检索结果-内蒙古大学图书馆

High Performance Interconnect Network for Tianhe System

Journal of Computer science & technology 2015年第2期30卷 259-272页

作者：廖湘科庞征王克非卢宇彤谢旻夏军董德尊所光 College of Computer National University of Defense Technology Changsha 410073 Science and Technology on Parallel and Distributed Processing Laboratory National Changsha 410073 China China University of Defense Technology State Key Laboratory of High Performance Computing National University of Defense Technology Changsha 410073 China

In this paper, we present the Tianhe-2 interconnect network and message passing services. We describe the architecture of the router and network interface chips, and highlight a set of hardware and software features effectively supporting high performance communications, ranging over remote direct memory access, collective optimization, hardwareenable reliable end-to-end communication, user-level message passing services, etc. Measured hardware performance results are also presented.

关键词： Tianhe-2 supercomputer interconnect network router architecture network interface architecture user-level message passing

来源：评论

学校读者我要写书评

暂无评论

PartialRC: A Partial Recomputing Method for Efficient Fault Recovery on GPGPUs

引用

Journal of Computer science & technology 2012年第2期27卷 240-255页

作者：徐新海杨学军薛京灵林宇斐林一松 National Laboratory for Parallel and Distributed Processing School of ComputerNational University of Defense Technology Programming Languages and Compilers Group School of Computer Science and Engineering University of New South Wales

GPGPUs are increasingly being used to as performance accelerators for HPC （High Performance Computing） applications in CPU/GPU heterogeneous computing systems, including TianHe-1A, the world＇s fastest supercomputer in the TOP500 list, built at NUDT （National University of Defense technology） last year. However, despite their performance advantages, GPGPUs do not provide built-in fault-tolerant mechanisms to offer reliability guarantees required by many HPC applications. By analyzing the SIMT （single-instruction, multiple-thread） characteristics of programs running on GPGPUs, we have developed PartialRC, a new checkpoint-based compiler-directed partial recomputing method, for achieving efficient fault recovery by leveraging the phenomenal computing power of GPGPUs. In this paper, we introduce our PartialRC method that recovers from errors detected in a code region by partially re-computing the region, describe a checkpoint-based faulttolerance framework developed on PartialRC, and discuss an implementation on the CUDA platform. Validation using a range of representative CUDA programs on NVIDIA GPGPUs against FullRC （a traditional full-recomputing Checkpoint-Rollback-Restart fault recovery method for CPUs） shows that PartialRC reduces significantly the fault recovery overheads incurred by FullRC, by 73.5% when errors occur earlier during execution and 74.6% when errors occur later on average. In addition, PartialRC also reduces error detection overheads incurred by FullRC during fault recovery while incurring negligible performance overheads when no fault happens.

关键词： GPGPU partial recomputing fault tolerance CUDA checkpointing

来源：评论

学校读者我要写书评

暂无评论

Factorization Machine-based Unsupervised Model Selection Method

Factorization Machine-based Unsupervised Model Selection Met...

引用

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Zhang, Ruyi Wang, Yijie Xu, Hongzuo Zhou, Haifang National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Machine learning is broadly used in many intelligent cybernetic systems. With the burgeoning of the communities of AI, the number of machine learning-based models is rapidly increasing, but picking a suitable and optimal (or relatively good) model from overwhelming options has become a conundrum when deploying a new system. Therefore, we are motivated by an intriguing question: Can we automatically select a proper model for new data? However, unsupervised model selection poses two main challenges: (i) Evaluation and comparison of candidate models on the new data are infeasible due to the lack of labels;and (ii) It is non-trivial to build relationships between model performance and data characteristics when the interaction between these characteristics should be considered. In light of these limitations, this paper proposes a factorization machine-based unsupervised model selection method. Following mainstream model selection protocols, we also leverage model performance on prior known datasets. Differently, we learn higher-order complex relationships between model performance and dataset characteristics. Specifically, our method transfers the historical performance into a second-order function of meta-features and embedding weights by harnessing the power of factorization machine. This function can be subsequently used to select a proper model when given a new dataset. Extensive experiments show that our method obtains more superior model selection performance than five state-of-the-art approaches, and our method executes faster than its competitors by approximate three magnitudes. © 2022 IEEE.

