行路由PEA廣度貪心調(diào)度映射算法
發(fā)布時間:2019-08-26 10:03
【摘要】:粗粒度可重構(gòu)單元陣列硬件任務的貪心映射是可重構(gòu)計算要解決的核心問題。不同的陣列具有不同的硬件約束條件,針對行路由粗粒度可重構(gòu)單元陣列提出一種廣度貪心映射算法BGMA(Breadth Greedy Mapping Algorithm)。該算法首先從第一個節(jié)點開始依次掃描,如果節(jié)點滿足條件則將其映射到PEA上,當遇到不滿足映射條件的節(jié)點時,該算法將跳過該節(jié)點繼續(xù)尋找滿足約束條件的節(jié)點進行映射,通過與廣度不貪心映射算法BNGMA(Breadth No Greedy Mapping Algorithm)相比較,BGMA的N1平均減少了35.1%(PEA_(6×6))和54.8%(PEA_(8×8)),N2平均減少了35.6%(PEA_(6×6))和54.6%(PEA_(8×8)),C_(CON)平均減少了15.7%(PEA_(6×6))和26.2%(PEA_(8×8)),T_(TOTAL)平均減少了20.2%(PEA_(6×6))和32.1%(PEA_(8×8))。實驗結(jié)果表明了貪心策略在映射算法中的重要性。
[Abstract]:Greedy mapping of hardware tasks of coarse-granularity reconfigurable cell array is the core problem to be solved in reconfigurable computing. Different arrays have different hardware constraints. A breadth greedy mapping algorithm BGMA (Breadth Greedy Mapping Algorithm). Is proposed for row routing coarse granularity reconfigurable cell arrays. The algorithm starts with the first node and maps it to PEA if the node satisfies the condition. When the node does not meet the mapping condition, the algorithm will skip the node and continue to find the node that satisfies the constraint condition to map, by comparing with the breadth non-greedy mapping algorithm BNGMA (Breadth No Greedy Mapping Algorithm). The N1 of BGMA decreased by 35.1% (PEA_ (6 脳 6) and 54.8% (PEA_ (8 脳 8), N2) by 35.6% (PEA_ (6 脳 6) and 54.6% (PEA_ (8 脳 8), C _ (CON) by 15.7% (PEA_ (6 脳 6) and 26.2% (PEA_ (8 脳 8), T _ (TOTAL) by 20.2% (PEA_ (6 脳 6) and 32.1% (PEA_ (8 脳 8). The experimental results show the importance of greedy strategy in mapping algorithm.
【作者單位】: 安徽工程大學計算機與信息學院;
【基金】:安徽省自然科學基金(No.1408085MF124) 安徽省高校省級自然科學基金重點項目(No.kj2015A003) 安徽工程大學國家自然科學預研基金
【分類號】:TP301.6;TP332
[Abstract]:Greedy mapping of hardware tasks of coarse-granularity reconfigurable cell array is the core problem to be solved in reconfigurable computing. Different arrays have different hardware constraints. A breadth greedy mapping algorithm BGMA (Breadth Greedy Mapping Algorithm). Is proposed for row routing coarse granularity reconfigurable cell arrays. The algorithm starts with the first node and maps it to PEA if the node satisfies the condition. When the node does not meet the mapping condition, the algorithm will skip the node and continue to find the node that satisfies the constraint condition to map, by comparing with the breadth non-greedy mapping algorithm BNGMA (Breadth No Greedy Mapping Algorithm). The N1 of BGMA decreased by 35.1% (PEA_ (6 脳 6) and 54.8% (PEA_ (8 脳 8), N2) by 35.6% (PEA_ (6 脳 6) and 54.6% (PEA_ (8 脳 8), C _ (CON) by 15.7% (PEA_ (6 脳 6) and 26.2% (PEA_ (8 脳 8), T _ (TOTAL) by 20.2% (PEA_ (6 脳 6) and 32.1% (PEA_ (8 脳 8). The experimental results show the importance of greedy strategy in mapping algorithm.
【作者單位】: 安徽工程大學計算機與信息學院;
【基金】:安徽省自然科學基金(No.1408085MF124) 安徽省高校省級自然科學基金重點項目(No.kj2015A003) 安徽工程大學國家自然科學預研基金
【分類號】:TP301.6;TP332
【相似文獻】
相關(guān)期刊論文 前10條
1 徐紅波;;空間填充曲線映射算法研究[J];科技信息(科學教研);2007年35期
2 孫培展;袁國良;;改進的隱式空間映射算法的研究[J];電子設(shè)計工程;2012年09期
3 趙文慶;基于性能驅(qū)動的工藝映射算法[J];計算機輔助設(shè)計與圖形學學報;1992年03期
4 黎洪松;;一種改進的自組織特征映射算法[J];中國民航學院學報;2006年01期
5 徐德智;黃利輝;陳建二;;一種新的基于樹分割的本體映射算法[J];小型微型計算機系統(tǒng);2009年11期
6 吳國福;竇強;竇文華;;基于查表的空間填充曲線映射算法[J];國防科技大學學報;2010年05期
7 陳];;心動陣列的自動映射算法[J];計算機研究與發(fā)展;1992年05期
8 黃勝;吳川川;楊曉非;王輝;張衛(wèi);;一種基于臨近原則的虛擬網(wǎng)絡(luò)映射算法[J];電信科學;2013年12期
9 柳玉起;李明林;馮少宏;易國鋒;;基于有限元映射算法的試驗網(wǎng)格顯示及其應用[J];華中科技大學學報(自然科學版);2007年03期
10 王琳珠;單_,
本文編號:2529193
本文鏈接:http://sikaile.net/kejilunwen/jisuanjikexuelunwen/2529193.html
最近更新
教材專著