All posts tagged: Supercomputing

NVIDIA Releases New Mini Developer Kit for Generative AI

NVIDIA Releases New Mini Developer Kit for Generative AI

Published by Webster

NVIDIA has introduced a new at-home supercomputer just in time for the holidays. The tech giant unveiled its new Jetson Orin Nano Super Developer Kit, a powerful new platform that delivers generative AI 70% faster than its predecessor. The compact supercomputer offers cutting-edge features and enhanced computing power for developers and hobbyists looking to train and refine generative AI tools, agents, and robots. Owners of the Jetson Orin NX and Orin Nano can also achieve higher performance with a new software upgrade. The Jetson Orin Nano Super Developer Kit currently costs $249. The NVIDIA Jetson Orin Nano Super Developer Kit comes as new hardware, or developers can download a software update to make their existing kit “super.” Image: NVIDIA What can the NVIDIA Jetson Orin Nano Super Developer Kit do? According to NVIDIA, the new developer kit: Packages a Jetson Orin Nano 8GB system-on-module (SoM) and a reference carrier board. Comprises an NVIDIA Ampere architecture GPU with tensor cores and a 6-core Arm CPU. Performs at 67 INT8 TOPS (total operations per second), a 70% …

NVIDIA Unveils AI & Supercomputing Advances at SC 2024

NVIDIA Unveils AI & Supercomputing Advances at SC 2024

Published by Webster

NVIDIA revealed various infrastructure, hardware, and resources for scientific research and enterprise at the International Conference for High Performance Computing, Networking, Storage, and Analysis, held Nov. 17 to Nov. 22 in Atlanta. Key among these announcements was the upcoming general availability of the H200 NVL AI accelerator. The newest Hopper chip is coming in December NVIDIA announced at a media briefing on Nov. 14 that platforms built with the H200 NVL PCIe GPU will be available in December 2024. Enterprise customers can refer to an Enterprise Reference Architecture for the H200 NVL. Purchasing the new GPU at an enterprise scale will come with a five-year subscription for the NVIDIA AI Enterprise service. Dion Harris, NVIDIA’s director of accelerated computing, said at the briefing that the H200 NVL is ideal for data centers with lower power — under 20kW — and air-cooled accelerator rack designs. The H200 NVL is targeted toward low-power HPC and AI workloads. Image: NVIDIA “Companies can fine-tune LLMs within a few hours” with the upcoming GPU, Harris said. H200 NVL shows a …

iQOO 13 Tipped to Get New Heat Dissipation System, Supercomputing Chip Q2

Published by Webster

iQOO 13 is expected to launch soon with the Snapdragon 8 Gen 4 chipset. The Vivo sub-brand is yet to announce a launch date but details about the handset are appearing on the Web. A new leak coming out of China suggests that the upcoming handset will get a new chip and heat dissipation system with a single-layer motherboard. The initial launch of the iQOO 13 could take place in China in November and it is expected to launch in India in early December. The iQOO 13 is likely to draw power from a 6,150mAh battery. A Weibo user familiar with the matter claims that the iQOO 13 will come with a new heat dissipation architecture with a single-layer motherboard for thermal management. The handset is said to boast a new VC heat sink as well (machine translated from Chinese). The same user in a separate post states that iQOO 13 will feature the company’s self-developed Q2 chip for gaming. Last year’s iQOO 12 and iQOO Neo 9 series pack Supercomputing Chip Q1 and are advertised to enable …

Microsoft hires former Meta exec to bolster AI supercomputing team

Published by Webster

Former Meta executive Jason Taylor is joining Microsoft’s AI supercomputing team. In a LinkedIn post on Monday, Microsoft CTO Kevin Scott says Taylor will take on the role of corporate vice president and deputy CTO to help “build the next set of systems that will push the frontier of AI forward.” Taylor worked at Meta from 2009 to 2022, where he most recently served as the company’s vice president of infrastructure. He handled AI, data, and privacy infrastructure, as well as managing the company’s server budgets, according to his LinkedIn profile. Taylor was also the chair of the Open Compute Project Foundation from 2015 to 2017, an organization that promotes open-source designs in data centers. Microsoft and OpenAI need more robust hardware to keep up with rapidly advancing AI systems. Last month, a report from The Information suggested Microsoft and OpenAI wanted to build a $100 billion supercomputer, dubbed “Stargate,” to power OpenAI’s models. (However, Microsoft’s Scott seems to push back on these rumors in his post on LinkedIn today, saying that most of the …

iQoo Neo 9 Pro Teased to Come With Q1 Supercomputing Chip; RAM, Storage Options Confirmed

Published by Webster

iQoo Neo 9 Pro with Snapdragon 8 Gen 2 SoC is all set to hit the Indian market on February 22. As we wait for the official announcement, the Vivo sub-brand has revealed more specifications about the Indian variant of the h andset. It is confirmed to come in 8GB and 12GB RAM options. The gaming-focused smartphone is teased to include a Q1 chip and a 50-megapixel dual rear camera unit. The handset will go on sale via Amazon in the country.The iQoo Neo 9 Pro was launched in China in December last year. The Chinese variant of the iQoo Neo 9 Pro runs on a MediaTek Dimensity chipset.  The latest teaser of the iQoo Neo 9 Pro has revealed that the smartphone will be available in 8GB RAM + 256GB and 12GB RAM + 256GB storage options. It is confirmed to include the company’s inbuilt Supercomputing chip Q1 that is claimed to provide 144 frames per second (fps) and up to 900 pixel resolution for gaming. The handset will support MEMC (Motion Estimation Motion …