gem5-gpu: A Heterogeneous CPU-GPU Simulator

Jason Power, Joel Hestness, Marc S. Orr, Mark D. Hill and David A. Wood. Computer Architecture Letters 2014.

Paper on IEEE Xplore Local Download Website Code Repository

Abstract

gem5-gpu is a new simulator that models tightly integrated CPU-GPU systems. It builds on gem5, a modular full-system CPU simulator, and GPGPUSim, a detailed GPGPU simulator. gem5-gpu routes most memory accesses through Ruby, which is a highly configurable memory system in gem5. By doing this, it is able to simulate many system configurations, ranging from a system with coherent caches and a single virtual address space across the CPU and GPU to a system that maintains separate GPU and CPU physical address spaces. gem5gpu can run most unmodified CUDA 3.2 source code. Applications can launch non-blocking kernels, allowing the CPU and GPU to execute simultaneously. We present gem5-gpu’s software architecture and a brief performance validation. We also discuss possible extensions to the simulator. gem5-gpu is open source and available at gem5-gpu.cs.wisc.edu.

Jason Power, Joel Hestness, Marc S. Orr, Mark D. Hill and David A. Wood, “gem5-gpu: A Heterogeneous CPU-GPU Simulator,” in IEEE Computer Architecture Letters, vol. 14, no. 1, pp. 34-36, Jan.-June 1 2015. doi: 10.1109/LCA.2014.2299539

@article{6709764, 
    author={Jason Power and Joel Hestness and Marc S. Orr and Mark D. Hill and David A. Wood}, 
    journal={IEEE Computer Architecture Letters}, 
    title={gem5-gpu: A Heterogeneous CPU-GPU Simulator}, 
    year={2015}, 
    volume={14}, 
    number={1}, 
    pages={34-36}, 
    doi={10.1109/LCA.2014.2299539}, 
    ISSN={1556-6056}, 
    month={Jan},
}

Updated: