======================================================================================================================================================================================================================================================================================== Non-Virtualized Topology ======================================================================================================================================================================================================================================================================================== .. raw:: html Introduction -------------------------------------------------------------------------------------------- This solution is comprised of a NVIDIA Certified Systems™ with GPU, CPU, Memory, et. al. installed with Omniverse and design software. NVIDIA-Certified Systems are configured to deliver excellent performance for a diverse range of workloads. They enable enterprises to confidently deploy hardware solutions that securely and optimally run their modern accelerated workloads. The `NVIDIA® RTX™ 4000 SFF `__ Ada Generation packs a powerful punch, delivering full-size performance in a compact form factor. Built on the NVIDIA Ada Lovelace architecture, the RTX 4000 SFF integrates 48 third-generation RT Cores, 192 fourth-generation Tensor Cores, and 6,144 CUDA cores with 20GB of graphics memory to deliver remarkable acceleration for rendering, AI, graphics, and compute workloads. Workstations powered by the RTX 4000 SFF give professionals the necessary performance, reliability, and versatility to stay ahead of the curve and succeed in today's competitive business landscape without sacrificing performance.  The `NVIDIA RTX A4000 `__ is the most powerful single-slot GPU for professionals, delivering real-time ray tracing, AI-accelerated compute, and high-performance graphics to your desktop. Built on the NVIDIA Ampere architecture, the RTX A4000 combines 48 second-generation RT Cores, 192 third-generation Tensor Cores, and 6,144 CUDA cores with 16GB of graphics memory with error-correction code (ECC) so you can innovate with uncompromised computing accuracy and reliability. The RTX A4000 also features a power-efficient, single-slot PCIe form factor that fits into a wide range of workstation chassis, so you can do exceptional work without limits. Harness the power of real-time ray tracing, simulation, and AI from your desktop with the `NVIDIA RTX A4500 `__ graphics card. Built on the NVIDIA Ampere architecture and featuring 20 GB of GPU memory, designers, engineers, and creators can push the limits of innovation forward, working interactively with complex models and datasets. The `NVIDIA RTX A5000 `__ delivers the power, performance, capabilities, and reliability professionals need to bring their boldest ideas to life. Built on the NVIDIA Ampere architecture, the RTX A5000 combines 64 second-generation RT Cores, 256 third-generation Tensor Cores, and 8,192 CUDA cores with 24GB of graphics memory to supercharge rendering, AI, graphics, and compute tasks. Connect two RTX A5000s with NVIDIA NVLink1 to scale memory and performance with multi-GPU configurations2, allowing professionals to work with memory intensive tasks such as large models, ultra-high resolution rendering, and complex compute workloads. Support for NVIDIA virtual GPU software increases the versatility for enterprise deployments. Unlock the power of your desktop with the `NVIDIA RTX™ A5500 `__ graphics card, delivering the performance, reliability, and features required for demanding multi-application workflows. Built on the NVIDIA Ampere architecture and featuring 24 gigabytes (GB) of GPU memory, it’s everything designers, engineers, scientists, and artists need to create without limits. The `NVIDIA RTX A6000 `__, built on the NVIDIA Ampere architecture, delivers everything designers, engineers, scientists, and artists need to meet the most graphics and compute-intensive workflows. The RTX A6000 is equipped with the latest generation RT Cores, Tensor Cores, and CUDA cores for unprecedented rendering, AI, graphics, and compute performance. Certified with a broad range of professional applications, tested by leading independent software vendors (ISVs) and workstation manufacturers, and backed by a global team of support specialists, NVIDIA RTX is the visual computing solution of choice for demanding enterprise deployments. The `NVIDIA RTX 6000 Ada `__ Generation delivers the features, capabilities, and performance to meet the challenges of today’s professional workflows. Built on the NVIDIA Ada Lovelace architecture, the RTX 6000 combines 142 third-generation RT Cores, 568 fourth-generation Tensor Cores, and 18,176 CUDA cores with 48GB of graphics memory for unprecedented rendering, AI, graphics, and compute workload performance. RTX 6000-powered workstations provide what you need to succeed in today’s ultra-challenging business environment. General GPU Recommendations -------------------------------------------------------------------------------------------- Multi-App + Omniverse 3D Design workflows ############################################## +------------------------+------------------------+----------------------------+ | Minimum | Recommended | Ultimate | +========================+========================+============================+ || || || | || RTX Enabled GPUs with || RTX Enabled GPUs with || Multiple RTX Enabled GPUs | || 12GB VRAM || 24 to 48GB VRAM || with 48GB VRAM | +------------------------+------------------------+----------------------------+ NVIDIA RTX GPU Recommendations for Professional Workstation Users ################################################################## +----------------------+-------------------+--------------------------+------------------------+-----------------------+ | Form Factor | Workload | Good | Better | Best | +======================+===================+==========================+========================+=======================+ || Mobile Workstation || All Workloads || RTX A5000 16GB || RTX A5000 16GB || RTX A5000 16GB | || || || RTX A5500 16GB || RTX A5500 16GB || RTX A5500 16GB | +----------------------+-------------------+--------------------------+------------------------+-----------------------+ || || || RTX 4000 SFF Ada 20GB || || | || || Light Workloads || RTX A4000 16GB || RTX A5000 24GB || RTX A6000 48GB | || || || RTX A4500 20GB || RTX A5500 24GB || RTX 6000 Ada 48GB | + +-------------------+--------------------------+------------------------+-----------------------+ || || Medium Workloads || RTX A5000 24GB || RTX A6000 48GB || RTX A6000 48GB x2 | || Desktop Workstation || || RTX A5500 24GB || RTX 6000 Ada 48GB || RTX 6000 Ada 48GB x2 | + +-------------------+--------------------------+------------------------+-----------------------+ || || Heavy Workloads || RTX A6000 48GB || RTX A6000 48GB x2 || RTX A6000 48GB x3+ | || || || RTX 6000 Ada 48GB || RTX 6000 Ada 48GB x2 || RTX 6000 Ada 48GB x3+| +----------------------+-------------------+--------------------------+------------------------+-----------------------+ +----------------------------------------------------------------+----------------------------------------------------------------+ | Minimum Recommendations - 12GB VRAM | High End Recommendations – 48GB+ VRAM | +================================================================+================================================================+ || Use Cases: || Use case: | || Small to Average Project (<12GB Dataset>) || Average to Large Projects (>12GB Datasets) | || - Suitable for lightweight design / rendering workloads || - Suitable for full design / rendering workloads | || - Limited dataset size support || - Full dataset size support | || - Limited representation and simulation performance || - Full representation and simulation performance | || - Application consideration should be noted when recommending || - Application consideration should be noted when recommending | || GPU as multiple applications may be utilizing GPU resourcing || GPU as multiple applications may be utilizing GPU resourcing | +----------------------------------------------------------------+----------------------------------------------------------------+ .. note:: GPUs should be updated with the latest drivers to ensure optimum performance and available features within Omniverse are available. .. |mobile| replace:: /content/images/prod_deployment_mobile-workstation.png .. |desktop| replace:: /content/images/prod_deployment_desktop-workstation.png Workload and Topology Overview -------------------------------------------------------------------------------------------- It is critical to ensure that the workloads and workflows are understood and validated as they are a critical factor in determining the best profile and sizing to utilize within the entire environment. The reference architecture in this document outlines a workflow with Creators / Designers, Reviewers, and End Client as users across the various mobile workstations and workstations. Your specific environment will differ so a POC (Proof of Concept) is critical to ensure that the performance is acceptable for your set of users. Large Enterprise ----------------------- Sample Use Case - Non-Virtualized Topology (Bare Metal) ########################################################## .. image:: /content/images/prod_deployment_large-ent-diagram.png :align: center +---------------------------+--------------------------------------------+ | Topology Components | | +===========================+============================================+ || Remote Clients || - Mobile Workstation | || || - WorkStation | || || - Tablet | || || - Phone | +---------------------------+--------------------------------------------+ || Remoting Client Software || - Anyware PCoIP Client | || || - Microsoft Remote Desktop | || || - Connection (Protocol) | +---------------------------+--------------------------------------------+ | GPU | Recommended NVIDIA RTX GPU for Omniverse | +---------------------------+--------------------------------------------+ | Omniverse Collaboration | Enterprise Nucleus Server | +---------------------------+--------------------------------------------+ || Omniverse Applications || - Omniverse USD Composer | || || - Omniverse USD Presenter | +---------------------------+--------------------------------------------+ | Third-Party Applications | Omniverse Connector Supported Applications | +---------------------------+--------------------------------------------+ .. note:: Microsoft Remote Desktop Connection (Protocol) may have reduced color accuracy and GPU feature in comparison to HP Anywhere PCoIP technology.