Report an Error

AMD Polaris 23

Default
Polaris 23
AMD's Polaris 23 GPU uses the GCN 4.0 architecture and is made using a 14 nm production process at GlobalFoundries. With a die size of 103 mm² and a transistor count of 2,200 million it is a small chip. Polaris 23 supports DirectX 12 (Feature Level 12_0). For GPU compute applications, OpenCL version 2.1 can be used. It features 640 shading units, 40 texture mapping units and 16 ROPs.
Further reading: Polaris Architecture Whitepaper

Graphics Processor

GPU Name
Polaris 23
Architecture
GCN 4.0
Foundry
GlobalFoundries
Process Size
14 nm
Transistors
2,200 million
Density
21.4M / mm²
Die Size
103 mm²
Released
Apr 11th, 2018

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
640
TMUs
40
ROPs
16
Compute Units
10
ACEs
4
HWSs
2
SEs
2
L1 Cache
16 KB per CU
L2 Cache
512 KB
Max. TDP
65 W

All GCN 4.0 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Polaris 23 GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
AMD Radeon RX 540X Mobile Polaris 23 MXL 2 GB 512 32 16 1124 MHz 1211 MHz 1500 MHz
AMD Radeon RX 550X Mobile Polaris 23 MXT 2 GB 640 40 16 1100 MHz 1176 MHz 1500 MHz
AMD Radeon 550X Mobile Polaris 23 MXT 4 GB 640 40 16 1100 MHz 1287 MHz 1500 MHz
AMD Radeon Pro WX 3200 Polaris 23 XT GL 4 GB 640 32 16 1295 MHz 1500 MHz
AMD Radeon RX 640 Mobile Polaris 23 XT 2 GB 640 40 16 1082 MHz 1218 MHz 1500 MHz
AMD Radeon 630 Mobile Polaris 23 MXL 2 GB 512 32 16 1082 MHz 1211 MHz 1500 MHz
AMD Radeon Pro WX 3200 Mobile Polaris 23 XT GLM 4 GB 640 32 16 1082 MHz 1000 MHz

Polaris 23 GPU Notes

Architecture Codename: Arctic Islands
Codename: Polaris 12 (Treasure)
CLRX Version: GCN 1.2
Graphics/Compute: GFX8 (gfx804)
Display Core Engine: 11.2
Unified Video Decoder: 6.3
Video Compression Engine: 3.4