国家自然科学基金(61272145)

作品数:5被引量:9H指数:2
导出分析报告
相关作者:文梅沈俊忠肖涛乔寓然杨乾明更多>>
相关机构:国防科学技术大学湖南省消防总队更多>>
相关期刊:《Frontiers of Information Technology & Electronic Engineering》《计算机工程与科学》更多>>
相关主题:OPENCLGPUCNN手机FPGA更多>>
相关领域:自动化与计算机技术更多>>
-

检索结果分析

结果分析中...
条 记 录,以下是1-5
视图:
排序:
CNN卷积计算在移动GPU上的加速研究被引量:5
《计算机工程与科学》2018年第1期34-39,共6页王湘新 时洋 文梅 
国家自然科学基金(61272145)
卷积神经网络(CNN)凭借其优秀的表现正在诸如图像分类、语音识别等领域里扮演着越来越重要的角色,已经有一些研究人员想要将这个深度学习过程复制到手机上。但是,由于CNN巨大的计算量,移植程序的性能一直难以令人满意。为了探讨如何解...
关键词:CNN 手机 移动GPU 快速算法 OPENCL 
Exploiting a depth context model in visual tracking with correlation filter
《Frontiers of Information Technology & Electronic Engineering》2017年第5期667-679,共13页Zhao-yun CHEN Lei LUO Da-fei HUANG Mei WEN Chun-yuan ZHANG 
Project supported by the National Natural Science Foundation of China(Nos.61502509,61402504,and 61272145);the National High-Tech R&D Program(863)of China(No.2012AA012706);the Research Fund for the Doctoral Program of Higher Education of China(No.21024307130004)
Recently correlation filter based trackers have attracted considerable attention for their high computational efficiency. However, they cannot handle occlusion and scale variation well enough. This paper aims at preve...
关键词:Visual tracking Depth context model Correlation filter Region growing 
一种支持优化分块策略的矩阵乘加速器设计被引量:4
《计算机工程与科学》2016年第9期1748-1754,共7页沈俊忠 肖涛 乔寓然 杨乾明 文梅 
国家863计划(2012AA012706);国家自然科学基金(61272145)
在许多应用领域中,大规模浮点矩阵乘法往往是最耗时的计算核心之一。在新兴的应用中经常存在至少有一个维度很小的大规模矩阵,我们把具备这种特性的矩阵称为非均匀矩阵。由于FPGA上用以存储中间结果的片上存储器容量十分有限,计算大规...
关键词:FPGA 非均匀矩阵 矩阵乘法 分块策略 
Improving performance portability for GPU-specific Open CL kernels on multi-core/many-core CPUs by analysis-based transformations
《Frontiers of Information Technology & Electronic Engineering》2015年第11期899-916,共18页Mei WEN Da-fei HUANG Chang-qing XUN Dong CHEN 
Project supported by the National Natural Science Foundation of China(No.61272145);the National High-Tech R&D Program(863)of China(No.2012AA012706)
OpenCL is an open heterogeneous programming framework. Although OpenCL programs are func- tionally portable, they do not provide performance portability, so code transformation often plays an irreplaceable role. When ...
关键词:OpenCL Performance portability Multi-core/many-core CPU Analysis-based transformation 
Efficient fine-grained shared buffer management for multiple OpenCL devices
《Journal of Zhejiang University-Science C(Computers and Electronics)》2013年第11期859-872,共14页Chang-qing XUN Dong CHEN Qiang LAN Chun-yuan ZHANG 
Project supported by the National Natural Science Foundation of China(Nos.61033008,61272145,60903041,and 61103080);the Research Fund for the Doctoral Program of Higher Education of China(No.20104307110002);the Hunan Provincial Innovation Foundation for Postgraduate(No.CX2010B028);the Fund of Innovation in Graduate School of NUDT(Nos.B100603 and B120605),China
OpenCL programming provides full code portability between different hardware platforms,and can serve as a good programming candidate for heterogeneous systems,which typically consist of a host processor and several ac...
关键词:Shared buffer OPENCL Heterogeneous programming Fine grained 
检索报告 对象比较 聚类工具 使用帮助 返回顶部