With the Radeon Instinct line, AMD joins Nvidia and Intel in the race to put its chips into AI applications--specifically, machine learning for everything from self-driving cars to art. The company plans to launch three products under the new brand in 2017, which include chips from all three of its GPU families. The passively cooled Radeon Instinct MI6 will be based on the company's Polaris architecture. It will offer 5.7 teraflops of performance and 224GBps of memory bandwidth, and will consume up to 150 watts of power. The small-form-factor, Fiji-based Radeon Instinct MI8 will provide 8.2 teraflops of performance and 512GBps of memory bandwidth, and will consume up to 175 watts of power.
Japan plans to build a super-efficient computer that could vault it to the top of the world's supercomputer rankings by the end of next year. With a processing capacity of 130 petaflops, the planned computer would outperform the current world leader, China's Sunway TaihuLight, which delivers 93 petaflops. One petaflop is one million billion floating-point operations per second. Japan's National Institute of Advanced Industrial Science and Technology (AIST) isn't just aiming to build the world's fastest supercomputers, it also wants to make one of the most efficient. It is aiming for a power consumption of under 3 megawatts -- a staggering figure, given that Japan's current highest entry in the Top500 supercomputer list, Oakforest-PACS, delivers one-tenth the performance (13.6 petaflops) for the same power.
The next version of Microsoft's SQL Server relational database management system is now available, and along with it comes a special offer designed specifically to woo Oracle customers. Until the end of this month, Oracle users can migrate their databases to SQL Server 2016 and receive the necessary licenses for free with a subscription to Microsoft's Software Assurance maintenance program. Microsoft announced the June 1 release date for SQL Server 2016 early last month. Among the more notable enhancements it brings are updateable, in-memory column stores and advanced analytics. As a result, applications can now deploy sophisticated analytics and machine learning models within the database at performance levels as much as 100 times faster than what they'd be outside it, Microsoft said.
Forget the CPU, GPU, and FPGA, Google says its Tensor Processing Unit, or TPU, advances machine learning capability by a factor of three generations. "TPUs deliver an order of magnitude higher performance per watt than all commercially available GPUs and FPGA," said Google CEO Sundar Pichai during the company's I/O developer conference on Wednesday. "We've been running TPUs inside our data centers for more than a year, and have found them to deliver an order of magnitude better-optimized performance per watt for machine learning. SGI had a commercial product called the Tensor Processing Unit in its workstations in the early 2000s that appears to have been a Digital Signal Processor, or DSP.
In all, I'd call the Lenovo ThinkPad X1 Tablet a perfectly competent Windows 10 tablet, whose 1.1GHz Core m5-6y57 processor and 8GB of memory can chew through average office tasks with aplomb. Unlike Microsoft's Surface series, the keyboard is included in the price of the ThinkPad X1 Tablet: 1,349 for our review unit. The modules all fit between the tablet and the keyboard: There's the 150 Productivity module, which combines an additional 24Whr battery, USB 3.0 connector, HDMI, and OneLink connection; the 280 Presenter module, which adds a pico projector for presentations, HDMI, and a 10Whr battery; and the 220 3D Imaging module, which adds an Intel RealSense depth camera, HDMI, and a USB 3.0 port. The ThinkPad X1 Tablet's chip runs at the same 1.1GHz core clock speed as the chip in the competing HP Elite x2.
Hamill is part of an all-star cast that spent time with game designer Chris Roberts (creator of Wing Commander) to bring full performance-capture acting to the characters in Squadron 42. The upcoming PC action game is part of the massive crowdfunded Star Citizen universe. Performance-capture acting involves three cameras on the face, 50 cameras capturing body movements, and a whole lot of sensors. If it wasn't fun to work with a guy who's playing the player, it could make this job kind of a chore rather than a delight, and luckily for us it was just great fun to do.
The DGX-1 supercomputer can deliver the computing power of 250 two-socket servers in a desktop box, claimed Nvidia, which introduced the system Tuesday at its GPU Technology Conference in San Jose, California. The computer can deliver about 170 teraflops of performance, and multiple boxes on a rack could deliver 2 petaflops of performance. Nvidia says DGX-1 is about 56 times faster than a server with two Intel Xeon-E5 2697 v3 chips, which can deliver about 3 teraflops of performance. It also has HBM2 (High-Bandwidth Memory 2) memory, which is made using FinFET technology, in which memory chips are stacked on top of each other.