NAS Parallel Benchmarks

Last updated
NAS Parallel Benchmarks
Original author(s) NASA Numerical Aerodynamic Simulation Program
Developer(s) NASA Advanced Supercomputing Division
Initial release1991 (1991)
Stable release
3.4
Website nas.nasa.gov/Software/NPB/

NAS Parallel Benchmarks (NPB) are a set of benchmarks targeting performance evaluation of highly parallel supercomputers. They are developed and maintained by the NASA Advanced Supercomputing (NAS) Division (formerly the NASA Numerical Aerodynamic Simulation Program) based at the NASA Ames Research Center. NAS solicits performance results for NPB from all sources. [1]

Contents

History

Motivation

Traditional benchmarks that existed before NPB, such as the Livermore loops, the LINPACK Benchmark and the NAS Kernel Benchmark Program, were usually specialized for vector computers. They generally suffered from inadequacies including parallelism-impeding tuning restrictions and insufficient problem sizes, which rendered them inappropriate for highly parallel systems. Equally unsuitable were full-scale application benchmarks due to high porting cost and unavailability of automatic software parallelization tools. [2] As a result, NPB were developed in 1991 [3] and released in 1992 [4] to address the ensuing lack of benchmarks applicable to highly parallel machines.

NPB 1

The first specification of NPB recognized that the benchmarks should feature

In the light of these guidelines, it was deemed the only viable approach to use a collection of "paper-and-pencil" benchmarks that specified a set of problems only algorithmically and left most implementation details to the implementer's discretion under certain necessary limits.

NPB 1 defined eight benchmarks, each in two problem sizes dubbed Class A and Class B. Sample codes written in Fortran 77 were supplied. They used a small problem size Class S and were not intended for benchmarking purposes. [2]

NPB 2

Since its release, NPB 1 displayed two major weaknesses. Firstly, due to its "paper-and-pencil" specification, computer vendors usually highly tuned their implementations so that their performance became difficult for scientific programmers to attain. Secondly, many of these implementation were proprietary and not publicly available, effectively concealing their optimizing techniques. Secondly, problem sizes of NPB 1 lagged behind the development of supercomputers as the latter continued to evolve. [3]

NPB 2, released in 1996, [5] [6] came with source code implementations for five out of eight benchmarks defined in NPB 1 to supplement but not replace NPB 1. It extended the benchmarks with an up-to-date problem size Class C. It also amended the rules for submitting benchmarking results. The new rules included explicit requests for output files as well as modified source files and build scripts to ensure public availability of the modifications and reproducibility of the results. [3]

NPB 2.2 contained implementations of two more benchmarks. [5] NPB 2.3 of 1997 was the first complete implementation in MPI. [4] It shipped with serial versions of the benchmarks consistent with the parallel versions and defined a problem size Class W for small-memory systems. [7] NPB 2.4 of 2002 offered a new MPI implementation and introduced another still larger problem size Class D. [6] It also augmented one benchmark with I/O-intensive subtypes. [4]

NPB 3

NPB 3 retained the MPI implementation from NPB 2 and came in more flavors, namely OpenMP, [8] Java [9] and High Performance Fortran. [10] These new parallel implementations were derived from the serial codes in NPB 2.3 with additional optimizations. [7] NPB 3.1 and NPB 3.2 added three more benchmarks, [11] [12] which, however, were not available across all implementations; NPB 3.3 introduced a Class E problem size. [7] Based on the single-zone NPB 3, a set of multi-zone benchmarks taking advantage of the MPI/OpenMP hybrid programming model were released under the name NPB-Multi-Zone (NPB-MZ) for "testing the effectiveness of multi-level and hybrid parallelization paradigms and tools". [1] [13]

The benchmarks

As of NPB 3.3, eleven benchmarks are defined as summarized in the following table.

