Motivated by the numerous healthcare applications of molecular communication within Internet of Bio-Nano Things (IoBNT) paradigm, this paper addresses the problem of abnormality detection in a blood vessel using multi...
详细信息
The work reported in this article addresses the challenge of building models for non-trivial aerobatic aircraft maneuvers in an automated fashion. It is built using a Behavioural Cloning approach where human pilots pr...
详细信息
The ambition to achieve higher computing performance, is based on using all the advantages of parallel approach. The devices, software development kits and other technologies are leaping forward. Nowadays, they allow ...
详细信息
The ambition to achieve higher computing performance, is based on using all the advantages of parallel approach. The devices, software development kits and other technologies are leaping forward. Nowadays, they allow programmer to use more effective and optimized template libraries. They empower him to acces functions of graphics processing unit through the highlevel language. This paper details the experience of using such optimization on basic and more complex algorithms and the measurement of overall effectiveness increase. Our experimental results demonstrate the overall acceleration on various types of GPU.
This paper presents algorithms for improving the performance of parallel programs on multiprogrammed shared-memory NUMA multiprocessors, via the use of user-level dynamic page migration. The idea that drives the algor...
详细信息
This paper presents algorithms for improving the performance of parallel programs on multiprogrammed shared-memory NUMA multiprocessors, via the use of user-level dynamic page migration. The idea that drives the algorithms is that a page migration engine can perform accurate and timely page migrations in a multiprogrammed system if it can correlate page reference information with scheduling information obtained from the operating system. The necessary page migrations can be performed as a response to scheduling events that break the implicit association between threads and their memory affinity sets. We present two algorithms that use feedback from the kernel scheduler to aggressively migrate pages upon thread migrations. The first algorithm exploits the iterative nature of parallel programs, while the second targets generic codes without making assumptions on their structure. Performance evaluation on an SGI Origin2000 shows that our page migration algorithms provide substantial improvements in throughput of up to 264% compared to the native IRIX 6.5.5 page placement and migration schemes.
As information develops, many individuals or communities change their habits in obtaining information, which is usually consumed in large quantities, so that sometimes it is difficult to understand, it becomes easier ...
详细信息
This paper presents a soft-switched AC/DC power converter structure, useful for current-fed inverters and forced commutated PWM rectifiers with an inductive load. Typical applications are high-power AC motor drives, m...
详细信息
Due to the increasing prevalence of multicore microprocessors and accelerator technologies in modern supercomputer design, new techniques for designing scientific applications are needed, in order to efficiently lever...
详细信息
Due to the increasing prevalence of multicore microprocessors and accelerator technologies in modern supercomputer design, new techniques for designing scientific applications are needed, in order to efficiently leverage all of the power inherent in these systems. The dataflow programming paradigm is well-suited to application design for distributed and heterogeneous systems than other techniques. Traditionally in dataflow middleware, application data domains are statically partitioned and distributed among the processors using a demand-driven algorithm. Unfortunately, this task scheduling technique can cause severe load imbalances in heterogeneous environments. Furthermore, in the presence of different types of processors, the optimum datasize can be different for each processor type. To solve the load imbalance problem and to leverage the optimum datasize dynamicity in a dataflow framework, we present an algorithm which automatically partitions the application workspace. By putting this partitioning into the purview of the dataflow runtime system, we can adaptively change the size of databuffers and correctly balance the load. Experiments with four applications show that our technique allows developers to skip the tedious and error-prone step of manually tuning the data granularity. Our technique is always competitive with the best-known data partitioning for these experiments, and can beat it under certain constraints.
A path-oriented differentiated services optical network has demands which require different types of expectations from the network. Exploiting excess capacity which the network already has to meet these different expe...
详细信息
The primary objective of university education is to provide students with the required information and skills to enable them to make a successful contribution to the national development effort. In order to evaluate t...
详细信息
There is a possibility of remaining indication of microorganisms on Martian subsurface and therefore, a robotic arm mounted on an exploration robot is required to dig to a certain depth and collect appropriate sample ...
详细信息
There is a possibility of remaining indication of microorganisms on Martian subsurface and therefore, a robotic arm mounted on an exploration robot is required to dig to a certain depth and collect appropriate sample to be analyzed. However, the environment on the surface of Mars is harsh and most of all, limited power is available from the solar panel. In this paper, FEMI (Force-and-Energy Manipulability Index) is proposed to evaluate a feasible arm configuration for low energy consumption in its soil sampling operation. FEMI is calculated by the combination of an energy manipulability of an arm and an external force generated at an end effector of the arm. The FEMI derives the most feasible configuration on the joint angles of the arm for each sampling point. The usefulness of the FEMI is confirmed through a numerical simulation of a robotic arm. The simulation also presents that the FEMI can be used to obtain mechanical parameters of the arm such as link length and motor power, that are optimally-designed for a certain mission.
暂无评论