
	Where results make sense

Topic: LINPACK

Related Topics

TOP500

Benchmark

Whetstone (benchmark)

Hint

FLOPS

Aquamark

Dhrystone

Computer architecture

Cleve Moler

CPU architecture

Supercomputer

TPC

MATLAB

	LINPACK
		LINPACK is a collection of Fortran subroutines that analyze and solve linear equations and linear least-squares problems.
		LINPACK uses column-oriented algorithms to increase efficiency by preserving locality of reference.
		LINPACK was designed for supercomputers in use in the 1970s and early 1980s.
	www.netlib.org /linpack (229 words)

	Spartanburg SC \| GoUpstate.com \| Spartanburg Herald-Journal
		It was written in Fortran by Jack Dongarra, Jim Bunch, Cleve Moler, and Pete Stewart, and was intended for use on supercomputers in the 1970s and early 1980s.
		LINPACK makes use of the BLAS (Basic Linear Algebra Subprograms) libraries for performing basic vector and matrix operations.
		For large-scale distributed-memory systems, HPL, a portable implementation of the High-Performance LINPACK Benchmark, is used as a performance measure for ranking supercomputers in the TOP500 list of the world's fastest computers.
	www.goupstate.com /apps/pbcs.dll/section?category=NEWS&template=wiki&text=LINPACK (235 words)

	Index to Benchmark Codes
		Results for the rate of solution of linear systems using Linpack and Lapack are also included in the article, although they are not the focus of the article.
		The changes in performance as a function of vector length correlate with the various levels of cache memory in a computer and can be used to judge the importance of utilizing the cache memory efficiently.
		Lapack is essentially the successor to Linpack and is written in such a way as to run efficiently on a cache-based computer.
	www.aip.org /cip/langer.htm (469 words)

	Benchmarking Intel Systems and Understanding the Results - K-12 Education
		Linpack is a class of standard floating-point benchmarks that measure a computer's floating-point rate of execution by running a computer program that solves a dense system of linear equations.
		It is not the different problem sizes (10,000 in Figure 5 and 1,000 in Figure 6), but rather the different underlying implementations of the matrix factorization in HPL and Linpack1000 that cause such a dramatic shift in performance.
		Linpack1000 is a vectorized version of Linpack, and its performance is completely determined by DAXPY operations.
	www.dell.com /content/topics/global.aspx/power/en/ps4q01_ctcbench?c=us&cs=k12home&l=en&s=edu&~f=lg (1203 words)

	LINPACK - Definition, explanation
		LINPACK is a software library for performing numerical linear algebra on digital computers.
		The best performance on the Linpack benchmark is used as a performance measure for ranking supercomputers in the TOP500 list of the world's fastest computers.
		Ranking of supercomputers according to the LINPACK benchmark.
	www.calsky.com /lexikon/en/txt/l/li/linpack.php (393 words)

	Long Live the Top 500 \| Linux Magazine
		The LINPACK benchmark (http://www.netlib.org/linpack/), first developed in 1979, was chosen due to its wide availability and suitability for the purpose.
		LINPACK measures how quickly a computer can solve a dense system of linear equations using the floating point compute power of the system.
		Whether the measurement is LINPACK or some other HPCC suite in the future, there are great truths that have been revealed in The List over the past twelve years since its inception.
	www.linux-mag.com /id/2445 (1988 words)

	LINPACK: numerical library for linear equation solution
		LINPACK is a numerical subroutine library for solving linear equations, least-squares problems, and for finding singular values.
		That is smaller than the size of the high-speed cache memory of most machines of the 1990s or later, so the code runs faster than it would if the data were not in cache.
		The N = 1000 LINPACK benchmark takes of the order of a billion flops, and more memory than is available in the caches of most machines, so it is somewhat better as a performance measurement, but it too gives unfair weight to certain architecture classes, such as vector computers.
	www.math.utah.edu /software/linpack.html (509 words)

	TechWeb: The Business Technology Network
		The Tokyo Tech TSUBAME is the fastest supercomputer outside of the United States as measured by sustained Linpack performance as of May 2006.
		The Linpack Benchmark is a highly parallel computing test designed to measure how fast a computer system solves linear equations, a common task in engineering and scientific applications.
		Linpack imposes maximum load on a benchmarked machine for up to a day for system of TSUBAME's size, requiring utmost system reliability to properly complete.
	www.techweb.com /showPressRelease.jhtml?articleID=X475355 (986 words)

