@inproceedings{ff796fbb24c34ae9b2ecf938925774a7,
title = "An empirical study of hpc workloads on huawei kunpeng 916 processor",
abstract = "The ARM-based server processors have been gaining momentum in high performance computing (HPC). While not designed specifically for HPC, Huawei Kunpeng 916 processor has 32 ARMv8 cores and is tempting for HPC workloads. However, its potential remains unknown. To throughly understand the potential, we conducted a systematic evaluation in three steps by using: 1) three well-known benchmarks (HPL, STREAM, and LMbench); 2) three typical scientific kernels (SpMV, N-body, and GEMM); 3) three widely used mini-Apps (TeaLeaf, Neutral, and SNAP) and a real-world application GTC-P. We compared the performance results of Kunpeng 916 with that of Intel Xeon E5-2680v3/4 (Haswell/Broadwell). The evaluation results show that Kunpeng 916 has higher memory bandwidth than the two Intel processors, thus it can achieve compelling performance for running memory bound HPC applications.",
keywords = "ARM, Benchmark, GTC-P, HPC, Huawei, Kunpeng, Performance Optimization",
author = "Wang, \{Yi Chao\} and Chen, \{Jin Kun\} and Li, \{Bin Rui\} and Zuo, \{Si Cheng\} and William Tang and Bei Wang and Liao, \{Qiu Cheng\} and Rui Xie and James Lin",
note = "Publisher Copyright: {\textcopyright} 2019 IEEE.; 25th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2019 ; Conference date: 04-12-2019 Through 06-12-2019",
year = "2019",
month = dec,
doi = "10.1109/ICPADS47876.2019.00057",
language = "English (US)",
series = "Proceedings of the International Conference on Parallel and Distributed Systems - ICPADS",
publisher = "IEEE Computer Society",
pages = "360--367",
booktitle = "Proceedings - 2019 IEEE 25th International Conference on Parallel and Distributed Systems, ICPADS 2019",
address = "United States",
}