The spirit of software pioneer Grace Hopper will live on at NVIDIA GTC. Accelerated systems using powerful processors - named in honor of the pioneer of software programming - will be on display at the global AI conference running March 18-21, ready to take computing to the next level. System makers will show more than 500 servers in multiple configurations across 18 racks, all packing NVIDIA GH200 Grace Hopper Superchips. They'll form the largest display at NVIDIA's booth in the San Jose Convention Center, filling the MGX Pavilion.

MGX Speeds Time to Market
NVIDIA MGX is a blueprint for building accelerated servers with any combination of GPUs, CPUs and data processing units (DPUs) for a wide range of AI, high performance computing and NVIDIA Omniverse applications. It's a modular reference architecture for use across multiple product generations and workloads. GTC attendees can get an up-close look at MGX models tailored for enterprise, cloud and telco-edge uses, such as generative AI inference, recommenders and data analytics. The pavilion will showcase accelerated systems packing single and dual GH200 Superchips in 1U and 2U chassis, linked via NVIDIA BlueField-3 DPUs and NVIDIA Quantum-2 400 Gb/s InfiniBand networks over LinkX cables and transceivers. The systems support industry standards for 19- and 21-inch rack enclosures, and many provide E1.S bays for nonvolatile storage.

GIGABYTE Technology, an industry leader in high-performance servers and workstations, today announced participation in the global AI conference, NVIDIA GTC, and will share an AI session and other resources to educate attendees. Additionally, with the release of the NVIDIA L4 Tensor Core GPU, GIGABYTE has already begun qualifying its G-series servers to support it with validation. Last, as the NVIDIA OVX architecture has reached a new milestone, GIGABYTE has begun production of purpose-built GIGABYTE servers based on the OVX 3.0 architecture to handle the performance and scale needed for real-time, physically accurate simulations, expansive 3D worlds, and complex digital twins.

NVIDIA Session (S52463) "Protect and Optimize AI Models on Development Platform"
GTC is a great opportunity for researchers and industries to share what they have learned in AI to help further discoveries. This time around, GIGABYTE has a talk by one of MyelinTek's senior engineers that is responsible for the research and development of MLOps technologies. The session demonstrates an AI solution using a pipeline function to quickly retrain new AI models and encrypt them.

ASUS today announced its participation in NVIDIA GTC, a developer conference for the era of AI and the metaverse. ASUS will offer comprehensive NVIDIA-certified server solutions that support the latest NVIDIA L4 Tensor Core GPU—which accelerates real-time video AI and generative AI—as well as the NVIDIA BlueField -3 DPU, igniting unprecedented innovation for supercomputing infrastructure. ASUS will also launch the new ProArt Studiobook Pro 16 OLED laptop with the NVIDIA RTX 3000 Ada Generation Laptop GPU for mobile creative professionals.

Purpose-built GPU servers for generative AI
Generative AI applications enable businesses to develop better products and services, and deliver original content tailored to the unique needs of customers and audiences. ASUS ESC8000 and ESC4000 are fully certified NVIDIA servers that support up to eight NVIDIA L4 Tensor Core GPUs, which deliver universal acceleration and energy efficiency for AI with up to 2.7X more generative AI performance than the previous GPU generation. ASUS ESC and RS series servers are engineered for HPC workloads, with support for the NVIDIA Bluefield-3 DPU to transform data center infrastructure, as well as NVIDIA AI Enterprise applications for streamlined AI workflows and deployment.

Mitsui & Co., Ltd., one of Japan's largest business conglomerates, is collaborating with NVIDIA on Tokyo-1—an initiative to supercharge the nation's pharmaceutical leaders with technology, including high-resolution molecular dynamics simulations and generative AI models for drug discovery.

Announced today at the NVIDIA GTC global AI conference, the Tokyo-1 project features an NVIDIA DGX AI supercomputer that will be accessible to Japan's pharma companies and startups. The effort is poised to accelerate Japan's $100 billion pharma industry, the world's third largest following the U.S. and China.

