AMD AeroBox GPU vs NVIDIA L40 CNX
GPU · Specs Compare
Graphics Card
Release Date
Mar 2020
Oct 2022
Generation
Console GPU
Tesla Ada
Type
Game console
Professional
Bus Interface
—
PCIe 4.0 x16
Clock Speeds
Base Clock
935 MHz
1005 MHz
Boost Clock
985 MHz
2475 MHz
Memory Clock
1066 MHz
2250 MHz
Memory
Memory Size
8GB
24GB
Memory Type
DDR3
GDDR6
Memory Bus
256bit
384bit
Bandwidth
68.22GB/s
864.0GB/s
Render Config
Compute Units
14
—
Shading Units
896
18176
TMUs
56
568
ROPs
16
192
SM Count
—
142
Tensor Cores
—
568
RT Cores
—
142
L1 Cache
—
128 KB (per SM)
L2 Cache
—
48 MB
Theoretical Performance
Pixel Rate
15.76 GPixel/s
475.2 GPixel/s
Texture Rate
55.16 GTexel/s
1406 GTexel/s
FP16 (half)
3.530 TFLOPS
89.97 TFLOPS
FP32 (float)
1.765 TFLOPS
89.97 TFLOPS
FP64 (double)
110.3 GFLOPS
1406 GFLOPS
Graphics Processor
GPU Name
Kryptos
AD102
Architecture
GCN 1.0
Ada Lovelace
Foundry
TSMC
TSMC
Process Size
16 nm
4 nm
Transistors
Unknown
76.3 billion
Die Size
Unknown
608 mm²
GPU Variant
—
AD102-???-A1
Board Design
TDP
100W
300W
Outputs
No outputs
1x HDMI 2.13x DisplayPort 1.4a
Suggested PSU
—
700 W
Power Connectors
—
1x 16-pin
Graphics Features
DirectX
12 (11_1)
12 Ultimate (12_2)
OpenGL
N/A
4.6
OpenCL
1.2
3.0
Vulkan
1.2
1.3
Shader Model
5.1
6.6
CUDA
—
8.9
▲ Specs Compare
Data sourced from official specifications and benchmark tests.