Two years ago, the NVIDIA® RTX™ platform revolutionized professional visual computing forever. Based on the NVIDIA Turing™ GPU architecture and armed with real-time ray tracing, accelerated AI, and photorealistic VR, it enabled designers and engineers to do their life’s work at a level of quality and performance unlike ever before. But the pace of innovation and the drive to achieve new breakthroughs never ceases. And now, global circumstances have presented a new set of challenges for professionals to create, build, entertain and discover in a world that looks dramatically different than the recent past.
With the introduction of the NVIDIA RTX A6000 desktop GPU, based on the NVIDIA Ampere architecture, NVIDIA has placed a whole new level of performance and capabilities in the hands of demanding professionals. This ensures they are not only ready to tackle the urgent needs of today, but are superbly equipped to meet the rapidly evolving, intensive demands of tomorrow.
The world of professional visualization is evolving rapidly. Advanced requirements like real-time ray tracing, AI, compute, engineering simulation, and immersive VR are common across industries, while millions of professionals have shifted to working from home.
The NVIDIA RTX A6000 delivers everything designers, engineers, and artists need to meet today's demands from their desktop. Built on the NVIDIA Ampere architecture, the RTX A6000 combines 84 second-generation RT Cores, 336 third-generation Tensor Cores, and 10,752 CUDA® Cores with 48 GB of ECC (optional) GDDR6 graphics memory for unprecedented rendering, AI, graphics, and compute performance. Connect two RTX A6000s with NVIDIA NVLink® for 96 GB of combined GPU memory. And access the power of your workstation from anywhere with remote-access software. Engineer amazing products, design state-of-the art buildings, drive scientific breakthroughs, and create immersive entertainment with the world’s most powerful graphics solution.
Overview of Essential NVIDIA Ampere Architecture Advances
The NVIDIA Ampere architecture based CUDA cores bring up to 2X the single-precision floating point (FP32) throughput compared to the previous generation, providing significant performance improvements for graphics workflows such as 3D model development and compute for workloads such as desktop simulation for computer-aided engineering (CAE).
Second-generation RT Cores provide up to 2X the throughput of the first generation, and the ability to concurrently run ray tracing with either shading or denoising capabilities. This accelerates renders for M&E content creation, AEC design evaluations, and manufacturing virtual prototyping. The addition of hardware accelerated Motion BVH (bounding volume hierarchy) further improves motion blur rendering performance by up to 7X when compared to the previous generation.
Third-generation Tensor Cores provide up to 5X the training throughput and, with the new Tensor Float 32 (TF32) precision, up to 10X higher inferencing throughput with structural sparsity over the previous generation with zero code changes. This accelerates the time required for AI model training or data science data prep and modeling workflows. Hardware support for structural sparsity provides additional acceleration by reducing network model size and speeding up model execution. The latest generation of Tensor Cores also support the brain floating-point format (Bfloat16).
Encode/decode engines: The RTX A6000 includes one video encode engine and two decode engines, including support for the AV1 video format and the performance required for multi-stream video applications for security and video serving.
The RTX A6000 supports PCI Express Gen 4 (PCIe Gen 4), which doubles the bandwidth of PCIe Gen 3 from 15.75 gigabytes per second (GB/sec) to 31.5 GB/sec for x16 connection, improving data transfer speeds from CPU memory for data-intensive tasks such as AI, data science, and creating 3D models from large datasets. Faster PCIe performance also accelerates GPU direct memory access (DMA) transfers, providing faster video data transfers from GPUDirect® for Video-enabled devices and faster input/output (I/O) with GPUDirect Storage.
48GB OF GPU MEMORY
The RTX A6000 features 48 GB of GDDR6 memory, double the memory size of the previous-generation 6000 series. Third-generation NVLink provides up to 96 GB of combined memory with two A6000 cards, providing the memory needed for rendering, data science, engineering simulation, and other GPU memory-intensive applications.
Virtualization-ready: Support for NVIDIA virtual GPU (vGPU) 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.
Four DisplayPort 1.4a connectors, support for multiple 8K monitors, NVIDIA Quadro Sync, NVIDIA Mosaic, and Warp and Blend enable massive immersive environments for cave automatic virtual environments (CAVE), video walls, and location-based entertainment deployments.
A single RTX A6000 can support up to four 5K (5120 x 2880) at 60 Hz displays. Display support also includes the ability to drive two 8K displays. RTX A6000 supports DisplayPort 1.4a, which enables a single cable to drive an 8K display at 60 Hz using Display Stream Compression (DSC). Advanced multi-display technologies such as NVIDIA Quadro Sync, NVIDIA Mosaic, and Warp and Blend provide a robust way to perform image synchronization and resolution scaling of a synchronized display surface with multiple projectors or displays.
