AMD Cedar

Cedar

Block Diagram

AMD's Cedar GPU uses the TeraScale 2 architecture and is made using a 40 nm production process at TSMC. With a die size of 59 mm² and a transistor count of 292 million it is a very small chip. Cedar supports DirectX 11.2 (Feature Level 11_0). For GPU compute applications, OpenCL version 1.2 can be used. It features 80 shading units, 8 texture mapping units and 4 ROPs.

Further reading: Evergreen Series Instruction Set Architecture

Graphics Processor

GPU Name: Cedar

Architecture: TeraScale 2

Foundry: TSMC

Process Size: 40 nm

Transistors: 292 million

Density: 4.9M / mm²

Die Size: 59 mm²

Released: Jan 31st, 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: 80

TMUs: 8

ROPs: 4

Compute Units: 2

Z-Stencil: 4

L1 Cache: 8 KB per CU

L2 Cache: 128 KB

Max. TDP: 25 W

All TeraScale 2 GPUs

AMD GPU Architecture History

2005-2007 R500
2005-2013 TeraScale
2009-2015 TeraScale 2
2010-2013 TeraScale 3
2011-2020 GCN 1.0
2013-2017 GCN 2.0
2014-2019 GCN 3.0
2016-2020 GCN 4.0
2017-2020 GCN 5.0
2018-2021 GCN 5.1
2019-2020 RDNA 1.0
2020-2022 RDNA 2.0
2020 CDNA 1.0
2021 CDNA 2.0
2022 RDNA 3.0

Graphics cards using the AMD Cedar GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	GPU Clock	Memory Clock
AMD Radeon HD 6350	Cedar PRO	512 MB	80	8	4	650 MHz	400 MHz
AMD Radeon HD 7350 OEM		512 MB	80	8	4	650 MHz	800 MHz
AMD FirePro 2270	Cedar WS	512 MB	80	8	4	600 MHz	600 MHz
AMD Radeon HD 6350A		512 MB	80	8	4	650 MHz	800 MHz
AMD Radeon HD 8350 OEM		1024 MB	80	8	4	650 MHz	667 MHz
AMD Radeon HD 6250	Cedar PRO	512 MB	80	8	4	650 MHz	500 MHz
AMD Radeon HD 6290	Cedar LE	1024 MB	80	8	4	650 MHz	800 MHz
AMD Radeon HD 7350 OEM PCI		512 MB	80	8	4	650 MHz	500 MHz
AMD Radeon R5 220 OEM	Cedar PRO	1024 MB	80	8	4	650 MHz	533 MHz
AMD FirePro 2270 PCIe x1	Cedar WS	512 MB	80	8	4	600 MHz	600 MHz