NVIDIA L40 CNX vs AMD Steam Deck OLED GPU

GPU · Specs Compare

Products
GPU NVIDIA L40 CNX NVIDIA · 2022-10
GPU AMD Steam Deck OLED GPU AMD · 2023-11
Graphics Card
Release Date
Oct 2022
Nov 2023
Generation
Tesla Ada
Console GPU
Type
Professional
Game console
Bus Interface
PCIe 4.0 x16
—
Clock Speeds
Base Clock
1005 MHz
1000 MHz
Boost Clock
2475 MHz
1600 MHz
Memory Clock
2250 MHz
1375 MHz
Memory
Memory Size
24GB
16GB
Memory Type
GDDR6
LPDDR5
Memory Bus
384bit
128bit
Bandwidth
864.0GB/s
88.00GB/s
Render Config
SM Count
142
—
Shading Units
18176
512
TMUs
568
32
ROPs
192
16
Tensor Cores
568
—
RT Cores
142
8
L1 Cache
128 KB (per SM)
128 KB per Array
L2 Cache
48 MB
1024 KB
Compute Units
—
8
L3 Cache
—
8 MB
Theoretical Performance
Pixel Rate
475.2 GPixel/s
25.60 GPixel/s
Texture Rate
1406 GTexel/s
51.20 GTexel/s
FP16 (half)
89.97 TFLOPS
3.277 TFLOPS
FP32 (float)
89.97 TFLOPS
1.638 TFLOPS
FP64 (double)
1406 GFLOPS
102.4 GFLOPS
Graphics Processor
GPU Name
AD102
Sephiroth
GPU Variant
AD102-???-A1
—
Architecture
Ada Lovelace
RDNA 2.0
Foundry
TSMC
TSMC
Process Size
4 nm
6 nm
Transistors
76.3 billion
2.4 billion
Die Size
608 mm²
131 mm²
Board Design
TDP
300W
15W
Suggested PSU
700 W
—
Outputs
1x HDMI 2.13x DisplayPort 1.4a
1x USB Type-C
Power Connectors
1x 16-pin
—
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
2.0
Vulkan
1.3
1.2
CUDA
8.9
—
Shader Model
6.6
6.5
▲ Specs Compare Data sourced from official specifications and benchmark tests.