BenchmarkName derived from [2] Available sinceDescription [2] Remarks
MGMultiGridNPB 1 [2] Approximate the solution to a three-dimensional discrete Poisson equation using the V-cycle multigrid method
CGConjugate GradientEstimate the smallest eigenvalue of a large sparse symmetric positive-definite matrix using the inverse iteration with the conjugate gradient method as a subroutine for solving systems of linear equations
FTFast Fourier TransformSolve a three-dimensional partial differential equation (PDE) using the fast Fourier transform (FFT)
IS Integer Sort Sort small integers using the bucket sort [5]
EP Embarrassingly Parallel Generate independent Gaussian random variates using the Marsaglia polar method
BTBlock TridiagonalSolve a synthetic system of nonlinear PDEs using three different algorithms involving block tridiagonal, scalar pentadiagonal and symmetric successive over-relaxation (SSOR) solver kernels, respectively
  • The BT benchmark has I/O-intensive subtypes [4]
  • All three benchmarks have multi-zone versions [13]
SPScalar Pentadiagonal [6]
LU Lower-Upper symmetric Gauss-Seidel [6]
UAUnstructured Adaptive [11] NPB 3.1 [7] Solve Heat equation with convection and diffusion from moving ball. Mesh is adaptive and recomputed at every 5th step.
DC Data Cube operator [12]
DTData Traffic [7] NPB 3.2 [7]

Related Research Articles

Supercomputer Extremely powerful computer for its era

A supercomputer is a computer with a high level of performance as compared to a general-purpose computer. The performance of a supercomputer is commonly measured in floating-point operations per second (FLOPS) instead of million instructions per second (MIPS). Since 2017, there are supercomputers which can perform over 1017 FLOPS (a hundred quadrillion FLOPS, 100 petaFLOPS or 100 PFLOPS). Since November 2017, all of the world's fastest 500 supercomputers run Linux-based operating systems. Additional research is being conducted in the United States, the European Union, Taiwan, Japan, and China to build faster, more powerful and technologically superior exascale supercomputers.

Ames Research Center Research center operated by NASA

The Ames Research Center (ARC), also known as NASA Ames, is a major NASA research center at Moffett Federal Airfield in California's Silicon Valley. It was founded in 1939 as the second National Advisory Committee for Aeronautics (NACA) laboratory. That agency was dissolved and its assets and personnel transferred to the newly created National Aeronautics and Space Administration (NASA) on October 1, 1958. NASA Ames is named in honor of Joseph Sweetman Ames, a physicist and one of the founding members of NACA. At last estimate NASA Ames has over US$3 billion in capital equipment, 2,300 research personnel and a US$860 million annual budget.

Earth Simulator

The Earth Simulator (ES), developed by the Japanese government's initiative "Earth Simulator Project", was a highly parallel vector supercomputer system for running global climate models to evaluate the effects of global warming and problems in solid earth geophysics. The system was developed for Japan Aerospace Exploration Agency, Japan Atomic Energy Research Institute, and Japan Marine Science and Technology Center (JAMSTEC) in 1997. Construction started in October 1999, and the site officially opened on 11 March 2002. The project cost 60 billion yen.

Moffett Federal Airfield Joint civil-military airport in California

Moffett Federal Airfield, also known as Moffett Field, is a joint civil-military airport located in an unincorporated part of Santa Clara County, California, United States, between northern Mountain View and northern Sunnyvale. On November 10, 2014, NASA announced that it would be leasing 1,000 acres (400 ha) of the airfield property to Google for 60 years.

Message Passing Interface (MPI) is a standardized and portable message-passing standard designed by a group of researchers from academia and industry to function on a wide variety of parallel computing architectures. The standard defines the syntax and semantics of a core of library routines useful to a wide range of users writing portable message-passing programs in C, C++, and Fortran. There are several well-tested and efficient implementations of MPI, many of which are open-source or in the public domain. These fostered the development of a parallel software industry, and encouraged development of portable and scalable large-scale parallel applications.

OpenMP Open standard for parallelizing

The application programming interface (API) OpenMP supports multi-platform shared-memory multiprocessing programming in C, C++, and Fortran, on many platforms, instruction-set architectures and operating systems, including Solaris, AIX, HP-UX, Linux, macOS, and Windows. It consists of a set of compiler directives, library routines, and environment variables that influence run-time behavior.

Jack Dongarra

Jack J. Dongarra ForMemRS; is an American University Distinguished Professor of Computer Science in the Electrical Engineering and Computer Science Department at the University of Tennessee. He holds the position of a Distinguished Research Staff member in the Computer Science and Mathematics Division at Oak Ridge National Laboratory, Turing Fellowship in the School of Mathematics at the University of Manchester, and is an adjunct professor in the Computer Science Department at Rice University. He served as a faculty fellow at Texas A&M University's institute for advanced study (2014–2018). Dongarra is the founding director of Innovative Computing Laboratory.

