2016 Fourth International Symposium on Computing and Networking (CANDAR)最新文献_第2页

A Directive Generation Approach Using User-Defined Rules 使用用户自定义规则的指令生成方法

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0095

K. Komatsu, Ryusuke Egawa, H. Takizawa, Hiroaki Kobayashi

{"title":"A Directive Generation Approach Using User-Defined Rules","authors":"K. Komatsu, Ryusuke Egawa, H. Takizawa, Hiroaki Kobayashi","doi":"10.1109/CANDAR.2016.0095","DOIUrl":"https://doi.org/10.1109/CANDAR.2016.0095","url":null,"abstract":"The appearance of various high-performance computing (HPC) systems compels a user to write a code considering the characteristic of each HPC system. To describe the system-dependent information without drastic code modifications, the directive sets such as the OpenMP directive set and the OpenACC directive set are useful. However, a code becomes complex to achieve high performance on various HPC systems because different directive sets are required for each HPC system. Thus, the code maintainability and readability are degraded. This paper proposes a directive generation approach that generates various kinds of directive sets using user-defined rules. Instead of several kinds of directive sets, a user writes a special placeholder that is utilized to specify a unique code pattern where several directives are inserted. Then, the special placeholder triggers generation of appropriate directives for each system using a user-defined rule with a code translation framework Xevolver. Because only special placeholders are inserted in a code, the proposed approach can keep the code maintainability and readability. From the demonstration of translation into three kinds of directive-based implementations, it is clarified that the proposed approach can replace directives into a smaller number of special placeholders. Moreover, it is clarified that the proposed approach can realize high performance portability by generating appropriate directives for each HPC system.","PeriodicalId":322499,"journal":{"name":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131079146","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Memory-Access-Efficient Implementation of the Approximate String Matching Algorithm on GPU 近似字符串匹配算法在GPU上的高效内存实现

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0090

L. S. N. Nunes, J. Bordim, K. Nakano, Yasuaki Ito

引用次数: 5

Evaluation of Task Mapping on Multicore Neural Network Accelerators 多核神经网络加速器上任务映射的评价

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0078

S. Shindo, Momoka Ohba, Tomoaki Tsumura, Shinobu Miwa

{"title":"Evaluation of Task Mapping on Multicore Neural Network Accelerators","authors":"S. Shindo, Momoka Ohba, Tomoaki Tsumura, Shinobu Miwa","doi":"10.1109/CANDAR.2016.0078","DOIUrl":"https://doi.org/10.1109/CANDAR.2016.0078","url":null,"abstract":"Deep neural networks are widely used for many applications such as image classification, speech recognition and natural language processing because of their high recognition rate. Since general-purpose processors such as CPUs and GPUs are not energy efficient for such neural networks, application specific hardware accelerators for neural networks (a.k.a. neural network accelerators or NNAs) have been proposed to improve the energy efficiency. There are many studies to increase the energy efficiency of NNAs, but few studies focus on task allocation on the accelerators. This paper provides the first exploration of task mapping to cores within NNAs for the increased performance. Intuitively, a well-tuned task mapping has less amount of communication between cores. To confirm this assumption, we tested two types of task mappings that generate different amount of communication between cores on an NNA. Our experimental results show that the number of communication between cores strongly affects the execution cycle of the NNA and the most effective task mapping differs depending on the size of neural networks.","PeriodicalId":322499,"journal":{"name":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129287622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Fast Hybrid Approach for Stream Compaction on GPUs gpu上流压缩的快速混合方法

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0089

V. Rego, Janche Sang, Chansu Yu

引用次数: 6

Computation Based on Signal Random Fluctuation in Asynchronous Cellular Automata 基于异步元胞自动机信号随机波动的计算

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0051

Wen-Li Xu, Jia Lee

引用次数: 1

A Password-Protected Secret Sharing Based on Kurosawa-Desmedt Hybrid Encryption 基于Kurosawa-Desmedt混合加密的密码保护秘密共享

