Items tagged with tesla p100

Google has been promising to upgrade its cloud platform with NVIDIA Tesla P100 GPUs, and now it has gone and done it. The upgraded hardware is available to customers in beta form, while NVIDIA's K80 GPUs are now generally available to customers. Google also announced the introduction of sustained use discounts (automatic discounts for running a VM instance for a significant portion of the month) on both the K80 and P100 GPUs. NVIDIA's P100 GPUs are based on the company's Pascal architecture, the same as found in GeForce GTX 10 series of consumer graphics cards. Google's pitch is that the switch... Read more...
NVIDIA is flexing its GPU muscle in the artificial intelligence and deep learning market thanks to a partnership with Chinese search giant Baidu. You can think of Baidu as the Chinese equivalent to Google’s dominance of the U.S. search and internet advertising market. Thanks to the partnership, NVIDIA is hoping to spread its hardware in three key areas. First off, NVIDIA’s next generation Volta-based GPU architecture to provide a robust deep learning platform for the Baidu Cloud. Used in combination with the its PaddlePaddle deep learning framework, Baidu will make use of Tesla Volta V100 and Tesla... Read more...
It takes some serious hardware to do the things that Facebook is able to do. In an effort to stay ahead of the technological curve, the social networking site announced today at the 2017 Open Compute Project (OCP) summit in Santa Clara a next-generation GPU server called Big Basin. It's the successor to the Big Sur GPU server announced in 2015 and it will help Facebook to continue leveraging artificial intelligence to power service like speech and text translations, photo classifiers, and real-time video classification. Big Basin was built in collaboration with Quanta Clout Technology (QCT), Facebook's... Read more...
Remember that scene when Al Pacino playing the part of Scarface famously said, "Say hello to my little friend!"? Well now NVIDIA is bringing out the big gun in PCI Express form in what it considers the "most advanced data center GPU ever built," the Tesla P100, a crazy fast GPU accelerator based on NVIDIA's powerful Pascal architecture built on a 16nm FinFET manufacturing process. This is the second iteration of the Tesla P100, the first of which NVIDIA unveiled during GTX 2016 a couple of months ago. Though it's built on a fancy 16nm FinFET process, the GP100 GPU inside the Tesla P100 is quite... Read more...
NVIDIA just pulled the wraps off its fastest GPU and compute engine yet: the Tesla P100. This new GPU powerhouse is based on NVIDIA’s next generation Pascal architecture, which means that it’s built on a 16nm FinFET process. But even with thoroughly modern FinFET process tech, the Tesla P100’s die size measures 600mm2 due in part to the 15.3 billion transistors that comprise the new compute engine — nearly twice that of Maxwell, for reference. The specifications of the Tesla P100 are second to none, as double-precision performance is rated at 5.3 teraflops (TFLOPs), while single-precision performance... Read more...