NVIDIA’s (NASDAQ: NVDA) invention of the GPU in 1999 sparked the growth of the PC gaming market, redefined modern computer graphics, and revolutionized parallel computing. More recently, GPU deep learning ignited modern AI — the next era of computing — with the GPU acting as the brain of computers, robots, and self-driving cars that can perceive and understand the world.
In 2006, the creation of the CUDA programming model and Tesla GPU platform opened up the parallel-processing capabilities of the GPU to general-purpose computing. A powerful new approach to computing was born.
NVIDIA® GeForce RTX™ delivers the ultimate gaming experience. Powered by the new NVIDIA Turing™ GPU architecture and the revolutionary RTX platform, RTX graphics cards fuse together real-time ray tracing, artificial intelligence, and programmable shading. In fact, GeForce RTX graphics cards are the first graphics cards built to deliver AI-enhanced gaming and real-time ray-tracing effects. Furthermore, they provide up to 6X faster ray-tracing performance than previous-generation Pascal-architecture cards.
“Games will never be the same,” said NVIDA CEO Jensen Huang. “Computer graphics has been reinvented.”
Real-Time Ray Tracing Realized
Ray tracing is the definitive solution for lifelike lighting, reflections, and shadows, offering a level of realism far beyond what is possible using traditional rendering techniques. Turing is the first GPU capable of rendering real-time ray tracing.
Simulating the path of a single light ray as it would be absorbed or reflected by various objects in the image, ray tracing is a technique for presenting three-dimensional (3D) images on a two-dimensional (2D) display by tracing a path of light through pixels on an image plane. In order to bring RTX to fruition, NVIDIA developed new graphical compute subsystems inside their GPUs called “RT Cores” which spur the ray tracing process.
Integrating the Power and Performance of Tensor Cores
To heighten the rendering quality of RTX, NVIDIA went one step better by integrating Tensor Cores – initially produced for deep learning – into the new RTX boards. The result is an accelerated, more efficient rendering process that leverages AI-fueled techniques like “denoising” and “inpainting.”
GeForce RTX graphics cards are also the world’s first graphics cards to feature GDDR6 memory, a new DisplayPort 1.4 output that can drive up to 8K HDR at 60Hz on future-generation monitors with a single cable, and a VirtualLink USB Type-C output for next-generation Virtual Reality headsets.
Programmable shaders defined modern graphics. Turing GPUs feature new advanced shading technologies that are more powerful, flexible, and efficient than ever before. Combined with GDDR6 —the world’s fastest memory — this performance lets customers experience games with maxed-out settings and exceptionally high frame rates.
Supported by the Biggest Names and Best Games
The NVIDIA RTX platform benefits from support in Microsoft’s new DirectX Raytracing (DXR) API as well as adoption by a rapidly growing list of premier video game titles.
The following select game titles will feature real-time ray tracing:
- Assetto Corsa Competizione; Kunos Simulazioni/505 Games
- Battlefield V; EA/DICE
- Justice; NetEase
- MechWarrior 5: Mercenaries; Piranha Games
- Shadow of the Tomb Raider; Square Enix/Eidos-Montréal/Crystal Dynamics/Nixxes
For a complete list, please see our related blog.
The following select game titles will utilize Deep Learning Super-Sampling (DLSS), a technology that applies deep learning and AI to rendering techniques:
- Atomic Heart; Mundfish
- Fractured Lands; Unbroken Studios
- JX3; Kingsoft
- Remnant: From the Ashes; Arc Games
- The Forge Arena; Freezing Raccoon Studios
For a complete list, please see our related blog.
GeForce RTX: New Family of Gaming GPUs
The new GeForce RTX 2080 Ti, 2080 and 2070 GPUs (SEE BELOW) showcase a long list of unprecedented gaming GPU features, including:
- New RT Cores to enable real-time ray tracing of objects and environments with physically accurate shadows, reflections, refractions and global illumination.
- Turing Tensor Cores to perform lightning-fast deep neural network processing.
- New NGX neural graphics framework to integrate AI into the overall graphics pipeline, enabling AI algorithms to perform unprecedented image enhancement and generation.
- New Turing shader architecture with Variable Rate Shading to enable shaders to focus processing power on areas of rich detail, boosting overall performance.
