NVIDIA Transforms the Workstation for the Age of Deep Learning | NVIDIA Blog (2022)

As demand for deep learning continues to gain momentum, it’s already changing the way people work. Driving the next wave of advancement in deep learning-infused workflows is the NVIDIA Volta GPU architecture.

In his keynote address at the GPU Technology Conference today, NVIDIA founder and CEO Jensen Huang unveiled the new Volta-based Quadro GV100, and described how it transforms the workstation with real-time ray tracing and deep learning.

The Quadro GV100 and its companion product, Quadro vDWS for the data center, address the growing demands of the world’s largest businesses — in such fields as automotive, architecture, engineering, entertainment and healthcare — to rapidly deploy deep learning-based research and development, accelerate deep learning-enhanced applications, enable photoreal VR and provide secure, anytime, anywhere access.

Bringing unprecedented capabilities in deep learning, rendering and simulation to designers, engineers and scientists, the new products allow professionals to design better products in a completely new way. GPU-accelerated techniques, like generative design, and the ability to conduct complex simulations faster mean businesses can explore more design choices, optimize their designs for performance and cost, and consequently bring groundbreaking products to market faster.

(Video) NeRF: Representing Scenes as Neural Radiance Fields for View Synthesis (ML Research Paper Explained)

Innovate Without Restrictions

The new Quadro GV100 packs 7.4 TFLOPS double-precision, 14.8 TFLOPS single-precision and 118.5 TFLOPS deep learning performance, and is equipped with 32GB of high-bandwidth memory capacity. Two GV100 cards can be combined using NVIDIA NVLink interconnect technology to scale memory and performance, creating a massive visual computing solution in a single workstation chassis.

Other benefits of the GV100 include:

  • Easy implementation of deep learning development – Access the NVIDIA GPU Cloud container registry with GV100 or other high-end Quadro GPUs for a comprehensive catalog of GPU-optimized software tools for deep learning and high performance computing on any workstation.
  • Accelerated deep learning training and inferencing on a desktop workstation – Dedicated Tensor Cores and the ability to scale two GV100s for up to 64GB of HBM2 memory with NVIDIA NVLink provide the performance required for demanding deep learning training and inferencing applications.
  • Supercharged rendering performance – Deep learning-accelerated denoising performance for ray tracing provides fluid visual interactivity throughout the design process.
  • Ability to run complex 3D simulations – Fast double-precision coupled with the ability to scale memory up to 64GB accelerates solver performance in computer-aided engineering workflows.
  • Collaborate, design and create in immersive VR – Support for advanced VR features and massive on-board memory capacity means designers can use physics-based, immersive VR platforms such as NVIDIA Holodeck to conduct design reviews and explore complex photoreal scenes and products at scale.

The World’s Most Powerful Virtual Workstation

With newly added support for the NVIDIA Tesla V100 GPUs, Quadro vDWS has the power to address increasingly compute-intensive workflows and securely deliver workstation-class performance to any connected device.

With Quadro vDWS, users can:

  • Run interactive, real-time simulations such as ANSYS Discovery Live
  • Speed rendering time of photorealistic images up to 80 percent faster than with previous generations
  • Leverage AI-enhanced applications for more fluid, visual interactivity throughout the design process
  • Work from anywhere, anytime, from any connected device, while data stays secure, never leaving the data center

Positive Early Reaction to the Quadro GV100

“With Adobe Sensei’s AI and machine learning platform, we’re enabling our creative and enterprise customers to solve digital experience challenges by working smarter, better and faster. The NVIDIA Volta GPU architecture that powers its new Quadro GV100 GPU is clearly a driving force in the evolution of AI. The speed and performance from NVIDIA’s GPUs are helping our customers deliver amazing, real-time experiences at scale across platforms, leveraging Adobe Sensei capabilities.”

(Video) Future Computers Will Be Radically Different (Analog Computing)

– Scott Prevost, vice president of Engineering at Adobe

“The capabilities of the new Volta architecture allow us to create and interact with mathematical models of extreme complexity which rival the accuracy of prohibitively expensive physics simulation, at a fraction of the cost. The new AI-dedicated Tensor Cores have dramatically increased the performance of our models and the speedier NVLink allows us to efficiently scale multi-GPU simulations.”

– Francesco “Frio” Iorio, director of Computational Science Research at Autodesk

“AI computing is allowing our customers to access new business insights and solve problems that were not possible before recent advances in technology. Dell’s capabilities to support customers in AI span IOT, workstations, and data center solutions. The Precision 7920 workstation with Quadro GV100 enables new levels of performance and compute capabilities for an AI-driven future with the simplicity of a deskside solution.”

