What NVIDIA and Industrial Light & Magic had to offer this week on stage at GTC was more than just a couple of videos. Cofer broke down his situation like so: “all of my data is localized at ILM, a lot of my work is presentation, and I need to go to LA and show some film. Now, I need to break everything down, but I don’t have access to how it was made.” He continued that because he needed more often to not to simply show work, not necessarily to work with the video itself, he needed a next-generation solution.

Popping out a MacBook Air, Cofer clicked to get to his simple workstation desktop. From there, he noted, he could “show you a live scene running Maya from ILM’s offices in the Presidio.” Cofer noted that “over the course of the year we [ILM] had five weeks and 500 shots left – a hundred shots a week.” Working with a virtual desktop on the MacBook and NVIDIA Kepler architecture, sculpting these scenes from anywhere on the planet virtually.

Pulling up an application called Nuke next, Cofer showed a running scene from Battleship with “shredders” flying through the air towards a ship in the sea. Cofer demonstrates that he’s able to remotely access the data which allows him to adjust the film that can move the shredder devices through the air in near real time, “accessing terabytes of information remotely.”

Finally, Cofer shows of a display of 100 screens showing streaming video at once, one one workstation. This power of virtualization is made possible with NVIDIA’s Kepler architecture and is made real with technology that is live today. Check out the rest of our NVIDIA coverage from this week through the timeline below and let us know what you’re looking forward to in the world of graphics processing now!

Also take a look at NVIDIA’s live stream of this event where we’ve picked up a couple of images that you see here in this post – thanks NVIDIA!

This new technology deployed on Kepler, noted Huang, was super energy efficient, this allowing for deployment on a massive scale. This architecture allows for every command buffer to be virtualized, NVIDIA now able to have one GPU shared with “countless users” as each virtual machine can be discerned from the next, each of them sending graphics commands individually. Machines can now have streams sent to them completely virtually with Kepler architecture, this allowing for a BYOD environment.

Bring Your Own Device is the new key here with NVIDIA, with one limitation currently being that in the past we’ve needed to integrate into one network which has tended thus far to be working with Windows. NVIDIA’s solution to this limitation problem has your GPU virtualized entirely, adding Kepler and newly developed GPU-aware hypervisor software (aka a virtual machine manager), with each machine then having a GPU to itself. NVIDIA is teaming up with Citrix to make this a reality.

Huang invited Sumit Dhawan, Group VP & General Manager at Citrix Systems to the stage to discuss the future of virtualization. Together Dhawan and Huang headed to stage left where an iPad was connected with Citrix Receiver, an app which here allows a massive 1,000 CUDA cores to be shown on the tablet at once – all of them virtualized.

UPDATE: Video provided by NVIDIA!

The cores aren’t actually running on the iPad, instead running on a remote server powered by NVIDIA VGX technology. Stay tuned for the rest of the big bang NVIDIA is releasing today at GTC and check out the timeline below to see what we’ve seen thus far – NVIDIA GPUs blowing up all week!

Thanks to NVIDIA for the awesome photographs snapped right up front at the GPU conference live! You can check out their in-house live stream at NVIDIA Blogs now!

Intel CEO Paul Otellini boasted that the company is able to push out new chip fabrication processes faster than any of its competitors thanks to its $2 billion a year investment in research and development and its employment of 1,900 PhD graduates. Intel has already begun building sites for its next-gen 14nm process in three locations and expects the new chips to arrive on time for next year.

Otellini also revealed that Intel plans to really focus on mobile chips, where the market is dominated by ARM. Intel is currently shipping 32nm mobile chips and expects to shrink down to 22nm by next year and then 14nm thereafter. The goal is to not only play catchup with its mobile chips, but to make them the company’s leading edge in processes within three years.

