Computer Graphics Forum is the premier journal for in-depth technical articles on computer graphics. Published jointly by Wiley and Eurographics, we enable our readers to keep pace with this fast-moving field with our...
Computer Graphics Forum is the premier journal for in-depth technical articles on computer graphics. Published jointly by Wiley and Eurographics, we enable our readers to keep pace with this fast-moving field with our rapid publication times and coverage of major international computer graphics events, including the annual Eurographics Conference proceedings. We welcome original research papers on a wide range of topics including image synthesis, rendering, perception and *** following is a list of the most cited articles based on citations published in the last three years, according to CrossRef.
Facilitating time to discovery by scientists through computing is an idea that has been around for a significant amount of time. Often, however, domain scientists and computer scientists work in parallel rather than i...
详细信息
Facilitating time to discovery by scientists through computing is an idea that has been around for a significant amount of time. Often, however, domain scientists and computer scientists work in parallel rather than in collaboration with one another. It has been a goal of this workshop (the fifth of its kind) to showcase the examples of such collaborations or tools that enable these collaborations to flourish. This editorial provides an overview of papers requested from a sampling of applied scientific collaborations that were presented at the 2008 Microsoft eScience Workshop. Copyright (C) 2010 John Wiley & Sons, Ltd.
concurrency control protocols play a vital role in ensuring the correctness of databases when transactions are processed in parallel. Plor is a non-real-time concurrency control protocol based on the 2-phase locking p...
详细信息
concurrency control protocols play a vital role in ensuring the correctness of databases when transactions are processed in parallel. Plor is a non-real-time concurrency control protocol based on the 2-phase locking protocol. Plor utilizes the Wound-Wait scheme, a timestamp-based scheme for deadlock prevention, as it provides lower tail latency. One problem of Plor with that it requires transactions to fetch timestamps from a single centralized atomic counter. This paper evaluates the implementation of the Fair Thread ID method (FairTID), a decentralized approach where transactions use the thread IDs as their timestamps instead. The FairTID method shows up to 1.5 times throughput improvement while reducing latency by 1.6 times and the deadline-miss ratio by 1.67 times over the baseline protocol. The application of the method is formally verified for fairness reasoning.
In the cloud computing environment, workflow scheduling presents a significant challenge due to the unpredictable and dynamic nature of user demands and cloud resources. To address the complexities of workflow schedul...
详细信息
In the cloud computing environment, workflow scheduling presents a significant challenge due to the unpredictable and dynamic nature of user demands and cloud resources. To address the complexities of workflow scheduling, this paper introduces a dynamic multi-objective workflow scheduling model that comprehensively considers task completion time, load balancing, as well as dynamic changes in power consumption and cost in real-world scenarios. To effectively solve this model and better adapt to dynamic multi-objective optimization problems, we propose a dynamic reference vector guided evolutionary algorithm (DRVEA). The proposed algorithm incorporates an adaptive random mutation strategy, which dynamically adjusts the evolutionary process based on changing optimization goals, thereby enhancing convergence and solution diversity. Experimental results, obtained from both workflow scheduling simulations and standard multi-objective test environments, demonstrate that the proposed algorithm outperforms existing methods, achieving superior results in both solution quality and adaptability.
Mixed-precision computation is a promising method for substantially improving high-performance computing applications. However, using mixed-precision data is a double-edged sword. While it can improve computational pe...
详细信息
Mixed-precision computation is a promising method for substantially improving high-performance computing applications. However, using mixed-precision data is a double-edged sword. While it can improve computational performance, the reduction in precision introduces more uncertainties and errors. As a result, precision tuning is necessary to determine the optimal mixed-precision configurations. Much effort is therefore spent on selecting appropriate variables while balancing execution time and numerical accuracy. Auto-tuning (AT) is one of the technologies that can assist in alleviating this intensive task. In recent years, ppOpen-AT, an AT language, introduced a directive for mixed-precision tuning called "Blocks." In this study, we investigated an AT strategy for the "Blocks" directive for multi-region tuning of a program. The non-hydrostatic icosahedral atmospheric model (NICAM), a global cloud-resolving model, was used as a benchmark program to evaluate the effectiveness of the AT strategy. Experimental results indicated that when a single region of the program performed well in mixed-precision computation, combining these regions resulted in better performance. When tested on the supercomputer "Flow" Type I (Fujitsu PRIMEHPC FX1000) and Type II (Fujitsu PRIMEHPC CX1000) subsystems, the mixed-precision NICAM benchmark program tuned by the AT strategy achieved a speedup of nearly 1.31x on the Type I subsystem compared to the original double-precision program, and a 1.12x speedup on the Type II subsystem.
暂无评论