– Rahul Tikoo, vice president and general manager of Precision Workstations at Dell

(Video) [ML News] CVPR bans social media paper promotion | AI restores Rembrandt | GPU prices down

“Design in the Age of Experience requires going beyond traditionalmethods to create a ‘New Reality’ experiencefor customers.To do this, designers must collaborate and create multisensory, real-world environments that enrich the customer experience. This requires serious GPU horsepower. That’s why we are excited about the performance gains we’ve seen in 3DEXPERIENCE with the new Quadro GV100. The ability to scale two Quadro GV100 GPUs using NVLink, coupled with the performance enhancements of NVIDIA VR SLI, doubled our performance allowing us to seamlessly interact with massive datasets comprised of several hundred million polygons.”

– Xavier Melkonian,CATIA DESIGN portfolio director at Dassault Systèmes

“The exponential growth in AI and the pace of change attributed to machine learning is rapid. HP Z Workstation customers are seeing unprecedented opportunities that have huge implications for not only businesses, but also end users. Combined with the Quadro GV100, HP Z Workstations are the ideal machine learning development platform, while providing the extreme power necessary for product designers, architects and others to create with high visual fidelity and obtain fast results. The HP ML Developers Portal now provides support for NVIDIA GPU Cloud, as well as state-of-the-art tools such as HP’s curated software stacks.”

– Carol Hess, vice president of Worldwide Workstation Product Management at HP Inc.

Our projects include the world’s tallest towers, longest spans, most varied programs and inventive forms. Utilizing NVIDIA GPUs throughout our 3D visualization and VR workflow helps us discover the smartest solution to every project. AI opens up new possibilities for enhancing our traditional design process. That’s why we are especially excited about the new Quadro GV100. It’s not only equipped with enough memory for us to work on massive projects, but its power to accelerate AI is truly a game changer for us. It’s as if we have an entirely new gear to speed up our projects and deliver higher quality results faster and more efficiently for our clients.”

(Video) Deep Learning Recommender Systems with Even Oldridge | AI with Alex

– Cobus Bothma, applied research director at KPF

“Technology is constantly pushing forward; breaking down walls and bringing with it innovation beyond what was imagined before. With the NVIDIA Quadro GV100 GPU for compute and 3D graphics, we are excited to see the progression and dedication towards pushing boundaries and unleashing the possibilities. Lenovo Workstations is excited to support the GV100 over the coming months as an addition to our overall AI and generative design solutions and to shape the future of creative work.”

– Rob Herman, general manager at Lenovo Workstations

“When we tested the NVIDIA Quadro GV100, we saw a 3x performance improvement right out of the box. We can’t wait to see what kind of performance levels we can achieve by tailoring our applications to really take advantage of it.”

– Paolo Emilio Selva, head of Software Engineering at Weta Digital

(Video) Deep Learning Hardware: Past, Present, and Future, Talk by Bill Dally

Availability

Quadro vDWS is available now for over 120 systems from 33 vendors. The NVIDIA Quadro GV100 is available immediately on nvidia.com and starting in April from leading workstation OEMs, including Dell, HP, Lenovo and Fujitsu, and authorized distribution partners, including PNY Technologies in North America and Europe, ELSA/Ryoyo in Japan and Leadtek in Asia Pacific.

Feature image courtesy of KPF.

FAQs

Is Nvidia GeForce good for deep learning? ›

NVIDIA GeForce RTX 2080 Ti is a powerful GPU that has many features that make it a fantastic choice for deep learning. Additionally, the NVIDIA GeForce RTX 2080 Ti has 13,6 million transistors and 13.45 teraflops of computing power – which means that it can process complex tasks quickly and efficiently.

What is Nvidia deep learning? ›

Deep learning is a subset of AI and machine learning that uses multi-layered artificial neural networks to deliver state-of-the-art accuracy in tasks such as object detection, speech recognition, language translation, and others.

Which GPU is best for deep learning? ›

NVIDIA's RTX 3090 is the best GPU for deep learning and AI in 2020 2021. It has exceptional performance and features make it perfect for powering the latest generation of neural networks. Whether you're a data scientist, researcher, or developer, the RTX 3090 will help you take your projects to the next level.

Is RTX 3070 Ti good for machine learning? ›

The RTX 3070 is perfect if you want to learn deep learning. This is so because the basic skills of training most architectures can be learned by just scaling them down a bit or using a bit smaller input images.

How much GPU is enough for deep learning? ›

While the number of GPUs for a deep learning workstation may change based on which you spring for, in general, trying to maximize the amount you can have connected to your deep learning model is ideal. Starting with at least four GPUs for deep learning is going to be your best bet.

