Intel Arc A350M vs Radeon Pro Vega 20

Intel Arc A350M
Radeon Pro Vega 20
768 Shaders
4GB GDDR6
1150MHz
1280 Shaders
4GB HBM2
1283MHz
Peak AI Performance
56.53 TOPS
INT4 Tensor
Peak AI Performance
6.57 TFLOPS
FP16
FP32
1.77 TFLOPS
FP32
3.28 TFLOPS
FP16
3.53 TFLOPS
FP16
6.57 TFLOPS
Form Factor
Soldered
-
Form Factor
Soldered
-
TDP
25W
TDP
50W
-
-
-
-
-
-
-
-
-
-
GB6 Metal N/A
0%
GB6 Vulkan N/A
0%
GB5 OpenCL 7,630
2%
GB5 OpenCL N/A
0%
GB5 CUDA N/A
0%
GB5 CUDA N/A
0%
GB5 Metal N/A
0%
GB5 Metal N/A
0%
GB5 Vulkan N/A
0%
GB5 Vulkan N/A
0%
OCT 2020.1 N/A
0%
OCT 2020.1 N/A
0%
OCT Metal 25
4%
OCT Metal N/A
0%
Peak AI Performance
56.53 TOPS
INT4 Tensor
Peak AI Performance
6.57 TFLOPS
FP16
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
FP16
3.53 TFLOPS
-
-
14.13 TFLOPS Tensor (FP32 Accumulate)
-
FP16
6.57 TFLOPS
-
-
-
-
FP32
1.77 TFLOPS
-
-
FP32
3.28 TFLOPS
-
-
FP64
440 GFLOPS
-
FP64
210 GFLOPS
-
BF16
-
14.13 TFLOPS Tensor
-
-
-
-
-
-
-
-
-
-
-
INT4
56.53 TOPS Tensor
-
-
-
-
INT8
-
28.26 TOPS Tensor
-
-
-
-
-
-
-
-
-
-
-
-
-
Pixel Fillrate
27.6 GPixel/s
Pixel Fillrate
41.056 GPixel/s
-
-
-
-
Texture Fillrate
55.2 GTexel/s
Texture Fillrate
102.64 GTexel/s
Manufacturer
Intel
Manufacturer
Apple
Chip Designer
Intel
Chip Designer
AMD
Architecture
Alchemist
Architecture
GCN 5
Family
Arc A
Family
Radeon Pro Vega
Codename
Xe HPG
ACM-G11
Variant
DG2-128
Codename
Treasure
Vega 12
Variant
Vega 12 XTA
Market Segment
Laptop
Market Segment
Laptop
Release Date
3/30/2022
Release Date
11/14/2018
Foundry
TSMC
-
Foundry
TSMC
-
Fabrication Node
N6
-
Fabrication Node
28nm
-
Die Size
157 mm²
-
Die Size
125 mm²
-
Transistor Count
7.2 Billion
-
Transistor Count
1.6 Billion
-
Transistor Density
45.86M/mm²
-
Transistor Density
12.40M/mm²
-
Form
Soldered
Form
Soldered
Shading Units
768 Shaders
-
Shading Units
1280 Shaders
-
Texture Mapping Units
48 TMUs
Texture Mapping Units
80 TMUs
Render Output Units
24 ROPs
Render Output Units
32 ROPs
Tensor Cores
96 T-Cores
-
-
Ray-Tracing Cores
6 RT-Cores
-
-
-
-
-
-
-
-
Compute Units
20 CUs
Execution Units
96 EUs
-
-
Graphics Processing Clusters
6 GPCs
-
-
-
-
300MHz Base
1150MHz
-
-
815MHz Base
1283MHz
-
-
-
-
L1
-
-
-
Unknown
L1
-
-
16KB/CU
-
L2
4MB Shared
L2
256KB Shared
-
-
-
-
-
-
4GB
GDDR6
-
4GB
HBM2
-
Bus Width
64Bit
Bus Width
1024Bit
Clock
1750MHz
Transfer Rate
14GT/s
Bandwidth
112GB/s
Clock
740MHz
Transfer Rate
1.5GT/s
Bandwidth
189.4GB/s
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
TDP
25W
TDP
50W
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
No Ports
Max Resolution
7680x4320
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
4
Multi Monitor Support
3
-
-
Content Protection
HDCP 1.4
Model
Arc
No Encoders
-
Codec
-
-
-
-
-
-
-
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Model
Arc
No Decoders
Codec
-
MPEG-2
-
JPEG
-
-
VP9
-
AVC (H.264)
HEVC (H.265)
-
AV1
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Direct X
12
Direct 3D
12_2
Direct X
12
Direct 3D
12_0
OpenGL
4.6
OpenCL
3.0
Vulkan
1.3
OpenGL
4.6
OpenCL
2.1
Vulkan
1.2
Shader Model
6.6
-
-
-
-
-
-
-
-
Shader Model
6.5
-
-
GFX
8
-
-
-
-
Not a Card
-
-
-
Not a Card
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
PCIe Version
4.0
PCIe Lanes
8
-
-
PCIe Version
3.0
PCIe Lanes
16
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
-
Change Comparison