Zobrazeno 1 - 10
of 138
pro vyhledávání: '"Han, Ruobing"'
Autor:
Wang, Qianghui1 (AUTHOR), Han, Ruobing1 (AUTHOR), Xing, Haihua1 (AUTHOR), Li, Heping1 (AUTHOR) lihepinghrb2002@nefu.edu.cn
Publikováno v:
BMC Genomics. 6/18/2024, Vol. 25 Issue 1, p1-13. 13p.
CUDA is one of the most popular choices for GPU programming, but it can only be executed on NVIDIA GPUs. Executing CUDA on non-NVIDIA devices not only benefits the hardware community, but also allows data-parallel computation in heterogeneous systems
Externí odkaz:
http://arxiv.org/abs/2206.07896
As CUDA programs become the de facto program among data parallel applications such as high-performance computing or machine learning applications, running CUDA on other platforms has been a compelling option. Although several efforts have attempted t
Externí odkaz:
http://arxiv.org/abs/2112.10034
With the rapid development of scientific computation, more and more researchers and developers are committed to implementing various workloads/operations on different devices. Among all these devices, NVIDIA GPU is the most popular choice due to its
Externí odkaz:
http://arxiv.org/abs/2109.00673
Autor:
Wen, Jian, Zhang, Tianmei, Ye, Shangrong, Zhang, Peng, Han, Ruobing, Chen, Xiaowang, Huang, Ran, Chen, Anjun, Li, Qinghua
Publikováno v:
In Heliyon 15 January 2024 10(1)
It has been reported that the communication cost for synchronizing gradients can be a bottleneck, which limits the scalability of distributed deep learning. Using low-precision gradients is a promising technique for reducing the bandwidth requirement
Externí odkaz:
http://arxiv.org/abs/1911.08907
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.
Publikováno v:
In Genomics, Proteomics & Bioinformatics June 2023 21(3):470-482
It is important to scale out deep neural network (DNN) training for reducing model training time. The high communication overhead is one of the major performance bottlenecks for distributed DNN training across multiple GPUs. Our investigations have s
Externí odkaz:
http://arxiv.org/abs/1902.06855