@inproceedings{0f62232c34ba4e5090d8276b9684d9b6,
title = "NNSim: Fast performance estimation based on sampled simulation of gpgpu kernels for neural networks",
abstract = "Existent GPU simulators are too slow to use for neural networks implemented in GPUs. For fast performance estimation, we propose a novel hybrid method of analytical performance modeling and sampled simulation of GPUs. By taking full advantage of repeated computation of neural networks, three sampling techniques are devised: Inter-Kernel sampling, Intra-Kernel sampling, and Streaming Multiprocessor sampling. The key technique is to estimate the average IPC through sampled simulation, considering the effect of the warp scheduler and memory access contention. Compared with GPGPU-Sim, the proposed technique reduces the simulation time by up to 450 times with less than 5.0% of accuracy loss.",
keywords = "Analytical Model, GPU Simulator, Sampled Simulation",
author = "Jintaek Kang and Kwanghyun Chung and Youngmin Yi and Soonhoi Ha",
note = "Publisher Copyright: {\textcopyright} 2018 Association for Computing Machinery.; 55th Annual Design Automation Conference, DAC 2018 ; Conference date: 24-06-2018 Through 29-06-2018",
year = "2018",
month = jun,
day = "24",
doi = "10.1145/3195970.3196079",
language = "English",
isbn = "9781450357005",
series = "Proceedings - Design Automation Conference",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Proceedings of the 55th Annual Design Automation Conference, DAC 2018",
address = "United States",
}