NVIDIA Tesla K20 family reintroduced as world’s most powerful GPU

This week the folks at NVIDIA are making it clear that the K20 family of Tesla GPU architecture is ready for action, and riding in on the wave of power comes the Titan – K20 accelerated and named world’s fastest supercomputer just this morning. The Titan supercomputer works with a beastly 18,688 NVIDIA Tesla K20X GPU accelerator units and makes it clear that this family is more than ready to knock the cap off the processing roof in more ways than one. In addition to being the fastest GPU in the world the K20X model working with the Titan has been revealed as the new #1 entry on the Green500 list for energy efficiency.

It’s a big day for NVIDIA with the Tesla K20 architecture being reintroduced in its final form powered by CUDA – also known as “the world’s most pervasive parallel programming model.” NVIDIA backs this claim up with 8,000 institutions with CUDA developers, 1,500,000 CUDA downloads, and a massive 395,000,000 GPUs shipped with CUDA built in. With 629 university courses being taught on CUDA across 62 countries, it’s safe to say that it’s here for some time to come.

The K20 family also makes with the undeniably next-level powerful performance on scientific applications – this being exactly why the Titan supercomputer uses the architecture for the massive bulk of its processes. The 2011 Gordon Bell Winner for computational simulation was 3.1 Petaflops (3.08 Petaflops on K Computer) with NVIDIA’s new effort bringing on 10+ Petaflops here in 2012.

Both the Tesla K20 and the Tesla K20X work with a single GK110 Kepler GPU with your favorite features – Dynamic Parallelism and Hyper-Q! These units have more than one teraflop peak double precision performance and deliver 10 times the performance of a single CPU – this claim by NVIDIA being based on the following: “Ws-lsMs performance comparison between single E5-2687W @ 3.10GHz vs single Tesla K20X. Tesla K20X > 650 gigaflops.”

There’s also a Tesla K10 model out there, you should know, with memory size of 8GB per board and just SMX inside instead of the addition of Dynamic Parallelism and Hyper-Q, which the K20 and K20X have. The K10 (again, having been on the market now for some time,) has a peak double precision floating point performance of 0.19 teraflops and is made for servers only – it’s peak single precision floating point performance, on the other hand, is 4.58 teraflops. The K20 rings in 1.17 teraflops and 3.52 teraflops for double and single precision floating point performance respectively. The K20X nabs 1.31 teraflops and 3.95 teraflops.

The K20 has 5GB memory size per board while the K20X has 6GB, and both devices have just the one GK110 GPU while the K10 has two GK104 units inside. The K20 units are made for massive beastly tasks like financial computing, computational chemistry and physics, and satellite imaging. The K10 on the other hand is made for seismic, image, signal processing, and video analytics.

The NVIDIA Tesla K20 family of GPU accelerators is ready for action this week – shipping today and available for order from your favorite computer store. NVIDIA is working with Appro, ASUS, Cray, Eurotech, Fujitsu, HP, IBM, Quanta Computer, SGI, Supermicro, T-Platforms, Tyan, and NVIDIA reseller partners as well – you’ll have no shortage of choices on your hands. Grab a K20 as fast as you can!


NVIDIA Tesla K20 family reintroduced as world’s most powerful GPU is written by Chris Burns & originally posted on SlashGear.
© 2005 – 2012, SlashGear. All right reserved.


NVIDIA-powered Titan becomes world’s fastest Supercomputer

It’s been revealed this morning that the Titan Supercomputer is not just one impressive beast in and of itself, it’s now officially the fastest on the planet. According to the TOP500 list update released this morning at the SC12 Supercomputing Conference, NIVIDA Tesla K20 GPU-accelerated Titan has indeed become the fastest supercomputer on Earth, and has out-done the rest of the supercomputers by a massive amount. Titan works with a massive 18,688 NVIDIA Tesla K20X GPU accelerators and has topped the previous record holder here near the end of 2012, that being the Lawrence Livermore National Laboratory’s Sequoia system.

The performance record that this beast now holds is a 17.59 petaflop mark as measured by the benchmark system known as Linpack – a system that measures all manner of devices all the way down to smartphones (with GPUs packed inside as well.) The Titan makes this massive stride into the future with the Tesla K20X accelerator, the “flagship of NVIDIA’s accelerated computing line.” NVIDIA notes that this new solution provides “the highest computing performance ever available in a single processor.”

NVIDIA’s claims are backed with two more benchmark results: 3.95 teraflops singleprecision and 1.31 teraflops double-precision peak floating point performance – beastly. Those come from a setup as follows: CPU results: Dual socket E5-2687w, 3.10 GHz, GPU results: Dual socket E5-2687w + 2 Tesla K20X GPUs. NVIDIA also notes that the family of processors being used here also includes the K20 (without the X) which has busted out 3.52 teraflops of single precision and 1.17 teraflops of double-precision peak performance.

