We set out 26 years ago to transform computer graphics.

Fueled by the massive growth of the gaming market and its insatiable demand for better 3D graphics, we’ve evolved the GPU into a computer brain at the intersection of virtual reality, high performance computing, and artificial intelligence.

NVIDIA GPU computing has become the essential tool of the da Vincis and Einsteins of our time. For them, we’ve built the equivalent of a time machine.


For 30 years, the dynamics of Moore’s law held true. But now CPU scaling is slowing while the demand for computing power surges ahead.

With AI, now machines can learn. AI can solve grand challenges that have been beyond human reach, but it must be fueled by massive compute power.

Accelerated computing is the path forward beyond Moore’s law, delivering 1000x computing performance every 10 years.


Our invention of the GPU in 1999 made real-time programmable shading possible, giving artists an infinite palette for expression.

In 2018, the introduction of the Turing architecture and NVIDIA RTX ray-tracing technology fulfilled another vision of computer scientists, paving the way to new levels of art and realism in real-time graphics.

We’ve led the field of visual computing for decades.


Turing-based Quadro® RTX delivers photoreal graphics that creators didn’t expect for another 5-10 years.

Quadro RTX GPUs can now accelerate photoreal rendering for large industries that previously only used CPU server farms: film, animation, architecture, product design, and others.

NVIDIA has reinvented computer graphics, again.


GeForce® RTX has redefined what’s possible in gaming. Real-time ray tracing and neural graphics processing come together to create eye-popping images and deliver a level of photorealism never before seen in PC gaming.

AAA games like Battlefield V, Shadow of the Tomb Raider, and Metro Exodus support RTX today. And with support in Microsoft DXR, Unreal Engine, and Unity, next-generation games can easily bring ray tracing to millions of gamers.


In 2006, the creation of our CUDA programming model and Tesla® GPU platform brought parallel processing to general-purpose computing. A powerful new approach to computing was born.

Now, the paths of high performance computing and AI innovation are converging.

From the world’s largest supercomputers to the vast datacenters that power the cloud, this new computing model is helping to answer complex questions, discover new science, and bring amazing capabilities to our mobile devices.

Now, the world’s largest industries — transportation, healthcare, logistics, manufacturing, robotics, smart cities, retail — are tapping into accelerated computing to bring AI to the edge.


GPU acceleration is the most accessible and energy-efficient path forward for the world’s most powerful computers. More than 600 applications support CUDA today, including the top 15 in HPC.

NVIDIA powers U.S.-based Summit, the world’s fastest supercomputer, as well as the fastest systems in Europe and Japan. 27,000 NVIDIA Volta Tensor Core GPUs accelerate Summit’s performance to more than 200 petaflops for HPC and 3 exaflops for AI.


Building amazing AI applications begins with training neural networks. NVIDIA DGX-2 is the world’s most powerful tool for AI training, uniting 16 GPUs to deliver 2 petaflops of training performance.

In July 2019, DGX-2 set new world records in the debut of MLPerf, a new set of industry benchmarks designed to test deep learning performance.

Image Classification
1.33 mins
Object Detection (Light Weight)
2.23 mins
Object Detection (Heavy Weight)
18.47 mins
Translation (Recurrent)
1.8 mins
Translation (Non-Recurrent)
1.59 mins
Reinforcement Learning
13.57 mins


Trained AI applications are deployed in large-scale, highly complex cloud data centers that serve voice, video, image, and recommendation services to billions of users. Hundreds of AI algorithms are in use today, making inference a big and costly challenge.

NVIDIA TensorRT software and the new T4 GPU converge to optimize, validate, and accelerate trained neural networks.


AI breakthroughs no longer come from scientific labs and hyperscale cloud providers alone.

Self-driving cars, automated farm equipment, and autonomous factory robots have moved quickly from ideas to reality. And it’s only the beginning.

The fourth industrial revolution has begun.


Autonomous vehicles will revolutionize the $10 trillion transportation industry.

NVIDIA DRIVE is an open platform and enables researchers and programmers to develop new algorithms or adapt them for specific vehicles.

To train the network, data from all over the world needs to be collected and fed into an NVIDIA DGX supercomputer.

Simulation expands the training set and covers dangerous scenarios that can’t be captured on the road. The trained model is deployed on an in-car supercomputer, for capabilities like pedestrian detection and driver monitoring.


Jetson AGX Xavier delivers the energy-efficient computational power needed for embedded systems like robots, drones, and smart cities. And the new Jetson Nano will enable millions more small, low-power AI systems for embedded IoT apps.

From Xavier to Nano, all of NVIDIA’s AI computers run on the same CUDA-X AI software stack.


NVIDIA is united by a unique culture — the operating system of our company. We dream big, take risks, and learn from our mistakes together. Speed is the key to our success. Craftsmanship is a passion. There are no org charts — the project is the boss.

These beliefs inform everything we do, from designing amazing products to building one of the world’s great companies — a place where people can do their life’s work.

World’s Best
   Performing CEOs
— Harvard Business Review
100 Best Companies
   to Work For
— Fortune
World’s Best CEOs
— Barron’s
Most Innovative
— Fast Company
Employees’ Choice:
   Highest Rated CEOs
— Glassdoor
50 Smartest
— MIT Tech Review
一分快三 | 下一页