CISE Research Instrumentation: Symmetric Multiprocessor for Research on Parallel Architecture, Compiler, Applications and On-demand Network-Computing Research

9617348西北大学研究仪器：用于并行体系结构研究的对称多处理器，编译程序，应用程序和按需网络计算这项研究仪器拨款使两所大学能够在四个研究领域进行合作：-用于高性能计算的分层处理器和存储器体系结构-高级程序分析和编译基础设施-大型(Petaflop)计算应用程序的表征-基于网络的计算中心的元编程和按需元计算本项目的重点是在四个方面推进高性能计算的最新水平：-能够每秒100万亿次操作(即100个TOP)的高性能计算机的设计，-用于分析和编译在具有多个处理器的机器上执行的程序的高级工具，-描述需要100-1000最高计算速率的应用程序，以及-基于网络的软件基础设施的设计，该基础设施允许通过传统的网络浏览器使用链接的计算机和链接的程序(即元计算机和元程序)。目前正在研究的主要想法正在通过广泛的计算实验和计算机模拟得到验证。用这笔赠款提供的资金购买的设备提供了该项目实验部分的计算速度、内存、存储和通信需求，否则这些需求是不可能实现的，或者需要长得令人无法接受的时间来执行。对称多处理机的可用性使实验成为可能，这对于验证本项目所追求的研究思路和结果是至关重要的。这项工作由西北大学和普渡大学的研究人员共同开展。

9617348 Taylor, Valerie E. Northwestern University CISE Research Instrumentation: Symmetric Multiprocessor for Research on Parallel Architecture, Compiler, Applications and On-demand Network-computing This research instrumentation grant enables collaboration between two universities in four areas of research:-Hierarchical Processor-and-Memory Architecture for- High Performance Computing - An Advanced Program Analysis and Compilation Infrastructure - Characterization of Large (Petaflop) Computational Applications - Metaprogramming and On-demand Metacomputing for Network-based Computational Hubs The focus of this project is on advancing the state of the art in high-performance computing on the four fronts:- the design of high-performance computers capable of 100 trillion operations per second (i.e. 100 TOPS),- advanced tools for analysis and compilation of programs for execution on machines with multiple processors,- the characterization of applications that require computation rates of 100-1000 TOPS and- the design of a network-based software infrastructure that allows the use of linked computers and linked programs (i.e.,metacomputers and metaprograms) through conventional network browsers. The main ideas currently under investigation are being validated through extensive computational experiments and computer simulations. The equipment acquired with the funds provided by this grant provides the computational speed, memory, storage and communication demands of the experimental component of this project which would otherwise not be possible or take unacceptably long times to perform. The experimentation made possible by the availability of a symmetric multiprocessor is essential to the validation of research ideas and results pursued in this project. This work is being carried collaboratively by researchers at Northwestern University and Purdue University.