The Experts below are selected from a list of 34383 Experts worldwide ranked by ideXlab platform
Franziska Plessow - One of the best experts on this subject based on the ideXlab platform.
-
efficient Multitasking parallel versus serial processing of multiple tasks
Frontiers in Psychology, 2015Co-Authors: Rico Fischer, Franziska PlessowAbstract:In the context of performance optimizations in Multitasking, a central debate has unfolded in Multitasking research around whether cognitive processes related to different tasks proceed only sequentially (one at a time), or can operate in parallel (simultaneously). This review features a discussion of theoretical considerations and empirical evidence regarding parallel versus serial task processing in Multitasking. In addition, we highlight how methodological differences and theoretical conceptions determine the extent to which parallel processing in Multitasking can be detected, to guide their employment in future research. Parallel and serial processing of multiple tasks are not mutually exclusive. Therefore, questions focusing exclusively on either task-processing mode are too simplified. We review empirical evidence and demonstrate that shifting between more parallel and more serial task processing critically depends on the conditions under which multiple tasks are performed. We conclude that efficient Multitasking is reflected by the ability of individuals to adjust Multitasking performance to environmental demands by flexibly shifting between different processing strategies of multiple task-component scheduling.
Michael J. Schulte - One of the best experts on this subject based on the ideXlab platform.
-
the case for gpgpu spatial Multitasking
High-Performance Computer Architecture, 2012Co-Authors: Jacob Adriaens, Katherine Compton, Nam Sung Kim, Michael J. SchulteAbstract:The set-top and portable device market continues to grow, as does the demand for more performance under increasing cost, power, and thermal constraints. The integration of Graphics Processing Units (GPUs) into these devices and the emergence of general-purpose computations on graphics hardware enable a new set of highly parallel applications. In this paper, we propose and make the case for a GPU Multitasking technique called spatial Multitasking. Traditional GPU Multitasking techniques, such as cooperative and preemptive Multitasking, partition GPU time among applications, while spatial Multitasking allows GPU resources to be partitioned among multiple applications simultaneously. We demonstrate the potential benefits of spatial Multitasking with an analysis and characterization of General-Purpose GPU (GPGPU) applications. We find that many GPGPU applications fail to utilize available GPU resources fully, which suggests the potential for significant performance benefits using spatial Multitasking instead of, or in combination with, preemptive or cooperative Multitasking. We then implement spatial Multitasking and compare it to cooperative Multitasking using simulation. We evaluate several heuristics for partitioning GPU stream multiprocessors (SMs) among applications and find spatial Multitasking shows an average speedup of up to 1.19 over cooperative Multitasking when two applications are sharing the GPU. Speedups are even higher when more than two applications are sharing the GPU.
-
Gpgpu Multitasking and scheduling
2012Co-Authors: Michael J. Schulte, Katherine Compton, Jacob AdriaensAbstract:The set-top and portable device market continues to grow, as does the demand for improved performance, cost, and power. The integration of Graphics Processing Units (GPUs) into these devices and the emergence of general-purpose computations on graphics hardware enable a new set of highly parallel applications. To facilitate these applications, I propose and make the case for a novel GPU Multitasking technique called spatial Multitasking. Traditional GPU Multitasking techniques, such as cooperative and preemptive Multitasking, partition GPU time among applications, while spatial Multitasking allows GPU resources to be partitioned among multiple applications simultaneously. I demonstrate the potential benefits of spatial Multitasking with an analysis and characterization of General-Purpose GPU (GPGPU) applications. My analysis indicates that many GPGPU applications fail to utilize available GPU resources fully, which suggests the potential for significant performance benefits using spatial Multitasking instead of, or in combination with, preemptive or cooperative Multitasking. I use simulation to evaluate a simple implementation of spatial Multitasking against cooperative Multitasking. This implementation of spatial Multitasking shows an average speedup of 1.14, 1.22, and 1.30 compared to cooperative Multitasking when two, three, and four applications share the GPU, respectively. I follow this with an evaluation of more complex resource partitioning heuristics for spatial Multitasking and show even greater speedup of spatial Multitasking over cooperative Multitasking. Finally, I explore providing Quality-of-Service to GPGPU applications using spatial Multitasking and show significant benefits compared to Quality-of-Service using temporal Multitasking.
