Large-Scale Heterogeneous Computing for 3D Deterministic Particle Transport on Tianhe-2A Supercomputer
نویسندگان
چکیده
Scalable parallel algorithm for particle transport is one of the main application fields in high-performance computing. Discrete ordinate method (S n ) most popular deterministic numerical methods solving equations. In this paper, we introduce a new large-scale heterogeneous computing energy group time-independent discrete ordinates neutron 3D Cartesian geometry (Sweep3D) on Tianhe-2A supercomputer. programming, use customized Basic Communication Library (BCL) and Accelerated Computing (ACL) to control communicate between CPU Matrix2000 accelerator. We OpenMP instructions exploit parallelism threads based Matrix 2000. The test results show that optimization applying modified by our can get 11.3 times acceleration at most. On supercomputer, efficiency 1.01 million cores compared with 170 thousand 52%.
منابع مشابه
Computing Permanents for Boson Sampling on Tianhe-2 Supercomputer
Junjie Wu, 2, ∗ Yong Liu, 2 Baida Zhang, Xianmin Jin, 4, † Yang Wang, 2 Huiquan Wang, 2 and Xuejun Yang 2, ‡ State Key Laboratory of High Performance Computing, National University of Defense Technology, Changsha 410073, China College of Computer, National University of Defense Technology, Changsha 410073, China State Key Laboratory of Advanced Optical Communication Systems and Networks, Instit...
متن کاملAdvanced learning for large-scale heterogeneous computing
Coming with the era of big data, nowadays we have witnessed a drastic growth of heterogeneous data information involved in scalable computing and analysis. It has opened up a new gate and aroused new challenges in developing effective machine learning technologies to cater for such a heterogeneous computing requirement. Exemplar scenarios include, but not limited to, crossmodality visual search...
متن کاملA Performance Model of Non-deterministic Particle Transport on Large-Scale Systems
In this work we present a predictive analytical model that encompasses the performance and scaling characteristics of a non-deterministic particle transport application, MCNP. Previous studies on the scalability of parallel Monte Carlo eigenvalue calculations have been rather general in nature [1]. It can be used for the simulation of neutron, photon, electron, or coupled transport, and has fou...
متن کاملDynamically Reconfigurable Scientific Computing on Large-Scale Heterogeneous Grids
Many scientific applications require computational capabilities not easily supported by current computing environments. We propose a scalable computing environment based on autonomous actors. In this approach, a wide range of computational resources, ranging from clusters to desktops and laptops, can run an application programmed using actors as program components in an actor language: SALSA. S...
متن کاملAn Interface for Biomedical Big Data Processing on the Tianhe-2 Supercomputer.
Big data, cloud computing, and high-performance computing (HPC) are at the verge of convergence. Cloud computing is already playing an active part in big data processing with the help of big data frameworks like Hadoop and Spark. The recent upsurge of high-performance computing in China provides extra possibilities and capacity to address the challenges associated with big data. In this paper, ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Frontiers in Energy Research
سال: 2021
ISSN: ['2296-598X']
DOI: https://doi.org/10.3389/fenrg.2021.701437