NVIDIA L40 vs AMD Radeon Pro WX Vega M GL
GPU Specs Compare
Graphics Card
Release Date
Oct 2022
Apr 2018
Generation
Tesla Ada
Vega
Type
Professional
Mobile
Bus Interface
PCIe 4.0 x16
IGP
Clock Speeds
Base Clock
735 MHz
931 MHz
Boost Clock
2490 MHz
1011 MHz
Memory Clock
2250 MHz
700 MHz
Memory
Memory Size
48GB
4GB
Memory Type
GDDR6
HBM2
Memory Bus
384bit
1024bit
Bandwidth
864.0GB/s
179.2GB/s
Render Config
SM Count
142
-
Shading Units
18176
1280
TMUs
568
80
ROPs
192
32
Tensor Cores
568
-
RT Cores
142
-
L1 Cache
128 KB (per SM)
16 KB (per CU)
L2 Cache
96 MB
1024 KB
Compute Units
-
20
Theoretical Performance
Pixel Rate
478.1 GPixel/s
32.35 GPixel/s
Texture Rate
1414 GTexel/s
80.88 GTexel/s
FP16 (half)
90.52 TFLOPS
2.588 TFLOPS
FP32 (float)
90.52 TFLOPS
2.588 TFLOPS
FP64 (double)
1414 GFLOPS
161.8 GFLOPS
Graphics Processor
GPU Name
AD102
Polaris 22
GPU Variant
AD102-895-A1
VegaM MGL XL
Architecture
Ada Lovelace
GCN 4.0
Foundry
TSMC
GlobalFoundries
Process Size
4 nm
14 nm
Transistors
76.3 billion
5 billion
Die Size
608 mm²
208 mm²
Board Design
TDP
300W
65W
Suggested PSU
700 W
-
Outputs
4x DisplayPort 1.4a
No outputs
Power Connectors
1x 16-pin
-
Graphics Features
DirectX
12 Ultimate (12_2)
12 (12_0)
OpenGL
4.6
4.6
OpenCL
3.0
2.1
Vulkan
1.3
1.2
CUDA
8.9
-
Shader Model
6.6
6.4
📊 Benchmark
Blender
3,901
-