关键词： Factorization

来源：评论

学校读者我要写书评

暂无评论

Iaso： an autonomous fault-tolerant management system for supercomputers

引用

Frontiers of Computer science 2014年第3期8卷 378-390页

作者： Kai LU Xiaoping WANG Gen LI Ruibo WANG Wanqing CHI Yongpeng LIU Hongwei TANG Hua FENG Yinghui GAO Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha 410073 China College of Computer National University of Defense Technology Changsha 410073 China ATR Laboratory National University of Defense Technology Changsha 410073 China

With the increase of system scale, the inherent reliability of supercomputers becomes lower and lower. The cost of fault handling and task recovery increases so rapidly that the reliability issue will soon harm the usability of supercomputers. This issue is referred to as the ＂reliability wall＂, which is regarded as a critical problem for current and future supercomputers. To address this problem, we propose an autonomous fault-tolerant system, named Iaso, in MilkyWay- 2 system. Iaso introduces the concept of autonomous management in supercomputers. By autonomous management, the computer itself, rather than manpower, takes charge of the fault management work. Iaso automatically manage the whole lifecycle of faults, including fault detection, fault diagnosis, fault isolation, and task recovery. Iaso endows the autonomous features with MilkyWay-2 system, such as self-awareness, self-diagnosis, self-healing, and self-protection. With the help of Iaso, the cost of fault handling in supercomputers reduces from several hours to a few seconds. Iaso greatly improves the usability and reliability of MilkyWay-2 system.

关键词： supercomputer autonomous management fault tolerant fault management MilkyWay-2 system

来源：评论

学校读者我要写书评

暂无评论

parallelization of Fast Monte Carlo Dose Calculation for Radiotherapy Treatment Planning on the ARMv8 Architecture 11

Parallelization of Fast Monte Carlo Dose Calculation for Rad...

引用

11th International Conference on Information science and technology, ICIST 2021

作者： Jin, Chi Wang, Qinglin Zhao, Yang Dou, Yong National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha China

ISBN: (纸本)9781665412667

Monte Carlo (MC) simulation plays a key role in radiotherapy. Since the simulation time of the MC program cannot fully meet the clinical requirements, we use the ARM-based FT-2000+ multi-core processor for parallelization, which provides an effective solution for accelerating MC dose calculation. In this paper, we implement and verify FT-DPM, which is an OpenMP-based MC Dose Planning Method on FT-2000+. FT-DPM utilizes the parallelism of MC simulation and the advantage of ARM architecture to achieve the parallelization on ARM architecture. Meanwhile, we optimize the original DPM program in terms of memory allocation, data structure and data type. The experiments show that, compared with the original DPM code, FT-DPM obtains very accurate results and reaches the maximum speedups of 155.94 times for the electron case. The parallel program based on FT-2000+ only takes 44.1 seconds to simulate the particle transport of 100 million times, showing good clinical application potential. In addition, the speedup and efficiency of FT-DPM running on different core counts are also discussed. © 2021 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

A Heterogeneous KBA parallel Algorithm for the Cartesian Discrete Ordinates for Multizone Heterogeneous System 8

A Heterogeneous KBA Parallel Algorithm for the Cartesian Dis...

引用

8th International Conference on Computer and Communication Systems, ICCCS 2023

作者： Li, Runhua Liu, Jie National University of Defense Technology Science and Technology on Parallel and Distributed Processing Laboratory Changsha China

ISBN: (纸本)9781665456128

Innovations in powerful high-performance computing (HPC) architecture are enabling high-fidelity whole-core neutron transport simulations at reasonable time. Especially, the currently fashionable heterogeneous architectures make the cost of such simulations at very low level. Neutron distribution of a reactor core is governed by the Boltzmann neutron transport equation (BTE), first viable solutions of which need tremendous computer resources. Among of the high-fidelity numerical methods, the discrete ordinates method (SN) is becoming popular in the reaction design community by taking a good balance between computational cost and accuracy. Recently, MT-3000, which is a multizone heterogeneous architecture with a peak double precision performance of 11.6 TFLOPS, is proposed. In this work, the BTE is solved by the SN with heterogenous Koch-Baker-Alcouffe (KBA) parallel algorithms based on the MT-3000 architecture. A communication mechanism has been established to efficiently transmit data among the acceleration cores and the CPU cores. The kernel computation procedure is largely accelerated by the vectorization and instruction pipelining techniques. Numerical experiments show that our formulation could achieve 1.37 TFLOPs with single MT-3000, that is 11.8% of its peak performance. © 2023 IEEE.

关键词： parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

Performance Optimization of a CFD Application on Intel Multicore and Manycore Architectures

Performance Optimization of a CFD Application on Intel Multi...

