Report an Error

AMD Polaris 20

Default
Polaris 20
Polaris 20 XTR
Polaris 20 XTR
Die Shot
Fritzchens Fritz
Die Shot
Block Diagram
Block Diagram
AMD's Polaris 20 GPU uses the GCN 4.0 architecture and is made using a 14 nm production process at GlobalFoundries. With a die size of 232 mm² and a transistor count of 5,700 million it is a medium-sized chip. Polaris 20 supports DirectX 12.0 (Feature Level 12_0). It features 2304 shading units, 144 texture mapping units and 32 ROPs.

Graphics Processor

GPU Name
Polaris 20
Architecture
GCN 4.0
Foundry
GlobalFoundries
Process Size
14 nm
Transistors
5,700 million
Density
24.6M / mm²
Die Size
232 mm²
Released
Apr 18th, 2017

Graphics Features

DirectX
12.0 (12_0)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.1.96
Shader Model
6.0

Render Config

Shading Units
2304
TMUs
144
ROPs
32
Max. TDP
185 W

All GCN 4.0 GPUs

Graphics cards using the AMD Polaris 20 GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Boost Clock Memory Clock
AMD Radeon RX 580 Polaris 20 XTX 8 GB 2304 144 32 1257 MHz 1340 MHz 2000 MHz
AMD Radeon RX 570 Polaris 20 XL 4 GB 2048 128 32 1168 MHz 1244 MHz 1750 MHz
AMD Radeon Pro 580 Polaris 20 XTX 8 GB 2304 144 32 1100 MHz 1200 MHz 1695 MHz
AMD Radeon Pro 575 Polaris 20 XL 4 GB 2048 128 32 1096 MHz 1700 MHz
AMD Radeon Pro 570 Polaris 20 4 GB 1792 112 32 1000 MHz 1105 MHz 1700 MHz
AMD Radeon RX 580 Mobile Polaris 20M XT 8 GB 2304 144 32 1000 MHz 1077 MHz 2000 MHz
AMD Radeon RX 580X Polaris 20 XTX 8 GB 2304 144 32 1257 MHz 1340 MHz 2000 MHz
AMD Radeon RX 570X Polaris 20 XL 8 GB 2048 128 32 1168 MHz 1244 MHz 1750 MHz
AMD Radeon RX 580X Mobile Polaris 20M XT 8 GB 2304 144 32 1000 MHz 1077 MHz 2000 MHz
AMD Radeon RX 580 2048SP Polaris 20 XL 4 GB 2048 128 32 1168 MHz 1284 MHz 1750 MHz
AMD Radeon RX 580G Polaris 20 XTX 8 GB 2304 144 32 1257 MHz 1330 MHz 2000 MHz
AMD Radeon RX 570G Polaris 20 XL 8 GB 2048 128 32 1168 MHz 1234 MHz 1750 MHz

Polaris 20 GPU Notes

Codename: Ellesmere
CLRX Version: GCN 1.2
Graphics/Compute: GFX8 (gfx803)
Display Core Engine: 11.2
Unified Video Decoder: 6.3
Video Compression Engine: 3.4
ROCm Support