| 研究生: |
張勝雲 Zhang, Sheng-Yun |
|---|---|
| 論文名稱: |
多執行绪虛擬機的研究和設計 Study and Design of a Multithreaded Virtual Machine |
| 指導教授: |
周哲民
Jou, Jer-Min |
| 學位類別: |
碩士 Master |
| 系所名稱: |
電機資訊學院 - 電機工程學系 Department of Electrical Engineering |
| 論文出版年: | 2008 |
| 畢業學年度: | 96 |
| 語文別: | 中文 |
| 論文頁數: | 59 |
| 中文關鍵詞: | 同步 、虛擬機 、多執行緒 |
| 外文關鍵詞: | synchronization, virtual machine, multithread |
| 相關次數: | 點閱:60 下載:1 |
| 分享至: |
| 查詢本校圖書館目錄 查詢臺灣博碩士論文知識加值系統 勘誤回報 |
超純量處理器利用應用程式內含的指令並行度,期望達到較高的效能,而多執行緒處理器則可以萃取出應用程式中的執行緒並行度,在增加一些硬體的情況下,達到更高的指令並行度。
近來,硬體變地愈來愈複雜來提高效能,甚至發展出多核的處理器,為了提高硬體的使用效率,虛擬機是一個可行的方法,在本篇論文裡,介紹一個利用多執行緒機制的虛擬機,它提供多執行緒的特性建構於在Alpha處理器的基礎上,因此本虛擬機可以提供多個應用程式或多個執行緒同時運行於其上,以期提高硬體的使用率,另一方面,本虛擬機是一個可以達到時脈精準的模擬器,且提供快速驗證的能力,因此我們可以測量其效能,但實際上卻不存在此硬體,藉此方式使得我們可以快速地修改目標硬體的原型和驗證其正確性。
The superscalar processor exploits ILP( instruction level parallelism) from an ordinary application to achieve speedup, and the multithreaded processor can additionally extract TLP( thread level parallelism) from an application. The multithreaded processor is able to reach much higher parallelism than a superscalar one with adding a little hardware.
Recently, hardware has become more and more complicate to raise performance and even the multi cores processor is proposed. Utilizing virtual machines is a solution to raise the utility rate of hardware. In this thesis, we introduce a multithreaded virtual machine and it offers multithreaded property based on the Alpha processor, which is a RISC superscalar processor. Hence, the virtual machine, called MTVM, can support that many applications and threads execute concurrently to raise the execution efficiency and the utility of Alpha. On the other hand, VTVM is a cycle-accurate simulator, which simulates a microarchitecture cycle-accurate, and provides the ability of rapidly functional simulation. Therefore, we can measure the performance of the real hardware, which doesn’t exist and rapidly modify the target processor and verify the correctness.
[1] James E.Smith and Ravi Nair : “Virtual Machines: Versatile Platforms for Systems and Processes”, Morgan Kaufmann, 2005.
[2] Anton Chernoff, Mark Herdeg, Ray Hookway, Chris Reeve, Norman Rubin, Tony Tye, S. Bharadwaj Yadavalli, and John Yates, “FX!32: a Profile-Directed Binary Translator”, IEEE Micro, vol. 18, no.2, 1998.
[3] Fabrice Bellard, QEMU open source processor emulator, http://fabrice.bellard.free.fr/qemu/index.html.
[4] Loikkanen et al., "A Fine-Grain Multithreading Superscalar Architecture," Proceedings of the 1996 Conference on Parallel Architectures and Compilation Techniques, IEEE, pp. 163-168. Oct. 20-23, 1996.
[5] D. Madon, E. Sanchez, and S. Monnier, "A study of a simultaneous multithreaded processor implementation," Proc. 5th International European Parallel Computing Conference, pp.716–726, Aug. 1999.
[6] Wallace, S. and Bagherzadeh, N, "Performance Issues of a Superscalar Microprocessor," Parallel Processing, 1994. ICPP 1994. International Conference, , pp.293-297, Aug. 1994.
[7] Tullsen, D.M., Eggers, S.J. and Levy, H.M., "Simultaneous multithreading: Maximizing on-chip parallelism," Computer Architecture, 1995. Proceedings. 22nd Annual International Symposium , pp. 392-403, Jun 1995.
[8] Tool Interface Standard (TIS) Executable and Linking Format (ELF) Specification Version 1.2 (May 1995).