AR/VR AND STEREO
Support for the latest high-resolution head-mounted display (HMD) devices, high-performance graphics, and large 48 GB of GPU memory enable the creation of incredibly immersive augmented reality (AR) and virtual reality (VR) experiences for training, product validations, building walkthroughs, and compelling entertainment. RTX A6000 provides the display performance required by the latest generation of higher-resolution HMDs. Support for up to four-way VR SLI, with two NVLink-connected RTX A6000s per HMD, provide the ultimate performance for incredibly detailed and immersive VR experiences. Enhance the analysis and visualization of design, engineering, and digital-content creation workflows with stereoscopic 3D display from a wide range of stereoscopic display devices.
THIRD-GENERATION NVIDIA NVLINK
Enables users to connect two RTX A6000s together to share GPU and memory. Performance can be scaled with up to 112.5 GB/s of bidirectional connection bandwidth and up to 96 GB of combined GDDR6 memory for the largest rendering, AI, VR, and visual computing workloads. This new NVLink connector features a shorter Z height, enabling NVLink functionality in a wider range of chassis. The NVLink bridge also serves as the connection between GPUs required for NVIDIA SLI® functionality.
MOTION BVH (BOUNDING VOLUME HIERARCHY)
Hardware-accelerated rendering of motion blur—a common cinematic effect that is difficult to render—means artists no longer need to rely on traditional methods of using motion vectors to achieve motion blur. Motion vectors give the artist flexibility to adjust motion blur in post but require visual fixes for reflections and translucency.
NVIDIA DEEP LEARNING SUPER SAMPLING (DLSS)
Real-time, AI-powered image super-resolution enables higher interactivity and frame rates for design and visualization applications. DLSS lets real-time engines render at lower resolution and uses AI to output at higher resolution while maintaining crisp, clear image quality.
NVIDIA RTX BROADCAST ENGINE
The NVIDIA RTX Broadcast Engine transforms your office into a broadcast studio, upgrading standard webcams and microphones into premium, smart devices with the power of AI. Improve the video and audio quality of livestreams with AI capabilities such as virtual backgrounds, webcam auto frame, and microphone noise removal. With dedicated AI processors called Tensor Cores on NVIDIA RTX GPUs, the AI networks can run in real time alongside your applications.
FORM FACTOR AND POWER EFFICIENCY
With a dual-slot, power-efficient design, the RTX A6000 fits into a wide range of workstation chassis, providing professionals with a generous selection of compatible workstations from worldwide OEM vendors.
The NVIDIA RTX A6000 Value and Productivity Proposition Extends Beyond Hardware
NVIDIA RTX Desktop Manager™ helps professionals organize single- or multi-monitor workspaces to boost productivity. Features like flexible window snapping, user profiles, windows management, and hotkey support deliver maximum control over your desktops and display real estate.
NVIDIA RTX™ Experience provides a full suite of productivity tools on NVIDIA desktop workstations. Features like automatic alerts for the latest NVIDIA RTX Enterprise Driver ensure your system is always optimized for performance. With native desktop recording in up to 8K and tools like Instant Replay, professionals can capture workflows, tutorials, and trainings with ease and upload to third-party sites like Twitch, broadcast live, or stream to NVIDIA Shield® for easy collaboration. NVIDIA RTX Experience also provides a great gaming experience with access to features like optimal playable settings (OPS) and NVIDIA Ansel and Freestyle.
Long-life, unified software drivers for the enterprise undergo extensive testing. This includes subjecting a broad range of workstations and business PCs carrying various NVIDIA workstation products to tens of thousands of machine hours of stress tests and thousands of hours of attended platform testing.
NVIDIA RTX A6000 Offers Tangible Advantages to Professionals Across Multiple Vertical Markets
Second-generation RT Cores provide up to 2X the throughput of the first generation and enable concurrent ray tracing and shading. Design reviews can be accelerated to review high-fidelity visualizations with physically accurate materials, lighting, and reflections in real time. This improved performance unlocks the ability to evaluate new product concepts rapidly and create stunning marketing content directly from computer-aided design (CAD) geometry.
Extend the power of engineering simulation throughout the design process with accelerated real-time structural, thermal, and fluid flow analysis software tools. Engineers can evaluate the impact of design changes instantly to iterate at the speed of light and revolutionize the performance of their designs. The NVIDIA Ampere architecture based CUDA cores bring up to 2X the single-precision floating point throughput and 1.9X improved power efficiency compared to previous generations, unlocking new potential for the industry.
