Dynamic Job Scheduling on the Grid Environment using the Great Deluge Algorithm

The utilization of the computational Grid processor network has become a common method for researchers and scientists without access to local processor clusters to avail of the benefits of parallel processing for compute-intensive applications. As a result, this demand requires effective and efficient dynamic allocation of available resources. Although static scheduling and allocation techniques have proved effective, the dynamic nature of the Grid requires innovative techniques for reacting to change and maintaining stability for users. The dynamic scheduling process requires quite powerful optimization techniques, which can themselves lack the performance required in reaction time for achieving an effective schedule solution. Often there is a trade-off between solution quality and speed in achieving a solution. This paper presents an extension of a technique used in optimization and scheduling which can provide the means of achieving this balance and improves on similar approaches currently published.

The Teaching Space Allocation Problem with splitting

A standard problem within universities is that of teaching space allocation which can be thought of as the assignment of rooms and times to various teaching activities. The focus is usually on courses that are expected to fit into one room. However, it can also happen that the course will need to be broken up, or ‘split’, into multiple sections. A lecture might be too large to fit into any one room. Another common example is that of seminars or tutorials. Although hundreds of students may be enrolled on a course, it is often subdivided into particular types and sizes of events dependent on the pedagogic requirements of that particular course. Typically, decisions as to how to split courses need to be made within the context of limited space requirements. Institutions do not have an unlimited number of teaching rooms, and need to effectively use those that they do have. The efficiency of space usage is usually measured by the overall ‘utilisation’ which is basically the fraction of the available seat-hours that are actually used. A multi-objective optimisation problem naturally arises; with a trade-off between satisfying preferences on splitting, a desire to increase utilisation, and also to satisfy other constraints such as those based on event location and timetabling conflicts. In this paper, we explore such trade-offs. The explorations themselves are based on a local search method that attempts to optimise the space utilisation by means of a ‘dynamic splitting’ strategy. The local moves are designed to improve utilisation and satisfy the other constraints, but are also allowed to split, and un-split, courses so as to simultaneously meet the splitting objectives.

Abatement and Allocation in the Pilot Phase of the EU ETS

We use historical industrial emissions data to assess the level of abatement and over-allocation that took place across European countries during the pilot phase (2005–2007) of the European Union Emission Trading Scheme. Using a dynamic panel data model, we estimate the counter factual (business-as-usual) emissions scenario for EU member states. Comparing this baseline to allocated and verified emissions, we find that both over-allocation and abatement occurred, along with under-allocation and emissions inflation. Over the three trading years of the pilot phase we find over-allocation of approximately 280 million EUAs and total abatement of 247 Mt CO2. However, we calculate that emissions inflation of approximately 73 Mt CO2 also occurred, possibly due to uncertainty about future policy design features.

Dynamic global security-aware synthesis using System-C

A dynamic global security-aware synthesis flow using the SystemC language is presented. SystemC security models are first specified at the system or behavioural level using a library of SystemC behavioural descriptions which provide for the reuse and extension of security modules. At the core of the system is incorporated a global security-aware scheduling algorithm which allows for scheduling to a mixture of components of varying security level. The output from the scheduler is translated into annotated nets which are subsequently passed to allocation, optimisation and mapping tools for mapping into circuits. The synthesised circuits incorporate asynchronous secure power-balanced and fault-protected components. Results show that the approach offers robust implementations and efficient security/area trade-offs leading to significant improvements in turnover.

BDDT: Block-level Dynamic Dependence Analysis for Task-Based Parallelism

We present BDDT, a task-parallel runtime system that dynamically discovers and resolves dependencies among parallel tasks. BDDT allows the programmer to specify detailed task footprints on any memory address range, multidimensional array tile or dynamic region. BDDT uses a block-based dependence analysis with arbitrary granularity. The analysis is applicable to existing C programs without having to restructure object or array allocation, and provides flexibility in array layouts and tile dimensions.
We evaluate BDDT using a representative set of benchmarks, and we compare it to SMPSs (the equivalent runtime system in StarSs) and OpenMP. BDDT performs comparable to or better than SMPSs and is able to cope with task granularity as much as one order of magnitude finer than SMPSs. Compared to OpenMP, BDDT performs up to 3.9× better for benchmarks that benefit from dynamic dependence analysis. BDDT provides additional data annotations to bypass dependence analysis. Using these annotations, BDDT outperforms OpenMP also in benchmarks where dependence analysis does not discover additional parallelism, thanks to a more efficient implementation of the runtime system.

Power-Capped DVFS and Thread Allocation with ANN Models on Modern NUMA Systems

Abstract—Power capping is an essential function for efficient power budgeting and cost management on modern server systems. Contemporary server processors operate under power caps by using dynamic voltage and frequency scaling (DVFS). However, these processors are often deployed in non-uniform memory
access (NUMA) architectures, where thread allocation between cores may significantly affect performance and power consumption. This paper proposes a method which maximizes performance under power caps on NUMA systems by dynamically optimizing two knobs: DVFS and thread allocation. The method selects the optimal combination of the two knobs with models based on artificial neural network (ANN) that captures the nonlinear effect of thread allocation on performance. We implement
the proposed method as a runtime system and evaluate it with twelve multithreaded benchmarks on a real AMD Opteron based NUMA system. The evaluation results show that our method outperforms a naive technique optimizing only DVFS by up to
67.1%, under a power cap.

Dynamic properties of bright points in an active region

Context. Bright points (BPs) are small-scale, magnetic features ubiquitous across the solar surface. Previously, we have observed and noted their properties for quiet Sun regions. Here, we determine the dynamic properties of BPs using simultaneous quiet Sun and active region data.

Aims. The aim of this paper is to compare the properties of BPs in both active and quiet Sun regions and to determine any difference in the dynamics and general properties of BPs as a result of the varying magnetic activity within these two regions.

Methods. High spatial and temporal resolution G-band observations of active region AR11372 were obtained with the Rapid Oscillations in the Solar Atmosphere instrument at the Dunn Solar Telescope. Three subfields of varying polarity and magnetic flux density were selected with the aid of magnetograms obtained from the Helioseismic and Magnetic Imager on board the Solar Dynamics Observatory. Bright points within these subfields were subsequently tracked and analysed.

Results. It is found that BPs within active regions display attenuated velocity distributions with an average horizontal velocity of ~0.6 km s-1, compared to the quiet region which had an average velocity of 0.9 km s-1. Active region BPs are also ~21% larger than quiet region BPs and have longer average lifetimes (~132 s) than their quiet region counterparts (88 s). No preferential flow directions are observed within the active region subfields. The diffusion index (γ) is estimated at ~1.2 for the three regions.

Conclusions. We confirm that the dynamic properties of BPs arise predominately from convective motions. The presence of stronger field strengths within active regions is the likely reason behind the varying properties observed. We believe that larger amounts of magnetic flux will attenuate BP velocities by a combination of restricting motion within the intergranular lanes and by increasing the number of stagnation points produced by inhibited convection. Larger BPs are found in regions of higher magnetic flux density and we believe that lifetimes increase in active regions as the magnetic flux stabilises the BPs.