Report an Error

AMD Redwood

Default
Redwood
Block Diagram
Block Diagram
AMD's Redwood GPU uses the TeraScale 2 architecture and is made using a 40 nm production process at TSMC. With a die size of 104 mm² and a transistor count of 627 million it is a small chip. Redwood supports DirectX 11.2 (Feature Level 11_0). It features 400 shading units, 20 texture mapping units and 8 ROPs.
Further reading: Evergreen Series Instruction Set Architecture

Graphics Processor

GPU Name
Redwood
Architecture
TeraScale 2
Foundry
TSMC
Process Size
40 nm
Transistors
627 million
Density
6.0M / mm²
Die Size
104 mm²
Released
May 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
Z-Stencil
40
L1 Cache
8 KB per CU
L2 Cache
256 KB
Max. TDP
39 W

All TeraScale 2 GPUs

Graphics cards using the AMD Redwood GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
AMD Radeon HD 7470A 1024 MB 400 20 8 775 MHz 800 MHz
AMD Radeon HD 6510 Redwood PRO 1024 MB 400 20 8 650 MHz 500 MHz
AMD Radeon HD 6390 Redwood LE 1024 MB 320 16 8 550 MHz 500 MHz
AMD Radeon HD 6610 Redwood PRO 1024 MB 400 20 8 650 MHz 800 MHz
AMD Radeon HD 8510 OEM Redwood PRO 1024 MB 400 20 8 650 MHz 500 MHz
AMD Radeon HD 6530 Redwood PRO 1024 MB 400 20 8 650 MHz 600 MHz
AMD Radeon HD 7570 OEM Redwood PRO 1024 MB 400 20 8 650 MHz 800 MHz
AMD Radeon HD 6490 Redwood LE 1024 MB 320 16 8 550 MHz 500 MHz

Redwood GPU Notes

Architecture Codename: Evergreen
Graphics/Compute: GFX4
Display Core Engine: 4.0
Unified Video Decoder: 2.3