After sourcing its GPUs from Imagination Technologies for years, Apple has decided to design its own GPU technology. With half of its revenue from Apple, Imagination Technologies stock has tanked as a result. GPUs, graphics processing units, are the workhorses for just about everything that Apple wants its smartphones and other devices to do, including machine learning, augmented reality and virtual reality, Siri and high resolution gaming. The GPU gets its power from its ability to multitask, processing in parallel. Continue reading Apple to Design its Own GPUs and Leave Long-Time Supplier

Moore’s Law, which states that the number of transistors in a chip doubles approximately every two years, is sputtering to an end. As a result, an increasing number of companies are relying on specialized computing, which transforms software tasks into silicon chips rather than relying on CPUs. This key technology is behind two recent developments: Intel’s acquisition of Israeli startup Mobileye, which produces chips and software for autonomous vehicles, and Nvidia’s latest iteration of a system to speed up machine learning. Continue reading The Rise of Specialized Computing and New Era of Chip Design

Nvidia unveiled its Jetson TX2 platform, designed for devices that have limited bandwidth like drones, traffic cameras, and manufacturing robots. Some of these devices, such as a camera drone, may capture large amounts of data without working in the cloud or a connected data center. Subsequently, these devices have to do most of the processing themselves and Jetson 3.0 promises to make them more powerful. The TX2 chip, which provides twice the performance of the TX1 while using only half the energy, is designed for artificial intelligence at the edge of a network. Continue reading Nvidia’s Jetson TX2 Powers Devices with Artificial Intelligence

Facebook unveiled new hardware for use in its data centers, designs for which will be made available to outside companies through its Open Compute Project. The announcements were made during this week’s OCP U.S. Summit in Santa Clara. One announcement centered on a new GPU server designed to better serve the company’s AI initiatives. Big Basin — successor to the company’s Big Sur high-performance compute platform — will help Facebook train machine learning models that are 30 percent larger than those running on current servers. Continue reading Facebook Introduces New Hardware for Use in Data Centers

At CES 2017, Scalable Graphics, which specializes in GPU-accelerated cloud computing, is set to introduce a wireless PC solution for virtual reality that is compatible with Oculus Rift and HTC Vive headsets. The company’s one-pound KwikVR is a wireless compression and transmission system that cuts the cord between the VR headset and the computer powering it. Wireless VR and other hardware upgrades or peripherals that make VR experiences better are likely to be trends at CES 2017. Continue reading Scalable Graphics to Feature Wireless KwikVR System at CES

Apple’s laptops may not have the power to run many virtual reality experiences, but an upcoming Kickstarter campaign aims to change that. The Wolfe offers an external Thunderbolt-connected GPU as a simple solution for supercharging laptops. According to its creators, The Wolfe increases the MacBook Pro’s GPU processing capabilities up to ten times. The form factor is a tidy, largish box housing an Nvidia GPU that is currently the baseline for the Oculus Rift and HTC Vive. Early Kickstarter backers will get one for $399. Continue reading The Wolfe Aims to Turn MacBooks into Virtual Reality Players

Nvidia introduced Titan X, a new chip that is a successor to a current chip with the same name, targeted at the high-end gaming and artificial intelligence communities. Priced at $1,200 and available beginning August 2, the new Pascal-based Titan X chip offers 12 billion transistors, compared to seven billion on a high-end Intel chip. The new Titan X will be available as an add-on card for PCs. Nvidia’s closest competitor, Advanced Micro Devices (AMD) offers a similar chip for PCs and game consoles. Continue reading Nvidia Rolls Out Titan X Chip for Games, Artificial Intelligence

Google has just built its own chip as part of its efforts to speed up artificial intelligence developments. The company revealed that this is just the first of many chips it plans to develop and build. At the same time, an increasing number of businesses are migrating to the cloud, lessening the need for servers that rely on chips to function. That’s led some to believe that Google and other Internet titans that follow its lead will impact the future of the chip industry, particularly such stalwarts as Intel and Nvidia. Continue reading Google Develops its Own Chip to Speed Up Machine Learning

