Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00023
Youngrang Kim, J. Lee, Jik-Soo Kim, Hyunseung Jei, Hongchan Roh
In this paper, we propose a new optimized memory management scheme that can improve the overall GPU memory utilization in multi-GPU systems for deep learning application acceleration. We extend the Nvidia's vDNN concept (a hybrid utilization of GPU and CPU memories) in a multi-GPU environment by effectively addressing PCIe-bus contention problems. In addition, we designed and implemented an intelligent prefetching algorithm (from CPU memory to GPU) that can achieve the highest processing throughput while sustaining a large min-batch size. For evaluation, we have implemented our memory usage optimization scheme on Tensorflow, the well-known machine learning library from Google, and performed extensive experiments in a multi-GPU testbed. Our evaluation results show that the proposed scheme can increase the mini-batch size by up to 60%, and improve the training throughput by up to 46.6% in a multi-GPU system.
{"title":"Efficient Multi-GPU Memory Management for Deep Learning Acceleration","authors":"Youngrang Kim, J. Lee, Jik-Soo Kim, Hyunseung Jei, Hongchan Roh","doi":"10.1109/FAS-W.2018.00023","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00023","url":null,"abstract":"In this paper, we propose a new optimized memory management scheme that can improve the overall GPU memory utilization in multi-GPU systems for deep learning application acceleration. We extend the Nvidia's vDNN concept (a hybrid utilization of GPU and CPU memories) in a multi-GPU environment by effectively addressing PCIe-bus contention problems. In addition, we designed and implemented an intelligent prefetching algorithm (from CPU memory to GPU) that can achieve the highest processing throughput while sustaining a large min-batch size. For evaluation, we have implemented our memory usage optimization scheme on Tensorflow, the well-known machine learning library from Google, and performed extensive experiments in a multi-GPU testbed. Our evaluation results show that the proposed scheme can increase the mini-batch size by up to 60%, and improve the training throughput by up to 46.6% in a multi-GPU system.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129401146","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00012
Danny Weyns
Engineering software that is subject to uncertainties that are difficult to anticipate before deployment is challenging. Self-adaptation extends a software system with an external feedback loop system that monitors the system and adapts its configuration or architecture to ensure that its qualities are met under uncertain operating conditions. In this tutorial, we provide a particular perspective on the evolution of the field of selfadaptation in six waves. These waves put complementary aspects of engineering self-adaptive systems in focus that synergetically have contributed to the current body of knowledge in the field.
{"title":"Engineering Self-Adaptive Software Systems – An Organized Tour","authors":"Danny Weyns","doi":"10.1109/FAS-W.2018.00012","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00012","url":null,"abstract":"Engineering software that is subject to uncertainties that are difficult to anticipate before deployment is challenging. Self-adaptation extends a software system with an external feedback loop system that monitors the system and adapts its configuration or architecture to ensure that its qualities are met under uncertain operating conditions. In this tutorial, we provide a particular perspective on the evolution of the field of selfadaptation in six waves. These waves put complementary aspects of engineering self-adaptive systems in focus that synergetically have contributed to the current body of knowledge in the field.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"122 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133665012","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00029
Jisun Oh, Seoyoung Kim, Yoonhee Kim
Virtualization is an innovative technology that accelerates software development by providing portability and maintainability of applications. However, it often leads underperformance especially caused by overheads from managing virtual machines. To address the limitation of virtual machines, container technology has emerged to deploy and operate distributed applications without launching entire virtual machines. Unfortunately, resources contention issues in container-based clusters, bringing substantial performance loss are still challenging. This paper proposes an adaptive fair-share method to share effectively in container-based virtualization environment. In particular, we focus on enabling GPU sharing between multiple concurrent containers without lack of GPU memory. We demonstrate that our approach contributes to overall performance improvement as well as higher resource utilization compared to default and static fair-share methods with homogeneous and heterogeneous workloads. Compared to two other conditions, their results show that the proposed method reduces by 16.37%, 15.61% in average execution time and boosts approximately by 52.46%, 10.3% in average GPU memory utilization, respectively.
