Home NVIDIA RTX 2000 Ada Generation

NVIDIA RTX 2000 Ada Generation

This is a GPU manufactured with TSMC 5nm process, based on Nvidia Ada Lovelace architecture and released on Feb 2024. It features 18.9 billion transistors, 2816 CUDA cores and 16GB GDDR6 memory, with 12MB L2 cache, theoretical performance of 12.00TFLOPS, with total power consumption of 70W.

Graphics Card

[Report Issues]
Release Date
Feb 2024
Generation
Quadro Ada
Type
Desktop
Bus Interface
PCIe 4.0 x8

Clock Speeds

[Report Issues]
Base Clock
1620 MHz
Boost Clock
2130 MHz
Memory Clock
2000 MHz

Memory

[Report Issues]
Memory Size
16GB
Memory Type
GDDR6
Memory Bus
128bit
Bandwidth
256.0GB/s

Render Config

[Report Issues]
SM Count
22
Shading Units
2816
TMUs
88
ROPs
48
Tensor Cores
88
RT Cores
22
L1 Cache
128 KB (per SM)
L2 Cache
12 MB

Theoretical Performance

[Report Issues]
Pixel Rate
102.2 GPixel/s
Texture Rate
187.4 GTexel/s
FP16 (half)
12.00 TFLOPS
FP32 (float)
12.00 TFLOPS
FP64 (double)
187.4 GFLOPS

Graphics Processor

[Report Issues]
GPU Name
AD107
Architecture
Ada Lovelace
Foundry
TSMC
Process Size
5 nm
Transistors
18.9 billion
Die Size
159 mm²

Board Design

[Report Issues]
TDP
70W
Suggested PSU
250 W
Outputs
4x mini-DisplayPort 1.4a
Power Connectors
None

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.9
Shader Model
6.7

Rankings

[Report Issues]
FP32 (float)
12.15 TFLOPS
NVIDIA TITAN Xp 12 GB GDDR5X
12.15 TFLOPS
12.03 TFLOPS
12 TFLOPS
11.8 TFLOPS
NVIDIA Tesla P40 24 GB GDDR5
11.76 TFLOPS
11.75 TFLOPS

Related Comparisons

© 2024 - TopCPU.net   Contact Us Privacy Policy