The Experts below are selected from a list of 20625 Experts worldwide ranked by ideXlab platform
Zheng Wang - One of the best experts on this subject based on the ideXlab platform.
-
automatic translation of data parallel programs for heterogeneous parallelism through openmp offloading
The Journal of Supercomputing, 2021Co-Authors: Farui Wang, Weizhe Zhang, Haonan Guo, Meng Hao, Zheng WangAbstract:Heterogeneous multicores like GPGPUs are now commonplace in modern computing systems. Although heterogeneous multicores offer the potential for high performance, programmers are struggling to program such systems. This paper presents OAO, a compiler-based approach to automatically translate shared-memory OpenMP data-parallel programs to run on heterogeneous multicores through OpenMP offloading directives. Given the large user base of shared memory OpenMP programs, our approach allows programmers to continue using a single-source-based programming language that they are familiar with while benefiting from the heterogeneous performance. OAO introduces a novel runtime optimization scheme to automatically eliminate unnecessary Host–Device communication to minimize the communication overhead between the Host and the accelerator Device. We evaluate OAO by applying it to 23 benchmarks from the PolyBench and Rodinia suites on two distinct GPU platforms. Experimental results show that OAO achieves up to 32 $$\times$$ speedup over the original OpenMP version, and can reduce the Host–Device communication overhead by up to 99% over the hand-translated version.
-
auto tuning streamed applications on intel xeon phi
International Parallel and Distributed Processing Symposium, 2018Co-Authors: Peng Zhang, Jianbin Fang, Tao Tang, Canqun Yang, Zheng WangAbstract:Many-core accelerators, as represented by the XeonPhi coprocessors and GPGPUs, allow software to exploit spatial and temporal sharing of computing resources to improve the overall system performance. To unlock this performance potential requires software to effectively partition the hardware resource to maximize the overlap between Host-Device communication and accelerator computation, and to match the granularity of task parallelism to the resource partition. However, determining the right resource partition and task parallelism on a per program, per dataset basis is challenging. This is because the number of possible solutions is huge, and the benefit of choosing the right solution may be large, but mistakes can seriously hurt the performance. In this paper, we present an automatic approach to determine the hardware resource partition and the task granularity for any given streamed application, targeting the Intel XeonPhi architecture. Instead of hand-crafting the heuristic for which the process will have to repeat for each hardware generation, we employ machine learning techniques to automatically learn it. We achieve this by first learning a predictive model offline using training programs; we then use the learned model to predict the resource partition and task granularity for any unseen programs at runtime. We apply our approach to 23 representative parallel applications and evaluate it on a CPU-XeonPhi mixed heterogenous many-core platform. Our approach achieves, on average, a 1.6x (upto 5.6x) speedup, which translates to 94.5% of the performance delivered by a theoretically perfect predictor.
X U Dongliang - One of the best experts on this subject based on the ideXlab platform.
-
design and optimization of embedded file system in embedded usb Host Device
Computer Engineering and Design, 2008Co-Authors: X U DongliangAbstract:Currently embedded USB-Host system has been applied far and wide,consequently how to realize the design and optimization of its file system becomes especially significant and crucial for the application of the embedded USB-Host system.On the basis of anal-yzing the structure principle of FAT16 file system and system structure of embedded file system based on the USB-Host Device,some optimizations methods to design and optimize the file system are presented.Then the related realization process of these optimizations is given.By implementing these methods,the efficiency and performance of file system are improved,especially for some applications with high requirement of real-time data.
George Spanoudakis - One of the best experts on this subject based on the ideXlab platform.
