Zobrazeno 1 - 10
of 19
pro vyhledávání: '"Junmin Xiao"'
Autor:
Hang Cao, Liang Yuan, He Zhang, Yunquan Zhang, Baodong Wu, Kun Li, Shigang Li, Minghua Zhang, Pengqi Lu, Junmin Xiao
Publikováno v:
IEEE Transactions on Parallel and Distributed Systems. 34:766-780
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::dec7cf9455614b726a21da74b71da5b7
https://doi.org/10.1109/tpds.2022.3231013
https://doi.org/10.1109/tpds.2022.3231013
Autor:
Junmin Xiao, Yunfei Pang, Qing Xue, Chaoyang Shui, Ke Meng, Hui Ma, Mingyi Li, Xiaoyang Zhang, Guangming Tan
Publikováno v:
SC22: International Conference for High Performance Computing, Networking, Storage and Analysis.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::7a80127eff49a83ca9db5a26756d9f4c
https://doi.org/10.1109/sc41404.2022.00087
https://doi.org/10.1109/sc41404.2022.00087
Autor:
Zhongzhe Hu, Junmin Xiao, Zheye Deng, Mingyi Li, Kewei Zhang, Xiaoyang Zhang, Ke Meng, Ninghui Sun, Guangming Tan
Publikováno v:
Proceedings of the 36th ACM International Conference on Supercomputing.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::eff6d702b92839c0c5bfdeca778d13b1
https://doi.org/10.1145/3524059.3532394
https://doi.org/10.1145/3524059.3532394
Publikováno v:
Concurrency and Computation: Practice and Experience. 34
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::61f0d46ef2c922f023c29b48fe442d13
https://doi.org/10.1002/cpe.7119
https://doi.org/10.1002/cpe.7119
Publikováno v:
Proceedings of the 27th ACM SIGPLAN Symposium on Principles and Practice of Parallel Programming.
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::469ef487de9bdabbdf71d234d6400d3f
https://doi.org/10.1145/3503221.3508443
https://doi.org/10.1145/3503221.3508443
Publikováno v:
International Journal of Parallel Programming. 48:750-770
Data assimilation is an analysis technique which combines observations and the numerical results from theoretical models to deduce more realistic and accurate data. It is widely used in investigations of the atmosphere, ocean and land surface. Due to
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::ee767171fa487e10662ce957c2b60286
https://doi.org/10.1007/s10766-019-00653-y
https://doi.org/10.1007/s10766-019-00653-y
Autor:
Jian Peng, Junmin Xiao
Publikováno v:
CCF Transactions on High Performance Computing. 1:144-160
In a computing platform composed of several homogeneous processors, any parallel schedule of an algorithm usually involves three basic costs: arithmetic throughput on each processor, data movement between processors, and synchronization latency for s
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::491760afe8218fcc8a5b29c97f24d73f
https://doi.org/10.1007/s42514-019-00011-x
https://doi.org/10.1007/s42514-019-00011-x
Publikováno v:
PPoPP
Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs), which have achieved great successes in numerous practical applications. Due to the complex data dependency and the increase in the amount of model
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::a0b6328976e449de582e4d8603c28399
https://doi.org/10.1145/3437801.3441609
https://doi.org/10.1145/3437801.3441609
Publikováno v:
SPAA
Convolution is the most time-consuming part in the computation of convolutional neural networks (CNNs). Due to the complex data dependency and the increase in the amount of model samples, the convolution suffers from high overhead on data movement. T
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::4f938b1119a6ed2e31f5d39f1383c1ef
https://doi.org/10.1145/3350755.3400267
https://doi.org/10.1145/3350755.3400267
Autor:
Junmin Xiao, Ninghui Sun, Hu Zhongzhe, Tian Zhongbo, Zhu Hongrui, Yao Chengji, Guangming Tan, Xiaoyang Zhang
Publikováno v:
ISPA/BDCloud/SocialCom/SustainCom
Large batch distributed synchronous stochastic gradient descent (SGD) has been widely used to train deep neural networks on a distributed memory system with multi-nodes, which can leverage parallel resources to reduce the number of iterative steps an
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::76f865bfdf658a5fbcbf8a7aa9cc467c
https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00074
https://doi.org/10.1109/ispa-bdcloud-sustaincom-socialcom48970.2019.00074