	IBM dominates list of top supercomputers
		It is based on the Linpack benchmark, which gauges the speed with which the systems can run certain mathematical operations.
		Though Linpack is sometimes criticized for not being a universal indicator of overall performance, a high ranking on the Top500 list is greatly coveted, and computer makers have been scrambling to outdo one another with benchmark results over the past few months in anticipation of yesterday's release of the list.
		That announcement was followed by preliminary Linpack results on the SGI system, which put it ahead of both Blue Gene/L and the Earth Simulator.
	www.computerworld.com /printthis/2004/0,4814,97354,00.html (509 words)

	Los Alamos takes second, third spots on Top500 supercomputing list: Los Alamos National Laboratory
		The project uses the Linpack benchmark, a mathematical code that all computers are required to run, as a performance measure to rank the computer systems.
		Known as the Space Simulator in friendly rivalry to the Japanese champion, the computer is used to study the evolution of the early universe, model supernovae behavior and conduct other astrophysical research.
		In recent Linpack runs, little Q has performed at speeds that would place it close to the current top 20 computers in the world.
	www.lanl.gov /news/index.php/fuseaction/nb.story/story_id/3248 (724 words)

	Earth Simulator still supercomputer champion - 21 June 2004 - New Scientist
		A supercomputer is an array of processors or "nodes" that work in parallel to solve a computationally challenging problem, for example modelling weather systems or the flow of oil through rocks.
		Past alternatives to Linpack have never been widely adopted, but Dongarra hopes that now the "time is right".
		However, he says Linpack will remain the benchmark for the TOP500: "Linpack is not going away.
	www.newscientist.com /article.ns?id=dn6045 (809 words)

	LINPACK
		LAPACK is modern (1990) and is intended to replace LINPACK.
		Documentation: usage instructions are available as comment lines in netlib's linpack directory.
		Library overview documentation is available as the readme file in netlib's linpack directory.
	www.scd.ucar.edu /softlib/LINPACK.html (149 words)

	PDLIB/SX: Business Solution \| NEC
		LINPACK is a set of subroutines for analyzing and solving linear equations and linear least-squares problems.
		EISPACK is a set of subroutines for computing the eigenvalues and eigenvectors of nine classes of matrices.
		PDLIB/SX consists of three versions: double precision with the IEEE floating-point format, double precision with the standard floating-point format and single precision with the extended floating-point format.
	www.nec.co.jp /hpc/mediator/sxm_e/software/61.html (270 words)

	[No title]
		These free packages are implementations of the LINPACK benchmarks which use BLAS and LAPACK software that has been highly tuned for maximum performance on Intel® Xeon® processor-based and Itanium®-based systems.
		This package is an implementation of the Massively Parallel MP LINPACK* benchmark for use on distributed memory computer systems (clusters).
		The Intel Optimized SMP LINPACK benchmark package doesnât perform any of the time consuming searching that HPL does, and while the Intel Optimized MP LINPACK benchmark package does do searching, it provides information early in the process so you donât have to wait until the entire run is completed before reconfiguring and beginning another run.
	www.intel.com /cd/software/products/asmo-na/eng/perflib/266857.htm (495 words)

	Sandia-designed supercomputer ranked world’s most efficient in two of six categories
		Next came the Linpack benchmark, which provided a real but relatively simple series of algorithms for a supercomputer to solve.
		Since 1993, those interested in supercomputers watched for the new Linpack numbers, published every six months, to determine and rank the 500 fastest computers in the world.
		Most recently, the limitations of this approach have encouraged the Linpack founders, in conjunction with supercomputer manufacturers, to develop still more realistic tests.
	www.eurekalert.org /pub_releases/2006-03/dnl-ssr033006.php (1038 words)

	Red Storm upgrade lifts Sandia supercomputer to 2nd in world, but 1st in scalability
		The machine, built by Cray Inc., is now rated second fastest in the world, with a Linpack speed of 101.4 teraflops.
		The widely recognized Linpack test measures a supercomputer's speed as applied to a computing problem.
		Its Linpack test demonstrated high reliability, repeatedly running for nine hours on over 26,000 processor cores without a failure.
	www.eurekalert.org /pub_releases/2006-11/dnl-rsu111506.php (696 words)

	It’s All About Speed \| Linux Magazine
		With its Linpack benchmark performance of 35.86 Tflops (trillions of operations per second), its performance beats that of the number two machine, the ASCI Q machine at Los Alamos National Laboratory, by a significant margin.
		HPL is a free implementation of the Linpack benchmark for distributed-memory computers.
		It is interesting to see how various hardware configurations perform on standard benchmarks like Linpack, and to get a sense of the relative speeds of different clusters and supercomputers.
	www.linux-mag.com /id/1458 (2465 words)

