In 2018, the NVIDIA® RTX™ platform revolutionized professional visual computing with the NVIDIA Turing™ GPU architecture. It combined the power of advanced graphics, computing, and AI to bring real-time ray tracing to reality years before previously thought possible. NVIDIA RTX technology enabled artists, designers, scientists, and researchers to work with photorealistic images in real-time, fundamentally changing the way they work.
Since the introduction of NVIDIA RTX technology, the world and how people work has changed drastically. Professional workflows need to enable a distributed and remote workforce with the ability to do work from anywhere. Artists are creating higher-resolution, hyper-realistic content with the ever-increasing demand for differentiated and visually compelling content. Designers and engineers are striving to create more complex and efficient designs to meet customer demands in highly supply-constrained environments. Scientists, researchers, and medical professionals are faced with incredible challenges that require the rapid development of solutions on a global scale.
With the introduction of the NVIDIA RTX 6000 Ada Generation desktop GPU, based on the NVIDIA Ada Lovelace architecture, NVIDIA is providing incredible new levels of performance for professionals to take on the challenges of today and be ready for the evolving, intensive demands of tomorrow.
The NVIDIA RTX 6000 Ada Generation combines 142 third-generation RT Cores, 568 fourth-generation Tensor Cores, and 18,176 CUDA® Cores with 48GB of GDDR6 ECC graphics memory to deliver the next generation of AI graphics and petaflop inferencing performance for unprecedented speed-up of rendering, AI, graphics, and compute workloads. RTX 6000 Ada-powered workstations provide what you need to succeed in today’s ultra-challenging business environment.
NVIDIA RTX 6000 Ada Delivers Creativity Enhancing and Workflow Redefining Capabilities
NVIDIA RTX 6000 Ada Generation is the most powerful workstation GPU offering high-performance, real-time ray tracing, AI-accelerated computing, and professional graphics rendering. Building upon the major Streaming Multiprocessor (SM) enhancements, the NVIDIA Ada Lovelace architecture also provides more cores, higher clocks, and a larger L2 cache than the previous Ampere architecture for more performance to enhance ray tracing operations, tensor matrix operations, and frame rates with DLSS (Deep Learning Super Sampling) 3.0.
NVIDIA Ada CUDA Cores bring double-speed processing for single-precision floating point (FP32) operations over the previous generation GPUs. This provides a significant 2x performance gain for graphics workflows like 3D model development and compute workflows like desktop simulation for computer-aided engineering (CAE). By enabling two FP32 primary data paths, NVIDIA RTX 6000 Ada doubles peak FP32 operations.
Incorporating Gen-3 ray tracing engines, NVIDIA Ada Lovelace architecture-based GPUs provide incredible ray-traced rendering performance. A single NVIDIA RTX 6000 Ada GPU can render complex professional models with physically accurate shadows, reflections, and refractions to empower users with instant insight. Working in concert with applications leveraging APIs such as NVIDIA OptiX, Microsoft XDR, and Vulkan ray tracing, systems based on the NVIDIA RTX 6000 Ada will power truly interactive design workflows to provide immediate feedback for unprecedented levels of productivity. The NVIDIA RTX 6000 Ada features up to 2x faster ray-triangle intersection throughput compared to the previous generation. The enhanced RT Cores also combine with new Shader Execution Reordering (SER) technology dynamically reorders inefficient workloads, dramatically improving shader performance to accelerate end-to-end ray-traced image rendering performance.
Specialized for deep learning matrix multiply and accumulate math operations at the heart of neural network training and inferencing functions, the NVIDIA RTX 6000 Ada includes enhanced Gen-4 Tensor Cores that accelerate more data types and still support the Fine-Grained Structured Sparsity feature that delivers more than 2x throughput for tensor matrix operations compared to the previous generation. The new Tensor Cores also accelerate new FP8 precision modes while independent floating-point and integer data paths allow more efficient execution of workloads using a mix of computation and addressing calculations. Independent floating-point and integer data paths allow more efficient execution of workloads using a mix of computation and addressing calculations.
Built with 48GB GDDR6 memory delivering up to 25% greater throughput for ray tracing, rendering, and AI workloads than the previous generation, the NVIDIA RTX 6000 Ada provides the industry’s largest graphics memory footprint to address the largest datasets and models in latency-sensitive professional applications. The RTX 6000 Ada meets strict data integrity requirements for mission-critical applications with uncompromised computing accuracy and reliability for workstations by offering an optional Error Correction Code (ECC) on graphics memory.
Video Decoding and Encoding Now Fully Integrate AV1
The Ada Lovelace architecture’s Gen-5 NVDEC is well-suited for transcoding and video playback applications for real-time decoding. The following video codecs are supported for hardware-accelerated decoding: MPEG-2, VC-1, H.264 (AVCHD), H.265 (HEVC), VP8, VP9, and AV1 video formats. Video encoding at 8K/60 will be achievable for professional video editing.
Gen-5 NVENC can take on the most demanding 4K or 8K video encoding tasks to free up the graphics engine and the CPU for other operations. The NVIDIA RTX 6000 Ada provides better encoding quality than software-based x264 encoders. The NVIDIA RTX 6000 Ada incorporates AV1 video encoding which is 40% more efficient than H.264 encoding for 4K HDR video. AV1 will provide better quality at the same bitrate bandwidth.
Faster PCIe Gen 4.0 performance also accelerates GPU direct memory access (DMA) transfers, enabling faster video data transfers from GPUDirect® for video-enabled devices and faster I/O with GPUDirect Storage to complement the NVENC and NVDEC enhancements.
NVIDIA RTX 6000 Ada’s support for NVIDIA RTX Virtual Workstation (vWS) software allows a personal workstation to be repurposed into multiple high-performance virtual workstation instances, enabling remote users to share resources to drive high-end design, AI, and compute workloads.
Ideal for Connecting, Building, and Operating 3D Pipelines and Virtual Worlds
Metaverse and 3D internet applications are here, and with them come highly complex production pipelines, geographically-dispersed teams, and a vast collection of incompatible software tools and siloed data. From designing true-to-reality 3D assets and environments, or operating large-scale, connected digital twins, enterprise teams need to navigate these challenges and the demanding industrial, scientific, and AI workflows that come with physically accurate, large-scale simulations. The NVIDIA RTX 6000 Ada and NVIDIA Omniverse™ Enterprise help teams overcome these challenges, and more.
NVIDIA Omniverse Enterprise is a scalable, end-to-end platform enabling enterprises to build and operate metaverse applications. Based on Universal Scene Description (USD), Omniverse Enterprise allows teams to connect and customize complex 3D pipelines and operate large-scale, physically accurate virtual worlds. The NVIDIA RTX 6000 Ada pairs perfectly with NVIDIA Omniverse Enterprise-based applications, ranging from unifying disparate 3D data workflows, to operating state-of-the-art digital twins.
NVIDIA RTX 6000 Ada Generation Product Specifications1
Architecture NVIDIA Ada Lovelace
Process Size 4nm NVIDIA Custom Process | TSMC
Transistors 76.3 Billion
Die Size 608.4 mm2
NVIDIA CUDA Cores 18,176
NVIDIA Tensor Cores 568 Gen-4
NVIDIA RT Cores 142 Gen-3
FP32 Performance1 91.1 TFLOPS
RT Core Performance1 210.6 TFLOPS
Tensor Performance1 1457.0 TFLOPS
GPU Memory 48GB GDDR6 with ECC
Memory Interface 384-bit
Memory Bandwidth 960 GB/s
Max Power Consumption 300 W
System Interface PCI Express 4.0 x16
Display Connectors 4x DisplayPort 1.4a
Form Factor 4.4” H x 10.5” L Dual-Slot
Thermal Solution Active Fansink
vGPU Software Support NVIDIA vPC, vApps, vWS
vGPU Profiles Supported 1GB, 2GB, 3GB, 4GB, 6GB, 8GB, 12GB, 16GB, 24GB, 48GB
NVIDIA 3D Vision Pro Support via optional 3-pin mini-DIN bracket
Frame Lock Compatible with NVIDIA Quadro Sync II
Power Connector 1x PCIe CEM5 16-pin
NVENC | NVDEC 3x | 3x | AV1 Encode and Decode
1Some product specifications are subject to change prior to release.
NVIDIA RTX 6000 Ada Generation General Availability