NVIDIA Releases NVIDIA RTX 2000 Ada Generation GPU

The new GPU delivers the company’s latest AI, graphics, and compute technology to compact workstations, taking better advantage of Generative AI’s sweeping changes, such as seamless editing of high-resolution videos and images and its use for realistic visual effects and content creation.

Today, in the NVIDIA blog, the company announced its new NVIDIA RTX 2000 Ada Generation GPU, which delivers the latest AI, graphics, and compute technology to compact workstations. Here are some highlights of the release and how the new GPU supports businesses as Generative AI sweeps across industries. The new GPUs are available now through global distribution partners such as Arrow Electronics, Ingram Micro, Leadtek, PNY, Ryoyo Electro and TD SYNNEX, and will be available from Dell Technologies, HP and Lenovo starting in April.

“AI and graphics are converging,” Rick Champagne, Director of Global Media & Entertainment Industry Strategy and Marketing, told AWN while discussing the evolution of AI features and their presence across virtually every major commercial application. “Studios are creating custom networks to accelerate common tasks and add capabilities they didn’t have before,” he adds. “Similarly, major commercial software providers like Adobe, Blackmagic Design, and Autodesk are all adding AI-based features to give their customers new creative options. To help AI startups, NVIDIA created the Inception program which now includes over 17,000 members, with many of those directly related to Media & Entertainment.”

Commenting on the economic benefit of adding the new GPUs to your production pipeline, Allen Bourgoyne, Director of Product Marketing, Enterprise Platforms at NVIDIA, adds, “When purchasing a workstation, it’s important that future proofing your investment is part of your consideration. You’re going to spend some money, and you want to get the most out of that investment. The Ada generation GPUs, with latest generation AI, rendering, FP32 and graphics technologies show significant increases in performance and capabilities, making them good investments. With AI playing an increasing role in professional workflows, we've added more GPU memory, to support an increase the number of simultaneous tools and applications used in your workflow. In a hybrid environment, you’ll be doing some AI locally, some in the cloud. We provide additional GPU memory in the latest generation of GPUs to provide room for your workflow to grow, if you're not there already, and with the performance improvements, this is a good value. It's something you'll be able to stick with for a while.”

The NVIDIA RTX 2000 Ada Generation GPU offers the following:

The latest AI, graphics, and compute technology in compact workstations up to 1.5x the performance of the previous-generation RTX A2000 12GB in professional workflows.
Optimized for creating 3D environments while laying a foundation for an AI-accelerated future.
Modern multi-application workflows, such as AI-powered tools, multi-display setups, and high-resolution content, put significant demands on GPU memory.
Offering 16GB of memory in the RTX 2000 Ada, users can access the latest technologies and tools.
Delivers realism in graphics with NVIDIA DLSS, for high-quality, photorealistic ray-traced images 3x+ faster.
An immersive experience for enterprise virtual-reality workflows.

Next-Generation RTX Technology:

The NVIDIA RTX 2000 Ada features the latest technologies in the NVIDIA Ada Lovelace GPU architecture, including:

Third-generation RT Cores: Up to 1.7x faster ray-tracing performance for high-fidelity, photorealistic rendering.
Fourth-generation Tensor Cores: Up to 1.8x AI throughput over the previous generation, with structured sparsity and FP8 precision to enable higher inference performance for AI-accelerated tools and applications.
CUDA cores: Up to 1.5x the FP32 throughput of the previous generation for significant performance improvements in graphics and compute workloads.
Power efficiency: Up to a 2x performance boost across professional graphics, rendering, AI, and compute workloads, all within the same 70W of power as the previous generation.
Immersive workflows: Up to 3x performance for virtual-reality workflows over the previous generation.
16GB of GPU memory: An expanded canvas enables users to tackle larger projects, along with support for error correction code memory to deliver greater computing accuracy and reliability for mission-critical applications.
DLSS 3: Delivers a breakthrough in AI-powered graphics, significantly boosting performance by generating additional high-quality frames.
AV1 encoder: Eighth-generation NVIDIA Encoder, aka NVENC, with AV1 support is 40% more efficient than H.264, enabling new possibilities for broadcasters, streamers, and video callers.

Content creators can edit high-resolution videos and images seamlessly and use AI for realistic visual effects and content creation assistance.

Champagne goes on to tell AWN, “Certainly, for AI running on the desktop, you'll get immediate performance improvements because of the latest gen Tensor cores. With the latest gen RT cores, you’ll also get major performance gains with GPU rendering, and combined with AI denoising, artists will get results back much faster. The RTX 2000 Ada gen also has dedicated silicon onboard for faster-than-real-time hardware encoding and decoding, which helps get video into the GPU to process it with AI.”

The latest RTX Enterprise Driver, available now to download, includes a range of features that enhance graphics workflows, along with support for the RTX 2000 Ada.

The AI-based, standard dynamic range to high dynamic range tone-mapping feature, called Video TrueHDR, expands the color range and brightness levels when viewing content in Chrome or Edge browser. It provides added support for Video Super Resolution and TrueHDR to the NVIDIA NGX software development kit, enhancement of low-resolution video quality sources, and easy conversion of SDR content to HDR.

Additional features in this release include:

TensorRT-LLM, an open-source library that optimizes and accelerates inference performance for the latest large language models on NVIDIA GPUs.
Video quality improvement and enhanced coding efficiency to video codecs through bit depth expansion techniques and new low-delay B frame.
Ability to offload work from the CPU to the GPU with the execute indirect extension NVIDIA API for quicker task completion.
Ability to display the GPU serial number in the NV Control Panel on desktops for easier registration to the NVIDIA AI Enterprise and NVIDIA Omniverse Enterprise platforms.

Additional information is available here.

Source: NVIDIA