Microsoft, Tencent and Baidu are adopting NVIDIA CV-CUDA for computer vision AI. NVIDIA CEO Jensen Huang highlighted work in content understanding, visual search and deep learning Tuesday as he announced the beta release for NVIDIA's CV-CUDA—an open-source, GPU-accelerated library for computer vision at cloud scale. "Eighty percent of internet traffic is video, user-generated video content is driving significant growth and consuming massive amounts of power," said Huang in his keynote at NVIDIA's GTC technology conference. "We should accelerate all video processing and reclaim the power."

CV-CUDA promises to help companies across the world build and scale end-to-end, AI-based computer vision and image processing pipelines on GPUs. The majority of internet traffic is video and image data, driving incredible scale in applications such as content creation, visual search and recommendation, and mapping. These applications use a specialized, recurring set of computer vision and image-processing algorithms to process image and video data before and after they're processed by neural networks.

It has been pretty much confirmed that the NVIDIA GeForce RTX 4070 (non-Ti) is launching in April, but now, the rumored date has been specified as April 13th. The latest report comes from a well known leaker, hongxing2020, over at Twitter, who has a pretty good track record and had correct dates for RTX 30 and RTX 40 series launch dates. In case you missed it, the NVIDIA GeForce RTX 4070 is based on the same AD104 GPU as the RTX 4070 Ti, with slightly fewer cores, but still comes with the same memory specification as the Ti version.

This means the GeForce RTX 4070 should feature 46 streaming multiprocessors (SMs) which should leave it with 5,888 CUDA cores enabled. It will come with 12 GB of GDDR6X memory on a 192-bit memory interface. The TDP is rumored at 200 W. There were some rumors that NVIDIA could have three different SKUs for the RTX 4070, with 16 GB, 12 GB, and 10 GB of VRAM, but so far, this has just remained as a vague rumor coming from Eurasian Economic Commission (EEC) regulatory filings. NVIDIA is slowly completing the RTX 40 series lineup, so hopefully we will not have to wait too long for updates on the RTX 4060 Ti and the RTX 4060. NVIDIA, and its founder and CEO, Jensen Huang, will be holding the opening keynote at GTC on March 21st, so we could get at least some updates for the future GeForce lineup.

NVIDIA today announced that company founder and CEO Jensen Huang will deliver the opening keynote at GTC 2023, covering the latest advancements in generative AI, the metaverse, large language models, robotics, cloud computing and more. More than 250,000 people are expected to register for the four-day event, which will include 650+ sessions from researchers, developers and industry leaders in virtually every computing domain. GTC will also feature a fireside chat with Huang and OpenAI co-founder Ilya Sutskever, plus talks by DeepMind's Demis Hassabis, Stability AI's Emad Mostaque and many others.

"This is the most extraordinary moment we have witnessed in the history of AI," Huang said. "New AI technologies and rapidly spreading adoption are transforming science and industry, and opening new frontiers for thousands of new companies. This will be our most important GTC yet."

During its GTC 2022 session, NVIDIA introduced its new generation of gaming graphics cards based on the novel Ada Lovelace architecture. Dubbed NVIDIA GeForce RTX 40 series, it brings various updates like more CUDA cores, a new DLSS 3 version, 4th generation Tensor cores, 3rd generation Ray Tracing cores, and much more, which you can read about here. However, today, we also got a new Ada Lovelace card intended for the data center. Called the L40, NVIDIA updated its previous Ampere-based A40 design. While the NVIDIA website provides sparse, the new L40 GPU uses 48 GB GDDR6 memory with ECC error correction. Using NVLink, you can get 96GBs of VRAM. Paired with an unknown SKU, we assume that it uses AD102 with adjusted frequencies to lower the TDP and allow for passive cooling.

NVIDIA is calling this their Omniverse GPU, as it is a part of the push to separate its GPUs used for graphics and AI/HPC models. The "L" model in the current product stack is used to accelerate graphics, with display ports installed on the GPU, while the "H" models (H100) are there to accelerate HPC/AI installments where visual elements are a secondary task. This is a further separation of the entire GPU market, where the HPC/AI SKUs get their own architecture, and GPUs for graphics processing are built on a new architecture as well. You can see the specifications provided by NVIDIA below.

