An Overview of the Intel TFLOPS Supercomputer

نویسندگان

  • Timothy G. Mattson
  • Greg Henry
چکیده

Computer simulations needed by the U.S. Department of Energy (DOE) greatly exceed the capacity of the world’s most powerful supercomputers. To satisfy this need, the DOE created the Accelerated Strategic Computing Initiative (ASCI). This program accelerates the development of new scalable supercomputers and will lead to a supercomputer early in the next century that can run at a rate of 100 trillion floating point operations per second (TFLOPS). Intel built the first computer in this program, the ASCI Option Red Supercomputer (also known as the Intel TFLOPS supercomputer). This system has over 4500 nodes, 594 Gbytes of RAM, and two independent 1 Tbyte disk systems. Late in the spring of 1997, we set the MP LINPACK world record of 1.34 TFLOPS. In this paper, we give an overview of the ASCI Option Red Supercomputer. The motivation for building this supercomputer is presented and the hardware and software views of the machine are described in detail. We also briefly discuss what it is like to use the machine.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

The Performance of the Intel TFLOPS Supercomputer

The purpose of building a supercomputer is to provide superior performance on real applications. In this paper, we describe the performance of the Intel TFLOPS Supercomputer starting at the lowest level with a detailed investigation of the Pentium® Pro processor and the supporting memory subsystem. We follow this with a description of the benchmarks used to track the performance of the machine ...

متن کامل

Scalable Platform Services on the Intel TFLOPS Supercomputer

This paper describes Scalable Platform Services (SPS)—a collection of software providing the manageability solution for Intel’s latest parallel processing supercomputer. Compared to previous generations of supercomputer management environments, such as that of the Intel Paragon Supercomputer, the SPS makes significant strides in feature offerings and overall usability. The SPS consists of dist...

متن کامل

Achieving Large Scale Parallelism Through Operating System Resource Management on the Intel TFLOPS Supercomputer

From the point of view of an operating system, a computer is managed and optimized in terms of the application programming model and the management of system resources. For the TFLOPS system, the problem is to manage and optimize large scale parallelism. This paper looks at the management in terms of three key topics: memory management, communication, and input/output. For memory management, we...

متن کامل

Parallel I/O Architecture of The First ASCI TFLOPS Machine

Intel’s Teraflops(TFLOPS) machine is the first ASCI machine that DOE is acquiring. This computer will be 10 times more powerful than the fastest machine today, and will be used primarily to simulate nuclear testing and to ensure the safety and effectiveness of the nation's nuclear weapons stockpile. This machine will contain over 9000 Intel’s Pentium® Pro processors and will provide a peak cpu ...

متن کامل

ParaNIS - Towards NIS client support for OSF/1 AD on the Intel Paragon

This paper presents the ParaNIS project, an attempt to implement Sun Microsystems’ Network Information Service Version 2 (formerly known as Yellow Pages) for the client side on the service partition of the Intel Paragon supercomputer. After a brief introduction to user administration on traditional UNIX systems, an overview of the classical NIS service is given. Whereas NIS was designed for c...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

عنوان ژورنال:

دوره   شماره 

صفحات  -

تاریخ انتشار 1998