NVIDIA L40 CNX
The NVIDIA L40 CNX is a GPU manufactured by NVIDIA, built on NVIDIA's officially announced 4 nm process technology, released in October 2022. This graphics card is equipped with 24GB GDDR6 memory, suitable for gaming and professional graphics applications.
Process Size
4 nm
Tensor Cores
568
Boost Clock
2475 MHz
Base Clock
1005 MHz
TDP
300W
L1 Cache
128 KB (per SM)
Memory Size
24GB
Memory Type
GDDR6
Bandwidth
864.0GB/s
Shader Model
6.6
Graphics Card
Release Date
Oct 2022
Generation
Tesla Ada
Type
Professional
Bus Interface
PCIe 4.0 x16
Clock Speeds
Base Clock
1005 MHz
Boost Clock
2475 MHz
Memory Clock
2250 MHz
Memory
Memory Size
24GB
Memory Type
GDDR6
Memory Bus
i
384bit
Bandwidth
i
864.0GB/s
Render Config
SM Count
i
142
Shading Units
i
18176
TMUs
i
568
ROPs
i
192
Tensor Cores
i
568
RT Cores
142
L1 Cache
128 KB (per SM)
L2 Cache
48 MB
Theoretical Performance
Pixel Rate
i
475.2 GPixel/s
Texture Rate
i
1406 GTexel/s
FP16 (half)
i
89.97 TFLOPS
FP32 (float)
i
89.97 TFLOPS
FP64 (double)
i
1406 GFLOPS
Graphics Processor
GPU Name
AD102
GPU Variant
AD102-???-A1
Architecture
Ada Lovelace
Foundry
TSMC
Process Size
4 nm
Transistors
76.3 billion
Die Size
608 mm²
Board Design
TDP
300W
Suggested PSU
700 W
Outputs
1x HDMI 2.13x DisplayPort 1.4a
Power Connectors
1x 16-pin
Graphics Features
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
i
1.3
CUDA
8.9
Shader Model
6.6