{"title":"Toward an Adaptive Fair GPU Sharing Scheme in Container-Based Clusters","authors":"Jisun Oh, Seoyoung Kim, Yoonhee Kim","doi":"10.1109/FAS-W.2018.00029","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00029","url":null,"abstract":"Virtualization is an innovative technology that accelerates software development by providing portability and maintainability of applications. However, it often leads underperformance especially caused by overheads from managing virtual machines. To address the limitation of virtual machines, container technology has emerged to deploy and operate distributed applications without launching entire virtual machines. Unfortunately, resources contention issues in container-based clusters, bringing substantial performance loss are still challenging. This paper proposes an adaptive fair-share method to share effectively in container-based virtualization environment. In particular, we focus on enabling GPU sharing between multiple concurrent containers without lack of GPU memory. We demonstrate that our approach contributes to overall performance improvement as well as higher resource utilization compared to default and static fair-share methods with homogeneous and heterogeneous workloads. Compared to two other conditions, their results show that the proposed method reduces by 16.37%, 15.61% in average execution time and boosts approximately by 52.46%, 10.3% in average GPU memory utilization, respectively.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133083346","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00047
Christian Gruhl, Sven Tomforde, B. Sick
The basic idea of self-improving system integration (SISSY) is that the system itself autonomously decides about its own integration status and combines this maintenance with mechanisms to optimise it. Such an approach requires a quantifiable basis of all necessary system attributes and a set of goal functions defining desired solutions. In this article, we define a basic model of such a SISSY system and use this as basis to revisit possible aspects for measuring and evaluating the integration status. Different assessment criteria are suggested, based on performance, cost, security, behaviour, and more.
{"title":"Aspects of Measuring and Evaluating the Integration Status of a (Sub-)System at Runtime","authors":"Christian Gruhl, Sven Tomforde, B. Sick","doi":"10.1109/FAS-W.2018.00047","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00047","url":null,"abstract":"The basic idea of self-improving system integration (SISSY) is that the system itself autonomously decides about its own integration status and combines this maintenance with mechanisms to optimise it. Such an approach requires a quantifiable basis of all necessary system attributes and a set of goal functions defining desired solutions. In this article, we define a basic model of such a SISSY system and use this as basis to revisit possible aspects for measuring and evaluating the integration status. Different assessment criteria are suggested, based on performance, cost, security, behaviour, and more.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115150723","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00026
Jiwoong Park, H. Yeom
Most RDMA applications are based on either RC QP(Reliable Connected Queue Pair) or UD QP(Unreliable Datagram Queue Pair). RC QP has advantages on usability but disadvantages on scalability while UD QP is scalable but hard to use. Dynamically Connected (DC) transport has been introduced to address the limitations when using one of the existing QPs. However, DC transport is only available with hardware support. In this paper, we design and implement a totally software-based DCT prototype to eliminate hardware dependency. Our experimental results show that although our prototype adds a first-time connection overhead it could provide the advantages of both RC QP and UD QP. We also write and evaluate a DC QP-based application to prove its effectiveness compared to RC QP-based one.
{"title":"Design and Implementation of Software-Based Dynamically Connected Transport","authors":"Jiwoong Park, H. Yeom","doi":"10.1109/FAS-W.2018.00026","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00026","url":null,"abstract":"Most RDMA applications are based on either RC QP(Reliable Connected Queue Pair) or UD QP(Unreliable Datagram Queue Pair). RC QP has advantages on usability but disadvantages on scalability while UD QP is scalable but hard to use. Dynamically Connected (DC) transport has been introduced to address the limitations when using one of the existing QPs. However, DC transport is only available with hardware support. In this paper, we design and implement a totally software-based DCT prototype to eliminate hardware dependency. Our experimental results show that although our prototype adds a first-time connection overhead it could provide the advantages of both RC QP and UD QP. We also write and evaluate a DC QP-based application to prove its effectiveness compared to RC QP-based one.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"76 5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127393401","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}
Pub Date : 2018-09-01DOI: 10.1109/fas-w.2018.00001
{"title":"Title Page i","authors":"","doi":"10.1109/fas-w.2018.00001","DOIUrl":"https://doi.org/10.1109/fas-w.2018.00001","url":null,"abstract":"","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125338691","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00032
I. Gerostathopoulos, Ali Naci Uysal, C. Prehofer, T. Bures
In this paper, we present Online Experiment-Driven Adaptation (OEDA), a tool for performing end-to-end optimization of a target system abstracted as a black-box by combining statistical and optimization methods and providing statistical guarantees along the optimization process. We present the requirements and architecture of OEDA and describe its built-in optimization process that chains together factorial design, Bayesian optimization, and t-test. OEDA allows the user to create reusable abstractions of systems-to-be-optimized and specify, run and observe the execution of end-to-end experiments. For instance, we support data exchange with common tools like Kafka, MQTT and HTTP. We show the benefits of OEDA in a web server application example. OEDA can be a useful vehicle for research in the area of automated experimentation, an emerging challenge where systems are capable of performing experiments (akin to A/B testing) to themselves in order to self-optimize.