[via PC Pro]

The P8Z77-V Deluxe is also “easily exceeding” 3 GHz memory frequencies with all four DIMMS populated, according to Asus. “The milestone also establishes that channel boards from ASUS are capable of very impressive overclocking feats thanks to their class leading Digi+ VRM power and control design,” the company bragged. As for the world records, they are as follows:

- AquaMark 3: 536638 marks using a Radeon™ HD 7970 graphics card clocked at 1600MHz core and 1900MHz GDDR5
- PiFast: 10.3 seconds with Intel® Core™ i7-3770K set to 6930MHz
- 3DMark®2001 SE: 164589 marks using a GeForce® GTX 580 clocked at 1553MHz core and 1250MHz GDDR5
- SuperPi: 5 seconds 187ms with Intel® Core™ i7-3770K set to 6961MHz
- SuperPi 32M: 4 minutes 52 seconds and 953ms with Intel® Core™ i7 set to 6735MHz

There is some good news, though, in that the mobile processors will be released at the same time as their desktop counterparts. It had been believed that the mobile side of things wouldn’t be available until at least June. The Ivy Bridge processors will be announced within a week of that April 29 launch date. Benchmarks and reviews are expected to go live on that same day.

More specifically, the following are the ones expected to be announced in the final week of April: mobile Core i7 and Core i7 Extreme families, desktop Core i7, Core i5-3570K, i5-3570T, i5-3550, i5-3550S, i5-3450 and i5-3450S. Prices will range from $184 for the i5-3450 to $1,096 for the i7-3920XM. Future processors will then be introduced later, in June, with Core i3 units due out in the third quarter of the year.

[via CPU-World]

No specific products have been mentioned, but the companies note that that they share a vision of creating “intelligent and practical robots capable of enhancing people’s lives”. iRobot has the history of working in the field or robotics, while TI’s OMAP chip will be leveraged thanks to its multi-core processing capabilities, as well as low power requirements.

iRobot are best known for the Roomba, the circular cleaning robot that will buzz, click, and whirr its way across your floor in the hope of leaving it sparklingly clean. The Roomba isn’t the only area the company where they apply robotics, though, supplying more than 4,500 government and industrial robots designed to undertake dangerous tasks, such as bomb disposals.

It’s unclear exactly which version of OMAP iRobot will be utilizing, although Texas Instruments have been keen to show off their OMAP 5 platform lately. It brings a new dual-core Cortex A15 processor, as well as two additional Cortex M4 cores, reportedly outstripping quad-core A9 chips in terms of performance. OMAP 5 is also able to handle four video feeds at a time, as well as having improved photo processing capabilities – the video features could be beneficial to robot applications that need realtime feeds, for example.

Tim Cook immediately went into talking about the NVIDIA Tegra 3 quad-core processor in all those Android tablets when talking about their own new A5X. After confirming the processor under the hood he revealed that the X stands for quad-core graphics. Graphics that are capable of around 4x the performance of the Tegra 3.

Apple A5 was already twice as fast, this is a graphics powerhouse”

The graph above makes the Tegra 3 seem tiny in comparison. If that turns out to be completely accurate the Android tablet and gaming market will have some catching up to do. We have a feeling we’ll be testing this very soon. His comments regarding the original A5 being twice as fast might not be completely true and when we compared the iPad 2 vs the quad-core Transformer Prime we didn’t find the same results. Hit the links below for our gaming and benchmark comparisons of the previous generation iPad.

Either way the iPad 2 was already fast, smooth, and extremely capable. Adding more power to the graphics side will only open things up more and offer more games with even better performance than before. iPad has grown up as a device from media consumption to a production machine! Who wants one? Get all of the news, details, and pricing from our Apple Hub!

Featuring Intel’s Sandy Bridge-E architecture, the Xeon E5-2600 family can handle a full eight cores per processor and as much as 768GB of system memory. The additional cores along with a smaller 32nm architecture, as opposed to 45nm, will make the processor 80 percent faster and 50 percent more efficient. It will also be the first server processor family to integrate PCI Express 3.0 support and I/O controller directly into the microprocessor.

