检索结果-内蒙古大学图书馆

ieee international Conference on Big Data and Cloud computing (BdCloud)

作者： Baoke Li Cong Cao Yuhai Lu Yanbing Liu Baohui Li Binxing Fang Jianhui Fu School of Cyber Security University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China Chinese Information Technology Securiry Evaluation Center Beijing China Institue of Electronic and Information Engineering of UESTC in Guangdong Dongguan China Shandong Institutes of Industrial Technology Jinan China

Graph computing recently receives intensive interests due to a wide range of needs to analyse big graphs in real time. many single-machine out-of-core graph computing systems have been developed to process large-scale graphs by utilizing effective memory access techniques. The current systems either focus on graph compression or pay attention to disk scheduling strategies. In this paper, we propose an efficient and unified out-of-core graph computing model on a single machine named D 2 Graph which combines the differential storage strategy and the dynamic caching mechanism. D 2 Graph improves the spatial locality of graph data and the temporal locality of graph computing at the same time. The main contributions of our work lie in three aspects: firstly, we design a fine-grained differential storage(FGDS) strategy to reorganize graph data on disk; secondly, we propose a dynamic caching mechanism (DCM) to selectively load the necessary edge chunks; thirdly, we combine FGDS and DCM to construct D 2 Graph and evaluate it on five public graph data sets. What’s more, to optimize the performance of D 2 Graph, we also make use of the multi-threaded parallel technology. A series of results show that D 2 Graph outperforms state-of-the-art out-of-core graph computing systems by 1.3x-17.9x.

关键词： Processor scheduling Computational modeling Scalability Heuristic algorithms Loading Parallel processing Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Masa: Responsive multi-DNN Inference on the Edge

Masa: Responsive Multi-DNN Inference on the Edge

引用

ieee international Conference on Pervasive computing and Communications (PerCom)

作者： Bart Cox Jeroen Galjaard Amirmasoud Ghiassi Robert Birke Lydia Y. Chen TU Delft Delft Netherlands ABB Research Switzerland Switzerland

ISBN: (纸本)9781665447256

Deep neural networks (DNNs) are becoming the core components of many applications running on edge devices, especially for real time image-based analysis. Increasingly, multi-faced knowledge is extracted via executing multiple DNNs inference models, e.g., identifying objects, faces, and genders from images. The response times of multi-DNN highly affect users' quality of experience and safety as well. Different DNNs exhibit diversified resource requirements and execution patterns across layers and networks, which may easily exceed the available device memory and riskily degrade the responsiveness. In this paper, we design and implement Masa, a responsive memory-aware multi-DNN execution framework, an on-device middleware featuring on modeling inter- and intra-network dependency and leveraging complimentary memory usage of each layer. Masa can consistently ensure the average response time when deterministically and stochastically executing multiple DNN-based image analyses. We extensively evaluate Masa on three configurations of Raspberry Pi and a large set of popular DNN models triggered by different generation patterns of images. Our evaluation results show that Masa can achieve lower average response times by up to 90% on devices with small memory, i.e., 512 MB to 1 GB, compared to the state of the art multi-DNN scheduling solutions.

关键词： Pervasive computing Schedules Image analysis Processor scheduling Image edge detection Real-time systems Safety

来源：评论

学校读者我要写书评

暂无评论

SABER-GPU: A Response-Based Cryptography Algorithm for SABER on the GPU

SABER-GPU: A Response-Based Cryptography Algorithm for SABER...

引用

Pacific Rim international Symposium on Dependable computing

作者： Kaitlyn Lee Michael Gowanlock Bertr Cambou School of Informatics Computing and Cyber Systems Northern Arizona University Flagstaff AZ U.S.A.