{"title":"A Tool for Online Experiment-Driven Adaptation","authors":"I. Gerostathopoulos, Ali Naci Uysal, C. Prehofer, T. Bures","doi":"10.1109/FAS-W.2018.00032","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00032","url":null,"abstract":"In this paper, we present Online Experiment-Driven Adaptation (OEDA), a tool for performing end-to-end optimization of a target system abstracted as a black-box by combining statistical and optimization methods and providing statistical guarantees along the optimization process. We present the requirements and architecture of OEDA and describe its built-in optimization process that chains together factorial design, Bayesian optimization, and t-test. OEDA allows the user to create reusable abstractions of systems-to-be-optimized and specify, run and observe the execution of end-to-end experiments. For instance, we support data exchange with common tools like Kafka, MQTT and HTTP. We show the benefits of OEDA in a web server application example. OEDA can be a useful vehicle for research in the area of automated experimentation, an emerging challenge where systems are capable of performing experiments (akin to A/B testing) to themselves in order to self-optimize.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121969427","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00014
Clément Elbaz, Louis Rilling, C. Morin
Cloud computing enabled service-level agreements (SLAs) to gain widespread use among information systems stakeholders. It is now normal for performance and availability of such systems to be carefully measured and evaluated. Contracts that include financial penalties in case of breach are now common. However security is lagging behind this trend; it is as important to stakeholders as performance and availability, but is generally not included in the scope of service-level agreements between stakeholders, and handled instead on a best-effort basis, without any transparency nor SLA with their clients. One reason for this is the difficulty of objectively measuring security. Indeed, the actual security level of a system is dependent on a wide range of factors, some intrinsic to the system - such as a design or implementation mistake resulting in a vulnerability - and some extrinsic to it. For instance, an external event such as the publication of a vulnerability in an open-source software dependency or a change of political context in a country can widely impact the risks faced by an information system even if no actual change were made to the system. These factors are even more numerous in multi-tenant cloud infrastructures because of the sheer number of actors involved - and their sometimes conflicting incentives - and opportunities for both attack and defense at scale. Security monitoring aims to detect and react to attacks in real time; Reactive security monitoring intends to take external events into account while doing so. Improving the accuracy of a system's overall security assessment can help transitioning security to a SLA paradigm and enable better transparency for all stakeholders.
{"title":"Reactive and Adaptive Security Monitoring in Cloud Computing","authors":"Clément Elbaz, Louis Rilling, C. Morin","doi":"10.1109/FAS-W.2018.00014","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00014","url":null,"abstract":"Cloud computing enabled service-level agreements (SLAs) to gain widespread use among information systems stakeholders. It is now normal for performance and availability of such systems to be carefully measured and evaluated. Contracts that include financial penalties in case of breach are now common. However security is lagging behind this trend; it is as important to stakeholders as performance and availability, but is generally not included in the scope of service-level agreements between stakeholders, and handled instead on a best-effort basis, without any transparency nor SLA with their clients. One reason for this is the difficulty of objectively measuring security. Indeed, the actual security level of a system is dependent on a wide range of factors, some intrinsic to the system - such as a design or implementation mistake resulting in a vulnerability - and some extrinsic to it. For instance, an external event such as the publication of a vulnerability in an open-source software dependency or a change of political context in a country can widely impact the risks faced by an information system even if no actual change were made to the system. These factors are even more numerous in multi-tenant cloud infrastructures because of the sheer number of actors involved - and their sometimes conflicting incentives - and opportunities for both attack and defense at scale. Security monitoring aims to detect and react to attacks in real time; Reactive security monitoring intends to take external events into account while doing so. Improving the accuracy of a system's overall security assessment can help transitioning security to a SLA paradigm and enable better transparency for all stakeholders.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114294754","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}
Pub Date : 2018-09-01DOI: 10.1109/FAS-W.2018.00024
Qichen Chen, H. Yeom
Non-volatile Memory is promising to persistent data storage, which has outstanding advantages against traditional storage devices such as HDD and SSD. One of its hugest advantages is its DRAM-like read latency and micro second level write latency, which is several hundred times faster than the original block device. However, one of the issues on using non-volatile memory as storage device is designing a suitable indexing system for data stores there, in which the characteristics of non-volatile memory can be able to make full use of. The state of the art indexing systems of non-volatile key-value stores are usually based on B+-tree or its variant, which are originally designed for mechanic hard disk and volatile memory. The semantics of B+-tree requires inside data being sorted and frequent split and merge for keeping its balance. However, both of sorting and splitting will cause extra write to non-volatile memory, which will downgrade the performance. As a result, B+-tree and its variant may not be naturally suitable for non-volatile memory. In this paper, we proposed a skiplist based indexing system for non-volatile memory key-value store(NV-Skiplist), which can take fully use of the features of both the non-volatile memory and DRAM. NV-Skiplist constructs its bottom layer in the non-volatile memory for data persistence and supporting range scan, it also builds its upper layers in the DRAM to retain fast index searching and prevent large consistent overhead. We also introduced a multi-ranged variant to increase the search performance. We evaluate the performance of NV-Skiplist on a non-volatile memory emulator with a server that has Intel Xeon E5-2620 v2 processor. The experimental results show that our design outperforms the original tree-based non-volatile key-value store on both insertion and search performance by both 27% and 12% in each case.
