Report an Error

AMD Sumo

AMD's Sumo GPU uses the TeraScale 2 architecture and is made using a 32 nm production process at TSMC. With a die size of 227 mm² and a transistor count of 1,178 million it is a medium-sized chip. Sumo supports DirectX 11.2 (Feature Level 11_0). For GPU compute applications, OpenCL version 1.2 can be used. It features 400 shading units, 20 texture mapping units and 8 ROPs.
Further reading: Evergreen Series Instruction Set Architecture

Graphics Processor

GPU Name
Sumo
Architecture
TeraScale 2
Foundry
TSMC
Process Size
32 nm
Transistors
1,178 million
Density
5.2M / mm²
Die Size
227 mm²
Released
Jun 14th, 2011

Graphics Features

DirectX
11.2 (11_0)
OpenGL
4.4
OpenCL
1.2
Vulkan
N/A
Shader Model
5.0
Compute
GFX4

Render Config

Shading Units
400
TMUs
20
ROPs
8
Compute Units
5
Max. TDP
65 W

All TeraScale 2 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Sumo GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
AMD Radeon HD 6480G IGP System Shared 240 12 4 444 MHz System Shared
AMD Radeon HD 6520G IGP System Shared 320 16 8 400 MHz System Shared
AMD Radeon HD 6620G IGP System Shared 400 20 8 444 MHz System Shared
AMD Radeon HD 6530D IGP System Shared 320 16 8 444 MHz System Shared
AMD Radeon HD 6550D IGP System Shared 400 20 8 600 MHz System Shared

Sumo GPU Notes

Architecture Codename: Evergreen
Codename: BeaverCreek
Graphics/Compute: GFX4
Display Core Engine: 4.1
Unified Video Decoder: 3.0
Video Compression Engine: 1.0