The Tesla K20X and K20 GPU accelerators have brought on more than 30 petaflops of performance over the past 30 days – that’s big. It’s so big, in fact, that it’s equivalent to the computational performance of the top 10 fastest supercomputers from 2011 combined.

In addition to being the fastest, the Tesla K20X GPU accelerator has been revealed to be three times more energy efficient than previous generation GPU accelerators – so says NVIDIA. The Titan has achieved 2,142.77 megaflops of performance per watt, this surpassing the previous most energy-efficient supercomputer on the planet as well – this according to the official Green500 list.

Have a peek at the timeline below to get more information on Titan as well as the K20 family of GPUs from NVIDIA – it’s big time computing action for all!


NVIDIA-powered Titan becomes world’s fastest Supercomputer is written by Chris Burns & originally posted on SlashGear.
© 2005 – 2012, SlashGear. All right reserved.


AMD’s dual-GPU FirePro S10000 gobbles watts, spews out nearly 6 TFLOPs for server graphics

AMD's dual-GPU FirePro S10000It can’t be easy, running a modern IT department. Not only are people making ever more graphics-hungry demands on your servers, but NVIDIA and AMD are locked in an unending spec war that can make it hard to keep up with the market. The FirePro S10000 is merely the latest salvo: a dual-GPU, server-focused version of the W9000 that greatly increases overall compute power, delivering 5.91 TFLOPs of single precision calculations and 1.48 TFLOPS of dual precision performance in a single PCIe 3.0 card with 6GB of GDDR5 RAM. Even though the Graphics Core Next GPUs have been slightly underclocked to 825MHz, and even though they technically offer better performance per watt than a single-GPU configuration, their overall 375w power draw could still get you in trouble with your local power station. That level of consumption is around 50 percent higher than a regular server card like the S9000 or Tesla K10 and it may well require you to research new server cases and coolers in addition to weighing up the $3,600 cost for the component itself. See? This was never going to be straightforward.

AMD’s dual-GPU FirePro S10000 gobbles watts, spews out nearly 6 TFLOPs for server graphics originally appeared on Engadget on Mon, 12 Nov 2012 05:23:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceAMD  | Email this | Comments

NVIDIA’s revenue hits a record $1.20 billion for Q3 powered by Tegra 3 tablets, Kepler GPUs

NVIDIA's revenue hits a record $120 billion for Q3 powered by Tegra 3 tablets, Kepler GPUs

Just as it predicted, NVIDIA’s earnings show revenue rose again in Q3, to a new record high of $1.20 billion, 15.3 percent higher than in Q2 up 12.9 percent from the same period last year. Its profits also grew accordingly, to $209.1 million, which should be no surprise thanks to its Tegra 3 chip’s place at the heart of tablets including Google’s Nexus 7 and Microsoft’s Surface for Windows RT, with more arriving daily. The Consumer Products division that includes the Tegra family and other hardware had a 27.6 percent rise in revenue for the quarter. Despite predictions of a slumping PC market, its consumer GPU unit had revenue up 10 percent from last quarter as Kepler based products reached into lower price points and notebook revenue rose. Riding high, the company has decided to issue dividends to shareholders as well as extend its current stock repurchasing program. Hit the source links for the full breakdown, but so far NVIDIA’s bets on the future of its chips in PCs and post-PC devices seem to be paying off.

Continue reading NVIDIA’s revenue hits a record $1.20 billion for Q3 powered by Tegra 3 tablets, Kepler GPUs

Filed under: , , , , ,

NVIDIA’s revenue hits a record $1.20 billion for Q3 powered by Tegra 3 tablets, Kepler GPUs originally appeared on Engadget on Thu, 08 Nov 2012 19:17:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceNVIDIA (1), (2 – PDF)  | Email this | Comments

Imagination Technologies snaps up CPU designer MIPS in an attempt to wrestle ARM

Imagination Technologies snaps up CPU designer MIPS in an attempt to wrestle ARM

Looks like we can kiss goodbye to any lingering politeness in the rivalry between these two UK chip houses, because the smaller one has just embarked on a cheeky expansion. Having been known mainly for its PowerVR graphics processors, not least in many Apple products, Imagination Tech could potentially push into the CPU arena too, through its $60 million acquisition of MIPS Technologies. Just Like ARM, MIPS designs low-power RISC processors for consumer electronics, but it has generally focused on smaller chips for devices like routers and TVs rather than smartphones and tablets. In addition to a portfolio of 82 exclusive patents, a squad of 160 MIPS engineers will now be transplanted to Imagination, where they’ll no doubt be debriefed and reassigned to conquering the world. Meanwhile, in some sort of flanking move, ARM has paid a far higher sum of $170 million to gain access to a number of other MIPS patents.

