A general methodology to adapt a trace representing a task, so that it can be used as a workload, is described. The adaptation is made assuming an ideal trace and unchanging nature of the user actions when responsiven...
详细信息
A general methodology to adapt a trace representing a task, so that it can be used as a workload, is described. The adaptation is made assuming an ideal trace and unchanging nature of the user actions when responsiveness conditions are changed. Collecting an ideal trace is possible in many circumstances, and in some cases, nonideal traces can be idealized. The notion of imperceptible delay for the run threshold mode is generalized, and its computation for both human and autonomous users is discussed. Generalizations of the model to account for reduction in action granularity at slower issue speeds due to constant rate sampling of input devices and user to user interaction are also discussed.
The initial performance results for the file systems demonstrate that the file system performance is scalable. The access bandwidth seen by the user when using prefetching is also scalable, and given a reasonable over...
详细信息
With the growing complexity and scale of future Internet of Things (IoT) applications, there is a need for effectively exploring associated design spaces. IoT applications make use of inherently distributed processing...
详细信息
ISBN:
(纸本)9781538634370
With the growing complexity and scale of future Internet of Things (IoT) applications, there is a need for effectively exploring associated design spaces. IoT applications make use of inherently distributed processing. In such networks-of-systems (NoS), computation and communication is tightly coupled. Traditional design of networks and systems in isolation ignores how choices in one influence the other, and approaches for joint network/system co-exploration are lacking. In this paper, we propose a novel prototyping platform to enable comprehensive NoS design space exploration. Fast and accurate host-compiled system models are combined with a standard network simulator to provide a unified network/system co-simulation framework. Furthermore, detailed models of network interfaces and protocol stacks are integrated into host-compiled system and OS models to allow accurately capturing of network and system interactions. We apply our NoS simulator to two case studies from smart camera and healthcare application domains, and we demonstrate benefits and opportunities for exploration and optimization in network/system co-design. Results indicate that, depending on application, network and system configurations, application throughput can vary by an average of 26%, while device core utilization can vary by as much as 130%. These results confirm strong network and system interactions that could not be observed or optimized without novel co-simulation tools.
Maintaining and updating signature databases is a tedious task that normally requires a large amount of user effort. The problem becomes harder when features can be distorted by observation noise, which we call volati...
详细信息
ISBN:
(纸本)9781450342667
Maintaining and updating signature databases is a tedious task that normally requires a large amount of user effort. The problem becomes harder when features can be distorted by observation noise, which we call volatility. To address this issue, we propose algorithms and models to automatically generate signatures in the presence of noise, with a focus on stack fingerprinting, which is a research area that aims to discover the operating system (OS) of remote hosts using TCP/IP packets. Armed with this framework, we construct a database with 420 network stacks, label the signatures, develop a robust classifier for this database, and fingerprint 66M visible webservers on the Internet.
We consider the problem of multiprocessor scheduling of jobs whose memory requirements place lower bounds on the fraction of the machine required in order to execute. We address three primary questions in this work: 1...
详细信息
Non-functional requirements (NFRs) of software systems are an important source of uncertainty in effort estimation. Furthermore, quantitatively approaching NFR early in a project is difficult. This paper makes a step ...
详细信息
ISBN:
(纸本)9783540855521
Non-functional requirements (NFRs) of software systems are an important source of uncertainty in effort estimation. Furthermore, quantitatively approaching NFR early in a project is difficult. This paper makes a step towards reducing the impact of uncertainty due to NFRs. It offers a new generic classification of the NFRs, and a NFR size measurement method (NFSM) that incorporates NFRs into the functional size quantification process. We chose the NFR framework as a vehicle to integrate NFRs into the requirements modeling process and to apply quantitative assessment procedures. Our solution proposal also rests on the functional size measurement method, COSMIC-FFP, adopted in 2003 as the TSO/IEC 19761 standard. We discuss the advantages of our approach and the open questions related to its design as well.
This paper analyses a variant of the M/G/1 queue in which the service times of arriving customers depend on the length of the interval between their arrival and the previous arrival. The dependence structure correspon...
详细信息
暂无评论