ASUS, the leading IT company in server systems, server motherboards and workstations, today announced its presence at NVIDIA GTC - a developer conference for the era of AI and the metaverse. ASUS will focus on three demonstrations outlining its strategic developments in AI, including: the methodology behind ASUS MLPerf Training v2.0 results that achieved multiple breakthrough records; a success story exploring the building of an academic AI data center at King Abdullah University of Science and Technology (KAUST) in Saudi Arabia; and a research AI data center created in conjunction with the National Health Research Institute in Taiwan.

MLPerf benchmark results help advance machine-learning performance and efficiency, allowing researchers to evaluate the efficacy of AI training and inference based on specific server configurations. Since joining MLCommons in 2021, ASUS has gained multiple breakthrough records in the data center closed division across six AI-benchmark tasks in AI training and inferencing MLPerf Training v2.0. At the ASUS GTC session, senior ASUS software engineers will share the methodology for achieving these world-class results—as well as the company's efforts to deliver more efficient AI workflows through machine learning.

GTC—To power the next wave of AI data centers, NVIDIA today announced its next-generation accelerated computing platform with NVIDIA Hopper architecture, delivering an order of magnitude performance leap over its predecessor. Named for Grace Hopper, a pioneering U.S. computer scientist, the new architecture succeeds the NVIDIA Ampere architecture, launched two years ago.

The company also announced its first Hopper-based GPU, the NVIDIA H100, packed with 80 billion transistors. The world's largest and most powerful accelerator, the H100 has groundbreaking features such as a revolutionary Transformer Engine and a highly scalable NVIDIA NVLink interconnect for advancing gigantic AI language models, deep recommender systems, genomics and complex digital twins.

NVIDIA today kicked off the 2022 Graphics Technology Conference, its annual gathering of compute and gaming developers discovering the very next in AI, data-science, HPC, graphics, autonomous machines, edge computing, and networking. At the 2022 show premiering now, NVIDIA is expected to unveil its next-generation "Hopper" architecture, which could make its debut as an AI/HPC product, much like "Ampere." Stay tuned for our live blog!15:00 UTC: The show gets underway with a thank-you to the sponsors.

NVIDIA today announced that it will host its GTC 2022 conference virtually from March 21-24, with a news-filled keynote by its founder and CEO Jensen Huang and more than 900 sessions from 1,400 speakers, including some of the world's top researchers and industry leaders in AI, high performance computing and graphics. Huang's keynote will be live-streamed on Tuesday, March 22, at 8 a.m. Pacific time. This GTC will focus on accelerated computing, deep learning, data science, digital twins, networking, quantum computing and computing in the data center, cloud and edge. There will be more than 20 dedicated sessions on how AI can help visualize and further climate science.

"As one of the world's leading AI conferences, GTC provides a singular opportunity to help solve huge challenges and redefine the future for developers, researchers and decision-makers across industries, academia, business and government," said Greg Estes, vice president of Developer Programs at NVIDIA. "There's a mother lode of content and opportunities for attendees of all levels to deepen their knowledge and make new connections."

NVIDIA today announced NVIDIA Omniverse Avatar, a technology platform for generating interactive AI avatars. Omniverse Avatar connects the company's technologies in speech AI, computer vision, natural language understanding, recommendation engines and simulation technologies. Avatars created in the platform are interactive characters with ray-traced 3D graphics that can see, speak, converse on a wide range of subjects, and understand naturally spoken intent.

Omniverse Avatar opens the door to the creation of AI assistants that are easily customizable for virtually any industry. These could help with the billions of daily customer service interactions—restaurant orders, banking transactions, making personal appointments and reservations, and more—leading to greater business opportunities and improved customer satisfaction. "The dawn of intelligent virtual assistants has arrived," said Jensen Huang, founder and CEO of NVIDIA. "Omniverse Avatar combines NVIDIA's foundational graphics, simulation and AI technologies to make some of the most complex real-time applications ever created. The use cases of collaborative robots and virtual assistants are incredible and far reaching."

