RTX 2000 Ada Generation Features: NVIDIA Ada Lovelace Architecture The NVIDIA RTX™ 2000 Ada Generation, based on the Ada Lovelace architecture, gives professionals the power of the latest RTX technology for accelerated ray tracing and AI to drive advanced visualization, creative, and design workflows for mainstream applications. CUDA Cores The NVIDIA Ada Lovelace architecture-based CUDA Cores deliver 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 single-precision compute for workloads like desktop simulation for CAE. Third-Generation RT Cores Third-generation RT cores in the RTX 2000 provide up to 1.7X faster ray tracing performance over the previous generation, significantly boosting rendering speeds for content creation, design reviews, and virtual manufacturing prototyping. Enhanced RT cores and Shader Execution Reordering (SER) technology optimize shader performance, further accelerating ray traced image rendering. Fourth-Generation Tensor Cores Fourth-generation Tensor Cores provide support for the new FP8 data format for inference providing up to 1.8X higher throughput for tensor matrix operations than the previous generation and reducing data memory usage by half compared to the FP16 data format for more efficient execution of workloads using a mix of computation and addressing calculations. PCIe Gen 4 The RTX 2000 supports PCIe Gen 4, which doubles the bandwidth of PCIe Gen3 from 15.75GB/sec to 31.5 GB/sec for x8 connections, improving data transfer speeds from CPU memory for data-intensive tasks such as AI, data science, and creating 3D models from large datasets. RTX 2000 Ada Generation utilizes a full-length PCIe Gen 4 x8 interface. Higher Speed GDDR6 Memory The RTX 2000 features 16GB of GDDR6 memory, providing the memory needed for rendering, data science, engineering simulation, and other GPU memory-intensive applications. Support for ECC memory delivers uncompromised computing accuracy and reliability for mission-critical applications. Error Correcting Code (ECC) on Graphics Memory 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. Fifth-Generation NVDEC Engine NVDEC is well-suited for transcoding and video playback applications for real-time decoding. The following codecs are supported for hardware-accelerated decoding: MPEG-2, VC-1, H.264 (AVCHD), H.265 (HEVC), VP8, VP9, and AV1. Eighth-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 incorporates 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 new DirectStorage for Windows API. RTX IO moves data from the storage to the GPU in a more efficient, compressed form, and improves I/O performance. Specifications: Product NVIDIA RTX™ 2000 Ada Generation Architecture NVIDIA Ada Generation Architecture Process Size 4N NVIDIA Custom Process Transistors 19.9 Billion Die Size 159 mm CUDA Cores 2816 Tensor Cores 88 RT Cores 22 Single Precision Performance 12 TFLOPS RT Core Performance 27.7 TFLOPS Tensor Performance 191.9 TFLOPS GPU Memory 16 GB GDDR6 with ECC Memory Interface 128-bit Memory Bandwidth 224 GB/sec Display Connectors 4x Mini DisplayPort 1.4a NVENC | NVDEC 1x | 1x (+ AV1 encode & decode) System Interface PCI Express 4.0 x8 NVLink Not Supported Form Factor 2.7” H x 6.6” L Dual Slot Thermal Solution Blower Active Fan Maximum Power Consumption 70 W Max Digital Resolution 7680 x 4320 x36 bpp at 60 Hz