引用

10th Annual Conference of Advanced Computer Architecture, ACA 2014

作者： Che, Yonggang Zhang, Lilun Wang, Yongxian Xu, Chuanfu Liu, Wei Cheng, Xinghua Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense Technology Changsha China

ISBN: (纸本)9783662444900

This paper reports our experience optimizing the performance of a high-order and high accurate Computational Fluid Dynamics (CFD) application (HOSTA) on the state of art multicore processor and the emerging Intel Many Integrated Core (MIC) coprocessor. We focus on effective loop vectorization and memory access optimization. A series techniques, including data structure transformations, procedure inlining, compiler SIMDization, OpenMP loop collapsing, and the use of Huge Pages, are explored. Detailed execution time and event counts from Performance Monitoring Units are measured. The results show that our optimizations have improved the performance of HOSTA by 1.61× on a two Intel Sandy Bridge processors based computer node and 1.97× on a Intel Knights Corner coprocessor, the public MIC product. The microarchitecture level effects of these optimizations are also discussed. © Springer-Verlag Berlin Heidelberg 2014.

关键词： Computational fluid dynamics

来源：评论

学校读者我要写书评

暂无评论

Data dependence-based optimistic data consistency maintenance method

Data dependence-based optimistic data consistency maintenanc...

引用

6th IEEE International Conference on Computer and Information technology, CIT 2006

作者： Zhou, Jing Wang, Yijie Li, Sikun National Key Laboratory for Parallel and Distributed Processing School of Computer Science National University of Defense Technology China

ISBN: (纸本)076952687X

Data replication introduces well-known consistency issues. This paper puts forward the question about data dependence in data consistency, which embodies pseudo-conflict updates and update dependency. According to that, an optimistic data consistency method is proposed. In our method, data object is partitioned into data blocks by fixed size, as the basic unit of data management. Updates are compressed by Bloom filter technique and propagated in double-path. Negotiation algorithms detect and reconcile update conflicts, and dynamic data management algorithms accommodate dynamic data processing. The results of the performance evaluation show that our method is an efficient method to achieve consistency, good dynamic property, and strong robustness. © 2006 IEEE.

关键词： Information technology

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for deep neural network-based partial differential equations solving

引用

Advances in Aerodynamics 2021年第1期3卷 635-648页

作者： Xinhai Chen Chunye Gong Qian Wan Liang Deng Yunbo Wan Yang Liu Bo Chen Jie Liu Science and Technology on Parallel and Distributed Processing Laboratory National University of Defense TechnologyChangshaChina China Aerodynamics Research and Development Center MianyangChina.

Deep neural networks(DNNs)have recently shown great potential in solving partial differential equations(PDEs).The success of neural network-based surrogate models is attributed to their ability to learn a rich set of solution-related ***,learning DNNs usually involves tedious training iterations to converge and requires a very large number of training data,which hinders the application of these models to complex physical *** address this problem,we propose to apply the transfer learning approach to DNN-based PDE solving *** our work,we create pairs of transfer experiments on Helmholtz and Navier-Stokes equations by constructing subtasks with different source terms and Reynolds *** also conduct a series of experiments to investigate the degree of generality of the features between different *** results demonstrate that despite differences in underlying PDE systems,the transfer methodology can lead to a significant improvement in the accuracy of the predicted solutions and achieve a maximum performance boost of 97.3%on widely used surrogate models.

关键词： Deep neural network Partial differential equation Surrogate model Transfer learning

来源：评论

学校读者我要写书评

暂无评论

DIPP—An LLC replacement policy for on-chip dynamic heterogeneous multi-core architecture

DIPP—An LLC replacement policy for on-chip dynamic heteroge...

引用

International Conference of Young Computer Scientists, Engineers and Educators, ICYCSEE 2015

作者： Yang, Zhang Zuocheng, Xing Xiao, Ma Science and technology on Parallel and distributed processing laboratory National University of Defense Technology ChangSha China

ISBN: (纸本)9783662462478

As the big data era is coming, it brings new challenges to the massive data processing. A combination of GPU and CPU on chip is the trend to release the pressure of large scale computing. We found that there are different memory access characteristics between GPU and CPU. The most important one is that the programs of GPU include a large number of threads, which lead to higher access frequency in cache than the CPU programs. Although the LRU policy favors the programs with high memory access frequency, the programs of GPU can’t get the corresponding performance boost even more cache resources are provided. So LRU policy is not suitable for heterogeneous multi-core processor. Based on the different characteristics of GPU and CPU programs on memory access, this paper proposes an LLC dynamic replacement policy--DIPP (Dynamic Insertion/ Promotion Policy) for heterogeneous multi-core processors. The core idea of the replacement policy is to reduce the miss rate of the program and enhance the overall system performance by limiting the cache resources that GPU can acquire and reducing the thread interferences between programs. Experiments compare the DIPP replacement policy with LRU and we conduct a classified discussion according to the program results of GPU. Friendly programs enhance 23.29% on the average performance (using arithmetic mean). Large working sets programs can improve 13.95%, compute-intensive programs enhance 9.66% and stream class programs improve 3.8%. © Springer-Verlag Berlin Heidelberg 2015.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：