Report an Error

AMD Liverpool

Default
Liverpool
CXD90026G
CXD90026G
CXD90026BG
CXD90026BG
CXD90037G
CXD90037G
Die Shot
Oleg Kashirin
Die Shot
Block Diagram
Block Diagram
AMD's Liverpool GPU uses the GCN 2.0 architecture and is made using a 28 nm production process at TSMC. With a die size of 348 mm² it is a large chip. Liverpool supports DirectX 11.1*. For GPU compute applications, OpenCL version 1.2 can be used. It features 1152 shading units, 72 texture mapping units and 32 ROPs.

Graphics Processor

Released
Nov 24th, 2013
GPU Name
Liverpool
Chip Variant
Starsha (Thebe-J)
Generation
Sea Islands
Architecture
GCN 2.0
Foundry
TSMC
Process Size
28 nm
Transistors
unknown
Die Size
348 mm²

Graphics Features

DirectX
11.1*
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1
Shader Model
5.1
CLRX
GCN 1.1.0

Render Config

Shading Units
1152
TMUs
72
ROPs
32
Compute Units
18
Max. TDP
75 W

All GCN 2.0 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Liverpool GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
AMD Playstation 4 GPU
CXD90026BG 8 GB 1152 72 32 800 MHz 1375 MHz

Liverpool GPU Notes

*Supports DirectX 11.1+ Features with PSSL
Generation: Sea Islands
Codename: Starsha (Thebe-J)
CLRX: GCN 1.1.0
Oct 18th, 2024 02:59 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts