本文關(guān)鍵詞： 嵌入式系統(tǒng) 流應(yīng)用 DVS 節(jié)能 并行流水　出處：《東北大學(xué)》2013年碩士論文　論文類(lèi)型：學(xué)位論文

【摘要】：嵌入式系統(tǒng)功能越來(lái)越強(qiáng)大,性能也大幅度提高,系統(tǒng)能耗越來(lái)越高,系統(tǒng)散熱問(wèn)題越來(lái)越突出。能耗問(wèn)題已經(jīng)成為制約嵌入式系統(tǒng)發(fā)展的瓶頸。因此,嵌入式系統(tǒng)的節(jié)能調(diào)度已經(jīng)成為嵌入式領(lǐng)域一個(gè)非常重要的研究課題。在多核架構(gòu)中,對(duì)流應(yīng)用采取并行流水調(diào)度已越發(fā)有效并廣泛流行于現(xiàn)有的各類(lèi)系統(tǒng)中,如媒體和圖像處理系統(tǒng)等。流應(yīng)用通常計(jì)算密集,對(duì)能量要求很高,他們運(yùn)行在能源有限的系統(tǒng)中時(shí)會(huì)引發(fā)很多問(wèn)題,因此節(jié)能研究將顯得尤為重要。本文主要研究支持片內(nèi)DVS (Dynamic Voltage Scaling)技術(shù)的多核處理器平臺(tái)中的流應(yīng)用的并行流水調(diào)度節(jié)能問(wèn)題。流應(yīng)用被建模為一個(gè)加權(quán)有向無(wú)環(huán)圖結(jié)構(gòu)的任務(wù)圖。一個(gè)流應(yīng)用通過(guò)靜態(tài)的并行流水調(diào)度策略并以基于流應(yīng)用的有向無(wú)環(huán)圖的結(jié)構(gòu)被分配到多核系統(tǒng)中�，F(xiàn)有的DVS技術(shù)相關(guān)研究大多基于連續(xù)的頻率調(diào)節(jié)模型,然而這并不適用于實(shí)際系統(tǒng)。因此,本文研究的能耗模型為離散頻率調(diào)節(jié)模型。本文的目標(biāo)是在保證吞吐量和延遲等服務(wù)質(zhì)量要求下,確定最優(yōu)化的頻率分配使流應(yīng)用的能耗最小化。本文針對(duì)支持受限縮放技術(shù)的處理器模型,提出了2種不同的啟發(fā)式頻率設(shè)定算法：PPS算法和PPC算法。PPS算法使所有任務(wù)初始頻率設(shè)定為最高值,然后逐漸尋找到任務(wù)降低頻率時(shí)使單位時(shí)間內(nèi)降低的能耗最多的任務(wù),降低其頻率即抻長(zhǎng)其執(zhí)行時(shí)間,直到所有任務(wù)均不能再抻長(zhǎng)為止。PPC算法使所有任務(wù)初始頻率設(shè)定為最低值,然后逐漸增加各任務(wù)頻率即縮短任務(wù)執(zhí)行時(shí)間,至所有任務(wù)滿足吞吐量約束為止,然后逐漸尋找到任務(wù)增加頻率時(shí)使單位時(shí)間內(nèi)增加的能耗最少的任務(wù),縮短其執(zhí)行時(shí)間,直到所有任務(wù)的執(zhí)行時(shí)間滿足延遲的約束為止。然后將其擴(kuò)展到支持任意縮放技術(shù)的處理器模型中,并將并行流水模型合理分段,基于分段并行流水模型提出了2種不同的啟發(fā)式頻率設(shè)定算法：PPSS算法和PPSC算法。通過(guò)模擬實(shí)驗(yàn)表明,本文提出的算法節(jié)能效果顯著,PPSS算法和PPSC算法效果比PPS算法和PPC算法更好。
[Abstract]:The function of embedded system is more and more powerful, the performance of embedded system is greatly improved, the system energy consumption is higher and higher, the problem of system heat dissipation is more and more prominent. The energy consumption problem has become the bottleneck restricting the development of embedded system. Energy saving scheduling of embedded system has become a very important research topic in embedded field. In multi-core architecture, parallel income scheduling has become more and more effective and popular in all kinds of existing systems. Such as media and image processing systems. Stream applications are usually computationally intensive and require a lot of energy. They can cause a lot of problems when they run in systems with limited energy. Therefore, the research on energy saving will be particularly important. This paper mainly studies the problem of parallel income scheduling energy saving in multi-core processor platform supporting DVS dynamic Voltage scaling technology. The flow application is modeled as a weighted directed acyclic. The task diagram of graph structure. A stream application is assigned to multi-core system by static parallel income scheduling strategy and directed acyclic graph structure based on flow application. Most of the existing research on DVS technology is based on continuous frequency regulation model. However, this is not suitable for practical systems. Therefore, the energy consumption model studied in this paper is a discrete frequency regulation model. The purpose of this paper is to ensure the quality of service, such as throughput and latency. Determining optimal frequency allocation minimizes energy consumption for stream applications. This paper proposes two different heuristic frequency setting algorithms: PPS algorithm: PPS algorithm and PPC algorithm. PPS algorithm sets the initial frequency of all tasks to the maximum value, and then gradually finds out the task that reduces the energy consumption per unit time when the task reduces the frequency. Reduce its frequency, that is, stretch its execution time, until all tasks can no longer be stretched. PPC algorithm sets the initial frequency of all tasks to the lowest value, and then gradually increases the frequency of each task, that is, shortens the task execution time. Until all tasks meet throughput constraints, and then gradually find the task that increases the frequency of the task with the least increase in energy consumption per unit of time, shortening its execution time, Until the execution time of all tasks meets the constraints of delay. Then it is extended to a processor model that supports arbitrary scaling techniques, and the parallel income model is reasonably segmented. Based on the piecewise parallel income model, two different heuristic frequency setting algorithms: PPSC and PPSC are proposed. The simulation results show that the proposed algorithm is more efficient than PPS and PPC.
【學(xué)位授予單位】：東北大學(xué)
【學(xué)位級(jí)別】：碩士
【學(xué)位授予年份】：2013
【分類(lèi)號(hào)】：TP368.1

【參考文獻(xiàn)】

相關(guān)期刊論文 前1條

1 林宇晗;孔繁鑫;徐惠婷;金曦;鄧慶緒;;線性加速比并行實(shí)時(shí)任務(wù)的節(jié)能研究[J];計(jì)算機(jī)學(xué)報(bào);2013年02期

，

本文編號(hào)：1517268