NVIDIA L20 vs AMD Radeon Vega 8 Mobile
GPU · Specs Compare
Graphics Card
Release Date
Nov 2023
Jan 2021
Generation
Server Ada
Cezanne
Type
Desktop
Integrated
Bus Interface
PCIe 4.0 x16
IGP
Clock Speeds
Base Clock
1440 MHz
300 MHz
Boost Clock
2520 MHz
2000 MHz
Memory Clock
2250 MHz
System Shared
Memory
Memory Size
48GB
System Shared
Memory Type
GDDR6
System Shared
Memory Bus
384bit
System Shared
Bandwidth
864.0GB/s
System Dependent
Render Config
SM Count
92
—
Shading Units
11776
512
TMUs
368
32
ROPs
128
8
Tensor Cores
368
—
RT Cores
92
—
L1 Cache
128 KB (per SM)
—
L2 Cache
96 MB
—
Compute Units
—
8
Theoretical Performance
Pixel Rate
322.6 GPixel/s
16.00 GPixel/s
Texture Rate
927.4 GTexel/s
64.00 GTexel/s
FP16 (half)
59.35 TFLOPS
4.096 TFLOPS
FP32 (float)
59.35 TFLOPS
2.048 TFLOPS
FP64 (double)
927.4 GFLOPS
128.0 GFLOPS
Graphics Processor
GPU Name
AD102
Cezanne
GPU Variant
AD102
—
Architecture
Ada Lovelace
GCN 5.1
Foundry
TSMC
TSMC
Process Size
5 nm
7 nm
Transistors
76.3 billion
9.8 billion
Die Size
609 mm²
156 mm²
Board Design
TDP
275W
45W
Suggested PSU
600 W
—
Outputs
4x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-pin
None
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_1)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.4
1.2
CUDA
8.9
—
Shader Model
6.9
6.4
Benchmark
3DMark Time Spy
—
719
3DMark Time Spy Extreme
—
351
▲ Specs Compare
Data sourced from official specifications and benchmark tests.