Home NVIDIA L40 CNX

NVIDIA L40 CNX

This is a GPU manufactured with TSMC 4nm process, based on Nvidia Ada Lovelace architecture and released on Oct 2022. It features 76.3 billion transistors, 18176 CUDA cores and 24GB GDDR6 memory, with 48MB L2 cache, theoretical performance of 89.97TFLOPS, with total power consumption of 300W.

Graphics Card

[Report Issues]
Release Date
Oct 2022
Generation
Tesla Ada
Type
Professional
Bus Interface
PCIe 4.0 x16

Clock Speeds

[Report Issues]
Base Clock
1005 MHz
Boost Clock
2475 MHz
Memory Clock
2250 MHz

Memory

[Report Issues]
Memory Size
24GB
Memory Type
GDDR6
Memory Bus
384bit
Bandwidth
864.0GB/s

Render Config

[Report Issues]
SM Count
142
Shading Units
18176
TMUs
568
ROPs
192
Tensor Cores
568
RT Cores
142
L1 Cache
128 KB (per SM)
L2 Cache
48 MB

Theoretical Performance

[Report Issues]
Pixel Rate
475.2 GPixel/s
Texture Rate
1406 GTexel/s
FP16 (half)
89.97 TFLOPS
FP32 (float)
89.97 TFLOPS
FP64 (double)
1406 GFLOPS

Graphics Processor

[Report Issues]
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

[Report Issues]
TDP
300W
Suggested PSU
700 W
Outputs
1x HDMI 2.1
3x DisplayPort 1.4a
Power Connectors
1x 16-pin

Graphics Features

[Report Issues]
DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
CUDA
8.9
Shader Model
6.6

Rankings

[Report Issues]
FP32 (float)
91.06 TFLOPS
91.06 TFLOPS
NVIDIA L40 48 GB GDDR6
90.52 TFLOPS
NVIDIA L40 CNX 24 GB GDDR6
89.97 TFLOPS
NVIDIA L40G 24 GB GDDR6
89.97 TFLOPS
88.45 TFLOPS
82.58 TFLOPS

Related Comparisons

Related News

© 2024 - TopCPU.net   Contact Us Privacy Policy