AMD Polaris 31
AMD's Polaris 31 GPU uses the GCN 4.0 architecture and is made using a 14 nm production process at GlobalFoundries. With a die size of 123 mm² and a transistor count of 3,000 million it is a small chip. Polaris 31 supports DirectX 12 (Feature Level 12_0). For GPU compute applications, OpenCL version 2.1 can be used. It features 896 shading units, 56 texture mapping units and 16 ROPs.
Further reading:
Polaris Architecture Whitepaper

Graphics Processor
- GPU Name
- Polaris 31
- Architecture
- GCN 4.0
- Foundry
- GlobalFoundries
- Process Size
- 14 nm
- Transistors
- 3,000 million
- Density
- 24.4M / mm²
- Die Size
- 123 mm²
- Released
- Jan 9th, 2019
Graphics Features
- DirectX
- 12 (12_0)
- OpenGL
- 4.6
- OpenCL
- 2.1
- Vulkan
- 1.2
- Shader Model
- 6.4
- Compute
- GFX8
- ROCm
- Yes
Render Config
- Shading Units
- 896
- TMUs
- 56
- ROPs
- 16
- Compute Units
- 14
- ACEs
- 4
- HWSs
- 2
- SEs
- 2
- L1 Cache
- 16 KB per CU
- L2 Cache
- 1024 KB
- Max. TDP
- 65 W
All GCN 4.0 GPUs
AMD GPU Architecture History
Graphics cards using the AMD Polaris 31 GPU
Name | Chip | Memory | Shaders | TMUs | ROPs | GPU Clock | Memory Clock |
---|---|---|---|---|---|---|---|
AMD Radeon RX 560X Mobile | Polaris 31 MXL | 4 GB | 896 | 56 | 16 | 1223 MHz | 1750 MHz |
Polaris 31 GPU Notes
Architecture Codename: Arctic Islands Codename: Baffin CLRX Version: GCN 1.2 Graphics/Compute: GFX8 (gfx803) Display Core Engine: 11.2 Unified Video Decoder: 6.3 Video Compression Engine: 3.4 |