
	Where results make sense

Topic: Gflops

Related Topics

FLOPS

Floating point

Naval aviation

2055 BC

Equity

Kosice

Despotism

Hebrew language

Charlize Theron

129 BCE

Propagandhi

Sommesous

Football Alliance

Sorbs

Herford

In the News (Wed 16 Dec 09)

Northern Trust

Marvin Harrison

Peter Chernin

Gary Locke

Match Play

Penelope Cruz

Mickey Rourke

AR Rahman

Danny Boyle

Hugh Jackman

	Ars Technica: Behind the benchmarks: SPEC, GFLOPS, MIPS et al - Page 1 - (4/1999) (Site not responding. Last check: 2007-10-29)
		I myself have even been known to quote GFLOP numbers from vendors; when that’s all you have to go on, then you don’t have too much of a choice.
		To measure GFLOPS (billion Floating Point Operations Per Second), you divide the number of floating point operations in a program by the execution time in milliseconds.
		Another, even bigger problem with GFLOPS is that the not all the same floating point instructions are implemented on all machines.
	arstechnica.com /cpu/2q99/benchmarking-1.html (1161 words)

	Avalon: An Alpha/Linux Cluster Achieves 10 Gflops for $150k
		The average wall clock times per timestep (including force calculation, timestep integration, and particle redistribution) are shown in Table 2, along with the corresponding Gflop rates obtained by counting the actual number of floating point operations in both the force and integration routines.
		Despite this, the overall performance is still nearly 11 Gflops, and the iteration time of 1.47 s represents a speedup of 3.4 over the 16 node run, or 77% parallel efficiency.
		The result for Avalon was 10.1 Gflops, a 64 processor 195 Mhz Origin 2000 obtained 13.1 Gflops, a 512 processor CM-5 obtained 14.1 Gflops (with assembly code), a 256 processor T3D obtained 7.9 Gflops, a 64 processor SP-2 66 Mhz-wide machine obtained 9.5 Gflops and 4096 processors of ASCI Red obtained 164.3 Gflops.
	loki-www.lanl.gov /papers/sc98 (3885 words)

	[No title]
		Peak speed in GFLOPS (billions of floating point operations per second) is thus obtained by dividing the number of independent CPU add and multiply pipes by the clock cycle time in nanoseconds (ns).
		When the operations are predominantly dyadic (simple add or multiply) as in the benchmark code, only one of the segments in the chained pipes can be in operation at a given time, so that it is more meaningful to count the chained pipe combination as one pipe instead of two.
		Thus a speed somewhat under 8 GFLOPS is not unreasonable for the benchmark.
	www.cs.cmu.edu /afs/cs.cmu.edu/Web/People/scandal/info/Kahaner/yosh (3533 words)

	FLOPS - Wikipedia, the free encyclopedia
		A relatively cheap but modern desktop computer using, for example, a Pentium 4 or Athlon 64 CPU, typically runs at a clock frequency in excess of 2 GHz and provides computational performance in the range of a few GFLOPS but the progression is not linear and depend on performances of CPU caches.
		The 1 TFLOPS for the Xbox 360 or 2 TFLOPS for the Playstation 3 ratings that were sometimes mentioned regarding the consoles would even appear to class them as supercomputers.
		An NVIDIA 7800 GTX 512 is capable of around 200 GFLOPS and the current (11/06) NVIDIA 8800 GTX is capable of sustaining 330 GFLOPS.
	en.wikipedia.org /wiki/FLOPS (1783 words)

