Parallel Computer

描述（由申请人提供）：我们建议建立一个824处理器的并行计算机系统，以支持范德比尔特大学医学院的计算密集型、美国国立卫生研究院资助的生物医学研究。该系统将使用贝奥武夫模型，以极低的成本提供超级计算机的性能。该系统将建立在我们过去三年成功的初步研究基础上，建立并利用了一个110个处理器的试验集群。该系统将被添加到最近由工程学院和物理系建立的270处理器并行计算机上，作为范德比尔特新科学计算中心的一部分。因此，所需的基础设施和专业知识已经到位。提议的并行计算机将由至少16名NIH资助的生物医学研究人员使用，并将支持来自68个活跃和16个未决NIH资助的至少100个计算项目。该系统的教师用户在范德比尔特大学医学院的七个不同部门有主要预约。研究项目包括生物信息学、生物物理学、生物统计学、遗传流行病学、基因组学、人类遗传学、蛋白质组学和结构生物学的计算研究。这一资源将使进行计算密集型生物医学研究成为可能，否则是不可行的，从而大大提高了各种生物医学学科的科学发现率。

DESCRIPTION (provided by applicant): We propose establishing an 824-processor parallel computer system to support computationally intensive, NIH-funded, biomedical research at Vanderbilt University Medical School. The proposed system will use the Beowulf model that provides supercomputer performance at a small fraction of the cost. This system will build upon our successful preliminary studies over the last three years establishing and utilizing a 110-processor pilot cluster. The proposed system will be added to a 270-processor parallel computer that was recently established by the School of Engineering and Department of Physics as part of Vanderbilt's new Scientific Computing Center. Thus, the required infrastructure and expertise is already in place. The proposed parallel computer will be used by a minimum of 16 NIH-funded biomedical researchers and will support at least 100 computational projects from 68 active and 16 pending NIH grants. The faculty users of the system have primary appointments in seven different departments within the Vanderbilt University School of Medicine. Research programs include computational studies in bioinformatics, biophysics, biostatistics, genetic epidemiology, genomics, human genetics, proteomics, and structural biology. This resource will make it possible to carry out computationally intensive biomedical investigations otherwise not feasible thus significantly increasing the rate of scientific discovery in a variety of biomedical disciplines.