The Official NVIDIA Blog

We’re bringing you another behind the scenes look here at NVIDIA. This week we met with Danny Shapiro, director of marketing for Quadro, who spoke with us about NVIDIA’s work with the film industry, and the hand GPUs played in helping “Avatar” snag the Oscar for best visual effects. 

Recently NVIDIA’s CEO spoke to Fortune’s Adam Lashinsky about Tegra and the future of the tablet market. Let me add some color to that story and dive deeper into what we see happening with tablets as the new Tegra-based ones begin hitting the market this year.
 
The tablet computer has been waiting in the wings of the PC industry for nearly 20 years. Back in the early 1990s there was the MessagePad PDA built on the Newton platform. In 2001, Microsoft introduced the Tablet PC. None of these was a huge success, so why is NVIDIA so excited about the new generation of tablet computers?
 
For one thing, digital content and the web have become integrated into our everyday lives in a way that just wasn’t happening when earlier tablets were introduced. Take a look around your kitchen (or your kids’ friends’ kitchens). Chances are, there’s a notebook computer somewhere in the scene. These notebooks get left in central areas of the home and are used for email, checking the weather, surfing the web or watching videos. None of these use cases requires a lot of typing, and most would lend themselves to a great touch device. In addition, all of these applications are dependent on an Internet connection and a device that is capable of a full and rich web experience. Can anyone say tablet?
 
At the same time that consumers' online habits have evolved, the web has evolved, too. The web of 2010 is far richer and more complex than the web of only a few years ago. For example, 87% of web sites use Flash, much of the video content is now HD and the most popular online games are Flash-based games like Zynga’s FarmVille, which is played by 75 million people a month. The web has become our “content store.” Sites like Hulu, YouTube, BBC iPlayer and Bharatmovies stream high-quality movies. Facebook, Twitter and MySpace have people constantly connected and sharing songs, pictures and videos. Finally, books and magazines are moving to digital forms, with Amazon Kindle for books and Adobe AIR for magazines.
 
With all this amazing content available, we just need a way to consume it. And this is where Tegra comes into the picture. The new Tegra-based tablets can handle all the rich media on the web, and they do it in a way that takes full advantage of a tablet’s portability and interface.
 
Tegra is the first platform that enables the whole Internet in well under 1 watt of power. And it’s the first mobile platform to offload the Flash graphics processing pipeline onto the GPU. This means full Flash 10.1 on your mobile device, so you get to experience the web as it was meant to be – not some watered-down version built for phones. Plus, GPU processing power means 1080p video encode and decode, ultra low-power audio playback and incredible graphics for appealing and intuitive user interfaces. With Tegra, manufacturers can build ultra-thin tablets with days of battery life, plus amazing performance and portability. Combine this with the wireless carriers’ desire to sell connections, and you have the perfect storm of content, capability and a channel to deliver gorgeous and exciting mobile devices.

It’s going to be a great year for consumers.

UPDATED: 3/10/10

Congratulations @philharmonik1 for winning Challenge #5! @philharmonik1 is the lucky winner of a $250 Newegg gift card!

Challenge #6: Enter to win a Windows 7 OS and an EVGA GeForce GT 240 GPU.

To enter, tweet the name of one of the first 2 games commercially released for the precursor to Microsoft’s DirectX API. Responding here with a comment will not count! You must enter on Twitter.

As always, include the hashtag #nvidiaHOG with your answer. Remember to read the instructions carefully...we will only accept answers on Twitter. Comments on this blog post won’t count.

Keep reading after the break for full rules and contest details.

Since 2001, NVIDIA has taken the money it would spend on a holiday party and invested it into a community project where hundreds of Santa Clara employees accomplish amazing things for neighborhoods in need. We call the event Project Inspire and it has become a much-loved holiday tradition for our employees and their families.

For this year’s Project Inspire, NVIDIA (along with our partner City Year) is extending an invitation to Silicon Valley schools, neighborhoods and community organizations to apply and be considered as NVIDIA’s next Project Inspire recipient.

