Nvidia RTX 2000 Ada

Nvidia RTX 2000 Ada

$726
Ray Tracing
38 Gaming
40 Workstation
31 AI/ML
75 Energy Efficiency
38 NanoReview Final Score
0 Steel Nomad Lite Score

Technical Specifications

Performance

Architecture Ada Lovelace
GPU Codename AD107
Base Clock 1620 MHz
Boost Clock 2130 MHz
Shading Units 2816
Tensor Cores 88
Ray-tracing Cores 22
Compute Units (Pipelines) 22

Memory

Memory Type GDDR6
Memory Size 16 GB
Memory Clock 2000 MHz
Effective Memory Speed 16000 Mbps
Bus 128-bit

Graphics APIs

DirectX 12
Vulkan 1.3
OpenGL 4.6
OpenCL 3.0
CUDA 8.9
Ray Tracing Yes
DLSS DLSS 3
DisplayPort 1.4a

Technical

TGP
70 W
Fabrication Process 5 nm
Die Size 159 mm²
Transistor Count 18 billion
Interface PCIe 4.0 x8
Manufacturing TSMC
Vendor Nvidia
Build Discrete
Released February 12, 2022

Other Specifications

Margin of Error High
Background Blur 170.5 img/sec
Face Detection 102.8 img/sec
Horizon Detection 3.25 Gpixels/sec
Edge Detection 4.12 Gpixels/sec
Gaussian Blur 4.06 Gpixels/sec
Feature Matching 1.13 Gpixels/sec
Stereo Matching 353.4 Gpixels/sec
Particle Physics 12273.1 FPS
API OpenGL
G2D Mark 1090
DirectX 11 141 FPS
DirectX 12 72 FPS
GPU Compute 8018 Ops/s
Aztec Ruins Normal Tier 501.2 FPS
Car Chase 473.9 FPS
Manhattan 3.1.1 (1440p) 383.2 FPS
T-Rex 1908.9 FPS
Tessellation 2404.8 FPS
ALU 2 2355.1 FPS
Driver Overhead 2 280.2 FPS
OS Windows
Image Classification (SP) 6382
Image Segmentation (HP) 16489
Image Super Resolution (Q) 17694
Face Detection (HP) 32453
Pose Estimation (Q) 56937
Text Classification (SP) 3097
Machine Translation (HP) 4324
Object Detection (SP) 7656
Depth Estimation (Q) 29700
Style Transfer (SP) 116441
Framework ONNX
Backend DirectML
Launch price (MSRP) $649
Case Desktop
Purpose Professional
Segment Mid-range
Texture Mapping Units (TMUs) 88
Render Output Units (ROPs) 48
L1 Cache 128KB per cluster
L2 Cache 12MB shared
Instructions Per Cycle 2 IPC
Pixel Fill Rate 102 GPixel/s
Texture Fill Rate 187 GTexel/s
Transistor Density 113.21 MTr/mm²
ECC No