	High Performance Computing in Europe (Site not responding. Last check: 2007-10-29)
		Last year their Rmax was comparable (310 Gflop/s), now academia comes to 500 Gflop/s compared to 940 on the research side.
		Number one in Europe in machines on the vendors side is Cray, 42 systems and 783 Gflop/s, if one adds the SGI figures, 20 machines and 126 Gflop/s, nearly 50% of the machines and 52% of Rmax show the dominance of this new group in Europe.
		In total 9 machines with an Rmax of 151 Gflop/s are installed, nearly of each system one machine, one Cray (25 Gflop/s), one Digital (5 Gflop/s), two IBMs (18 Gflop/s), one Intel (19 Gflop/s), one Meiko (5 Gflop/s), two NEC (42 Gflop/s) and one SGI (16 Gflop/s).
	www.hoise.com /primeur/PL/96/pl-top500/ES-PL-11-96-2.html (2641 words)

	© AMDboard.com - University of Kentucky supercomputer breaks the $100 per GFLOPS barrier
		Performance on that program depends partly on the theoretical peak GFLOPS of the processors, but also on the parallel implementation and efficiency of the network that allows the processors to work together.
		The remarkable thing about KASY0's price/performance is that, while network hardware is often the dominant cost for a system of its size (128 plus 4 spare nodes), less than 11% of the system cost went for the network hardware.
		At the University of Kentucky, as Professor of Electrical and Computer Engineering and James F. Hardymon Chair in Networking, Dietz's goal is to develop and freely diseminate the new technologies that will allow scientists and engineers to solve their most important computational problems.
	www.amdboard.com /hn08230301.html (826 words)

	100 Gflops Codes
		The figure to the right shows the maximu performance scaling with increasing number of processors: the solid curve shows the scaling of global performance as the number of processors is increased and the problem size is varied so as to maximize performance.
		NOTE: The MPS code has also achieved a peak performance of 160 GFlops on a special purpose Cray T3E-1200 that was available for a limited time at CRAY.
		NOTE: The HPS code has also achieved a peak performance of 167 GFlops on a special purpose Cray T3E-1200 that was available for a limited time at CRAY.
	astro.uchicago.edu /Computing/HPCC/Milestones/milestone9.htm (650 words)

	15 November 2002 - News Item - Myrinet Clusters in the November 2002 Top500 List
		This list is interesting for the wide geographic distribution of these clusters, their variety of purposes, and the diversity of suppliers, including five self-made clusters.
		When the interprocess communication is limited by ethernet, these ethernet clusters achieved 289 Gflops, less than half the performance of Platinum, a Myrinet cluster.
		The 761.98 Gflops LINPACK performance of this Myrinet/Linux cluster is a superb 82.68% of peak, a great demonstration of the capabilities of Itanium-2 systems in clusters with Myrinet components and software.
	www.myri.com /news/02b15 (1193 words)

	23 June 2003 News Item - Myrinet Clusters in the June 2003 Top500 List
		#56 at 1028 Gflops is a 256-node IBM Netfinity (dual 2GHz Xeon) cluster at the University of Southern California.
		#119 at 671.3 Gflops is a self-made Myrinet/Linux cluster of 256 2.4GHz Xeon processors at the Fermi National Accelerator Laboratory in Batavia, Illinois.
		#121 at 654.7 Gflops is a 128-node IBM xSeries (dual 2.0GHz Xeon) cluster at the Fraunhofer Institut, Ernst-Mach Institute in Freiburg.
	www.myri.com /news/03623 (1412 words)

	Parallel Computing Hardware (Site not responding. Last check: 2007-10-29)
		The peak performance of the system is 30.7 GFlops (for 128 CPU), the maximal memory capacity is 32 Gbytes with 4 Gbytes/sec peak I/O bandwidth.
		The peak performance of the system is 3.84 GFlops (for 128 CPU), the maximal memory capacity is 4 Gbytes with 500 Mbytes/sec peak I/O bandwidth.
		The connection structure is multiplane and has two types of connections: through crossbar between two processors in the same plane and through two corresponding crossbars between processors placed on different planes.
	www.pact.sscc.ru /hardware/computer (5558 words)

