期刊文献+
共找到2篇文章
< 1 >
每页显示 20 50 100
基于GPU的自适应邻域压缩禁忌搜索的软硬件划分算法 被引量:2
1
作者 侯能 何发智 +1 位作者 周毅 陈壹林 《中国科学:信息科学》 CSCD 北大核心 2018年第8期978-999,共22页
软硬件划分是软硬件协同设计中的关键步骤,决定了哪些功能由硬件执行,哪些功能由软件执行.软硬件划分属于NP难问题.现代嵌入式系统的复杂性提高,造成软硬件划分问题规模变大,需要采用启发式方法求解.禁忌搜索是求解软硬件划分的有效方法... 软硬件划分是软硬件协同设计中的关键步骤,决定了哪些功能由硬件执行,哪些功能由软件执行.软硬件划分属于NP难问题.现代嵌入式系统的复杂性提高,造成软硬件划分问题规模变大,需要采用启发式方法求解.禁忌搜索是求解软硬件划分的有效方法.然而,算法的求解过程非常耗时.已有的禁忌搜索求解软硬件划分是串行实现,要折中考虑解的质量和算法的运行时间.这种考虑牺牲了解的质量.本文提出基于GPU的自适应邻域压缩(compacting neighborhood)禁忌搜索的软硬件划分算法.首先,提出自适应策略.自适应策略能够增强算法的搜索集中性,提高解的质量.GPU的大规模并行特性可以降低算法的运行时间.其次,为了使算法在GPU上高效地执行,提出基于GPU的任务图表达、线程–候选解映射、数据布局和访存等一系列优化策略.最后,实验采用统一设备架构(CUDA)编程,并根据相关基准任务图,通过不同的计算–通信比和实时约束条件,对提出的方法进行验证.结果表明,本文方法的解质量要优于已有的方法.对比将自适应邻域压缩禁忌搜索自然移植到GPU后的运行时间,提出的GPU上的执行优化策略明显地降低了求解时间.另外,在更大规模的软硬件划分上验证了基于GPU的方法在时间上的优势. 展开更多
关键词 软硬件协同设计 启发式方法 图形处理单元 禁忌搜索 自适应算法
原文传递
An efficient GPU-based parallel tabu search algorithm for hardware/software co-design 被引量:5
2
作者 neng hou Fazhi He +1 位作者 Yi Zhou Yilin Chen 《Frontiers of Computer Science》 SCIE EI CSCD 2020年第5期135-152,共18页
Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel... Hardware/software partitioning is an essential step in hardware/software co-design.For large size problems,it is difficult to consider both solution quality and time.This paper presents an efficient GPU-based parallel tabu search algorithm(GPTS)for HW/SW partitioning.A single GPU kernel of compacting neighborhood is proposed to reduce the amount of GPU global memory accesses theoretically.A kernel fusion strategy is further proposed to reduce the amount of GPU global memory accesses of GPTS.To further minimize the transfer overhead of GPTS between CPU and GPU,an optimized transfer strategy for GPU-based tabu evaluation is proposed,which considers that all the candidates do not satisfy the given constraint.Experiments show that GPTS outperforms state-of-the-art work of tabu search and is competitive with other methods for HW/SW partitioning.The proposed parallelization is significant when considering the ordinary GPU platform. 展开更多
关键词 hardware/software co-design hardware/software partitioning graphics processing unit GPU-based parallel tabu search single kernel implementation kernel fusion strategy optimized transfer strategy
原文传递
上一页 1 下一页 到第
使用帮助 返回顶部