	Daemon News: Mailing List Archives
		> > Sample runs of Linpack (modified so that test is run multiple > times to allow JITs to do their work): The Linpack benchmark you are using seems to solve a size 200 x 200 problem.
		A benchmark program with a larger (500 x 500) problem set is also available at the Linpack benchmark for Java page http://www.netlib.org/benchmark/linpackjava/ The larger problem set will show results that are closer to the peak performance because longer computation time hides JIT compilation time.
		Linpack > Mflops/s: 85.833 Time: 0.01 secs Norm Res: 1.43 Precision: > 2.220446049250313E-16 In this case, the execution time (0.01 sec) is too short, then the result in Mflops is not very precise.
	www.daemonnews.org /mailinglists/FreeBSD/freebsd-java/msg03956.html (316 words)

	MFLOPS
		LINPACK - это пакет фортран-программ для решения систем линейных алгебраических уравнений.
		Целью создания LINPACK отнюдь не было измерение производительности.
		В стандартном варианте LINPACK выделен внутренний уровень базовых подпрограмм, каждая из которых выполняет элементарную операцию над векторами.
	www.citforum.ru /hardware/app_kis/glava_8.shtml (1076 words)

	iXBT: Обзор некоторых пакетов измерения производительности ...
		В этой статье позволю себе остановиться на двух тестах: Linpack Benchmark в версии для массивно-параллельных систем — HPL (Portable Implementation of the High-Performance Linpack Benchmark for Distributed-Memory Computers) и NAS Parallel Benchmarks (NPB).
		Linpack benchmark (LB) появился на свет в далеком 1979 году как дополнение к библиотеке Linpack (набор подпрограмм для решения различных СЛАУ) [4].
		Было представлено описание двух тестов: Linpack Benchmark и NAS Parallel Benchmarks.
	www.ixbt.com /cpu/cluster-benchtheory.shtml (2150 words)

	MS4 LINPACK and Its Impact on High-Performance Computing
		LINPACK and Its Impact on High Performance Computing
		The intent of this minisymposium is to give some historical perspective on the impact LINPACK had on the development of high-performance computing.
		In the current minisymposium we will provide a perspective on these developments, and present survey talks on the current state of the art in these areas.
	www.siam.org /meetings/archives/an97/ms4.htm (152 words)

	Computing Research Policy Blog: DOE/IBM's Blue Gene Nearly Doubles its Speed Record
		He also notes that the LINPACK score (upon which the Top500 list is based) isn't the best way to assess a supercomputer's relative benefit to a discipline, despite it's popularity -- something I probably should have noted in my post.
		In my defense, as limited as the LINPACK score is in what it says about a particular machine, it is the one number most people out here (certainly in the policy world) cling to when trying to understand progress in supercomputing.
		Though it wasn't the message we sought to convey, the fact that the Japanese Earth Simulator was X teraflops faster than our "best" machine certainly focused the mind of a lot of policymakers in Congress last year, for better or worse.
	www.cra.org /govaffairs/blog/archives/000308.html (388 words)

	Optimizing Java Linpack (Site not responding. Last check: )
		I took the original Java Linpack benchmark, by Jack Dongarra and Reed Wade, and applied some of the optimizations from my Java Optimization page:
		Used temporary scalars to hold frequently-used elements of 1D arrays (common subexpression elimination).
		Consider this a salutory reminder of the dangers of optimization!
	www.cs.cmu.edu /~jch/java/linpack.html (196 words)

	The Linpack Benchmark \| TOP500 Supercomputing Sites (Site not responding. Last check: )
		LINPACK was chosen because it is widely used and performance numbers are available for almost all relevant systems.
		A parallel implementation of the Linpack benchmark and instructions on how to run it can be found at http://www.netlib.org/benchmark/hpl/.
		The benchmark used in the LINPACK Benchmark is to solve a dense system of linear equations.
	www.top500.org /about/linpack (420 words)

	TAU - Computation Center - Explain - LINPACK (Site not responding. Last check: )
		LINPACK is a collection of Fortran subroutines which analyse and solve various systems of simultaneous linear algebraic equations.
		The subroutines are designed to be completely machine independent, fully portable, and to run at near optimum efficiency in most operating environments.
		LINPACK Users Guide by J.J. Dongarra, C.B. Moler, J.R. Bunch and G.W.Stewart is avaible in room 202 at the Computation Center.
	www.tau.ac.il /cc/pages/explain/linpack.html (69 words)

Try your search on: Qwika (all wikis)