Report an Error

AMD Latte

Default
Latte
Die Shot
Die Shot
AMD's Latte GPU uses the TeraScale 2 architecture and is made using a 40 nm production process at Renesas. With a die size of 146 mm² and a transistor count of 880 million it is a small chip. Latte does not support DirectX. It features 320 shading units, 16 texture mapping units and 8 ROPs.

Graphics Processor

GPU Name
Latte
Architecture
TeraScale 2
Foundry
Renesas
Process Size
40 nm
Transistors
880 million
Density
6.0M / mm²
Die Size
146 mm²
Released
Nov 18th, 2012

Graphics Features

DirectX
N/A
OpenGL
N/A
OpenCL
N/A
Vulkan
N/A
Shader Model
5.0
Compute
GFX3

Render Config

Shading Units
320
TMUs
16
ROPs
8
Compute Units
5
Max. TDP
45 W

All TeraScale 2 GPUs

Graphics cards using the AMD Latte GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Memory Clock
AMD Wii U GPU 2 GB 320 16 8 550 MHz 800 MHz

Latte GPU Notes

Graphics/Compute: GFX3
Display Core Engine: 3.2
Unified Video Decoder: 2.2

EDRAM size: 32 MB