NVIDIA AD102 Graphics Processing Unit (GPU)

Specs based on NVIDIA GeForce RTX 4090
Overview
Manufacturer
NVIDIA
Release Date
October 12th, 2022
Graphics Processing Unit
Architecture
Ada
Fabrication Process
4 nm
Die Size
608 mm2
Transistors Count
76.3B
Transistors Density
125.5M TRAN/mm2
Tensor Cores
512
RT Cores
128
CUDAs
16384
SM
128
TMUs
512
ROPs
176
Clocks
Base Clock
2235 MHz
Memory Configuration
Memory Size
24576 MB
Memory Type
GDDR6X
Memory Bus Width
384-bit
Memory Bandwidth
1,008.0 GB/s
Performance
Pixel Fillrate
443.5 GPixels/s
Texture Fillrate
1.3 TTexel/s
SPFP Performance
82.6 TFLOPS
Performance per W
183.5 GFLOPS/W
Performance per mm2
135.8 GFLOPS/mm2
Physical
Interface
PCI-Express 4.0 x16
Typical Thermal Design Power
450 W
SLI Support
Unsupported
API Support
DirectX
12.2
Vulkan
1.2
OpenGL
4.6
OpenCL
3.0




 ModelGPU ModelUnified CoresBoost ClockMemory ClockMemory Config.
NVIDIA L40 AD102 TBC TBC TBC TBC
NVIDIA RTX A6000 ADA AD102 TBC TBC TBC TBC
NVIDIA GeForce RTX 4090 Ti AD102-350 TBC TBC TBC TBC
NVIDIA GeForce RTX 4090 AD102-300
 
16384
 
2520 MHz
 
21 Gbps
 
24 GB G6X 384b