NVIDIA nTeresting Newsletter – 25 November 2013

NVIDIA nTeresting Newsletter – 25 November 2013


In this issue:


· GeForce TITAN is named video card of the Year by PC Magazine.
· NVIDIA has great Linux drivers, which is why Valve selected us for the Steam Box prototypes.
· IBM turns to NVIDIA GPUs for supercomputing.
· Tesla K40 GPU accelerator is the world’s fastest.
· Fast and Green, NVDIA GPU-powered supercomputers propagate the Top500 list.
· GPU Technology Theater was standing-room-only at SC13.


GeForce GTX, Best of the Year


PC Magazine has announced their Best Products of the Year. The top video card was form NVIDIA.


“NVIDIA’s supercomputer-inspired GK110 comes to NVIDIA’s high-end consumer business as the NVIDIA GeForce GTX Titan. This $1,000 single-GPU card packs seven billion transistors, 6GB of RAM, and 2,688 shader cores. This is the first time NVIDIA has brought a specialized niche product over to the general consumer market.”


The best gaming laptop was GeForce-powered, too.


“But the most important bump in performance was seen in graphics capability, where Razer has replaced last year’s mobile NVIDIA GTX 660M graphics with a more powerful GeForce GTX 765M.”


As was the Gaming Desktop of the Year.


“Our review unit came with Windows 8, and as usual Falcon NW keeps the software preloads to a minimum. The SSDs are mostly empty, since Windows, the drivers and utilities for the graphics cards, and NVIDIA’s GeForce Experience are all that occupy the C: drive. GeForce Experience can help you automatically setup optimal quality and resolution settings for your system, depending on any game it has in its database. NVIDIA has also promised first-day driver support for all current and upcoming AAA gaming titles, so you’ll be able to optimally play the day you download the next Bioshock Infinite on launch day. Other neat GeForce Experience features include Shadowplay, which will automatically record the last 20 minutes of gameplay, so you can save gameplay videos for future analysis, or so you can relieve a particularly sweet move and share the experience with your friend.”


NVIDIA, Still Best for Linux


People who know Linux know who has the best Linux support.


“As some good news for the Linux graphics community after discovering the AMD Radeon R9 290 is currently a big disappointment on Linux (likely due to the Linux Catalyst driver not being kept up as well as the Windows Catalyst version), I was testing the GeForce GTX 780 Ti along with some other new NVIDIA GPUs and it’s been a breeze. The GeForce GTX 780 Ti in particular has been a beauty on Linux and is the focus of today’s Linux hardware review.”


People who make gaming PC using a Linux OS know, too.


“Valve went with NVIDIA graphics exclusively in their first-run Steam Machines prototypes for a reason.”


We’re in favor of any initiative that promotes open-platform gaming and takes advantage of our market-leading Linux support


IBM Embraces GPUs – Partners with NVIDIA to Build Next-Gen Supercomputers


The world’s most recognized supercomputer brand came out big in favor of GPU-accelerated computing this week with two huge announcements.


First, Big Blue and NVIDIA will integrate Tesla GPU accelerators into its line of Power supercomputers, giving researchers, engineers and other HPC customers new ultra-high performance, energy efficient systems to power their work.


“Computing giant IBM and chipmaker NVIDIA will today announce a significant partnership that will have them teaming up on the design and building of new supercomputing systems and servers.”


“Really, what we’re looking at here is a pair of 800 pound gorillas in HPC partnering up for what looks like world domination.”


If that wasn’t enough, Big Blue is also planning – for the first time – to accelerate its massive portfolio of enterprise database and big data analytics applications with CUDA GPUs. These apps used by thousands of companies worldwide, and the added GPU horsepower will let IBM customers crunch through and analyze massive amounts of data at supercharged speed.


“…broad partnership that will see GPUs and GPU acceleration coming to both IBM’s data analytic software and to the IBM Power supercomputers running some of those applications.”


“…a move aimed at enabling organizations to better process and analyze massive amounts of data and one that will expand the reach of such accelerators into the enterprise.”


“IBM Power Systems will fully support existing applications developed with NVIDIA CUDA… allowing supercomputing centers and HPC customers to immediately take advantage of groundbreaking performance advantages.”


NVIDIA Unleashes World’s Fastest GPU Accelerator


We took the wraps of the latest addition to our Tesla GPU product line, with the launch of the Tesla K40 GPU accelerator. With 40 percent higher performance than the current leader – the Tesla K20X GPU— and 10 times faster than today’s top CPU, the Tesla K40 accelerator packs extreme performance for scientific, engineering, HP) and enterprise applications.


“NVIDIA’s new Tesla K40 is likely to have the biggest impact in this space…The graphics chip vendor dominates the Top 500 systems…thanks in part of the maturity of its Cuda programming environment.”


“[The] Tesla K40 should extend the company’s lead further…”


“The chip, aimed at such workloads as big data and scientific calculations, also offers 10 times the performance of systems using only CPUs.”


“One player eager to step up to the Tesla K40 is the Texas Advanced Computing Center (TACC) at the University of Texas at Austin.”


Europe’s #1 Fastest, World’s Greenest Supercomputers Powered by GPUs


Tesla GPUs are making a major impact in science and in the world’s supercomputing and HPC communities. According to the Top500 list of the world’s most powerful supercomputers release this week at SC13, Tesla GPUs helped elevate a new Swiss system, “Piz Daint,” to the #1 spot as Europe’s fastest.


The first petascale-class system to break the 3 gigaflop per watt barrier (3.11 gigaflops/watt) — nearly 50 percent more efficient than next most efficient petascale system – Piz Daint will enable large-scale simulations for climate modeling, weather prediction and a host of other scientific research domains.


Also, according to the new Green500 list of the most energy efficient supercomputers, Tesla GPUs helped give a new system at Tokyo Tech – named Tsubame-KFC, a nod to its use of innovative oil-based cooling technology – a push to the #1 spot on that list.


“Piz Daint is operated by the Swiss National Supercomputing Centre (CSCS) in Lugano, Switzerland and is now the ‘most powerful system in Europe’…”


“…NVIDIA graphics accelerators powers the world’s top 10 most energy-efficient supercomputers… the most energy-efficient supercomputer in the world is the Tsubame-KFC..”


“The biannual Green500 list …for the first time all the top 10 systems benefitted from GPU acceleration.”


Leadership Science in our SC13 GPU Technology Theater


In case you weren’t at SC13, we hosted dozens of standing-room-only talks by researchers, engineers and technologists sharing how GPU-accelerated computing is allowing them to reach new milestones in innovation and scientific discovery. You can view all of these presentations at our SC13 GPU Technology Theater web site: http://www.nvidia.com/object/sc13-technology-theater.html


Leave a Reply

Your email address will not be published. Required fields are marked *

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>