From latex specifications to parallel codes

The advent of multicore systems, joined to the potential acceleration of the graphics processing units, has given us a low cost computation capability unprecedented. The new systems alleviate some well-known important architectural problems at the expense of a considerable increment of the programmability wall. Heterogeneity, at both the architectural and programming levels, poses a great challenge to programmers. As a contribution, we propose a development methodology for the automatic source-to-source transformation on specific domains. This methodology is successfully instantiated as a framework to solve Dynamic Programming problems. As a result of applying our framework, the end user (a physicist, a mathematician or a biologist) can express her problem through a latex equation and automatically derive efficient parallel codes for current homogeneous or heterogeneous architectures. The approach allows an easy portability to new emergent architectures.     

A cluster-DEE-based strategy to empower protein design

The Medical and Pharmaceutical industries have shown high interest in the precise engineering of protein hormones and enzymes that perform existing functions under a wide range of conditions. Proteins are responsible for the execution of different functions in the cell: catalysis in chemical reactions, transport and storage, regulation and recognition control. Computational Protein Design (CPD) investigates the relationship between 3-D structures of proteins and amino acid sequences and looks for all sequences that will fold into such 3-D structure. Many computational methods and algorithms have been proposed over the last years, but the problem still remains a challenge for Mathematicians, Computer Scientists, Bioinformaticians and Structural Biologists. In this article we present a new method for the protein design problem. Clustering techniques and a Dead-End-Elimination algorithm are combined with a SAT problem representation of the CPD problem in order to design the amino acid sequences. The obtained results illustrate the accuracy of the proposed method, suggesting that integrated Artificial Intelligence techniques are useful tools to solve such an intricate problem.     

An investigation of the performance portability of OpenCL

This paper reports on the development of an MPI/OpenCL implementation of LU, an application-level benchmark from the NAS Parallel Benchmark Suite. An account of the design decisions addressed during the development of this code is presented, demonstrating the importance of memory arrangement and work-item/work-group distribution strategies when applications are deployed on different device types. The resulting platform-agnostic, single source application is benchmarked on a number of different architectures, and is shown to be 1.3–1.5× slower than native FORTRAN 77 or CUDA implementations on a single node and 1.3–3.1× slower on multiple nodes. We also explore the potential performance gains of OpenCL’s device fissioning capability, demonstrating up to a 3× speed-up over our original OpenCL implementation.     

Efficient implementation of the implicit error correction nVoD schema

Implicit Error Correction is a near Video-on-Demand (nVoD) schema that trades bandwidth utilization for initial playback delay while potentially allowing an infinite number of users. Additionally, it provides error protection without further bandwidth increase by exploiting the implicit redundancy of nVoD protocols, using linear combinations of the segments transmitted in a given time slot. This paper introduces a new implementation that outperforms the original schema by adding two new mechanisms: redundancy channels and feedback error correction.     

Implications of failure criteria choices on the rapid concept design of composite grillage structures using multiobjective optimisation

Grillage topologies are commonly used in many composite structural applications to produce low mass designs that have a high stiffness. While composite failure criteria are being compared in many different simple structures, for example plates and tubes, literature must also compare more complicated applications, including grillages, as there are distinct differences in behaviour. This paper therefore performs analysis of grillage structures with more up to date failure criteria, taken from the world wide failure exercise, than previously investigated. The grillage theory selected is that of Navier theory with elastic equivalent properties due to its low computational expense for use with a genetic algorithm to optimise a composite structure. The results take an example from leisure boatbuilding showing the grillages produced from the different limit states, comparing the cost and mass. The final results show that the method allows a rapid analysis of grillages and that the selection of the limit state has an important effect on the optimised grillage topology.     

DETERMINATION OF FEEDBACK FOR HUMAN POSTURE CONTROL WITHOUT PHYSICAL INTERVENTION

Abstract

This paper is a study of a method to determine from external observations only, potential sets of feedback gains that can be used by humans to control their postural stance.

These gains amplify sensor signals in order to produce torques at the joints. The method consists of modeling the human biped in two ways-as a one degree-of-freedom inverted pendulum with a vestibular estimator and as a two degree-of-freedom compound inverted pendulum for which the vestibular system is approximated. The feedback gains in these models are systematically changed until the computer simulated motion of the nonlinear model is close enough to observed human motion. Comparisons are made between these results and those of other experimental investigations.

An analysis of minimal sets of gains and sensitivity of the gains to measurement errors in weights, lengths, and moment of inertia are discussed.