-
HPCA - The case for GPGPU spatial Multitasking
IEEE International Symposium on High-Performance Comp Architecture, 2012Co-Authors: Jacob Adriaens, Katherine Compton, Nam Sung Kim, Michael J. SchulteAbstract:The set-top and portable device market continues to grow, as does the demand for more performance under increasing cost, power, and thermal constraints. The integration of Graphics Processing Units (GPUs) into these devices and the emergence of general-purpose computations on graphics hardware enable a new set of highly parallel applications. In this paper, we propose and make the case for a GPU Multitasking technique called spatial Multitasking. Traditional GPU Multitasking techniques, such as cooperative and preemptive Multitasking, partition GPU time among applications, while spatial Multitasking allows GPU resources to be partitioned among multiple applications simultaneously. We demonstrate the potential benefits of spatial Multitasking with an analysis and characterization of General-Purpose GPU (GPGPU) applications. We find that many GPGPU applications fail to utilize available GPU resources fully, which suggests the potential for significant performance benefits using spatial Multitasking instead of, or in combination with, preemptive or cooperative Multitasking. We then implement spatial Multitasking and compare it to cooperative Multitasking using simulation. We evaluate several heuristics for partitioning GPU stream multiprocessors (SMs) among applications and find spatial Multitasking shows an average speedup of up to 1.19 over cooperative Multitasking when two applications are sharing the GPU. Speedups are even higher when more than two applications are sharing the GPU.
Scott Mahlke - One of the best experts on this subject based on the ideXlab platform.
-
dynamic resource management for efficient utilization of Multitasking gpus
Architectural Support for Programming Languages and Operating Systems, 2017Co-Authors: Jason Jong Kyu Park, Yongjun Park, Scott MahlkeAbstract:As graphics processing units (GPUs) are broadly adopted, running multiple applications on a GPU at the same time is beginning to attract wide attention. Recent proposals on Multitasking GPUs have focused on either spatial Multitasking, which partitions GPU resource at a streaming multiprocessor (SM) granularity, or simultaneous multikernel (SMK), which runs multiple kernels on the same SM. However, Multitasking performance varies heavily depending on the resource partitions within each scheme, and the application mixes. In this paper, we propose GPU Maestro that performs dynamic resource management for efficient utilization of Multitasking GPUs. GPU Maestro can discover the best performing GPU resource partition exploiting both spatial Multitasking and SMK. Furthermore, dynamism within a kernel and interference between the kernels are automatically considered because GPU Maestro finds the best performing partition through direct measurements. Evaluations show that GPU Maestro can improve average system throughput by 20.2% and 13.9% over the baseline spatial Multitasking and SMK, respectively.
Se-hoon Jeong - One of the best experts on this subject based on the ideXlab platform.
-
When does Multitasking facilitate information processing? Effects of Internet-based Multitasking on information seeking and information gain
Korean Social Science Journal, 2014Co-Authors: Yoori Hwang, Se-hoon JeongAbstract:This study examined whether Internet-based Multitasking facilitates information gain by allowing users to seek additional information online. Study 1, using survey data, suggested that TV-Internet Multitasking increased information gain, whereas TV-print media Multitasking reduced it. In addition, online information seeking mediated the effect of TV-Internet Multitasking on information gain. Study 2, using experimental data, confirmed the differential effects of TV-Internet Multitasking and TV-print Multitasking on information gain. The theoretical and practical implications of these findings are further discussed.
-
Multitasking and Persuasion: The Role of Structural Interference
Media Psychology, 2014Co-Authors: Se-hoon Jeong, Yoori HwangAbstract:Although the inhibiting effects of Multitasking can be explained by 2 components, capacity interference (CI) and structural interference (SI), studies that have specifically focused on SI are limited. Thus, the present study examined the effects of SI in persuasion using 2 experimental studies. Results of Study 1 showed that SI (not CI) reduced both comprehension and counterarguing. In addition, results of Study 2 showed that SI effects occur not only in single-channel Multitasking but also in dual-channel Multitasking, and that SI effects occur not only when content interference is high (language-based Multitasking) but also when it is low (non–language-based Multitasking). The role of SI in Multitasking effects has important implications for research on audience behaviors and persuasive communication.