Today we’re announcing a request for applications at www.projectinspire2010.com. It’s your chance to help us create big impact in the community. Can you spread the word?

If you know of a worthy school, community center, neighborhood or other in Silicon Valley, just send them this link: www.projectinspire2010.com. All of the details about how to apply can be found on this page. The opportunity to get several thousand dollars worth of services and up to 1,000 volunteers to help can mean jump starting lasting change in many low income communities.

• Some of the stats from Project Inspire events over the past three years include:
• Number of youth impacted: 2,800
• Number of computers donated: 250
• Children who will gain job skills in multimedia design: 300+
• Number of community volunteers: 400
• Number of NVIDIA volunteers: 2,100
• Amount of partnership dollars: $244,000
• Partners include: Adobe Systems, Fairmont Hotels, Webcor, Home Depot and more

The principal of last year’s Project Inspire school, McKinley Elementary has said that the school has had zero graffiti since we completely repainted the school on December 5 (graffiti used to be a weekly occurrence). It’s a great example of the community taking pride in the work that it helped us accomplish.

Every Friday, NVIDIA sends out an email round-up of CUDA, GPU Computing and GPGPU news called "CUDA: Week in Review." Below we've shared a few highlights from this week's issue.

If you like what you read and are interested in joining the email list, you can sign up here. You can also check out previous issues here.

World Cup Fans: Rejoice!
Those of you who are soccer/football fans know the 2010 FIFA World Cup starts in June in South Africa. But did you know that CUDA will be playing a role? Mirics, an NVIDIA partner, is teaming up with Hong Kong-based USmart to develop multi-standard broadcast television platforms so fans can watch World Cup TV on mobile devices in Europe, Asia, and South America. Check out the TMCnet article, here.

Next-Generation Water and Lighting in Just Cause 2
Square Enix London Studios announced that the PC release of Just Cause 2 will feature GPU-accelerated water and lighting. Developer Avalanche Studios tapped CUDA to make the game’s environments more beautiful and immersive. CUDA-enhanced features include rivers, lakes and oceans rendered with realistic waves and ripples. The game is also optimized for 3D Vision. Watch the video on Kotaku now.

Yellow Dog Enterprise Linux for CUDA
Fixstars Corp. of Tokyo released Yellow Dog Enterprise Linux (YDEL) for CUDA, the first commercial Linux distribution for GPU computing. Michael Feldman at HPCwire said, "General-purpose GPU computing is now positioned to be the most widely used accelerator technology for high performance computing."

 

NVIDIA Optimus technology has been a hit, getting accolades for its unique ability to automatically and seamlessly select the right graphics processor for the job, between an NVIDIA discrete GPU or an Intel integrated GPU. It works with GeForce notebook GPUs and the recently announced next generation ION.

Here at CeBIT nearly 20 different Optimus notebooks and netbooks are on display.

ASUS is showing 12 systems with Optimus Technology in their booth:

• U30Jc (13.3”)
  
• UL50Vf (15.6”)
• UL80Jt (14”)
• U33Jc (13.3”)
• U43Jc (14”)
• UL30Jt (13.3”)
• K52Jc (15.6”)
• N82Jv (14”)
• N61Jv (16”)
• N71Jv (17”)
• NX90 (18.4”)
• 1201PN (12.1” with Next Generation NVIDIA Ion)

MSI is showing 2 Optimus notebooks.The new MSI F Series is designed to be professional, slim and powerful, and the FX400 and the FX600 both feature an NVIDIA GeForce 310M GPUs with NVIDIA Optimus technology:

• FX400 (14”)
• FX600 (15.6”).  

Clevo is displaying 2 Optimus notebooks in their private meeting room suite:

• B4100 (14”)
• B5100 (15”).

And in NVIDIA’s Cebit demo rooms we’re showing several of the above ASUS notebooks, plus 2 additional Optimus notebooks - the Medion Akoya P6622 (15.6”) with GeForce 310M and the recently announced Acer Aspire One 532g (10”) with next generation NVIDIA ION.
Optimus is on a roll.

