NVIDIA has just announced its new RTX 2000 Ada workstation GPU, which offers 1.5x the performance of the previous-gen RTX A2000 12GB workstation GPU (and 4GB more framebuffer, with 16GB GDDR6 ECC memory).
The new NVIDIA RTX 2000 Ada workstation GPU features the AD107 GPU with 2816 CUDA cores, 16GB of GDDR6 ECC memory on a 128-bit memory bus and PCIe 4.0 x8 lanes. Not bad, considering NVIDIA is charging $625 (before taxes) for the workstation GPU.
Still, there is up to 1.7x faster ray-tracing performance, up to 1.8x AI throughput over the previous-gen workstation GPU, up to 2x the performance boost across professional graphics, rendering, AI, and compute workloads, all within the same 70W TDP as the previous-gen workstation GPU.
NVIDIA's new RTX 2000 Ada workstation GPU features:
- 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.
NVIDIA's new RTX 2000 Ada workstation GPU made it into the hands of Dassault Systèmes for its SOLIDWORKS applications, Rob Wolkers Design and Engineering, and WSP.
Mark Kauffman, assistant vice president and technical lead at WSP said: "The new RTX 2000 Ada Generation GPU boasts impressive features compared to previous generations, with a compact design that offers exceptional performance and versatility. Its 16 GB of RAM is a game-changer, enabling smooth loading of asset-heavy content, and its ability to run applications like Autodesk 3ds Max, Adobe After Effects and Unreal Engine, as well as support path tracing, expands my creative possibilities".
Olivier Zegdoun, graphics applications research and development director for SOLIDWORKS at Dassault Systèmes talked about NVIDIA's new RTX 2000 Ada workstation GPU, where he said: "The new NVIDIA RTX 2000 Ada-with its higher-efficiency, next-generation architecture, low power consumption and large frame buffer-will benefit SOLIDWORKS users. It delivers excellent performance for designers and engineers to accelerate the development of innovative product experiences with full-model fidelity, even with larger datasets".
Rob Wolkers, owner and senior industrial design engineer at Rob Wolkers Design and Engineering, added: "Today's design and visualization workflows demand more advanced compute and horsepower. Equipped with next-generation architecture and a large frame buffer, the RTX 2000 Ada Generation GPU improves productivity in my everyday industrial design and engineering workflows, allowing me to work with large datasets in full fidelity and generate renders with more lighting and reflection scenarios 3x faster".