異構系統架構(HSA)是以有效支持一個廣泛安排資料平行與任務平行程式模型而設計的晶片架構正在快速崛起。但是現在可供使用的模擬器很少能支持全系統模擬這樣的多指令集的架構。所以，在這篇文章中，我為大家介紹一個新的全系統模擬器，這個模擬器以QEMU為基礎，並可以很好的支持異構系統架構的各種特性，把CPU和GPU以一個緊湊的協同工作方式整合在一起。換句話說，在這個模擬器中，所有的處理器都作為一個集成的中央處理器的一部份而分別執行不同的指令集。另外，我還是用PQEMU的原理，通過多執行緒的方式通過是用多執行緒分別執行不同的被模擬核心來加速此模擬器的整體模擬速度

Heterogeneous system architecture (HSA) is rising quickly, which designed to effi-ciently support a wide assortment of data-parallel and task-parallel programing models. While there is few full system emulators can simulate this system which can support multiple instruction sets based on CPU(s), GPU(s), and specialized processor(s). In this paper, we introduce a new full system emulator based on QEMU which follows the HSA property, integrate CPU and GPU in a closely co-work way. In other words, in this emulator all these processors are part of an integrated processor with multiple ISA. Besides the implementation of this emulator uses the conception of PQEMU [1] to emulate the multi processors in parallel thus speeds up the overall simulation.

[1]Jiun-Hung Ding; Po-Chun Chang; Wei-Chung Hsu; Yeh-Ching Chung; , "PQEMU: A Parallel System Simulator Based on QEMU," Parallel and Distrib-uted Systems (ICPADS), 2011 IEEE 17th International Conference on , vol., no., pp.276-283, 7-9 Dec. 2011 doi: 10.1109/ICPADS.2011.102
[2]A. Bakhoda, G. L. Yuan, W. L. Fung, H. Wong, and T. M. Aamodt. Analyzing CUDA workloads using a detailed GPU simulator. In Proceedings of 2009 IEEE International Symposium on Performance Analysis of Systems and Software, April 2009.
[3]T. Benjamins, MACSIM: Multi Agent Crisis Simulator, Interpreter, and Mon-itor. Master Thesis, Delft University of Technology, the Netherlands, 2006
[4]COREMU: a scalable and portable parallel full-system simulator by: Zhaoguo Wang, Ran Liu, Yufei Chen, Xi Wu, Haibo Chen, Weihua Zhang, Binyu Zang In Proceedings of the 16th ACM symposium on Principles and practice of parallel programming (2011), pp. 213-222, doi:10.1145/1941553.1941583
[5]Chris Latter, LLVM: A Compilation Framework for Lifelong Program Analy-sis & Transformation, UIUC, CGO’04.
[6]Khronos OpenCL Working Group. "The opencl specification." A. Munshi, Ed (2008).
[7]Sylvain Collange, Marc Daumas, David Defour, David Parello. Barra: A Par-allel Functional Simulator for GPGPU. 18th Annual IEEE/ACM International Symposium on Modeling, Analysis and Simulation of Computer and Telecom-munication Systems (MASCOTS), 2010.
[8]Gregory Diamos, Ocelot: A Dynamic Optimization Framework for Bulk-Synchronous Applications in Heterogeneous Systems, Georgia Tech, PACT 2010.
[9]Vitaly Zakharenko, FusionSim: Characterizing the Performance Benefits of Fused CPU/GPU Systems, Toroto MS Thesis, 2012.