Report an Error
AMD Scorpio
Scorpio
Default 2
Fritzchens Fritz
Die Shot
AMD's Scorpio GPU uses the GCN 2.0 architecture and is made using a 16 nm production process at TSMC. With a die size of 359 mm² and a transistor count of 7,000 million it is a large chip. Scorpio supports DirectX 12 (Feature Level 12_0). For GPU compute applications, OpenCL version 1.2 can be used. It features 2560 shading units, 160 texture mapping units and 32 ROPs.
Graphics Processor
Released
Nov 7th, 2017
GPU Name
Scorpio
Codename Cactus
Generation Sea Islands
Architecture
GCN 2.0
Foundry
TSMC
Process Size
16 nm
Transistors
7,000 million
Density
19.5M / mm²
Die Size
359 mm²
Package
BGA-2409
Graphics Features
DirectX
12 (12_0)
OpenGL
N/A
OpenCL
1.2
Vulkan
1.1
Shader Model
6.0
CLRX GCN 1.1.0
Render Config
Shading Units
2560
TMUs
160
ROPs
32
Compute Units
40
Max. TDP
150 W
AMD GPU Architecture History
Graphics cards using the AMD Scorpio GPU
Name
Chip
Memory
Shaders
TMUs
ROPs
GPU Clock
Memory Clock
12 GB
2560
160
32
1172 MHz
1700 MHz
Scorpio GPU Notes
Generation: Sea Islands
Codename Console: Scorpio
Codename SoC: Anubis
Codename GPU: Cactus (Microsoft)
CLRX: GCN 1.1.0
Sign in / Register
New Forum Posts
Popular Reviews
Apr 1st, 2024
Fractal Design Terra Review
Apr 17th, 2024
Thermalright Phantom Spirit 120 EVO Review
Apr 9th, 2024
Corsair 2000D Airflow Review
Mar 28th, 2024
Minisforum EliteMini UM780 XTX (AMD Ryzen 7 7840HS) Review
Oct 12th, 2022
ASUS GeForce RTX 4090 STRIX OC Review
Oct 11th, 2022
NVIDIA GeForce RTX 4090 Founders Edition Review - Impressive Performance
Sep 19th, 2023
ASUS GeForce RTX 4090 Matrix Platinum Review - The RTX 4090 Ti
Oct 12th, 2022
MSI GeForce RTX 4090 Suprim X Review
Feb 10th, 2023
MSI GeForce RTX 4090 Gaming X Trio Review
Oct 12th, 2022
Gigabyte GeForce RTX 4090 Gaming OC Review
Controversial News Posts