[Thanks, Michael]

Imagination Technologies snaps up CPU designer MIPS in an attempt to wrestle ARM originally appeared on Engadget on Tue, 06 Nov 2012 06:41:00 EDT. Please see our terms for use of feeds.

Permalink   |  sourceReuters, ARM  | Email this | Comments

iPad 4th gen GPU innards revealed

The newest iPad has had its guts revealed once again, showing off not just the pieces we knew about, the A6X processor included, but the GPU and its abilities as well. The folks at AnandTech have gone in for a deep-dive into the A6X as it exists on the iPad 4, showing a brand new PowerVR SGX 554 GPU. The A6X processor retains many elements from the A5X processor the iPad 3 worked with, including the memory controller interface sitting adjacent to the GPU cores instead of the CPU cores, as it was in the A5 and the standard A6 (on the iPhone 5).

The A6X has been revealed to also retain the 128-bit wide memory interface that the A5X worked with, integrating here two of Apple’s Swift cores running right up to 1.4GHz right out of the box. The PowerVR SGX 554 GPU living here in the iPad 4 is far and away more advanced than the units used in the iPad 3 or the iPhone 5, doubling the # of SIMDs of the iPad 3′s GPU, the PowerVR SGX 543MP4, essentially one generation back.

This new GPU appears to have double the ALU per core that the iPad 3′s unit works with (8 Vec4 ALUs per core vs. 4 Vec4) and brings on what Chipwork‘s analysis suggests is 2 sets of 4 identical sub-cores and one central core. That analysis shows 9 sub-cores, that is, as shown below, again from Chipworks. Anand suggests that this architecture points toward a theoretical performance greater than 77 GFLOPS – hot stuff!

You’ll find in benchmarks galore that this iPad – surprise – beats the older iPad models by a significant margin regardless of the test. The GPU appears to be clocking at least 15% higher than the iPad 3′s greatest hits, while tests like GLBenchmark are showing 65% benchmark performance improvement in some cases – in other words: really, really good. Have a peek at our full iPad 4th gen review for more everyday testing and sweet daily action.


iPad 4th gen GPU innards revealed is written by Chris Burns & originally posted on SlashGear.
© 2005 – 2012, SlashGear. All right reserved.


TITAN sees unprecedented demand for supercomputing science projects

Today the folks at Oak Ridge National Laboratory, NVIDIA, and Cray have brought on the next generation of accelerated computing with not just a re-naming of the Jaguar supercomputer, but integration with NVIDIA’s solutions for GPU-powered greatness. This update turns the Titan (as it is now called) into the flagship accelerated computing system – the flagship for the whole world, that is. This is now a 200-cabinet Cray XK7 supercomputer working with 18,688 notes – AMD 16-core Opteron plus NVIDIA Tesla K20 GPUs – enough to change the way we work.

This project is a next-level teaming of the Cray XK7, the “most scalable supercomputer” on the planet, and the NVIDIA Tesla K20 GPU, aka the “world’s fastest accelerator.” This combination beings on CUDA and Open ACC programming and new features that expand programmability far beyond what’s been available before, and with the NVIDIA GPU units being used now, they’re working with 3x higher performance per watt. This means one whole heck of a lot less power consumed for the same tasks as were being performed before.

This supercomputer is currently in the acceptance process for a series of scientific applications. The program that surrounds this unit is made to expand the access groups have to supercomputing, judging each application for a program individually and giving them time based on the percentages allotted to each of the following: Plasma, Nuclear, Materials, Engineering, Earth Science, Computer Science, Chemical Science, Biology, and Astrophysics. This is all done through the US Department of Energy’s INCITE: Innovative and Novel Computational Impact on Theory and Experiment.

This program has seen a record number of proposals, with demand being approximately three times larger than they’re actually able to supply. Have a peek at the gallery below to see a few examples of what these applicants are proposing:

gomang
proagesae
proafods
projessasd

This also brings the Jaguar – again, now called Titan – up to a whole new specifications set. The compute notes remain the same at 18,688, but the Login and I/O nodes go up from 256 all the way to 512. The memory per node was at 16Gb and is now at 32GB + 6GB. Number of Opteron cores jumps from 224,256 to 299,008, and the total system memory was at 300TB and is now at 710TB. With the addition of 18,688 NVIDIA K20 Kepler accelerators, this beast’s former peak performance at 2.3 Petaflops is dwarfed by its current peak at 20+ Petaflops.

2012-P02904
2012-P02909
2012-P03100
2012-P03132R
2012-P03133R
2012-P02910
2012-P03134R
2012-P03135R
2012-P02907
2012-P02901
2012-P02873
2012-P02849
2012-P02847
2012-P02843
proadfa


TITAN sees unprecedented demand for supercomputing science projects is written by Chris Burns & originally posted on SlashGear.
© 2005 – 2012, SlashGear. All right reserved.


