HIGH PERFORMANCE BIOMEDICAL COMPUTING

高性能生物医学计算程序的目标是 识别和解决生物医学中的计算问题， 得益于高性能硬件、现代软件工程 原则和高效算法。 这项工作包括提供高 高性能并行计算机系统，用于NIH工作人员和开发 生物医学应用的并行算法。 CSL正在为许多生物医学应用开发算法， 可以受益于计算加速，包括图像处理 电子显微照片，蛋白质和核酸序列分析，核 磁共振波谱，x射线晶体学，蛋白质折叠 预测，量子化学方法，分子动力学模拟，人类 遗传连锁分析、医学成像和放射治疗 规划 每个应用领域的开发团队包括计算机 CSL的工程师和科学家设计和实施所需的 并行算法和方法，以及提供 必要的应用知识，并成为开发软件的用户。 最终的目标是为高性能并行计算提供便利 这是在国家卫生研究院做的科学研究。 在通过计算开发这些 苛刻的应用程序。 CSL正在调查以下高 性能计算问题：将问题划分为许多部分， 可以在不同的处理器上独立执行， 因此，处理器间通信的延迟可以保持在很小的范围内， 计算时间的一小部分，设计部件， 负载可以均匀地分布在可用的处理器上， 平衡，设计算法，使处理器的数量是一个 参数和算法可以动态配置， 可用的机器，开发工具和环境，从生产 可移植的并行程序和监控系统的性能，并证明 在给定机器上的并行算法满足其规格。

The goals of the high performance biomedical computing program are to identify and solve those computational problems in biomedicine that can benefit from high performance hardware, modern software engineering principles, and efficient algorithms. This effort includes providing high performance parallel computer systems for the NIH staff and developing parallel algorithms for biomedical applications. CSL is developing algorithms for a number of biomedical applications that can benefit from computational speedup including image processing of electron micrographs, protein and nucleic acid sequence analysis, nuclear magnetic resonance spectroscopy, x-ray crystallography, protein folding prediction, quantum chemical methods, molecular dynamics simulations, human genetic linkage analysis, medical imaging, and radiation treatment planning. Development teams for each application area include computer engineers and scientists from CSL who design and implement the required parallel algorithms and methods, and biomedical scientists who provide the necessary application knowledge and become users of the developed software. The ultimate goal is to have high performance parallel computing facilitate the science that is done at NIH. While developing these computationally demanding applications. CSL is investigating the following high performance computing issues: partitioning a problem into many parts that can be independently executed on different processors, designing algorithms so that delays of interprocessor communication can be kept to a small fraction of the computation time, designing the parts so that the computing load can be distributed evenly over the available processors or dynamically balanced, designing algorithms so that the number of processors is a parameter and the algorithms can be configured dynamically for the available machine, developing tools and environments from producing portable parallel programs and monitoring system performance, and proving that a parallel algorithm on a given machine meets its specifications.