NVIDIA today unveiled the world's first cloud-native, multi-tenant AI supercomputer—the next-generation NVIDIA DGX SuperPOD featuring NVIDIA BlueField -2 DPUs. Fortifying the DGX SuperPOD with BlueField-2 DPUs—data processing units that offload, accelerate and isolate users' data—provides customers with secure connections to their AI infrastructure.

The company also announced NVIDIA Base Command, which enables multiple users and IT teams to securely access, share and operate their DGX SuperPOD infrastructure. Base Command coordinates AI training and operations on DGX SuperPOD infrastructure to enable the work of teams of data scientists and developers located around the globe.

Remember that time when NVIDIA CEO Jensen Huang pulled the company's HGX system (based on Ampere GA100) out of his own oven? Well, it seems we might be looking at something similar come GTC, which is set for April 12th. The event will again take place solely via online transmissions and announcements due to the still heavily-grassing COVID-19 pandemic, and NVIDIA teased a new kick-off presentation from its CEO - from his kitchen.

NVIDIA has usually taken GTC as an opportunity to showcase products not for the consumer segment, however, so temper your expectations. You should also likely temper your expectations regarding Huang taking enough RTX 30-series graphics cards form his oven to satisfy the incredible demand and stock issues we've been seeing with NVIDIA's latest and greatest. What we could be looking for (as an appetizer to this year's over 1500 presentations) are products focused on the professional computing markets, from quantum computing to AI, passing through RTX Ampere accelerators for professionals, NVIDIA Drive products, as well as Jetson announcements. NVIDIA did warn some surprises might be in store, but again, this doesn't mean these are surprises aimed at consumer gaming products. Catch up on NVIDIA's official announcement and a previously-released GTC retrospective video after the break.

NVIDIA today announced NVIDIA AI Enterprise, a comprehensive software suite of enterprise-grade AI tools and frameworks optimized, certified and supported by NVIDIA, exclusively with VMware vSphere 7 Update 2, separately announced today.

Through a first-of-its-kind industry collaboration to develop an AI-Ready Enterprise platform, NVIDIA teamed with VMware to virtualize AI workloads on VMware vSphere with NVIDIA AI Enterprise. The offering gives enterprises the software required to develop a broad range of AI solutions, such as advanced diagnostics in healthcare, smart factories for manufacturing, and fraud detection in financial services.

NVIDIA has launched its GeForce RTX 3000 series of graphics cards based on the Ampere architecture three months ago. However, we are already getting information about the next-generation that the company plans to introduce. In the past, the rumors made us believe that the architecture coming after Ampere is allegedly being called Hopper. Hopper architecture is supposed to bring multi-chip packaging technology and be introduced after Ampere. However, thanks to @kopite7kimi on Twitter, a reliable source of information, we have data that NVIDIA is reportedly working on a monolithic GPU architecture that the company internally refers to as "ADxxx" for its codenames.

The new monolithically-designed Lovelace architecture is going make a debut on the 5 nm semiconductor manufacturing process, a whole year earlier than Hopper. It is unknown which foundry will manufacture the GPUs, however, both of NVIDIA's partners, TSMC and Samsung, are capable of manufacturing it. The Hopper is expected to arrive sometime in 2023-2024 and utilize the MCM technology, while the Lovelace architecture will appear in 2021-2022. We are not sure if the Hopper architecture will be exclusive to data centers or extend to the gaming segment as well. The Ada Lovelace architecture is supposedly going to be a gaming GPU family. Ada Lovelace, a British mathematician, has appeared on NVIDIA's 2018 GTC t-shirt known as "Company of Heroes", so NVIDIA may have already been using the ADxxx codenames internally for a long time now.