Titan supercomputer goes live with potent CPU/GPU tag team

The Titan supercomputer at the Oak Ridge National Laboratory has been upgraded, tackling complex climate change calculations with 20 petaflops worth of new processors. Under the (considerable) hood its NVIDIA’s “Kepler” GPUs and AMD Opetron 6274 processors doing the heavy lifting, though NVIDIA can’t resist pointing out that its graphics chips are in fact carrying 90-percent of the overall load. The GPUs, more commonly found powering gaming rigs, help make Titan “the world’s fastest supercomputer for open scientific research.”

That research will include simulating physical systems, such as weather patterns, or progressions in energy, climate change, efficient engines, materials, and other fields. However, unlike most supercomputers, where access is jealously guarded, Titan takes a more open approach to access.

Researchers from schools and universities, government labs, and private industry can access Titan – by arrangement, of course – to crunch their own data. Final testing is still underway by the laboratory and Cray, and the supercomputer’s first year will be dominated by work on the Department of Energy’s Innovative and Novel Computational Impact on Theory and Experiment (INCITE) program.

“The improvements in simulation fidelity will accelerate progress in a wide range of research areas such as alternative energy and energy efficiency, the identification and development of novel and useful materials and the opportunity for more advanced climate projections” James Hack, director of ORNL’s National Center for Computational Sciences, said of the new machine.

In total, there are 299,008 CPU cores, sixteen to each of 18,688 nodes; each node also has an NVIDIA Tesla K20 graphics accelerator. The cores are used to guide the simulations, while the GPUs are relied upon to do the actual data crunching; altogether, it’s more than 10x faster and 5x more power efficient than the Jaguar supercomputer Titan replaces.

In fact, Titan can simulate 1-5 years per day of computing time, whereas Jaguar took a day to work through around three months worth of data. ORNL says it’s the equivalent of “the world’s 7 billion people being able to carry out 3 million calculations per second.”


Titan supercomputer goes live with potent CPU/GPU tag team is written by Chris Davies & originally posted on SlashGear.
© 2005 – 2012, SlashGear. All right reserved.


Cray’s Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan

Cray's Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan

Cray’s Jaguar (or XK7) supercomputer at Oak Ridge National Laboratory has been loaded up with the first shipping NVIDIA Telsa K20 GPUs and renamed Titan. Loaded with 18,688 of the Kepler-based K20s, Titan’s peak performance is more than 20 petaflops. Sure, the machine has an equal number of 16-core AMD Opteron 6274 processors as it does GPUs, but the Tesla hardware packs 90 percent of the entire processing punch. Titan is roughly ten times faster and five times more energy efficient than it was before the name change, yet it fits into the same 200 cabinets as its predecessor. Now that it’s complete, the rig will analyze data and create simulations for scientific projects ranging from topics including climate change to nuclear energy. The hardware behind Titan isn’t meant to power your gaming sessions, but the NVIDIA says lessons learned from supercomputer GPU development trickle back down to consumer-grade cards. For the full lowdown on the beefed-up supercomputer, hit the jump for a pair of press releases.

Continue reading Cray’s Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan

Filed under: ,

Cray’s Jaguar supercomputer upgraded with NVIDIA Tesla GPUs, renamed Titan originally appeared on Engadget on Mon, 29 Oct 2012 03:01:00 EDT. Please see our terms for use of feeds.

Permalink   |   | Email this | Comments

AMD Never Settle bundle gives Radeon HD 7000 buyers free games they’d actually care to play

AMD Never Settle bundle gives Radeon HD 7000 buyers free games they'd actually care to play

Just about anyone who has bought more than one aftermarket graphics card knows that bundled games rarely matter. They’re usually year-old titles or neutered editions built only to showcase the GPU’s performance for a few hours. AMD thinks its Never Settle bundle might finally get us to notice. Buy any modern Radeon HD video card from the 7770 GHz Edition on up and you’ll get a download code for at least one new game you’d genuinely want to try, ranging from Far Cry 3 on basic cards to a full three-game deal that supplies Far Cry 3, Hitman: Absolution and Sleeping Dogs to high rollers buying the 7900 series. There’s likewise a discount for Medal of Honor: Warfighter and promises of bundles in 2013 for Bioshock Infinite and the reimagined Tomb Raider. As long as you’re not dead set on springing for a GeForce board in the next few months, one of the qualifying cards might be worth a look to jumpstart your game collection.

Filed under: , , ,

AMD Never Settle bundle gives Radeon HD 7000 buyers free games they’d actually care to play originally appeared on Engadget on Mon, 22 Oct 2012 00:01:00 EDT. Please see our terms for use of feeds.

Permalink   |   | Email this | Comments