	Geek.com Geek News - New microprocessor can perform 25 GFLOPs (Site not responding. Last check: 2007-10-29)
		I thought GFLOPs were a measure applied to parallel processing, in particular unbalance parallel processing, like in cluster computers.
		Their GFLOP rating is very high, but the problems they solve are very limited, so it is really a difficult to program niche product.
		I mean price per GFLOP would be hard to determine, but you cant fit 60,000 AMD Opterons (made into a supercomputer) in 1/4 of a floor in a building.
	www.geek.com /news/geeknews/2003Oct/bch20031016022213.htm (1410 words)

	Vector and Scalar Parallel Supercomputers
		(5.935 GFLOPS/16 CPUs, 15.360 GFLOPS Peak/16 CPUs, 0.743 GFLOPS/1 CPU, 0.960 GFLOPS Peak/1 CPU.
		(20.48 GFLOPS peak/1024 CPUs, 20 MIPS and 0.020 GFLOPS Peak/CPU.)
		Configurations greater than one hundred and twenty eight processors (nodes) are considered "special requests." Each cabinet (system frame) holds sixteen nodes, communicating through a SP Switch at 110MB/second peak, full duplex, to make a 128p distributed-memory setup with 16p shared-memory cabinets.
	www.geocities.com /Athens/6270/superp.html (2646 words)

	Confused about GFLOPS ratings - Beyond3D Forum (Site not responding. Last check: 2007-10-29)
		There's a lot of GFLOPS ratings thrown around nowadays, but it seems that marketing has got the advantage and it's not that easy to actually compare them...
		The peak rating of 256 GFlops for the prototype CELL processor is unmatched by any other device announced to date.
		Make no mistake, that when you are talking hundreds or thousands of GFLOPs or more, it will be a far more plausible proposition to come up with a Cell solution than asking Intel or even IBM to come up with a single, monolithic CPU design that can do that.
	www.beyond3d.com /forum/showthread.php?t=17580 (5133 words)

	Project Background (Site not responding. Last check: 2007-10-29)
		The group at Columbia pioneered the construction of highly parallel machines dedicated to QCD calculations in 1982, and produced a series of three successful machines between 1985 and 1989 which were used to obtain a variety of new results in QCD.
		The theoretical work of the group at Columbia as well as the design and construction of the machines at Columbia is supported in part by the U.S. Department of Energy.
		In addition to the 400 Gflops machine installed at Columbia and the 600 Gflops machine at the RIKEN/Brookhaven Research Center, a number of smaller versions have been supplied to collaborating institutions.
	phys.columbia.edu /~cqft/backgrnd.htm (299 words)

	NEC Announces Latest Vector Supercomputer
		Higher performance: The single-node model (includes up to 8 CPUs) achieves a peak vector performance of 281.6 GFLOPS, while the multi-node model achieves the world's fastest peak vector performance of 144 TFLOPS when configured with 512 nodes.
		This was the world's first supercomputer to achieve a performance exceeding one GFLOPS.
		An increase in performance per single core has become more challenging in the recent HPC market due to the multi-core processor design that is applied to CPUs.
	www.hpcwire.com /hpc/991398.html (483 words)

	'Space weather' computers at NASA break through 100 Gflops (Site not responding. Last check: 2007-10-29)
		The five science teams who recently achieved NASA's performance goal have added their programmes to an emerging group of applications running at 100 Gflop/s and beyond.
		Ectonics and low-gravity fluid dynamics were among those that recently broke a 100 billion calculations per second (Gflops) performance milestone as part of the HPCC Earth and Space Sciences Project at NASA Goddard Space Flight Center in Maryland.
		These programs -- one of which exceeded the milestone by more than a factor of two -- were run on a 1,024-processor CRAY T3E-1200E configuration.
	www.hoise.com /articles/SW-PR-11-98-1.html (161 words)

