Report an Error

AMD Trinidad

Default
Trinidad
Block Diagram
Block Diagram
CU Diagram
CU Diagram
LDS Diagram
LDS Diagram
AMD's Trinidad GPU uses the GCN 1.0 architecture and is made using a 28 nm production process at TSMC. With a die size of 212 mm² and a transistor count of 2,800 million it is a medium-sized chip. Trinidad supports DirectX 12 (Feature Level 11_1). For GPU compute applications, OpenCL version 2.1 (1.2) can be used. It features 1280 shading units, 80 texture mapping units and 32 ROPs.
Further reading: GCN 1.0 Architecture Whitepaper , Southern Islands Instruction Set Architecture

Graphics Processor

Released
May 5th, 2015
GPU Name
Trinidad
Desktop Variant
Pitcairn / Curacao
Mobile Variant
Wimbledon/Neptune
Generation
Southern Islands
Architecture
GCN 1.0
Foundry
TSMC
Process Size
28 nm
Transistors
2,800 million
Density
13.2M / mm²
Die Size
212 mm²
Package
FCBGA-1737

Graphics Features

DirectX
12 (11_1)
OpenGL
4.6
OpenCL
2.1 (1.2)
Vulkan
1.2.170
Shader Model
6.5 (5.1)
WDDM
2.7
Compute
GFX6 (gfx601)
DCE
6.0
UVD
4.0
VCE
1.0
CLRX
GCN 1.0.0

Render Config

Shading Units
1280
TMUs
80
ROPs
32
Compute Units
24
Z-Stencil
128
ACEs
2
GEs
2
L1 Cache
16 KB per CU
L2 Cache
512 KB
Max. TDP
180 W

All GCN 1.0 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Trinidad GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
Trinidad PRO 2 GB 1024 64 32 925 MHz 975 MHz 1400 MHz
Trinidad PRO 2 GB 1280 80 32 925 MHz 975 MHz 1400 MHz
Trinidad XT 2 GB 1280 80 32 980 MHz 1030 MHz 1400 MHz
Trinidad PRO 2 GB 1024 64 32 925 MHz 975 MHz 1400 MHz

Trinidad GPU Notes

Generation: Southern Islands
Desktop Variant: Pitcairn / Curacao
Mobile Variant: Wimbledon / Neptune
Graphics/Compute: GFX6 (gfx601)
Display Core Engine: 6.0
Unified Video Decoder: 4.0
Video Compression Engine: 1.0
CLRX: GCN 1.0
Apr 25th, 2024 00:29 EDT change timezone

New Forum Posts

Popular Reviews

Controversial News Posts