Radeon RX Vega M GL and L40 CNX - video card comparison
Radeon RX Vega M GL
L40 CNX
Architecture
GCN 4.0 (2016−2020)
Ada Lovelace
GPU code name
Polaris 22
AD102
Market segment
Laptop
Desktop
Release date
February 2018
October 2022
Interface
IGP
PCIe 4.0 x16
Supplementary power connectors
-
1x 16-pin
Boost clock speed
1011 MHz
2475 MHz
Core clock speed
931 MHz
-
Floating-point performance
2,588 gflops
-
Manufacturing process technology
14 nm
4 nm
Number of transistors
5,000 million
76,300 million
Pipelines / CUDA cores
1280
18176
Power consumption (TDP)
65 Watt
300 Watt
Texture fill rate
80.88
1,406
Memory type
HBM2
GDDR6
Maximum RAM amount
4 GB
24 GB
Memory bus width
1024 Bit
384 Bit
Memory clock speed
1400 MHz
18 GB/s
Memory bandwidth
179.2 GB/s
864.0 GB/s
Shared memory
-
-
Display Connectors
No outputs
1x HDMI 2.1, 3x DisplayPort 1.4a
HDMI
-
+
DirectX
12 (12_0)
12 Ultimate (12_2)
CUDA
-
8.9
OpenCL
2.0
3.0
OpenGL
4.6
4.6
Shader Model
6.4
6.7
Vulkan
1.2.131
1.3