-
Why do media users multitask
Computers in Human Behavior, 2014Co-Authors: Yoori Hwang, Hyoungjee Kim, Se-hoon JeongAbstract:We examined users' motives for general, medium-specific, and content-specific Multitasking.The key motives were information, social, enjoyment, efficiency, and habit.General Multitasking was predicted by information, efficiency, and habit.Medium specific and content specific types of Multitasking were predicted by various different motives. This study examined the major motives for Multitasking, and how those motives are related to general, medium-specific, and content-specific types of Multitasking. The major motives for Multitasking identified in this study are as follows: information, social, enjoyment, efficiency, and habit. Of these motives, general Multitasking behavior was predicted by information, efficiency, and habit. In terms of medium-specific types of Multitasking, TV-based Multitasking was predicted by habit motive, Internet-based Multitasking was predicted by information and enjoyment, and mobile-based Multitasking was predicted by information motives. In terms of content-specific Multitasking, news-related Multitasking was predicted by information motives, entertainment-related Multitasking was predicted by information and enjoyment motives, and advertising-related Multitasking was predicted by information and social motives.
-
Does Multitasking Increase or Decrease Persuasion? Effects of Multitasking on Comprehension and Counterarguing
Journal of Communication, 2012Co-Authors: Se-hoon Jeong, Yoori HwangAbstract:This study examined the effects of Multitasking on persuasion, including comprehension andcounterarguingofpersuasivemessages,whichwerepresentedinthreedifferentcontexts: (a) nonMultitasking with full attention paid to the message, (b) Multitasking with primary attention paid to the message, and (c) Multitasking with secondary attention paid to the message. Consistent with predictions, the results suggested that Multitasking reduced the actual and perceived levels of comprehension and also reduced counterarguing. The implications for research on persuasion are further discussed.
Terry Judd - One of the best experts on this subject based on the ideXlab platform.
-
Making sense of Multitasking
Computers & Education, 2014Co-Authors: Terry JuddAbstract:Media Multitasking and Facebook use are commonplace among college and university-aged students. While the two are often linked and each has been independently associated with reductions in academic performance, their relationship to each other is not particularly well understood.This relationship was examined by analysing comprehensive time-based logs of students' computer-based tasks, including Facebook, during unsupervised, self-directed learning sessions. A total of 3372 sessions contributed by 1249 students were analysed. Multitasking was extremely common - around 99% of sessions involved some Multitasking (at least three instances of a particular task within a 20?min period). Facebook was the second most common task overall (University was first), accounting for 9.2% of all task instances and being present in 44% of sessions. Sessions containing Facebook typically contained more, shorter duration tasks and were significantly more likely to include Multitasking behaviour. The introduction of Facebook within a session was associated with an increase in Multitasking and a reduction in focused (no more than two tasks in a 20?min period) behaviour. Facebook users (students who contributed at least five sessions and used Facebook in at least one of these sessions) were also more likely to multitask and less likely to engage in focused behaviour. These results confirm that Facebook use is a key contributor to students' task switching and Multitasking behaviours. We examine the relationship between Facebook use and Multitasking behaviour.Facebook use is associated with increased task-switching and Multitasking.Facebook use initiates and promotes Multitasking behaviours.Facebook users are more likely to multitask during self-directed learning.
-
Making sense of Multitasking: Key behaviours
Computers & Education, 2013Co-Authors: Terry JuddAbstract:Traditionally viewed as a positive characteristic, there is mounting evidence that Multitasking using digital devices can have a range of negative impacts on task performance and learning. While the cognitive processes that cause these impacts are starting to be understood and the evidence that they occur in real learning contexts is mounting, the mechanics and extent of students' task switching and Multitasking during learning activities is neither well documented or understood. This study seeks to redress this gap by defining and describing key task switching and Multitasking behaviours adopted by students. It employs computer-based task switching and self-directed learning as the technology and learning frameworks within which these behaviours are explored. A custom monitoring system was used to capture and analyse 3372 computer session logs of students undertaking self-directed study within an open-access computer laboratory. Each session was broken down into a sequence of tasks within a series of time segments. Segments and sessions were then analysed and classified as conforming to one of three core behaviours - little or no task switching (focused), task switching without Multitasking (sequential) and Multitasking. Multitasking was much more common than focused or sequential behaviours. Multitasking was present in more than 70%, was most frequent in over 50% and occurred exclusively in around 35% of all sessions. By comparison, less than 10% of sessions were exclusively focused and only 7% were exclusively sequential. Once initiated, focused and Multitasking behaviours appear to be quite stable. Students were much more likely to continue with them than to switch to an alternate behaviour. Sequential behaviour is far less stable and appears to represent a transitional state between Multitasking and focused behaviours. The importance of personal, social and learning contexts in setting and influencing Multitasking behaviours are discussed, as are some of the potential effects of these behaviours on learning practises and outcomes.