During its GPU Technology Conference (GTC) in China, Mr. Bill Dally—NVIDIA's chief scientist and SVP of research—has presented many interesting things about how the company plans to push the future of HPC, AI, graphics, healthcare, and edge computing. Mr. Dally has presented NVIDIA's research efforts and what is the future vision for its products. Among one of the most interesting things presented was a plan to ditch the standard electrical data transfer and use the speed of light to scale and advance node communication. The new technology utilizing optical data transfer is supposed to bring the power required to transfer by a significant amount.

The proposed plan by the company is to use an optical NVLink equivalent. While the current NVLink 2.0 chip uses eight pico Joules per bit (8 pJ/b) and can send signals only to 0.3 meters without any repeaters, the optical replacement is capable of sending data anywhere from 20 to 100 meters while consuming half the power (4 pJ/b). NVIDIA has conceptualized a system with four GPUs in a tray, all of which are connected by light. To power such a setup, there are lasers that produce 8-10 wavelengths. These wavelengths are modulated onto this at a speed of 25 Gbit/s per wavelength, using ring resonators. On the receiving side, ring photodetectors are used to pick up the wavelength and send it to the photodetector. This technique ensures fast data transfer capable of long distances.

NVIDIA today announced that it will be hosting another GTC keynote for the coming month of October. To be held between October 5th and October 9th, the now announced keynote will bring updates to NVIDIA's products and technologies, as well as provide an opportunity for numerous computer science companies and individuals to take center stage on discussing new and upcoming technologies. More than 500 sessions will form the backbone of GTC, with seven separate programming streams running across North America, Europe, Israel, India, Taiwan, Japan and Korea - each with access to live demos, specialized content, local startups and sponsors.

This GTC keynote follows the May 2020 keynote where the world was presented to NVIDIA's Ampere-based GA100 accelerator. A gaming and consumer-oriented event is also taking place on September 1st, with expectations being set high for NVIDIA's next-generation of consumer graphics products. Although if recent rumors of a $2,000 RTX 3090 graphics card are anything to go by, not only expectations will be soaring by then.

Thanks to the sources of VideoCardz, we now have the first picture of the next-generation NVIDIA Tesla A100 graphics card. Designed for computing oriented applications, the Tesla A100 is a socketed GPU designed for NVIDIA's proprietary SXM socket. In a post few days ago, we were suspecting that you might be able to fit the Tesla A100 GPU in the socket of the previous Volta V100 GPUs as it is a similar SXM socket. However, the mounting holes have been re-arranged and this one requires a new socket/motherboard. The Tesla A100 GPU is based on GA100 GPU die, which we don't know specifications of. From the picture, we can only see that there is one very big die attached to six HBM modules, most likely HBM2E. Besides that everything else is unknown. More details are expected to be announced today at the GTC 2020 digital keynote.

NVIDIA is rumored to introduce their next-generation Ampere architecture very soon, at its GTC event happening on May 14th. We're expecting to see an announcement for the successor to the company's DGX lineup of pre-built compute systems—using the upcoming Ampere architecture of course. At the heart of these machines, will be a new GA100 GPU, that's rumored to be very fast. A while ago, we've seen NVIDIA register a trademark for "DGX A100", which seems to be a credible name for these systems featuring the new Tesla A100 graphics cards.

Today, NVIDIA's CEO was spotted in an unlisted video that's published on the official NVIDIA YouTube channel. It shows him pulling out of the oven what he calls "world's largest GPU", that he has been cooking all the time. Featuring eight Tesla A100 GPUs, this DGX A100 system appears to be based on a similar platform design as previous DGX systems, where the GPU is a socketed SXM2 design. This looks like a viable upgrade path for owners of previous DGX systems—just swap out the GPUs and enjoy higher performance. It's been a while since we have seen Mr. Huang appear with his leather jacket, and in the video, he isn't wearing one, is this the real Jensen? Jokes aside, you can check out the video below, if it is not taken down soon.Update May 12th, 5 pm UTC: NVIDIA has listed the video and it is not unlisted anymore.