	ClusterMonkey - Life, The Universe, and Your Cluster - A Study in Cluster Optimization
		The result, Test 6, was only 11.45 GFLOPS, which was down from 13.26 GFLOPS with the ATLAS library.
		According to Tim, the theoretical peak is computed by simply adding the total GHz (1.756) of all the processors and then multiplying by 2 for double precision because the Athlon/Sempron has two independent floating point units, one that can perform an FADD per clock, and the other can do one FMUL per clock.
		We should also note that the cost at construction vs. cost today could be considered less than fair as all computer hardware costs less in the future.
	www.clustermonkey.net /content/view/120/33/1/1 (2139 words)

	Top 500 - Orion Context (Site not responding. Last check: 2007-10-29)
		Orion has a peak speed of 144 Gflops (i.e., 144 billion calculations per second) and has now achieved a Linpack benchmark result of 110 Gflops.
		Entry level to the Top 500 list is currently 55 Gflops, compared to 43 Gflops in the previous list and 33 Gflops before that.
		Orion's result of 110 GFlops puts it at number 188 in the world.
	www.physics.adelaide.edu.au /ncflgt/top500context.html (412 words)

	Xbox2 CPU : 240 Gflops..? - Beyond3D Forum (Site not responding. Last check: 2007-10-29)
		It seems to also be possible to decrease or increase the number of cores within a CPU module.
		Actually according to Aaron Spink (a real engineer) a better estimate is 105 GFLOPS, taking into account the main FPUs on the PPC cores as well as the FP SIMD units.
		However given the known dispatch limits, even with unlimited bandwidth and no latency, you wouldn't be able to sustain issues to a scaler FPU and AltiVec units....
	www.beyond3d.com /forum/showthread.php?t=17531 (1451 words)

	[Beowulf] standards for GFLOPS / power consumption measurement?
		Many of your questions may have already been answered in earlier discussions or in the FAQ.
		> > So when speaking of gflops per dollar at linpack, this will destroy of > course any record of $2500 currently, especially for applications needing > bandwidth to other processors, if i see what i paid for this self > constructed beowulf.
		> >> The Clusterworld value box with 8 Sempron 2500s specifies a peak Gflops > by > >> measuring CPU Ghz x 2 (1 - FADD, 1 FMUL), and comes out with a rating of > 52% > >> of peak using HPL @ ~ $140/Gflop (sustained?) > > > >It is hard to compare.
	www.beowulf.org /archive/2005-May/012838.html (796 words)

	PC Vs Console - Emotion Engine, FPU, Vector Units, and GS GFLOPS
		But over all, the Gflop rating is a very good benchmark for graphic power.
		This means the GS must put out at least 4 gflops I mean if it has a higher raw poly rate than EE, but GS isn't as advanced due to rendering capabillities so I figure 4 gflops for sony gs.
		Your theory for Emotion Engine GFLOPS distribution is commended for the effort, but your chosen numbers are unfortunately incorrect.
	www.pcvsconsole.com /hank/answer.php?file=595 (450 words)

	Texas Memory Systems - Digital Signal Processing (DSP) Division
		This ASIC (the TM-44 "Blackbird") was designed to provide faster processing and bandwidth than the competitors without resorting to extreme power hog circuits.
		Offering 192 GFLOPS and 16 GB/s of storage bandwidth in just 3 rack units and 600W, it offers a perfect combination of power and efficiency.
		Each TM-44 DSP node has 8 GFLOPS of processing power, 8 GB/sec of memory bandwidth, and many additional units necessary to maintain processing efficiency.
	www.superdsp.com (1014 words)

	Supercomputers
		It has a measured maximal performance of 1,608 GFlops, and a peak performance of 3,072 GFlops.
		Installed at Leibniz Rechenzentrum—a department in the Bavarian Academy of Sciences—Munich, Germany, this machine is used for academic research in areas like physics and geophysics, chemistry, astronomy, meteorology, engineering, and software engineering.
		It has a measured performance of 1,035 GFlops and a peak performance of 1,344 GFlops.
	www.pcquest.com /content/techtrends/200112806.asp (486 words)