- New memory system featuring ultra-fast GDDR6 with over 600GB/s of memory bandwidth for high-speed, high-resolution gaming.
- NVIDIA NVLink®, a high-speed interconnect to provide higher bandwidth (up to 100 GB/s) and improved scalability for multi-GPU configurations (SLI).
- Hardware support for USB Type-C™ and VirtualLink™, a new open industry standard being developed to meet the power, display and bandwidth demands of next-generation
- VR headsets through a single USB-C™ connector.
- New and enhanced technologies to improve performance of VR applications, including Variable Rate Shading, Multi-View Rendering and VRWorks Audio.
GeForce RTX™ Product Line
GeForce RTX 2080 Ti
NVIDIA’s newest flagship graphics card is a revolution in gaming realism and performance. Its powerful NVIDIA Turing GPU architecture, breakthrough technologies, and 11 GB of next-gen, ultra-fast GDDR6 memory make it the world’s ultimate gaming GPU.
GeForce RTX 2080
The GeForce RTX 2080 is powered by the all-new NVIDIA Turing architecture to deliver altogether new levels of gaming realism, speed, power efficiency, and immersion.
GeForce RTX 2070
The powerful new GeForce RTX™ 2070 takes advantage of the cutting-edge NVIDIA Turing™ architecture to immerse game players in breakthrough levels of realism and performance.
The world’s leading platform for the accelerated data center
Accelerating scientific discovery, visualizing big data for insights, and providing smart AI-based services to the enterprise are everyday challenges for researchers and engineers. Solving these challenges takes increasingly complex and precise simulations, the processing of tremendous amounts of data, or training and running sophisticated deep learning networks. These workloads also require accelerating data centers to meet the growing demand for exponential computing.
NVIDIA® Tesla® is the world’s leading platform for the accelerated data center, deployed by the largest supercomputing centers and enterprises. It enables breakthrough performance with fewer, more powerful servers, resulting in faster scientific discoveries and insights while saving money.
NVIDIA Tesla is also the world’s fastest, most efficient data center platform for inference. Tesla provides the optimal inference solution—combining the highest throughput, best efficiency, and best flexibility to power AI-driven experiences.
With over 550 HPC applications GPU-optimized in a broad range of domains, including 15 of the top 15 HPC applications, and all deep learning frameworks, every modern data center can save money with the Tesla platform.
Given the increasingly broad spectrum of data center applications, NVIDIA has gone to great lengths to provide you with the data center products most appropriate for you. As such, the NVIDIA Tesla data center platform features products to account for virtually every data center need, including:
- NVIDIA Tesla V100 for NVIDIA® NVLink™
- NVIDIA Tesla V100 for PCIe
- NVIDIA Tesla P4
- NVIDIA Tesla P40
Tesla V100 GPU
At the 2018 GPU Technology Conference (GTC18), it was announced that the memory capacity of the NVIDIA® Tesla® V100 GPU – widely adopted by the world’s leading researchers – was doubled to handle the most memory-intensive deep learning and high performance computing workloads.
Now equipped with 32GB of memory, Tesla V100 GPUs will help data scientists train deeper and larger deep learning models that are more accurate than ever. They can also improve the performance of memory-constrained HPC applications by up to 50 percent compared with the previous 16GB version.
NVIDIA Tesla V100 for NVLink
NVIDIA Tesla V100 for PCIe
NVIDIA Tesla P4
The Tesla P4 is powered by the NVIDIA Pascal™ architecture and purpose-built to boost efficiency for scale-out servers running deep learning workloads, enabling smart responsive AI-based services. It reduces inference latency by 15X in any hyperscale infrastructure and provides a remarkable 60X better energy efficiency than traditional CPUs. This unlocks a new wave of AI services previous impossible due to latency limitations.
NVIDIA Tesla P40
The NVIDIA Tesla P40 is purpose-built to deliver maximum throughput for deep learning deployment. With 47 TOPS of inference performance and INT8 operations per GPU, a single server with 8 Tesla P40s delivers the performance of over 140 traditional CPU servers. As models increase in accuracy and complexity, CPUs are no longer capable of delivering interactive user experience. The Tesla P40 delivers over 30X lower latency than a CPU for real-time responsiveness in even the most complex models. Plus, the Tesla P40 offers great inference performance, INT8 precision and 24GB of onboard memory for an outstanding user experience.