ISBN: (纸本)9781665424776

The Internet of Things (IoTs) contain many low-powered devices that require secure communication. Post-quantum cryptography (PQC) is needed to address quantum computers that eventually will be able to break current encryption schemes. However, IoT devices are low-powered and often do not have the computational power to carry out computationally expensive error correction schemes. To address this limitation, we propose leveraging response-based cryptography (RBC) to secure IoT devices. Physical unclonable functions (PUFs) can replace random number generators that are used in the public key creation procedures. In this scheme, a server authenticates a client by generating the same seed from the image of the client's PUF stored in the server in a secure environment, thus replacing static public keys with dynamically generated key pairs. In this paper, we focus on generating the public key from the SABER PQC algorithm. Due to the inherent bit error rates existing in PUF technology, the protocol requires that the server recognizes the erratic keys. This error correction requires a massive parallel search over a key space bounded by the expected PUF error rate. This paper examines the use of parallel computing technologies to rapidly find a client's public key within reasonable time constraints. In particular, we examine using multi-core CPUs and many-core Graphics Processing Units (GPUs) in shared-memory environments. The design space for the SABER PQC algorithm is large. Therefore, we focus on performance engineering several CUDA kernels used in the RBC search that systematically explore this space. Our RBC search algorithms are highly scalable: the multi-core CPU algorithm achieves a speedup of 61.82 x on 64 CPU cores, and our multi-GPU algorithm achieves a near-perfect speedup of 2.93 x on 3 GPUs. Using a typical PUF error rate that requires searching 1.75 × 10 8 keys, we find that our GPU algorithm can authenticate a user within 6 seconds, which is well below our au

关键词： Computers Quantum computing Graphics processing units Public key Clustering algorithms Physical unclonable function Central Processing Unit

来源：评论

学校读者我要写书评

暂无评论

Towards Architecture-aware Hierarchical Communication Trees on Modern HPC systems

Towards Architecture-aware Hierarchical Communication Trees ...

引用

international Conference on High Performance computing

作者： Bharath Ramesh Jahanzeb Maqbool Hashmi Shulei Xu Aamir Shafi Mahdieh Ghazimirsaeed Mohammadreza Bayatpour Hari Subramoni Dhabaleswar K. Panda The Ohio State University Columbus USA

ISBN: (纸本)9781665410175

Modern HPC systems built with emerging multi-/many -core architectures have high core-counts and deep memory hierarchies. It is challenging to design communication libraries on these systems with the conventional wisdom of using OS processes as the basic building block to build communication algorithms. Instead, the next generation of communication libraries should treat hardware as the “first-class citizen” and utilize the underlying topology as the basic building block. Driven by this overarching principle, we present a framework for Optimized Shared Memory Processing (OSMP) and communication for these platforms. An abstract representation of the underlying hardware topology is maintained by OSMP in the form of a topology tree, which is later exploited by runtime libraries to execute communication operations in a topology-aware manner. This can be done by simply traversing the topology tree with an existing communication primitive as the base-case. OSMP does not mandate any changes to the original communication algorithm. We focus on collective operations such as barrier, reduction, and broadcast as candidate communication patterns. We demonstrate the efficacy of OSMP by decoupling the implementation of collective algorithms and system topology and evaluate it on four state-of-the-art multi-tmany-core architectures: Intel Cascade Lake, AMD Rome, ARM A64fx and IBM POWER9. Results show that even the basic algorithms can be made topology-aware by exploiting OSMP. This provides significant benefits over state-of-the-art algorithm implementations for intra-node communication. Using various micro-benchmarks and applications, we demonstrate that our proposed designs can achieve up to 7.8× improvements at the micro-benchmark level, and 15% for applications over state-of-the-art intra-node collective communication designs employed by production MPI libraries.

关键词： Program processors Runtime library High performance computing Conferences Production Lakes Libraries

来源：评论

学校读者我要写书评

暂无评论

CUDA-DClust+: Revisiting Early GPU-Accelerated DBSCAN Clustering Designs

CUDA-DClust+: Revisiting Early GPU-Accelerated DBSCAN Cluste...

引用

international Conference on High Performance computing

作者： Madhav Poudel Michael Gowanlock School of Informatics Computing and Cyber Systems Northern Arizona University Flagstaff AZ U.S.A.