NASA Advanced Supercomputing Division

The NASA Advanced Supercomputing (NAS) Division is located at NASA Ames Research Center, Moffett Field in the heart of Silicon Valley in Mountain View, California. It has been the major supercomputing and modeling and simulation resource for NASA missions in aerodynamics, space exploration, studies in weather patterns and ocean currents, and space shuttle and aircraft design and development for over thirty years.

Michael Foreman (astronaut)

Michael James Foreman is a retired U.S. Navy pilot and a NASA astronaut. While with NASA, Foreman was part of a mission that delivered the Japanese Experiment Module and the Canadian Special Purpose Dexterous Manipulator to the International Space Station. Foreman was also a crewmember of the STS-129 mission in November 2009. In 2018, he was elected mayor of Friendswood, Texas. His wife Lorrie is a civil engineer.

The Parallel Virtual File System (PVFS) is an open-source parallel file system. A parallel file system is a type of distributed file system that distributes file data across multiple servers and provides for concurrent access by multiple tasks of a parallel application. PVFS was designed for use in large scale cluster computing. PVFS focuses on high performance access to large data sets. It consists of a server process and a client library, both of which are written entirely of user-level code. A Linux kernel module and pvfs-client process allow the file system to be mounted and used with standard utilities. The client library provides for high performance access via the message passing interface (MPI). PVFS is being jointly developed between The Parallel Architecture Research Laboratory at Clemson University and the Mathematics and Computer Science Division at Argonne National Laboratory, and the Ohio Supercomputer Center. PVFS development has been funded by NASA Goddard Space Flight Center, The DOE Office of Science Advanced Scientific Computing Research program, NSF PACI and HECURA programs, and other government and private agencies. PVFS is now known as OrangeFS in its newest development branch.

Trilinos is a collection of open-source software libraries, called packages, intended to be used as building blocks for the development of scientific applications. The word "Trilinos" is Greek and conveys the idea of "a string of pearls", suggesting a number of software packages linked together by a common infrastructure. Trilinos was developed at Sandia National Laboratories from a core group of existing algorithms and utilizes the functionality of software interfaces such as the BLAS, LAPACK, and MPI . In 2004, Trilinos received an R&D100 Award.

Finite element machine Project

The Finite Element Machine (FEM) was a late 1970s-early 1980s NASA project to build and evaluate the performance of a parallel computer for structural analysis. The FEM was completed and successfully tested at the NASA Langley Research Center in Hampton, Virginia. The motivation for FEM arose from the merger of two concepts: the finite element method of structural analysis and the introduction of relatively low-cost microprocessors.

The Research Institute for Advanced Computer Science (RIACS) was founded June 1, 1983 as a joint collaboration between the Universities Space Research Association (USRA) and the NASA Ames Research Center. The Institute was created to conduct basic and applied research in computer science, covering a broad range of research topics of interest to the aerospace community including supercomputing, computational fluid dynamics, computational chemistry, high performance networking, and artificial intelligence.

NASA Research Park

NASA Research Park is a research park run by NASA which is developing a world-class, shared-use research and development campus in association with government entities, academia, industry and non-profit organizations. It is situated near San Jose, California. NASA Research Park was approved by NASA HQ in the fall of 2002 and over the past decade has grown into the research park it is today with 61 tenants and partners.

The Center for Simulation of Advanced Rockets (CSAR) is an interdisciplinary research group at the University of Illinois at Urbana-Champaign, and is part of the United States Department of Energy's Advanced Simulation and Computing Program. CSAR's goal is to accurately predict the performance, reliability, and safety of solid propellant rockets.

Pleiades (supercomputer)

Pleiades is a petascale supercomputer housed at the NASA Advanced Supercomputing (NAS) facility at NASA's Ames Research Center located at Moffett Field near Mountain View, California. It is maintained by NASA and partners Hewlett Packard Enterprise and Intel.

The LINPACK Benchmarks are a measure of a system's floating point computing power. Introduced by Jack Dongarra, they measure how fast a computer solves a dense n by n system of linear equations Ax = b, which is a common task in engineering.