{"title":"Design of Skiplist Based Key-Value Store on Non-Volatile Memory","authors":"Qichen Chen, H. Yeom","doi":"10.1109/FAS-W.2018.00024","DOIUrl":"https://doi.org/10.1109/FAS-W.2018.00024","url":null,"abstract":"Non-volatile Memory is promising to persistent data storage, which has outstanding advantages against traditional storage devices such as HDD and SSD. One of its hugest advantages is its DRAM-like read latency and micro second level write latency, which is several hundred times faster than the original block device. However, one of the issues on using non-volatile memory as storage device is designing a suitable indexing system for data stores there, in which the characteristics of non-volatile memory can be able to make full use of. The state of the art indexing systems of non-volatile key-value stores are usually based on B+-tree or its variant, which are originally designed for mechanic hard disk and volatile memory. The semantics of B+-tree requires inside data being sorted and frequent split and merge for keeping its balance. However, both of sorting and splitting will cause extra write to non-volatile memory, which will downgrade the performance. As a result, B+-tree and its variant may not be naturally suitable for non-volatile memory. In this paper, we proposed a skiplist based indexing system for non-volatile memory key-value store(NV-Skiplist), which can take fully use of the features of both the non-volatile memory and DRAM. NV-Skiplist constructs its bottom layer in the non-volatile memory for data persistence and supporting range scan, it also builds its upper layers in the DRAM to retain fast index searching and prevent large consistent overhead. We also introduced a multi-ranged variant to increase the search performance. We evaluate the performance of NV-Skiplist on a non-volatile memory emulator with a server that has Intel Xeon E5-2620 v2 processor. The experimental results show that our design outperforms the original tree-based non-volatile key-value store on both insertion and search performance by both 27% and 12% in each case.","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"96 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128136798","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}
Pub Date : 2018-09-01DOI: 10.1109/fas-w.2018.00007
H. Yeom, Kento Aida, Jaeyoung Choi, Young-ri Choi, E. Deelman, Sandro Fiore, R. G. Diaz, Hyeonsang Eom, E. Heien, J. Jensen, Jik-Soo Kim, Yoonhee Kim, Youngjae Kim, Jaewook Lee, K. Lee, J. Lee, Myungho Lee, Young-Choon Lee, R. Montella, Taiga Nakamura, Beom-Il Nam, S. Pallickara, Seung-Jong Park, Sungyong Park, R. Quick, Ilkyeun Ra, D. Sarramia, Yoshio Tanaka, Taro Tezuka, S. Timm, Ananta Tiwari, J. L. Vázquez-Poletti, J. Wozniak
{"title":"AMGCC 2018 Foreword","authors":"H. Yeom, Kento Aida, Jaeyoung Choi, Young-ri Choi, E. Deelman, Sandro Fiore, R. G. Diaz, Hyeonsang Eom, E. Heien, J. Jensen, Jik-Soo Kim, Yoonhee Kim, Youngjae Kim, Jaewook Lee, K. Lee, J. Lee, Myungho Lee, Young-Choon Lee, R. Montella, Taiga Nakamura, Beom-Il Nam, S. Pallickara, Seung-Jong Park, Sungyong Park, R. Quick, Ilkyeun Ra, D. Sarramia, Yoshio Tanaka, Taro Tezuka, S. Timm, Ananta Tiwari, J. L. Vázquez-Poletti, J. Wozniak","doi":"10.1109/fas-w.2018.00007","DOIUrl":"https://doi.org/10.1109/fas-w.2018.00007","url":null,"abstract":"","PeriodicalId":164903,"journal":{"name":"2018 IEEE 3rd International Workshops on Foundations and Applications of Self* Systems (FAS*W)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121641815","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：