In this paper, we propose an adoplivc scan (AS) strategy for submesh allocation. The earlierframe sliding (FS) strategy [I] allocates submeshes based on fixed orientations of incoming faska. It also slides fiunaes om mesh planes by fdzed strides. Our AS a1Iocation strategy diflers from the FS slrafegy in the following two ways: (1) it does not jiz the orientations of incoming tasks;(2) it scans on mesh planes adapfively. Experimental studies show that oar AS strategy oedperfornas the FS slmdegy in t e m s of external fmgmentaiion, completion la'nae, land processor uii/izaiion.

No abstract

L7-filter is a significant component in Linux's QoS framework that classifies network traffic based on application layer data. It enables subsequent distribution of network resources in respect to the priority of applications. Considerable research has been reported to deploy multicore architectures for computationally intensive applications. Unfortunately, the proliferation of multi-core architectures has not helped fast packet processing due to: 1) the lack of efficient parallelism in legacy network programs, and 2) the non-trivial configuration for scalable utilization on multi-core servers.In this paper, we propose a highly scalable parallelized L7-filter system architecture with affinity-based scheduling on a multi-core server. We start with an analytical study of the system architecture based on an offline design. Similar to Receive Side Scaling (RSS) in the NIC, we develop a model to explore the connection level parallelism in L7-filter and propose an affinity-based scheduler to optimize system scalability. Performance results show that our optimized L7-filter has superior scalability over the naive multithreaded version. It improves system performance by about 50% when all the cores are deployed.

A database (TAMUdust2020) of the optical properties of irregular aerosol particles is developed for applications to radiative transfer simulations involving aerosols, particularly dust and volcanic ash particles. The particle shape model assumes an ensemble of irregular hexahedral geometries to mimic complex aerosol particle shapes in nature. State-of-the-art light scattering computational capabilities are employed to compute the single-scattering properties of these particles for wide ranges of values of the size parameter, the index of refraction, and the degree of sphericity. The database therefore is useful for various radiative transfer applications over a broad spectral region from ultraviolet to infrared. Overall, agreement between simulations and laboratory/in-situ measurements is achieved for the scattering phase matrix and backscattering of various dust aerosol and volcanic ash particles. Radiative transfer simulations of active and passive spaceborne sensor signals for dust plumes with various aerosol optical depths and the effective particle sizes clearly demonstrate the applicability of the database for aerosol studies. In particular, the present database includes, for the first time, robust backscattering of nonspherical particles spanning the entire range of aerosol particle sizes, which shall be useful to appropriately interpret lidar signals related to the physical properties of aerosol plumes. Furthermore, thermal infrared simulations based on in-situ measured refractive indices of dust aerosol particles manifest the effects of the regional variations of aerosol optical properties. This database includes a user-friendly interface to obtain user-customized aerosol single-scattering properties with respect to spectrally dependent complex refractive index, size, and the degree of sphericity.

International audienceElectricity is one of most widely used energies and encouraged to be saved by scientific management and new technologies such as Time-of-Use policy. Batch scheduling can significantly improve production efficiency and is used in many high electricity consumption and high technology industries. This paper investigates a new bi-objective single machine batch scheduling problem with TOU policy. The first objective is to improve productivity and the second aims to minimize the total electricity cost. For the problem, a bi-objective mixed integer nonlinear programming model is formulated. Its corresponding single objective optimization problems are linearized by analyzed properties such that the multiobjective e-constraint method can be used to obtain Pareto solutions