QEMU 為 Quick EMUlator 之縮寫，它是一個高速處理器模擬器，它不但具有跨平台的特性，並且使用了動態二進制轉譯技術來提高模擬效率。現在的硬體設備都已邁向多核心機器的時代，但是目前QEMU的並非平行執行，因此在多核心機器上失去了多執行緒平行運算的特性。而PQEMU（多執行緒QEMU）可以在底層為多核心機器的架構上，有效地運用多核心處理器，其效能平均比QEMU快至3.79倍。目前PQEMU所支援的模擬指令集架構為ARM，本論文所提出的設計是PQEMU在提供模擬x86指令集架構時需要決解模擬原子指令之設計。x86指令集有18個原子指令以上，在設計模擬這些原子指令時將會很復雜。所以本設計主要的想法是由於底層指令集架構與上層所模擬之指令集架構均為x86指令集架構，因此可以應用產生一對一直接對應之原子指令來決解模擬x86原子指令上的問題。為了評估這項設計，在四核心 x86 i7 的硬體系統上模擬並執行簡單有效之平行評效程式。實驗結果顯示，一對一直接對應原子指令之效能明顯比 Transactional memory 的方法平均快約 34﹪。

QEMU for the Quick EMUlation abbreviation, it is a fast processor emulator, which has cross-platform features, and uses dynamic binary translation technology to improve the emulation efficiency. Nowadays, hardware devices are moving towards the era of multi-core machine, but the QEMU does not run in parallel, and therefore lost a multi-threaded parallel computing features in a multi-core machine. The PQEMU (multi-threaded QEMU) is designed for multi-core machines, and gains the advantages of multi-core processors. Its performance is average to 3.79 times faster than QEMU. PQEMU supports ARM instruction set architecture. The design proposed in this paper is the design of emulating the atomic instructions of x86 ISA. There are more than 18 atomic instructions in the x86 instruction set and it will be very complicated to design. The main idea of this design is due to the underlying ISA and the upper emulated ISA both are the x86 ISA, so it can apply one-to-one direct mapping to simulate the x86 atomic instructions. In order to evaluate the design, we emulate an x86 based machine on Intel core i7 quad-core hardware system and executes the simple and affective efficiency rating program. The experimental results show the effectiveness of one-to-one direct mapping emulation is average 34% faster than that of transactional memory approach.

[1] F. Bellard. QEMU, a fast and portable dynamic translator. In In Proc. of the USENIX Annual Technical Conference, pages 41–46, April 2005.
[2] M. Rosenblum, S. Herrod, E. Witchel, and A. Gupta, The SimOS approach, IEEE Parallel and Distributed Technology, vol. 4, no. 3, 1995.
[3] Peter S. Magnusson et al. Simics: A Full System Simulation Platform. IEEE Computer, 35(2):50–58, February 2002.
[4] Witchel, E. and Rosenblum R. Embra: fast and flexible machine simulation. In Proc. of the SIGMETRICS ’96 Conference on Measurement and Modeling of Computer Systems. 68-78, 1996.
[5] Cmelik, R.F., and Keppel, D. Shade: a fast instruction set simulator for execution profiling. Technical Report UWCSE-93-06-06, CSE Dept., University of Washington, 1993.
[6] COREMU. http://sourceforge.net/p/coremu/home/.
[7] D. C. Burger and T. M. Austin. The SimpleScalar tool set, version 2.0. Computer Architecture News, 25(3):13–25, June 1997.
[8] D. Brooks, V. Tiwari, and M. Martonosi. Wattch: A framework for architectural-level power analysis and optimizations. In Proc. of the 27th Annual International Symposium on Computer Architecture, pages 83–94, June 2000.
[9] Vijay S. Pai, Parthasarathy Ranganathan, and Sarita V. Adve. RSIM: An Execution-Driven Simulator for ILP-Based Shared-Memory Multiprocessors and Uniprocessors. In Proc. of the Third Workshop on Computer Architecture Education, February 1997.
[10] Bohrer, P., et al., Mambo: A Full System Simulator for the PowerPC Architecture. SIGMETRICS Perf. Eval. Rev. 31, 4 (Mar. 2004), 8-12, 2004.
[11] Binkert, N.L., Derslinki, R.G., Hsu, L.R., Lim, K.T., Saidi, A.G., Reinhardt, S.K., 2006. The M5 Simulator: Modeling Networked Systems. IEEE Micro. 26,4 (July-Aug. 2006), 52-60.
[12] PTLsim: A Cycle Accurate Full System x86-64 Microarchitectural Simulator. In Proceedings of the IEEE International Symposium on Performance Analysis of Systems and Software, ISPASS 2007 (San Jose, CA, 2007). 23-34.
[13] K. P. Lawton, Bochs: A portable PC emulator for Unix, Linux Journal, vol. 1996, no. 29, p. 7, 1996.
[14] Lantz, R. Fast functional simulation with parallel Embra. In Proc. of the 4th Annual Workshop on Modeling, Benchmarking and Simulation, 2008.