Nvidia CEO Jen-Hsun Huang debuted the much-anticipated GeForce GTX 1080 gaming GPU, the first based on the new Pascal architecture, promising dramatic improvements in performance, memory and power efficiency. Huang told the crowd at DreamHack in Austin, Texas that the new GPU delivers twice the performance and three times the efficiency of Titan X. For a sense of Pascal’s capabilities for gaming and virtual reality, attendees were treated to demos involving next generation character models, the Ansel game capture tool and the compelling “VR Funhouse” experience. Continue reading Nvidia Unveils GeForce GTX 1080 Advanced Graphics Card

During the Nvidia keynote at CES 2016, CEO and co-founder Jen-Hsun Huang introduced a new computer for autonomous vehicles called the Drive PX2. Following last year’s Drive CX, the PX2 touts processing power equivalent to 150 MacBook Pros, according to Huang. The lunchbox-sized, water-cooled computer features 12 CPU cores that support eight teraflops and 24 “deep learning” tera operations per second. As a result, the PX2 can reportedly process data in real time from 12 video cameras, radar, lidar and additional sensors to enhance the self-driving car experience. Continue reading CES: Nvidia Unveils New ‘Supercomputer’ for Self-Driving Cars

When Tesla released all of its patents to the public in 2014, it jumpstarted the electric car ecosystem while continuing to succeed. Facebook made its data-center architecture available to the masses, still making a tidy $12+ billion in revenue last year. Open source code is now fueling tremendous innovation and digital capabilities. Whereas companies in the past dominated by using licensed software to create monopolies, today’s companies relying on open source code differentiate themselves by the services they offer. Continue reading Open Source Speeds Developments in Artificial Intelligence

DesignWorks, Nvidia’s newly announced suite of software tools, technologies, and libraries for designers enables “photoreal rendering for unparalleled accuracy, easy transfer of materials and digital models between applications, and the ability to incorporate virtual reality into design software,” the company said in a press announcement. Alongside the launch of DesignWorks, Nvidia also announced two new professional GPUs: the Quadro M5000 and Quadro M4000, based on Nvidia’s Maxwell GPU architecture. Continue reading Nvidia Launches DesignWorks Software Suite for Designers

Qualcomm announced that its Snapdragon 810 CPU and Adreno 430 GPU will power Google’s next generation Project Tango smartphone, coming out in the third quarter of 2015. The new phone promises to offer the same capabilities of the Nvidia-powered Project Tango tablet, but in a smaller form factor. “We’re excited to work together with Google and Android developers to help deliver new, innovative visual experiences using depth-sensing technology on mobile devices,” said Raj Talluri, SVP of product management, Qualcomm. Continue reading Qualcomm Tech to Power Next-Gen Project Tango Smartphone

Oculus is getting ready for the release of its long-awaited Oculus Rift VR headset with recommendations for PC specs and a special event on June 11. The company recommends a powerful GPU to handle rendering. The Rift will initially require a desktop PC running Windows 7 SP1 or newer, 2 USB 3.0 ports, and HDMI 1.3 video output supporting a 297MHz clock through a direct output architecture. Meanwhile, Oculus has halted work on Mac and Linux support while it readies the PC software for launch. Continue reading Oculus Reveals PC Specs for Upcoming Launch of Rift Headset

The latest trend in artificial intelligence involves implementing a much more efficient microprocessor rather than a whole cloud computing system to power deep learning research. These microprocessors, or graphical processing units (GPUs), are great at math-crunching skills, which makes them ideal for deep learning networks. Now, companies such as Google, Facebook, and various labs that run supercomputers, are using GPU-based computers to power their AI and deep learning operations. Continue reading AI: GPU-Based Computing is Proving Ideal for Deep Learning