This post is an introduction to a series of reports on computer scientists and other researchers who are unlocking the high-performance computing potential of parallel programming using large numbers of processor cores. But first some background on the opportunity and the challenge of parallel computing.

Some time around the middle of the last decade, the race to ever-faster computing hit the wall. Until then, designers had delivered soaring performance through three well-understood technologies: shrinking the already microscopic transistors, cramming more of them into each processor, and running them at higher speeds

The problem was that faster processor performance translated into higher power consumption and more heat, and even if you could find a way to get rid of the excess heat before the chips fried, continuation of the trend posed unacceptable economic and environmental costs.

An alternative route to faster computing had been around for some time. Instead of driving the processors harder, use more of them.  Mainframe computers and servers had long used multiple processors to handle heavy loads, but advances in chip technology made it possible to combine multiple processors on a single chip, an approach that is both more efficient and much cheaper. Today, high-performance computing is a story of dividing computational workloads over multiple processor cores. In the case of personal computers, this means both a handful of cores in the CPU and dozens, sometimes hundreds of cores in the graphics processing unit (GPU).

We’re bringing you another behind the scenes look here at NVIDIA. This week we met with David Ragones, director of product marketing, to talk about the next-generation NVIDIA ION GPU that launched at CeBit on March 2. The new ION GPU vastly outperforms basic netbook graphics* by delivering rich HD media in games, movies, and Internet-based video.

*-Tested with 3D Mark 06 using a Next-generation NVIDIA ION GPU, Atom N450 CPU, and 1GB DDR2 memory versus Intel GMA 3150 graphics with an Atom N450 and 1GB DDR2 memory.

It’s cool when new technologies from two different companies, work perfectly together. In fact, when it happens the engineer inside of me sort of, well, geeks out.

The first technology, NVIDIA Optimus, automatically optimizes your notebook for great performance and great battery life. You can read more about it here: www.nvidia.com/optimus

The second technology comes from Intel. As you may know, Intel launched their WiDi technology at CES this year – WiDi displays your laptop screen on your TV wirelessly through an adapter connected to your TV so you can share movies and photos on the big screen.

An Intel WiDi notebook includes a Core i Family CPU with Intel Integrated Graphics, an Intel WiDi Adapter, and Intel WiDi software. You can read more about it here: www.intel.com/go/wirelessdisplay

The way Optimus works with Intel WiDi is pretty impressive--meaning there is no additional hardware or software changes required. A notebook manufacturer simply needs to build a notebook that meets the Intel WiDi design requirements, and the NVIDIA Optimus design requirements, and it just works.

Other engineers reading this will know that getting two new technologies to work together usually requires patches or hardware changes. But the unique architecture of Optimus enables it to work perfectly with Intel WiDi. Actually, NVIDIA Optimus technology is the only discrete GPU solution that does work with Intel WiDi.

When you have an extra 5 minutes, check out the YouTube video below. It shows 7 examples of real-world people using CUDA on NVIDIA Tesla, Quadro and GeForce GPUs. Each person leverages GPU computing to accomplish something in a new and inspired way, whether it’s a tool for law enforcement or a process for analyzing electromagnetic interference.

Segments:

• 0:00 – 0:38: Siemens Medical (Roee Lazebnik) – CUDA, Quadro, 3D Vision
• 0:39 – 1:19: Kaspersky Lab (Roel Schouwenberg) – CUDA, Tesla
• 1:20 – 1:42: Muvee (Elvin Low) – CUDA, GeForce
• 1:43 – 2:30: CyberLink (Tom Vaughan) – CUDA, GeForce, 3D Vision
• 2:31 – 3:20: Agilent (Amolak Badesha) – CUDA, Quadro, 3D Vision
• 3:21 – 4:13: Adobe (Karl Soulé) – CUDA, Quadro, GeForce
• 4:14 – 5:12: MotionDSP (Mike Sonders) – CUDA, GeForce