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0108

T. Arai, Satoshi Obana

{"title":"A Password-Protected Secret Sharing Based on Kurosawa-Desmedt Hybrid Encryption","authors":"T. Arai, Satoshi Obana","doi":"10.1109/CANDAR.2016.0108","DOIUrl":"https://doi.org/10.1109/CANDAR.2016.0108","url":null,"abstract":"Needs for secret sharing scheme is increasing as demands for cloud services grow. However, secret sharing scheme possesses a drawback in that unauthorized users who can access storages storing partial information can reconstruct a secret. Password-Protected Secret Sharing (PPSS) was proposed in order to resolve such a drawback. PPSS is a secret sharing scheme that ensures only the owner of the secret who knows correct password to get the original secret by applying password authentication to partial information. The first PPSS was proposed by Bagherzandi et al. in 2011. When a secret is large, their scheme encrypts the secret with symmetric key encryption (SKE) and then encrypts the symmetric key with CPA secure public key encryption (PKE). Because of such combination, it seems difficult to prove strong security (i.e., CCA security) of their scheme at least in the standard model. In this paper, we propose a new PPSS model and scheme which does not use a simple combination of SKE and CPA secure PKE but use Kurosawa-Desmedt hybrid encryption, that is proven to be CCA secure in the standard model. Proposed PPSS is constructed by combining public key part of Kurosawa-Desmedt hybrid encryption with password authentication. Our scheme is expected to be more secure than that of Bagherzandi et al.","PeriodicalId":322499,"journal":{"name":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","volume":"3 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131437757","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 2

A User-Defined Code Transformation Approach to Overlapping MPI Communication with Computation MPI通信与计算重叠的用户定义代码转换方法

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0094

Yasuharu Hayashi, H. Takizawa, Hiroaki Kobayashi

引用次数: 1

Introducing PSO for Optimal Packet Scheduling of Collective Communication 引入粒子群算法实现集体通信的最优分组调度

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0080

T. Yokota, K. Ootsu, Takeshi Ohkawa

{"title":"Introducing PSO for Optimal Packet Scheduling of Collective Communication","authors":"T. Yokota, K. Ootsu, Takeshi Ohkawa","doi":"10.1109/CANDAR.2016.0080","DOIUrl":"https://doi.org/10.1109/CANDAR.2016.0080","url":null,"abstract":"Interconnection network is an inevitable component that is responsible to the system's communication capability. It affects the system-level performance as well as the physical and logical structure of the parallel system. Many studies are reported to enhance the interconnection network technology, however, we have to further discuss remaining issues for building large-scale systems. One of the most important issues is congestion management. In an interconnection network, packets are transferred simultaneously, and the packets interfere to each other on the network. Congestion arises as a result of the interference among packets. Its fast spreading speed degrades communication performance drastically and it continues for long time. Thus, we should appropriately control the network to suppress the congested situation for maintaining the maximum performance. Many studies address the problem and present effective methods, however, the maximal performance in an ideal situation is not sufficiently clarified. Solving the ideal performance is, in general, an NP-hard problem. This paper introduces particle swarm optimization (PSO) method to overcome the problem. In this paper, we first formalize the optimization problem suitable for the PSO method and present three PSO methods for avoiding local minima. We furthermore introduce some non-PSO methods for comparison. Our preliminary evaluation results reveal high potentials of the PSO method.","PeriodicalId":322499,"journal":{"name":"2016 Fourth International Symposium on Computing and Networking (CANDAR)","volume":"185 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2016-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115901041","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

A Self-Optimizing Routing Algorithm in a 3-Dimensional Virtual Grid Network 三维虚拟网格网络中的自优化路由算法

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0020

Yonghwan Kim, Y. Katayama

引用次数: 0

A Hotel Recommendation System Based on Reviews: What Do You Attach Importance To? 基于评论的酒店推荐系统:你重视什么?

2016 Fourth International Symposium on Computing and Networking (CANDAR) Pub Date : 2016-11-01 DOI: 10.1109/CANDAR.2016.0129

Koji Takuma, Junya Yamamoto, S. Kamei, S. Fujita

引用次数: 19