NVIDIA has announced that their annual GTC (Graphics Technology Conference) keynote will be held on May 14th, via a fully online distribution through YouTube set for 6 a.m. PST. Originally canceled due to the COVID-19 pandemic, NVIDIA planned to make a digital-only event covering GTC on the same day of March 23rd, but elected to postpone it since "there were no announcements that were too critical not to be able to be told at a later time". The "Get AMPED" catchphrase does seem to point to some Ampere announcements, though, and the entire PC enthusiast community very much thinks that is one critical announcement.

The GTC 2020 note will be a recorded announcement led by NVIDIA CEO Jensen Huang. The leather jacket-toting CEO will highlight the company's latest innovations in AI, high performance computing, data science, autonomous machines, healthcare and graphics during the recorded keynote, which will be made available, on demand, on YouTube. Starting on May 19th, though, the graphics technology event will continue via live webinars, demos, and recorded talks discussing the very latest in AI, HPC, data science, graphics, and more.

NVIDIA was supposed to launch its next-generation "Ampere" lineup of server-class GPUs at this year's GTC event. However, NVIDIA's president and CEO, Jensen Huang, shared the news that NVIDIA will now be showcasing the important GTC news it has prepared, but instead will only provide online materials from developers and researchers from all over the world. In the blog update, Mr. Huang said the following: "We have exciting products and news to share with you. But this isn't the right time. We're going to hold off on sharing our GTC news for now. That way, our employees, partners, the media and analysts who follow us, and our customers around the world can focus on staying safe and reducing the spread of the virus."

"We will still stream tons of great content from researchers and developers who have prepared great talks. This is a time to focus on our family, our friends, our community. Our employees are working from home. Many hourly workers will not need to work but they'll all be fully paid. Stay safe everyone. We will get through this together.", he added. While we won't get any new GPUs judging by this announcement, we can expect to see them once this situation is resolved.

NVIDIA's ANZ (Australia and New Zealand) Twitter handle posted a curious-looking teaser of something to look forward to on March 19. The now-deleted Tweet contained an animation showing the shape of an eye tracking two points of light crossing its iris. This date falls just a couple of days ahead of the March 22 debut of GTC 2020, the NVIDIA-promoted trade-show covering all things graphics tech. As many on the tweet and online forums discussing have pointed out, the announcement could probably be related to a commercial release of NVIDIA's foveated rendering technology that was demonstrated way back at SIGGRAPH 2016, at a time when VR and related technologies were all the rage.

The concept of foveated rendering is straightforward: eye-tracking is leveraged to ensure that areas of the frame you're looking at are rendered in greater detail than the others, to conserve system resources and improve performance. This is achieved by tracking your foveal vision (the primary part of your vision focused on detail), while shedding resources on parts of the frame that fall within your peripheral vision. Compared to 2016, rendering technologies to facilitate foveated rendering have advanced. A related technology is variable shading rate (VRS), which allows an application to render different parts of the scene at different levels of detail, and improve performance.A video presentation detailing NVIDIA's foveated rendering tech from 2016 follows.

NVIDIA today announced that, in light of the spread of the coronavirus, it is deferring plans to deliver a webcast keynote as part of the digital version of its GPU Technology Conference later this month. The company will, instead, issue on Tuesday, March 24, news announcements that had been scheduled to be shared in the keynote. This will be followed by an investor call with NVIDIA founder and Chief Executive Officer Jensen Huang, which will be accessible to other listeners. The call will begin at 8am Pacific time and will be accessible at investor.nvidia.com.

NVIDIA had initially planned to host its 11th annual GTC on March 22-26 at the San Jose Convention Center, with an anticipated audience of 10,000. Amid the worsening coronavirus situation, the company said earlier this month that it was shifting much of the conference to its digital platform. The company believes that continuing public health uncertainties would challenge its ability to produce and deliver a digital keynote. Other components of GTC Digital will still take place, including live webinars, recorded talks and panels, research posters, trainings, and Connect with Experts sessions available starting Wednesday, March 25. More details will be provided in the coming days.