【摘要】：分析并量化了操作系統(tǒng)任務(wù)調(diào)度時(shí)上下文切換對(duì)CPU性能影響,得出了任務(wù)上下文切換代價(jià)對(duì)CPU效率影響關(guān)系.在此影響關(guān)系的基礎(chǔ)上,提出了一種可行的Hyper-Scheduling方法.此方法通過在CPU內(nèi)部設(shè)置一條特殊的任務(wù)切換專用流水線數(shù)據(jù)通路,并在通用寄存器堆上寄生一個(gè)相同的寄存器堆(影子寄存器堆)和監(jiān)視訪存狀態(tài)的寄生邏輯,來監(jiān)視各硬件資源運(yùn)行情況,實(shí)現(xiàn)在CPU硬件資源閑置狀態(tài)時(shí)進(jìn)行預(yù)先數(shù)據(jù)準(zhǔn)備或任務(wù)保存.當(dāng)任務(wù)切換時(shí)將這條特殊數(shù)據(jù)通路與CPU主數(shù)據(jù)通路流水線進(jìn)行交換,使上下文切換時(shí)間可趨近于零,任務(wù)切換代價(jià)被消除,上下文頻繁切換或時(shí)間片長度縮短至近于零的情況下,CPU效率仍能夠保持性能最大化.
[Abstract]:The influence of context switching on CPU performance is analyzed and quantified, and the relationship between task context switching cost and CPU efficiency is obtained. Based on the relationship, a feasible Hyper-Scheduling method is proposed. In this method, a special task switching special pipeline data path is set up inside the CPU, and a common register file (shadow register file) is parasitized on the general register file and the parasitic logic of monitoring the memory access state is monitored. To monitor the running situation of each hardware resource, the CPU hardware resource can be prepared or saved in advance when the CPU hardware resource is idle. When the task switches, the special data path is exchanged with the CPU main data path pipeline, so that the context switching time can approach zero, and the task switching cost is eliminated. The CPU efficiency can be maximized when the context is switched frequently or the time slice length is shortened to near zero.
【作者單位】： 華東師范大學(xué)可信物聯(lián)網(wǎng)產(chǎn)學(xué)研聯(lián)合研發(fā)中心;華東師范大學(xué)軟件學(xué)院;
【分類號(hào)】：TP332

【相似文獻(xiàn)】

相關(guān)期刊論文 前3條

1 吳貞海;劉福巖;;基于快速上下文切換擴(kuò)展的快速地址空間切換[J];計(jì)算機(jī)工程;2010年10期

2 劉月吉;張盛兵;黃嵩人;;一種DSP的快速上下文切換機(jī)制[J];計(jì)算機(jī)應(yīng)用研究;2012年01期

3 崔光佐,李曉明,胡銘曾;一種支持多線索快速切換的上下文機(jī)制:多上下文并行機(jī)制[J];計(jì)算機(jī)研究與發(fā)展;1997年S1期

相關(guān)碩士學(xué)位論文 前1條

1 王海洋;適于頻繁上下文切換的TG-share分支預(yù)測器[D];中國科學(xué)院研究生院（計(jì)算技術(shù)研究所）;2002年

，

本文編號(hào)：2126629