Radeon Pro 575 vs Radeon Pro Vega 20
Radeon Pro 575
Radeon Pro Vega 20
|
2048 Shaders
4GB GDDR5
1096MHz
|
1280 Shaders
4GB HBM2
1283MHz
|
|
Peak AI Performance
4.49 TFLOPS
FP16
|
Peak AI Performance
6.57 TFLOPS
FP16
|
|
FP32
4.49 TFLOPS
|
FP32
3.28 TFLOPS
|
|
FP16
4.49 TFLOPS
|
FP16
6.57 TFLOPS
|
|
Form Factor
Soldered
|
Form Factor
Soldered
|
|
TDP
115W
|
TDP
50W
|
Peak AI Performance
|
|
Radeon Pro 575 - 4.49 TFLOPS FP16
x1
Radeon Pro Vega 20 - 6.57 TFLOPS FP16
x1.46
FP32
|
|
Radeon Pro 575 - 4.49 TFLOPS FP32
x1.37
Radeon Pro Vega 20 - 3.28 TFLOPS FP32
x1
FP16
|
|
Radeon Pro 575 - 4.49 TFLOPS FP16
x1
Radeon Pro Vega 20 - 6.57 TFLOPS FP16
x1.46
|
|
Radeon Pro 575 - 217.6GB/s
x1.15
Radeon Pro Vega 20 - 189.4GB/s
x1
|
|
Radeon Pro 575 - 115W
x2.3
Radeon Pro Vega 20 - 50W
x1
|
|
Radeon Pro 575 - GB6 OpenCL 36,140
x1.49
Radeon Pro Vega 20 - GB6 OpenCL 24,325
x1
|
Manufacturer
Apple
|
Manufacturer
Apple
|
|
Chip Designer
AMD
|
Chip Designer
AMD
|
|
Architecture
GCN 4
|
Architecture
GCN 5
|
|
Family
Radeon Pro
|
Family
Radeon Pro Vega
|
|
Codename
Ellesmere
Polaris 20
Variant
Polaris 20 XLA
|
Codename
Treasure
Vega 12
Variant
Vega 12 XTA
|
|
Market Segment
Laptop
|
Market Segment
Laptop
|
|
Release Date
6/6/2017
|
Release Date
11/14/2018
|
|
Foundry
GlobalFoundries
|
Foundry
TSMC
|
|
Fabrication Node
14LPP
|
Fabrication Node
28nm
|
|
Die Size
232 mm²
|
Die Size
125 mm²
|
|
Transistor Count
5.7 Billion
|
Transistor Count
1.6 Billion
|
|
Transistor Density
24.57M/mm²
|
Transistor Density
12.40M/mm²
|
|
Form
Soldered
|
Form
Soldered
|
|
Shading Units
2048 Shaders
|
Shading Units
1280 Shaders
|
|
Texture Mapping Units
128 TMUs
|
Texture Mapping Units
80 TMUs
|
|
Render Output Units
32 ROPs
|
Render Output Units
32 ROPs
|
|
Compute Units
32 CUs
|
Compute Units
20 CUs
|
|
-
1096MHz
|
815MHz Base
1283MHz
|
|
Peak AI Performance
4.49 TFLOPS
FP16
|
Peak AI Performance
6.57 TFLOPS
FP16
|
|
FP16
4.49 TFLOPS
|
FP16
6.57 TFLOPS
|
|
FP32
4.49 TFLOPS
|
FP32
3.28 TFLOPS
|
|
FP64
280 GFLOPS
|
FP64
210 GFLOPS
|
|
Pixel Fillrate
35.072 GPixel/s
|
Pixel Fillrate
41.056 GPixel/s
|
|
Texture Fillrate
140.288 GTexel/s
|
Texture Fillrate
102.64 GTexel/s
|
|
L1
16KB/CU
|
L1
16KB/CU
|
|
L2
2MB Shared
|
L2
256KB Shared
|
|
4GB
GDDR5
|
4GB
HBM2
|
|
Bus Width
256Bit
|
Bus Width
1024Bit
|
|
Clock
1700MHz
Transfer Rate
6.8GT/s
Bandwidth
217.6GB/s
|
Clock
740MHz
Transfer Rate
1.5GT/s
Bandwidth
189.4GB/s
|
|
TDP
115W
|
TDP
50W
|
|
Max Resolution
5120x2880
|
Max Resolution
4096x2160
|
|
Max Resolution Refresh Rate
60Hz
|
Max Resolution Refresh Rate
60Hz
|
|
Variable Refresh Rate
FreeSync
|
Variable Refresh Rate
FreeSync
|
|
Display Stream Compression (DSC)
Not Supported
|
Display Stream Compression (DSC)
Not Supported
|
|
Multi Monitor Support
3
|
Multi Monitor Support
3
|
|
Content Protection
HDCP 2.2
|
Content Protection
HDCP 1.4
|
|
Model
VCE 3.0
|
No Encoders
-
|
|
Codec
AVC (H.264)
HEVC (H.265)
|
-
-
-
|
|
Model
UVD 6.3
|
No Decoders
|
|
Codec
MPEG-1
MPEG-2
MPEG-4
JPEG
VC-1
AVC (H.264)
HEVC (H.265)
|
-
-
-
-
-
-
-
|
|
Direct X
12
Direct 3D
12_0
|
Direct X
12
Direct 3D
12_0
|
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.3
|
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
|
|
Shader Model
6.7
GFX
8
|
Shader Model
6.5
GFX
8
|
|
Not a Card
|
Not a Card
|
|
PCIe Version
3.0
PCIe Lanes
16
|
PCIe Version
3.0
PCIe Lanes
16
|
Copy Link