รายละเอียดเพิ่มเติม
Performance for Endless Possibilities
NVIDIA RTX™ 2000 Ada Generation, a powerful low-profile GPU brings the power of RTX in the reach of more professionals. With real-time ray tracing, AI-accelerated compute, and high-performance graphics, the RTX 2000 redefines the capabilities of compact workstations. Featuring the NVIDIA Ada Lovelace GPU architecture, it combines 22 third-generation RT Cores, 88 fourth-generation Tensor Cores, 2,816 CUDA® cores, and 16GB of GDDR6 graphics memory with ECC support. The RTX 2000 delivers breakthroughs in speed, efficiency, and power for demanding visual computing workflows, enabling creators, designers, and engineers to achieve new levels of productivity and innovation with this compact powerhouse.
*Performance testing with RTX 2000 Ada Generation and RTX A2000 12GB GPUs and Intel Core i9-12900K. Performance based on pre-release build, subject to change.
Performance Features
NVIDIA Ada Lovelace Architecture
NVIDIA RTX™ 2000 Ada Generation is a powerful dual-slot, low profile GPU solution offering high-performance real-time ray tracing, AI-accelerated compute, and professional graphics rendering for mainstream applications for the small form factor workstations in a compact and power efficient form factor.
Building upon major Streaming Multiprocessor (SM) enhancements, the NVIDIA Ada Lovelace architecture also provides more efficient cores, higher clocks, and a larger L2 cache than the previous Ampere architecture for more graphics performance, enhanced ray tracing operations, tensor matrix operations, and concurrent executions of single precision and inferencing operations.
CUDA Cores
The NVIDIA Ada Lovelace architecture-based CUDA cores bring up to 1.5X 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). The RTX 2000 enables two FP32 primary data paths, doubling peak FP32 operations.
3rd Generation RT Cores
Incorporating 3rd generation ray tracing engines, NVIDIA Ada Lovelace architecture-based GPUs provide incredible ray traced rendering performance. A single RTX 2000 board 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 DXR and Vulkan ray tracing, systems based on the RTX 2000 will power truly interactive design workflows to provide immediate feedback for unprecedented levels of productivity. The RTX 2000 is up to 65% faster in ray tracing compared to the previous generation. This technology also speeds up the rendering of ray-traced motion blur for faster results with greater visual accuracy.
4th Generation Tensor Cores
Purpose-built for deep learning matrix arithmetic at the heart of neural network training and inferencing functions, the RTX 2000 includes enhanced Tensor Cores that accelerate more datatypes and includes a new Fine-Grained Structured Sparsity feature that delivers up to1.5 x throughput for tensor matrix operations compared to the previous generation. New Tensor Cores will accelerate new FP8 precision modes. Independent floating-point and integer data paths allow more efficient execution of workloads using a mix of computation and addressing calculations.
PCIe Gen 4
PCI Express Gen 4 (PCIe Gen 4) provides double the bandwidth of PCIe Gen 3, improving data-transfer speeds from CPU memory for data-intensive tasks like AI and data science. RTX 2000 Ada Generation utilizes a full length PCIe Gen 4 x8 interface.
Higher Speed GDDR6 Memory
RTX 2000 Ada Generation features 16GB of fast GDDR6 graphics memory running at 7GHz. With larger memory than the previous generation, the RTX 2000 provides and ideal memory size to address datasets and models in latency-sensitive professional applications.
Error Correcting Code (ECC) on Graphics Memory
Error Correction Code (ECC) on graphics memory detects and corrects data corruption in memory, meeting strict data integrity requirements for mission-critical applications with uncompromised computing accuracy and reliability for workstations.
5th Generation NVDEC Engine (1)
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.
8th Generation NVENC Engine
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 RTX 2000 provides better encoding quality than software-based x264 encoders. The RTX 2000 incorporate 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.
Graphics Preemption
Pixel-level preemption provides more granular control to better support time-sensitive tasks such as VR motion tracking.
Compute Preemption
Preemption at the instruction level provides finer-grain control over compute tasks to prevent long-running applications from either monopolizing system resources or timing out.
NVIDIA RTX IO
Accelerating GPU-based lossless decompression performance by up to 100x and 20x lower CPU utilization compared to traditional storage APIs using Microsoft’s DirectStorage for Windows API. RTX IO moves data from the storage to the GPU in a more efficient, compressed form, improving I/O performance.
(1) This feature requires implementation by software applications, and it is not a stand-alone utility. Please contact rtxprohelp@nvidia.com for details on availability.
Display Features
NVIDIA® Quadro® Mosaic Technology
Transparently scale the desktop and applications across up to 4 GPUs and 16 displays from a single workstation while delivering full performance and image quality.
DisplayPort 1.4a
Support up to four 5K monitors @ 60Hz, or dual 8K displays @ 60Hz per card. RTX 2000 Ada Generation supports HDR color for 4K @ 60Hz for 10/12b HEVC decode and up to 4K @ 60Hz for 10b HEVC encode. Each DisplayPort connector can drive ultra-high resolutions of 4096×2160 @ 120 Hz with 30-bit color.
NVIDIA RTX™ Desktop Manager
Gain unprecedented end-user control of the desktop experience for increased productivity in single large display or multi-display environments, especially in the current age of large, widescreen displays.
OpenGL Quad Buffered Stereo Support
Provide a smooth and immersive 3D Stereo experience for professional applications.
Ultra-High-Resolution Desktop Support
Get more Mosaic topology choices with high resolution displays devices with a 32K Max desktop size.
Software Support
NVIDIA® RTX™ Experience
NVIDIA RTX Experience delivers a suite of productivity tools to your desktop workstation, including desktop recording in up to 8K, automatic alerts for the latest NVIDIA RTX Enterprise driver updates, and access gaming features. The application is available for download here https://www.nvidia.com/en-us/design-visualization/software/rtx-experience/
Software Optimized for AI
Deep learning frameworks such as Caffe2, MXNet, CNTK, TensorFlow, and others deliver dramatically faster training times and higher multi-node training performance. GPU accelerated libraries such as cuDNN, cuBLAS, and TensorRT delivers higher performance for both deep learning inference and High-Performance Computing (HPC) applications.
NVIDIA® CUDA® Parallel Computing Platform
Natively execute standard programming languages like C/C++ and Fortran, and APIs such as OpenCL, OpenACC and Direct Compute to accelerates techniques such as ray tracing, video and image processing, and computation fluid dynamics.
Unified Memory
A single, seamless 49-bit virtual address space allows for the transparent migration of data between the full allocation of CPU and GPU memory.
NVIDIA Enterprise-Management Tools
Maximize system uptime, seamlessly manage wide-scale deployments and remotely control graphics and display settings for efficient operations.