Is 4GB graphic card enough for deep learning? ›

It is okay to have NVIDIA GeForce RTX 3050 Ti 4GB GDDR6 for normal usage but for deep learning research I would recommend Intel 5 processor with atleast 12 GB Ram in your laptop otherwise with low configuration laptop while compiling your program it will stuck in the process.

When did NVIDIA start deep learning? ›

Hence NVIDIA released CuDNN in 2014 which was a dedicated CUDA based library for Deep Learning that provided functions for the primitive operations of neural networks like backpropagation, convolutional, pooling, etc. Soon all the well known deep learning libraries like PyTorch, Tensorflow, Matlab, MXNet, etc.

How does NVIDIA use machine learning? ›

NVIDIA provides a suite of machine learning and analytics software libraries to accelerate end-to-end data science pipelines entirely on GPUs. This work is enabled by over 15 years of CUDA development. GPU-accelerated libraries abstract the strengths of low-level CUDA primitives.

What is NVIDIA software used for? ›

NVIDIA's enterprise software solutions do just that, spanning all modern workloads and giving IT admins, data scientists, 3D designers, and DevOps teams access to the tools they need to easily manage and optimize their accelerated systems, from cloud and data center to edge.

Do I need a GPU for deep learning? ›

Graphics processing units (GPUs), originally developed for accelerating graphics processing, can dramatically speed up computational processes for deep learning. They are an essential part of a modern artificial intelligence infrastructure, and new GPUs have been developed and optimized specifically for deep learning.

Should I buy a GPU for deep learning? ›

GPUs are specialised hardware architectures originally designed for real-time video game graphics, but have now grown into a mature High Performance Computing (HPC) platform. GPUs can reduce training times by a significant factor and are thus almost an essential tool for serious deep learning practitioners.

Is CPU important for deep learning? ›

For Deep learning applications, As mentioned earlier, The CPU is responsible mainly for the data processing and communicating with GPU. Hence, The number of cores and threads per core is important if we want to parallelize all that data preparation.

Is RTX 3060 good for deep learning? ›

Yes, it's a low end chip, but the 12GB make it quite attractive. It might not run fast, but it'll be able to run things that won't run on the 8GB cards, so if the 10/12GB cards are out of my budget, it seems like an option worth considering.

Is RTX 2060 good for deep learning? ›

GPU Recommendations. RTX 2060 (6 GB): if you want to explore deep learning in your spare time. RTX 2070 or 2080 (8 GB): if you are serious about deep learning, but your GPU budget is $600-800. Eight GB of VRAM can fit the majority of models.

Is RTX 3050 good for machine learning? ›

It's good enough to start and learn deep learning but once you start working on real projects they won't fit in the GPU memory.

Which GPU is best for data science? ›

The Titan RTX and RTX 2080 Ti aren't far behind.
  • NVIDIA Titan V. The Titan V is a PC GPU that was designed for use by scientists and researchers. ...
  • NVIDIA Titan RTX. The Titan RTX is a PC GPU based on NVIDIA's Turing GPU architecture that is designed for creative and machine learning workloads. ...
  • NVIDIA GeForce RTX 2080 Ti.

Videos

1. The Promise of Digital Transformation
(NVIDIA)
2. Machine Learning for Accelerated Aero-Thermal Design in The Age of Electromobility
(ENGYS)
3. The Power of Deep Learning with Bryan Catanzaro from NVIDIA
(ARK Invest)
4. Accelerating AI Training Using GPUs on Cloudera Machine Learning
(Cloudera, Inc.)
5. Grandmaster Series – Building World-Class NLP Models with Transformers and Hugging Face
(NVIDIA Developer)
6. Cheapest (0$) Deep Learning Hardware Options | 2021
(Aleksa Gordić - The AI Epiphany)

Top Articles

Latest Posts

Article information

Author: Kareem Mueller DO

Last Updated: 12/12/2022

Views: 5676

Rating: 4.6 / 5 (66 voted)

Reviews: 89% of readers found this page helpful

Author information

Name: Kareem Mueller DO

Birthday: 1997-01-04

Address: Apt. 156 12935 Runolfsdottir Mission, Greenfort, MN 74384-6749

Phone: +16704982844747

Job: Corporate Administration Planner

Hobby: Mountain biking, Jewelry making, Stone skipping, Lacemaking, Knife making, Scrapbooking, Letterboxing

Introduction: My name is Kareem Mueller DO, I am a vivacious, super, thoughtful, excited, handsome, beautiful, combative person who loves writing and wants to share my knowledge and understanding with you.