Intel aims to address the growing server needs of a more connected world, forecasting at least 3 billion connected users with 15 billion connected devices by 2015. The new server chips have already begun shipping to manufacturers, including HP, Dell, IBM, Oracle, and Cisco, which are all expected to announce Xeon-based server platforms today.

Rival AMD recently acquired startup SeaMicro for $334 million to enter this same enterprise server market aimed at cloud computing. The move was seen as a blow to Intel, which had appeared to have formed a tight relationship with SeaMicro. However, VP and general manager of Intel’s Datacenter and Connected Systems Group, Diane Bryant, dismissed that notion today, saying that Intel was “not impressed” with SeaMicro and had declined to purchase the company.

[via ZDNet]

We’ve also got word that MasterImage is here at the conference with their technology on display as well, so you can fully expect we’ll be jumping in on that action soon as well. For now though, you’ve got this fabulous video from Qualcomm. Watch as the MSM8960 is shown off with full 3D action, both capturing and displaying, in what Qualcomm is calling the next generation of said technology. Can the chipmaking group convince us that glasses-free 3D is a viable technology for future generations?

We’ll be continuing to knock out information on Qualcomm with their upcoming S4 quad-core processor all this week and beyond, this week of course being Mobile World Congress 2012 in Barcelona. Have a peek at our [MWC 2012 portal] for all the MWC action as we capture it, and see our [Snapdragon portal] for information on that processor line specifically. Of course also have a peek at the [Qualcomm portal] for the full Qualcomm line of hardware and software-related solutions. Stay tuned!

At this pace, Intel is moving faster than Moore’s Law, according to which the number of transistors that can fit into an integrated circuit doubles about every two years. At the same time, the chips will either have the same performance but half the size or have the same size but double the performance. With 14nm, Intel is getting very close to reaching the theoretical limit of silicon, which is around 9nm to 11nm. However, the company has mentioned before that it expects to eventually jump to 8nm by 2015.

Intel believes that the mobile market moves at a far faster pace than desktops and hence the company will be going be shrinking down the slicon aggressively. One major reason Intel will be able to go at such a rapid pace is its adoption of FinFETs next year, which will allow a single transistor to act as a multi-gate device. In this way, one transistor can perform much more calculations than in a traditional system and hence reduce the number of electrodes and consequently the size of chips. Furthermore, Otellini affirmed that Intel had plenty of manufacturing capacity for both PC and non-PC devices.

[via TheVerge]

Intel’s Ivy Bridge chips are the successors to its current Sandy Bridge family and is built on a more advanced 22nm process with new 3D Tri-Gate transistors. The next-gen architecture promises up to 37 percent faster performance along with a 50 percent reduction in power consumption.

Previously leaked roadmaps pegged the new Ivy Bridge chips to begin shipments in the March and April time frame, but that has now been pushed back. “I think maybe it’s June now,” said Maloney in response to inquiries about the Ivy Bridge delay.

Maloney explained that the delay was due to issues with the manufacturing process of the smaller chips and not due to a lack of demand. Although Ivy Bridge likely won’t ship until June, the time frame will still meet Intel’s original goal of releasing the chips within the second quarter.

What tipped off the possibility of both processors being developed is Apple’s iOS device processor-naming scheme and the appearance of two new processor model names deep in the code of iOS 5.1 beta. The original iPad had used an A4 chip, which had the model number S5L8930X, while the iPad 2′s A5 chip had the model number SL8940X, a full 10-point step up. The reported A5X chip has a model number of S5L8945, indicating a half-step up. But what has been found in iOS 5.1 code includes a new mystery S5L8950X processor, suggesting a full step up to an A6 processor.

As to why Apple would develop two next-gen processors is unclear, but speculation points to a few possible explanations. Apple could have developed both chips together to see which would be better fit for the new iPad. It could also be developing the quad-core A6 for the iPad 3, while preparing the A5X for the next-gen iPhone, a rumored Apple TV update, or another iOS device. Still, there’s the possibility that the A5X will be for a cheaper iPad tablet or a smaller 8-inch iPad tablet.