The Graph500 is a rating of supercomputer systems, focused on data-intensive loads. The project was announced on International Supercomputing Conference in June 2010. The first list was published at the ACM/IEEE Supercomputing Conference in November 2010. New versions of the list are published twice a year. The main performance metric used to rank the supercomputers is GTEPS.

In the nation's quest to provide security along its lengthy coastlines, air reconnaissance was put forth by the futuristic Rear Admiral William A. Moffett. Through his efforts, two Naval Air Stations were commissioned in the early 1930s to port the Naval Airships (dirigibles) which he believed capable of meeting this challenge.

As the coalition of Bay Areas counties predicted when it lobbied for the creation of Moffett Federal Airfield in the late 1920s, the base's research program and facilities catalyzed the development of numerous private technology and aerospace corporations, among them Lockheed Martin and the Hiller Aircraft Corporation.

References

  1. 1 2 "NAS Parallel Benchmarks Changes". NASA Advanced Supercomputing Division. Retrieved 2009-02-23.
  2. 1 2 3 4 5 Baily, D.; Barszcz, E.; Barton, J.; Browning, D.; Carter, R.; Dagum, L.; Fatoohi, R.; Fineberg, S.; Frederickson, P.; Weeratunga, S. (March 1994), "The NAS Parallel Benchmarks" (PDF), NAS Technical Report RNR-94-007, NASA Ames Research Center, Moffett Field, CA
  3. 1 2 3 Bailey, D.; Harris, T.; Saphir, W.; van der Wijngaart, R.; Woo, A.; Yarrow, M. (December 1995), "The NAS Parallel Benchmarks 2.0" (PDF), NAS Technical Report NAS-95-020, NASA Ames Research Center, Moffett Field, CA
  4. 1 2 3 4 Wong, P.; van der Wijngaart, R. (January 2003), "NAS Parallel Benchmarks I/O Version 2.4" (PDF), NAS Technical Report NAS-03-002, NASA Ames Research Center, Moffett Field, CA
  5. 1 2 3 Saphir, W.; van der Wijngaart, R.; Woo, A.; Yarrow, M., New Implementations and Results for the NAS Parallel Benchmarks 2 (PDF), NASA Ames Research Center, Moffett Field, CA
  6. 1 2 3 4 van der Wijngaart, R. (October 2002), "NAS Parallel Benchmarks Version 2.4" (PDF), NAS Technical Report NAS-02-007, NASA Ames Research Center, Moffett Field, CA
  7. 1 2 3 4 5 6 "NAS Parallel Benchmarks Changes". NASA Advanced Supercomputing Division. Retrieved 2009-03-17.
  8. ↑ Jin, H.; Frumkin, M.; Yan, J. (October 1999), "The OpenMP Implementation of NAS Parallel Benchmarks and Its Performance" (PDF), NAS Technical Report NAS-99-011, NASA Ames Research Center, Moffett Field, CA
  9. ↑ Frumkin, M.; Schultz, M.; Jin, H.; Yan, J., "Implementation of the NAS Parallel Benchmarks in Java" (PDF), NAS Technical Report NAS-02-009, NASA Ames Research Center, Moffett Field, CA
  10. ↑ Frumkin, M.; Jin, H.; Yan, J. (September 1998), "Implementation of NAS Parallel Benchmarks in High Performance Fortran" (PDF), NAS Technical Report NAS-98-009, NASA Ames Research Center, Moffett Field, CA
  11. 1 2 Feng, H.; van der Wijngaart, F.; Biswas, R.; Mavriplis, C. (July 2004), "Unstructured Adaptive (UA) NAS Parallel Benchmark, Version 1.0" (PDF), NAS Technical Report NAS-04-006, NASA Ames Research Center, Moffett Field, CA
  12. 1 2 Frumkin, M.; Shabanov, L. (September 2004), "Benchmarking Memory Performance with the Data Cube Operator" (PDF), NAS Technical Report NAS-04-013, NASA Ames Research Center, Moffett Field, CA
  13. 1 2 van der Wijngaart, R.; Jin, H. (July 2003), "NAS Parallel Benchmarks, Multi-Zone Versions" (PDF), NAS Technical Report NAS-03-010, NASA Ames Research Center, Moffett Field, CA
This page is based on this Wikipedia article
Text is available under the CC BY-SA 4.0 license; additional terms may apply.
Images, videos and audio are available under their respective licenses.