ALBERT

Description: The effective use of a supercomputer depends on many aspects, including the ability of users to write efficient programs to use the resources of the system in an optimal manner. However, it is the responsibility of the system managers of these systems to insure the maximum effectiveness of the overall system is achieved. Many varying techniques have been developed at the Numerical Aerodynamic Simulation (NAS) Program to advance the management of these critical systems. Many of the issues and techniques used for managing supercomputers are common to multi-user UNIX systems, regardless of the version of UNIX or the power of the hardware. However, a UNICOS supercomputer presents some special challenges and requires additional features and tools to be developed to effectively manage the system. Only part of the challenge is related to performance monitoring and improvement. Much of the responsibility of the system manager is to provide fair and consistent access to the system resources, which is at times a difficult problem. After an introduction to the environment at the Numerical Aerodynamic Simulation Project is given as background this paper will first discuss the areas which are common to UNDC system management. Then the paper will discuss the specific areas of UNICOS which must be used to operate the system efficiently. The paper goes on to discuss the methods of supporting individual users in order to increase their effectiveness and the efficiency of their programs. This is accomplished through a professional support staff who interact on a daily basis to support the NAS scientific client community.

Description: Pipelining is a common strategy for extracting parallelism from a collection of independent computational tasks, each of which is spread among a number of processors and has an implied data dependence. When implemented on MIMD parallel computers with finite process interrupt times, pipeline algorithms suffer from slowdown--in addition to the expected pipeline fill time--due to a wave-like propagation of delays. This phenomenon, which has been observed experimentally using the performance monitoring system AIMS, is investigated analytically, and an optimal correction is derived to eliminate the wave. Efficiency increase through the correction is verified experimentally.

Description: Having an understanding of UNICOS Kernel Internals is valuable information. However, having the knowledge is only half the value. The second half comes with knowing how to use this information and apply it to the development of tools. The kernel contains vast amounts of useful information that can be utilized. This paper discusses the intricacies of developing utilities that utilize kernel information. In addition, algorithms, logic, and code will be discussed for accessing kernel information. Code segments will be provided that demonstrate how to locate and read kernel structures. Types of applications that can utilize kernel information will also be discussed.

Description: A discussion is presented of several areas where system management and user support can have a large impact in the overall efficiency of the Cray supercomputer. After an introduction to the environment at the Numerical Aerodynamic Simulation Project is given as background, the areas which are common to UNIX system management are examined. Then, the specific areas of the UNICOS supercomputer which must be used to operate the system efficiently are discussed. Methods of supporting individual users in order to increase their effectiveness and the efficiency of their programs are also discussed.

Description: This tutorial will discuss the top five RISC microprocessors and the parallel systems in which they are used. It will provide a unique cross-machine comparison not available elsewhere. The effective performance of these processors will be compared by citing standard benchmarks in the context of real applications. The latest NAS Parallel Benchmarks, both absolute performance and performance per dollar, will be listed. The next generation of the NPB will be described. The tutorial will conclude with a discussion of future directions in the field. Technology Transfer Considerations: All of these computer systems are commercially available internationally. Information about these processors is available in the public domain, mostly from the vendors themselves. The NAS Parallel Benchmarks and their results have been previously approved numerous times for public release, beginning back in 1991.

Description: At a recent press conference, NASA Administrator Dan Goldin encouraged NASA Ames Research Center to take a lead role in promoting research and development of advanced, high-performance computer technology, including nanotechnology. Manufacturers of leading-edge microprocessors currently perform large-scale simulations in the design and verification of semiconductor devices and microprocessors. Recently, the need for this intensive simulation and modeling analysis has greatly increased, due in part to the ever-increasing complexity of these devices, as well as the lessons of experiences such as the Pentium fiasco. Simulation, modeling, testing, and validation will be even more important for designing molecular computers because of the complex specification of millions of atoms, thousands of assembly steps, as well as the simulation and modeling needed to ensure reliable, robust and efficient fabrication of the molecular devices. The software for this capacity does not exist today, but it can be extrapolated from the software currently used in molecular modeling for other applications: semi-empirical methods, ab initio methods, self-consistent field methods, Hartree-Fock methods, molecular mechanics; and simulation methods for diamondoid structures. In as much as it seems clear that the application of such methods in nanotechnology will require powerful, highly powerful systems, this talk will discuss techniques and issues for performing these types of computations on parallel systems. We will describe system design issues (memory, I/O, mass storage, operating system requirements, special user interface issues, interconnects, bandwidths, and programming languages) involved in parallel methods for scalable classical, semiclassical, quantum, molecular mechanics, and continuum models; molecular nanotechnology computer-aided designs (NanoCAD) techniques; visualization using virtual reality techniques of structural models and assembly sequences; software required to control mini robotic manipulators for positional control; scalable numerical algorithms for reliability, verifications and testability. There appears no fundamental obstacle to simulating molecular compilers and molecular computers on high performance parallel computers, just as the Boeing 777 was simulated on a computer before manufacturing it.

Description: The Numerical Aerodynamics Simulation (NAS) Facility's CRAY C916/1024 has 240+ GB of SuperHome storage with 2 TB of migrated storage. NAS is a beta test site for the Storage Technology Corporation (STK) Redwood (SD-3) device and Cray's DMF 2.3. This discussion will include a list of resolved problems and various metrics relative to transfer, search, rewind, unload, and mount timings. Also covered will be how DMF 2.3 with the advance tape MSP will integrate the Redwood tape drives along with the existing STK 4490 tape drives to potentially reduce the number of tapes used by 85%.

Description: The NASA Ames Numerical Aerodynamic Simulation program Aeronautics Consolidated Supercomputing Facility (NAS/ACSF) supercomputing center services over 1600 users, and has numerous analysts with root access. Several tools have been developed to monitor object library usage and changes. Some of the tools do "noninvasive" monitoring and other tools implement run-time logging even for object-only libraries. The run-time logging identifies who, when, and what is being used. The benefits are that real usage can be measured, unused libraries can be discontinued, training and optimization efforts can be focused at those numerical methods that are actually used. An overview of the tools will be given and the results will be discussed.

Description: The advent of inexpensive, high performance computer and new efficient algorithms have made possible the automatic recognition of numerically computed constants. In other words, techniques now exist for determining, within certain limits, whether a computed real or complex number can be written as a simple expression involving the classical constants of mathematics. In this presentation, some of the recently discovered techniques for constant recognition, notably integer relation detection algorithms, will be presented. As an application of these methods, the author's recent work in recognizing "Euler sums" will be described in some detail.

Description: We prove known identities for the Khinchin constant and develop new identities for the more general Hoelder mean limits of continued fractions. Any of these constants can be developed as a rapidly converging series involving values of the Riemann zeta function and rational coefficients. Such identities allow for efficient numerical evaluation of the relevant constants. We present free-parameter, optimizable versions of the identities, and report numerical results.