Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications最新文献

A unified scaling model in the era of big data analytics 大数据分析时代的统一尺度模型

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318268

Zhongwei Li, Feng Duan, Hao Che

{"title":"A unified scaling model in the era of big data analytics","authors":"Zhongwei Li, Feng Duan, Hao Che","doi":"10.1145/3318265.3318268","DOIUrl":"https://doi.org/10.1145/3318265.3318268","url":null,"abstract":"As scale-out execution of big data analytics has become predominate datacenter workloads, it is of paramount importance to faithfully characterize the scaling properties for such workloads. To date, the most widely cited scaling laws for big data analytics is the traditional Amdahl's law, which was discovered well before the era of big data analytics. A key observation made in this paper is that both the system and workload models underlying the traditional scaling laws are too simplistic to fully characterize the scaling properties for big data analytics workloads. In this paper, we put forward a Unified Scaling model for Big data Analytics (USBA), based on a multi-stage system model and a discretized workload model. USBA allows for flexible workload scaling unifying the fixed-size and fixed-time workload models underlying Amdahl's and Gustafson's laws, respectively, and flexible system scaling in terms of both number of stages and degree of parallelism per stage. Moreover, to faithfully characterize the scaling properties for big data analytics workloads, USBA accounts for variabilities of task response times and barrier synchronization. Finally, application of USBA to the scaling analysis of four Spark-based data mining and graph benchmarks demonstrates that USBA is able to adequately characterize the scaling design space and predict the scaling properties of real-world big data analytics workloads. This makes it possible to use USBA as a useful tool to facilitate job resource provisioning for big data analytics in datacenters.","PeriodicalId":241692,"journal":{"name":"Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123131614","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

Performance analysis of co-operative MIMO channel over sensor control networks 传感器控制网络协同MIMO信道性能分析

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318286

Summera Shamrooz, Qianmu Li

引用次数: 0

OPS: an optimized partial stripe write scheme to improve performance of XOR-based disk arrays tolerating triple disk failures OPS:一种优化的部分分条写方案，用于提高基于xor的磁盘阵列在三盘故障情况下的性能

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318274

Xunsong Huang, Chentao Wu, Jie Li

引用次数: 2

A radio environment map construction scheme with hidden Markov Model based spectrum occupancy prediction 一种基于隐马尔可夫模型的频谱占用预测无线电环境图构建方案

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318284

Liwei Huang, W. Shao, Yan Zhang, Jun-Jie Yang, Yaxiang Liu

引用次数: 4

Two-stage population based training method for deep reinforcement learning 基于两阶段人口的深度强化学习训练方法

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318294

Yinda Zhou, W. Liu, Bin Li

{"title":"Two-stage population based training method for deep reinforcement learning","authors":"Yinda Zhou, W. Liu, Bin Li","doi":"10.1145/3318265.3318294","DOIUrl":"https://doi.org/10.1145/3318265.3318294","url":null,"abstract":"Deep reinforcement learning (DRL) methods has been widely applied on more and more challenging learning tasks, and achieved excellent performance. However, the efficiency of deep reinforcement learning is notoriously sensitive to their own hyperparameter configuration. The optimization process of deep reinforcement learning is highly dynamic and non-stationary, rather than a simple fitting process. So, its optimal hyperparameter should be adaptively adjusted according to the current learning process, rather than using a fixed set of hyperparameter configurations from beginning to end. DeepMind innovatively proposed a population based training (PBT) method for deep reinforcement learning, which achieved hyperparameter adaptation and made the model better trained. However, we assume that at the early stage when the learning model has little knowledge of the environment, frequent hyperparameter change will not be helpful for the model to learn efficiently, while learning with a reasonable fixed hyperparameter configuration will help the model obtain necessary knowledge as quick as possible, which we consider is more important for reinforcement learning at early stage. In this paper, we verified our hypothesis through experiments, and a Two-Stage Population Based Training (TS-PBT) method is proposed, which is a more efficient population based training method for deep reinforcement learning. Experiments show that at the same computational budget, our TS-PBT method makes the final performance of the model significantly better than the PBT method. TS-PBT achieved 40%, 310%, 2%, 53%, 30% and 38% performance improvement over PBT separately in six test environments.","PeriodicalId":241692,"journal":{"name":"Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-03-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121950329","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: 0

A parallel clustering algorithm for logs data based on Hadoop platform 基于Hadoop平台的日志数据并行聚类算法

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318281

J. Huo, Jia-Yow Weng, Hong Qu

引用次数: 3

Automatic essay scoring with recurrent neural network 基于递归神经网络的论文自动评分

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318296

Changzhi Cai

引用次数: 6

Data fusion algorithms for wireless sensor networks based on deep learning model 基于深度学习模型的无线传感器网络数据融合算法

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318297

Lihong Wang, Kuiliang Xia

引用次数: 4

A road network matching method based on particle swarm optimization 一种基于粒子群优化的路网匹配方法

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318282

F. Zhu, Peng-Zhong Wang

引用次数: 0

Siamese bayesian networks for AI based differential diagnosis 基于人工智能的连体贝叶斯网络鉴别诊断

Proceedings of the 3rd International Conference on High Performance Compilation, Computing and Communications Pub Date : 2019-03-08 DOI: 10.1145/3318265.3318298

Monish Kaul, Nikhil S. Narayan, A. Narayanan

引用次数: 0