	Co-processors to accelerate desktop PC to 50 GFlops \| TG Daily (Site not responding. Last check: 2007-10-29)
		The company claims that new chip, named CSX600, is the world's fastest 64-bit floating point processor, delivering a sustained performance of 25 GFlops.
		Since the boards follow the single-slot PCI-X standard, there only limitation of the number of boards in a system is determined by the number of available slots.
		What makes Clearspeed's card attractive is the fact that it can be installed in an existing computer within minutes and immediately can result in added performance for 32-bit and 64-bit systems.
	www.tgdaily.com /2005/06/20/co/index.html (630 words)

	Clearspeed updates 50 GFlops accelerator board \| TG Daily (Site not responding. Last check: 2007-10-29)
		The device still delivers an estimated additional performance 50 GFlops, but now comes in a much smaller form factor that will allow more users and system builders to integrate the board into their workstations.
		An alternative to boost performance could be Clearspeed's Advance board, which promises to add about 50 GFlops of additional processing power to a workstation system.
		While the firm hinted to such a move already back in August of last year, Beese now says that a PCIe board may not appear too soon: "There is typically only one PCIe slot in today's PCs and the slot is naturally dedicated to PC graphics," he said.
	www.tgdaily.com /2006/06/27/clearspeed_advance_board (649 words)

	[Beowulf] standards for GFLOPS / power consumption measurement?
		So when speaking of gflops per dollar at linpack, this will destroy of course any record of $2500 currently, especially for applications needing bandwidth to other processors, if i see what i paid for this self constructed beowulf.
		>> The Clusterworld value box with 8 Sempron 2500s specifies a peak Gflops by >> measuring CPU Ghz x 2 (1 - FADD, 1 FMUL), and comes out with a rating of 52% >> of peak using HPL @ ~ $140/Gflop (sustained?) > >It is hard to compare.
		I don't know what sustained or peak means in the >context of their tests.
	www.scyld.com /pipermail/beowulf/2005-May/012831.html (457 words)

	Woodcrest will outperform all other CPUs on the market
		Basically, a 3GHz Woodcrest chip gives you 3 billion x 4 FP ops x 2 cores per second, or 24 GFLOPS theoretical peak (Rpeak number in Linpack) per socket in 64-bit precision.
		So, it is 2.8 billion x 2 FP ops x 2 cores per second, or 11.2 GFLOPs Rpeak per socket.
		We all know that Itanic is darn great at least in Linpack, with over 90% efficiency in some cases - but its clock is nearly half that of Woodcrest, with the same peak FP rate per cycle anyway.
	www.theinquirer.net /?article=31836 (523 words)

	Hardware - SIMD Executive Summary
		Thus, it is possible that you may write a function that performs even better than 38.2 GFlops.
		We advertise 38.2 GFlops because that is the speed of the fastest function we have tested.
		It comes from a convolution function that is among the many vectorized functions in Accelerate.framework, a standard part of MacOS X. Below is a small table of a few Accelerate.framework functions and the average number of GFLops we measure for them over a number of runs on a 2.0 GHz dual processor machine.
	developer.apple.com /hardware/ve/summary.html (755 words)

	How many Gflops?
		There is the perpetual question of "what's a gigaflop" that makes this question ambgiguous if not meaningless.
		In L2 I've measured about 270-275 peak MFLOPS (double precision) with cpu-rate (http://www.phy.duke.edu/brahma) (which averages the rate at which addition, subtraction, multiplication and division occur, where division is generally very slow and a rate limiting factor) on a 1.2 GHz Tbird Athlon.
		It is quite possible for aggressive optimization, different compiler choices, hand-coded assembler, and perhaps the use of e.g.
	www.beowulf.org /pipermail/beowulf/2001-May/003432.html (673 words)

Try your search on: Qwika (all wikis)