
In this study, we focus on data sorting, which is a basic arithmetic operation, and we present a sorting library that can be used with the OpenCL programming model for field-programmable gate arrays (FPGAs). Our sorting library is built by combining three hardware sorting algorithms. It consumes more than twice the overall hardware resources compared to the merge sort restructured for the OpenCL programming model for FPGAs. However, its operating frequency is 1.09x higher and its sorting throughput is three orders of magnitude greater than the baseline.
非常庞大的硬件合并排序器
DOI: 10.1109/fpt.2018.00023
发表时间: 2018
期刊: 2018 International Conference on Field-Programmable Technology (FPT)
影响因子: --
作者:
M. Saitoh;Kenji Kise
通讯作者: Kenji Kise
Cannon 矩阵乘法算法在 Intel Stratix 10 FPGA 上的 OpenCL 实现
DOI: 10.1109/icfpt47387.2019.00020
发表时间: 2019
期刊: 2019 International Conference on Field-Programmable Technology (ICFPT)
影响因子: --
作者:
P. Gorlani;T. Kenter;C. Plessl
通讯作者: C. Plessl
FPGA 上经济高效且可扩展的合并排序树
DOI: 10.1109/candar.2016.0023
发表时间: 2016
期刊: 2016 Fourth International Symposium on Computing and Networking (CANDAR)
影响因子: --
作者:
T. Usui;Thiem Van Chu;Kenji Kise
通讯作者: Kenji Kise
无反馈数据路径的高性能且经济高效的硬件合并排序器
DOI: 10.1109/fccm.2018.00038
发表时间: 2018
期刊: 2018 IEEE 26th Annual International Symposium on Field-Programmable Custom Computing Machines (FCCM)
影响因子: --
作者:
M. Saitoh;E. Elsayed;Thiem Van Chu;Susumu Mashimo;Kenji Kise
通讯作者: Kenji Kise