NVIDIA RTX A6000 features an industry-leading 48 GB of GDDR6 memory, double the frame buffer of the previous-generation 6000 series, which allows mechanical engineers and engineering analysts to easily work with large assemblies in their CAD package of choice. Third-generation NVIDIA NVLink can connect two RTX A6000s to provide up to 96 GB of combined GPU memory, so industrial designers, mechanical engineers, and engineering analysts can tackle the largest and most complex workloads.
ARCHITECTURE, ENGINEERING, AND CONSTRUCTION (AEC)
NVIDIA RTX A6000 features an industry-leading 48 GB of GDDR6 memory, double the frame buffer of the previous-generation 6000 series, which enables AEC teams to work with massive building information modeling (BIM) models. Third-generation NVIDIA NVLink can connect two RTX A6000s to provide up to 96 GB of combined GPU memory, so architects, designers, and engineers can tackle the largest and most complex workloads.
Second-generation RT Cores provide up to 2X the throughput of the first generation and enable concurrent ray tracing and shading. Design teams and architectural visualization specialists can quickly iterate on high-fidelity renders using physically accurate shadows, reflections, and refractions in real time.
Support for the latest high-resolution HMD devices, high-performance graphics, and huge 48 GB of GPU memory enable the creation of incredibly immersive AR/VR experiences for better design, design reviews, training, and virtual construction rehearsal workflows.
MEDIA AND ENTERTAINMENT
Iterate more, render faster, and gain distinct advantages over CPU rendering, from previsualization through final frames. NVIDIA RTX A6000’s second-generation RT Cores improve ray-tracing performance by up to 80%. Photorealistic ray tracing can now be achieved in real time, enabling higher-fidelity workflows, from interactive rendering to real-time virtual production.
NVIDIA RTX A6000 features an industry-leading 48 GB of GDDR6 memory, enabling studios to work in real time with complex geometry and high-resolution textures. Third-generation NVIDIA NVLink can connect two RTX A6000s to provide up to 96 GB of combined GPU memory, so artists can work interactively with massive photorealistic environments made up of hundreds of billions of polygons.
Dramatically accelerate production pipelines with third-generation Tensor Cores. New Tensor Cores provide up to 5X the training throughput over the previous generation with zero code changes. Many creative applications have adopted AI-accelerated features that can aid artists with time-consuming tasks such as up-scaling video, denoising renders, enhancing audio, and retiming video. Apps like Autodesk Flame, Adobe Premiere Pro®, and Blackmagic Design DaVinci Resolve already take advantage of Tensor Cores to accelerate content creation tasks.
With 38.7 TFLOPS of FP32 compute performance and 309.7 TFLOPS of Tensor performance with structural sparsity, RTX A6000 enables geoscientists to speed up their visualization workflows and gain faster insight into subsurface data. NVIDIA NVLink lets users combine two RTX A6000s to provide up to 96 GB of GDDR6 memory, scientists can work with massive datasets.
Third-generation Tensor Core technology with the new TF32 precision for deep learning enables RTX A6000 to drive the latest AI-augmented exploration and production software workflows faster than ever.
Powerful performance enables RTX A6000 to drive the most immersive VR environments using the latest generation of high-resolution HMDs for realistic immersive training, well planning, and exploration.
With real-time ray-tracing capabilities, RTX A6000 enables the creation of the most vivid GPU-accelerated renders, providing valuable insights to scientists and researchers faster than ever before.
Dedicated deep learning hardware in RTX A6000 helps researchers create new AI-augmented technologies for solving the most difficult problems or deploy AI-integrated solutions to drive discoveries and push the boundaries of exploration.
VR enables scientists to gain insights only available in immersive environments. RTX A6000 supports the resolutions required by next-generation HMDs. Using NVIDIA SLI technology to combine four RTX A6000s, researchers can access the most powerful VR rendering solution available in a workstation to create the most compelling virtual environments possible.
The NVIDIA Ampere architecture provides RTX A6000 with the power to visualize massive datasets at resolutions of up to 8K.
Third-Generation Tensor Cores support the TF32 precision that provides up to 5X the training performance of the previous generation for faster model training.
PCIe Gen 4 provides 2X the bandwidth of Gen 3, speeding up data transfers from CPU and storage, accelerating data prep and training dataset loading.
RTX A6000 provides 48 GB of GPU memory, and with NVLink, scales up to 96 GB of memory to work with large datasets for data prep and model training.
Contact PNY for Additional Information
For additional information on the category redefining NVIDIA RTX A6000, contact PNY at GOPNY@PNY.COM or visit the NVIDIA RTX A6000 product landing page. A turnkey bundle that includes the NVIDIA RTX A6000 and the NVIDIA Quadro Sync II board for scalable visualization and M&E applications is also available.