ISBN: (纸本)9781665410175

Density-based clustering algorithms are widely used unsupervised data mining techniques to find the clusters of points in dense regions that are separated by low-density regions. This algorithm is inherently sequential and has limitations in its parallel implementation. There have been several parallel algorithms presented in the literature for multi-core CPUs and many-core GPUs. One such algorithm for the GPU is CUDA-DCLUST. In this paper, we propose a new GPU-accelerated DBSCAN algorithm with several optimizations. In comparison to prior work, our algorithm, Cuda-dclust+:(i) computes the indexing structure on the GPU, (ii) uses kernel fusion to combine the index search and cluster expansion kernels, which reduces communication and synchronization overhead with the host, and (iii) seed list management control is primarily given to the GPU rather than the CPU, which further decreases CPU-GPU communication overhead. We compare our algorithm to three state-of-the-art parallel algorithms in the literature on six real-world datasets. We find that our algorithm achieves a speedup of up to ~23x over the fastest GPU algorithm.

关键词： High performance computing Conferences Clustering algorithms Graphics processing units Synchronization Data mining Parallel algorithms

来源：评论

学校读者我要写书评

暂无评论

A multi-staged niched evolutionary approach for allocating parallel tasks with joint optimization of performance, energy, and temperature

引用

JOURNAL OF PARALLEL AND DISTRIBUTED computing 2019年 134卷 65-74页

作者： Ahmad, Ishfaq Sheikh, Hafiz Fahad Univ Texas Arlington Dept Comp Sci & Engn Arlington TX 76019 USA

This paper presents a multi-stage multi-objective evolutionary approach (MS-MOEA) for allocating parallel computations on multi-core processors by joint optimizing performance (P), energy (E), and temperature (T). Evolutionary techniques have been shown to be effective for solving optimization problems, including our own previous work on solving the PET-optimized scheduling (PETOS) problem. There have long been a great many debates and rivalries between various evolutionary approaches, such as the SPEA or NSGA, with regard to their relative matters. The novelty of the proposed MS-MOEA approach is its amalgamation of the basic evolutionary algorithms that are already shown to be highly effective, thereby creating a niche of these techniques. The niche takes advantages of the strengths of each baseline technique for achieving additional enhancement in the precision of the optimization. We propose six multi-stage hybrids, each designed with either niched fitness assignment strategy, or combining populations from multiple MOEAs, or incorporating the problem knowledge into the conventional technique. The experimental results measure the quality of resulting Pareto fronts and demonstrate that the proposed MS-MOEAs yield better optimization for the PETOS problem in achieving three-objective in parallel task-to-core mapping. (C) 2019 Elsevier Inc. All rights reserved.

关键词： Evolutionary algorithms Energy-efficient computing Task allocation Task graphs Static scheduling

来源：评论

学校读者我要写书评

暂无评论

Memristive Oscillatory Networks for computing: The Chemical Wave Propagation Paradigm

Memristive Oscillatory Networks for Computing: The Chemical ...

引用

ieee international workshop on Cellular Nanoscale Networks and their Applications, (CNNA)

作者： Theodoros Panagiotis Chatzinikolaou Iosif-Angelos Fyrigos Vasileios Ntinas Stavros Kitsios Panagiotis Bousoulas Michail-Antisthenis Tsompanas Dimitris Tsoukalas Georgios Ch. Sirakoulis Democritus University of Thrace Xanthi Greece Universitat Politecnica de Calatunya Barcelona Spain National Technical University of Athens Athens Greece

During the last decade, there is an ever-growing concern regarding the future of CMOS technology, as well as the emerging difficulties on handling upcoming technological issues related with silicon transistors' dimensions, electrical power, energy consumption, and last but not least reaching the physical limits of this technology. At the same time, new computing alternatives beyond the classical computing systems, namely von Neumman architectures, are heavily sought after to tackle energy and memory-wall problems. In this talk, we focus on a hybrid analogue computational circuit-level system with unipolar memristor nanodevices connected in oscillatory networks and based on wave-like propagation of information. These methods are inspired by biochemical processes occurring in nature. The proposed insightful electrochemical wave propagation is apparent in many natural and biological systems and is modelled with powerful, inherently parallel computational tools, like Cellular Automata (CAs). This framework enables us to further proceed into realising alternative types of computations executed on the designed, modelled and fabricated memristor nanodevices, which are finally employed for the design and development of wave based electronic computational units. The proposed nanoelectronic memristive oscillatory networks will be in the advantageous position to perform both classical and unconventional calculations, like multi-digit, in memory and neuromorphic, to name a few of them. Thus, we will have a powerful tool targeting beyond the existing von Neumann information processing techniques and alleviating the aforementioned disadvantages associated with them.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Communicate Efficiently with Group Division in Decentralized multi-Agent Cooperation 13

Learning to Communicate Efficiently with Group Division in D...