-
WARDOG: Awareness detection watchbog for Botnet infection on the Host Device
IEEE Transactions on Sustainable Computing, 2021Co-Authors: George Hatzivasilis, Othonas Soultatos, Panos Chatziadam, K. Fysarakis, Ioannis G. Askoxylakis, Sotiris Ioannidis, George Alexandris, Vasilis Katos, George SpanoudakisAbstract:Botnets constitute nowadays one of the most dangerous security threats worldwide. High volumes of infected machines are controlled by a malicious entity and perform coordinated cyber-attacks. The problem will become even worse in the era of the Internet of Things (IoT) as the number of insecure Devices is going to be exponentially increased. This paper presents WARDOG – an awareness and digital forensic system that informs the end-user of the botnet’s infection, exposes the botnet infrastructure, and captures verifiable data that can be utilized in a court of law. The responsible authority gathers all information and automatically generates a unitary documentation for the case. The document contains undisputed forensic information, tracking all involved parties and their role in the attack. The deployed security mechanisms and the overall administration setting ensures non-repudiation of performed actions and enforces accountability. The provided properties are verified through theoretic analysis. In simulated environment, the effectiveness of the proposed solution, in mitigating the botnet operations, is also tested against real attack strategies that have been captured by the FORTHcert honeypots, overcoming state-of-the-art solutions. Moreover, a preliminary version is implemented in real computers and IoT Devices, highlighting the low computational/communicational overheads of WARDOG in the field.
Hai Shen - One of the best experts on this subject based on the ideXlab platform.
-
real time data storage under embedded file system in embedded usb Host Device
Computer Engineering and Design, 2007Co-Authors: Hai ShenAbstract:With development of mobile data storage,embedded USB-Host system has been applied widely.So it is necessary and critical for some embedded USB-Host system to realize file system.The structure of FAT16 and the hiberarchy design frame of embedded file system in a USB-Host Device are introduced first,and some optimization methods for realization of file system are proposed.These methods improve the performance of file system greatly and satisfy some data sampling systems,which are used in real-time fields.
Kalus Jiří - One of the best experts on this subject based on the ideXlab platform.
-
A System for Organizing Running Races
Vysoké učení technické v Brně. Fakulta informačních technologií, 2017Co-Authors: Kalus JiříAbstract:This master’s thesis deals with the analysis, design and implementation of a system for organizing running races with the support of racers registration and the possibility of multiple online and offline checkpoints during the race. The system is composed of two web applications and a client desktop application. An administration web application is used to create and manage the race. A presentation web application with optional registration is responsible for publishing the race. It is possible to scan RFID chips of the racers on multiple track stations during the race using a client application. The RFID chips are scanned by an RFID reader connected to Host Device. If the client application is connected to the internet, the scanned times of racers are displayed on the presentation application in real time. Web applications are implemented with the ASP.NET MVC technology. Authorization and Authentication is provided by ASP.NET Identity. The client application is implemented using the WPF technology
-
A System for Organizing Running Races
Vysoké učení technické v Brně. Fakulta informačních technologií, 2017Co-Authors: Kalus JiříAbstract:Práce se zabývá analýzou, návrhem a implementací systému pro organizaci běžeckých závodů s podporou registrace a možností více traťových stanovišť v průběhu závodu. Systém je komponován ze dvou webových aplikací a klientské desktopové aplikace. Administrační webová aplikace slouží k vytvoření a správě závodu. Za publikaci závodu s podporou registrace nese zodpovědnost prezentační webová aplikace. V průběhu závodu je možné snímat RFID čipy závodníků na více traťových stanovištích pomocí klientské aplikace. RFID čipy jsou snímány RFID čtečkou, zapojenou do cílovém zařízení. Je-li klientská aplikace připojena k internetu, jsou zaznamenané časy zobrazeny na webovém prezentačním rozhraní v aktuálním čase. Webové aplikace jsou implementovány technologií ASP.NET MVC. Autorizaci a autentizaci zprostředkovává ASP.NET Identity. Klientská aplikace je implementována technologií WPF.This master’s thesis deals with the analysis, design and implementation of a system for organizing running races with the support of racers registration and the possibility of multiple online and offline checkpoints during the race. The system is composed of two web applications and a client desktop application. An administration web application is used to create and manage the race. A presentation web application with optional registration is responsible for publishing the race. It is possible to scan RFID chips of the racers on multiple track stations during the race using a client application. The RFID chips are scanned by an RFID reader connected to Host Device. If the client application is connected to the internet, the scanned times of racers are displayed on the presentation application in real time. Web applications are implemented with the ASP.NET MVC technology. Authorization and Authentication is provided by ASP.NET Identity. The client application is implemented using the WPF technology.