Radeon Pro Vega 20 vs NVIDIA GeForce MX450 GDDR5
Radeon Pro Vega 20
NVIDIA GeForce MX450 GDDR5
|
1280 Shaders
4GB HBM2
1283MHz
|
896 Shaders
2GB GDDR5
1575MHz
|
|
Peak AI Performance
6.57 TFLOPS
FP16
|
Peak AI Performance
5.65 TFLOPS
FP16
|
|
FP32
3.28 TFLOPS
|
FP32
2.82 TFLOPS
|
|
FP16
6.57 TFLOPS
|
FP16
5.65 TFLOPS
|
|
Form Factor
Soldered
|
Form Factor
Soldered
|
|
TDP
50W
|
TDP
31W
|
Peak AI Performance
|
|
Radeon Pro Vega 20 - 6.57 TFLOPS FP16
x1.16
GeForce MX450 GDDR5 - 5.65 TFLOPS FP16
x1
FP32
|
|
Radeon Pro Vega 20 - 3.28 TFLOPS FP32
x1.16
GeForce MX450 GDDR5 - 2.82 TFLOPS FP32
x1
FP16
|
|
Radeon Pro Vega 20 - 6.57 TFLOPS FP16
x1.16
GeForce MX450 GDDR5 - 5.65 TFLOPS FP16
x1
|
|
Radeon Pro Vega 20 - 189.4GB/s
x2.96
GeForce MX450 GDDR5 - 64GB/s
x1
|
|
Radeon Pro Vega 20 - 50W
x1.61
GeForce MX450 GDDR5 - 31W
x1
|
GB6 OpenCL N/A
0%
|
|
|
GB6 Metal 35,050
14%
|
GB6 Metal N/A
0%
|
|
0%
|
0%
|
|
GB5 OpenCL N/A
0%
|
GB5 OpenCL 27,310
9%
|
|
GB5 CUDA N/A
0%
|
GB5 CUDA 29,245
8%
|
|
0%
|
0%
|
|
GB5 Vulkan N/A
0%
|
GB5 Vulkan 25,690
13%
|
|
OCT 2020.1 N/A
0%
|
OCT 2020.1 60
8%
|
|
0%
|
0%
|
|
Manufacturer
Apple
|
Manufacturer
NVIDIA
|
|
Chip Designer
AMD
|
Chip Designer
NVIDIA
|
|
Architecture
GCN 5
|
Architecture
Turing
|
|
Family
Radeon Pro Vega
|
Family
GeForce MX
|
|
Codename
Treasure
Vega 12
Variant
Vega 12 XTA
|
Codename
NV167
TU117
Variant
N18S-G5
|
|
Market Segment
Laptop
|
Market Segment
Laptop
|
|
Release Date
11/14/2018
|
Release Date
8/1/2020
|
|
Foundry
TSMC
|
Foundry
TSMC
|
|
Fabrication Node
28nm
|
Fabrication Node
12FFN
|
|
Die Size
125 mm²
|
Die Size
200 mm²
|
|
Transistor Count
1.6 Billion
|
Transistor Count
4.7 Billion
|
|
Transistor Density
12.40M/mm²
|
Transistor Density
23.50M/mm²
|
|
Form
Soldered
|
Form
Soldered
|
|
Shading Units
1280 Shaders
|
Shading Units
896 Shaders
|
|
Texture Mapping Units
80 TMUs
|
Texture Mapping Units
56 TMUs
|
|
Render Output Units
32 ROPs
|
Render Output Units
32 ROPs
|
|
-
-
|
Streaming Multiprocessors
14 SMs
|
|
Compute Units
20 CUs
|
-
-
|
|
-
-
|
Graphics Processing Clusters
2 GPCs
|
|
815MHz Base
1283MHz
|
1395MHz Base
1575MHz
|
|
Peak AI Performance
6.57 TFLOPS
FP16
|
Peak AI Performance
5.65 TFLOPS
FP16
|
|
FP16
6.57 TFLOPS
|
FP16
5.65 TFLOPS
|
|
FP32
3.28 TFLOPS
|
FP32
2.82 TFLOPS
|
|
FP64
210 GFLOPS
|
FP64
90 GFLOPS
|
|
Pixel Fillrate
41.056 GPixel/s
|
Pixel Fillrate
50.4 GPixel/s
|
|
Texture Fillrate
102.64 GTexel/s
|
Texture Fillrate
88.2 GTexel/s
|
|
L1
-
-
16KB/CU
|
L1
32KB/SM Tex
64KB/SM
-
|
|
L2
256KB Shared
|
L2
1MB Shared
|
|
4GB
HBM2
|
2GB
GDDR5
|
|
Bus Width
1024Bit
|
Bus Width
64Bit
|
|
Clock
740MHz
Transfer Rate
1.5GT/s
Bandwidth
189.4GB/s
|
Clock
2000MHz
Transfer Rate
8GT/s
Bandwidth
64GB/s
|
|
TDP
50W
|
TDP
31W
|
|
Max Resolution
4096x2160
|
Max Resolution
7680x4320
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
-
FreeSync
|
Variable Refresh Rate
G-Sync
FreeSync
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Supported
|
|
Multi Monitor Support
3
|
Multi Monitor Support
2
|
|
Content Protection
HDCP 1.4
|
Content Protection
HDCP 2.2
|
|
No Encoders
|
No Encoders
|
|
No Decoders
|
No Decoders
|
|
Direct X
12
Direct 3D
12_0
|
Direct X
12
Direct 3D
12_1
|
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
|
OpenGL
4.6
OpenCL
3.0
Vulkan
1.2
|
|
Shader Model
6.5
-
-
GFX
8
-
-
-
-
|
Shader Model
6.6
CUDA
7.5
-
-
PureVideo HD
VP10
VDPAU
Feature Set J
|
|
Not a Card
|
Not a Card
|
|
PCIe Version
3.0
PCIe Lanes
16
|
PCIe Version
4.0
PCIe Lanes
4
|
Copy Link