引用

13th ieee international Conference on Service-Oriented System Engineering (SOSE) / 10th international workshop on Joint Cloud computing (JCC) / ieee international workshop on Cloud computing in Robotic systems (CCRS)

作者： Liu, Shuqi Geng, Mingyang Xu, Kele Northeastern Univ Natl Key Lab Big Data Management & Anal Shenyang Liaoning Peoples R China Natl Univ Def Technol Natl Key Lab Parallel & Distributed Proc Changsha Hunan Peoples R China

ISBN: (数字)9781728114422

ISBN: (纸本)9781728114422

Recent advances in multi-agent reinforcement learning show that agents can spontaneously learn when and what to communicate with each other to support effective cooperation. However, the existing approaches assume a fully-connected network with unlimited bandwidth, which is impractical in many real-world scenarios. For instance, in many multi-robot applications, robots are connected only through an unstable wireless network with limited bandwidth. Therefore, we must enable the agents to learn communication strategy that takes the consumption of network resources into account. This paper proposes a group division-based attentional communication model (GDAC), which can divide agents into groups according to their "attention" in the learned communication strategy. According to the novel "attention" mechanism, agents can be dynamically grouped according to their task relevance, and the communication only takes places inside the same group. As a result, it avoids a fully-connected communication architecture and can significantly reduce the bandwidth consumption at runtime. This model has been successfully applied to the environmental exploration task with a group of agents. The results show that GDAC could effectively reduce the total amount of communication message and yield improved performance over the existing fully-connected communication architecture.

关键词： multi-agent cooperation attention mechanism deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Design of Knowledge Templates and multi-view Symbols for Experiential Learning 13

Design of Knowledge Templates and Multi-view Symbols for Exp...

引用

ieee 13th international Symposium on Embedded multicore/many-core systems-on-Chip (MCSoC)

作者： Hoshino, Takayuki Yoshioka, Rentaro Univ Aizu Grad Sch Comp Sci & Engn Aizu Wakamatsu Fukushima Japan Nihon Unisys Ltd Technol Res & Innovat Tokyo Japan

ISBN: (纸本)9781728148823

A design of a knowledge description method based on Knowledge Templates and multi-view Symbols for experiential learning is proposed. The proposed method is a unique approach for acquiring empirical data as knowledge and applying them to computing. For the domain of experiential learning, a knowledge model is designed based on the concept of Knowledge Templates, and a corresponding representation language is designed based on multi-view Symbols. This allows description of both domain specific knowledge and subjective knowledge to be acquired more easily and reliably compared to using natural languages. These designs also demonstrate the application of these concepts to a specific knowledge domain. In addition, the design is evaluated by simulated visualizations of knowledge and use-case based analysis.

关键词： Knowledge Template multi-view Symbol Knowledge Description Experiential Learning Knowledge Engineering

来源：评论

学校读者我要写书评

暂无评论

Toward Performance-Portable Finite Element Methods on High-Performance systems 3

Toward Performance-Portable Finite Element Methods on High-P...

引用

3rd international Conference on Recent Advances in Signal Processing, Telecommunications and computing (ieee SigTelCom)

作者： Kucher, Vladyslav Hunloh, Jens Gorlatch, Sergei Univ Munster Einsteinstr 62 Munster Germany

ISBN: (纸本)9781538679630

We aim at performance portability of finite-element methods for solving PDE (Partial Differential Equations) on high-performance systems, i.e., ensuring that the same application code achieves good performance across a broad class of parallel architectures, including multi-core CPUs and many-core GPUs from different vendors. We achieve this goal by extending the popular PDE solving framework DUNE and integrating it with our parallel programming framework PACXX. We describe the implementation of our approach and we show how it allows the application programmers to use single C++ source code on a variety of target architectures by compiling it with different back-ends of the PACXX framework, achieving competitive performance against manually optimized original DUNE kernels.

关键词： High-performance computing Finite elements Parallel computing multi-core CPU many-core GPU Partial Differential Equations (PDE) C plus plus libraries Compilers

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：