AMD Arcturus
Arcturus
Die Shot
Block Diagram
CU Diagram
SIMD Diagram
AMD's Arcturus GPU uses the CDNA 1.0 architecture and is made using a 7 nm production process at TSMC. With a die size of 750 mm² and a transistor count of 50,000 million it is a very big chip. Arcturus does not support DirectX. For GPU compute applications, OpenCL version 2.1 can be used. It features 8192 shading units, 512 texture mapping units and 64 ROPs.
Further reading:
CDNA Architecture 
Graphics Processor
- GPU Name
- Arcturus
- Architecture
- CDNA 1.0
- Foundry
- TSMC
- Process Size
- 7 nm
- Transistors
- 50,000 million
- Density
- 66.7M / mm²
- Die Size
- 750 mm²
- Released
- Nov 16th, 2020
Graphics Features
- DirectX
- N/A
- OpenGL
- N/A
- OpenCL
- 2.1
- Vulkan
- N/A
- Shader Model
- N/A
- Compute
- GFX9
- ROCm
- 4.0
Render Config
- Shading Units
- 8192
- TMUs
- 512
- ROPs
- 64
- Compute Units
- 128
- FP16 Units
- 65536
- FP64 Units
- 4096
- ACEs
- 4
- HWSs
- 1
- DMAs
- 1
- SEs
- 8
- L1 Cache
- 16 KB per CU
- L2 Cache
- 8192 KB
- Max. TDP
- 300 W
All CDNA 1.0 GPUs
- AMD Arcturus
AMD GPU Architecture History
Graphics cards using the AMD Arcturus GPU
| Name | Chip | Memory | Shaders | TMUs | ROPs | Base Clock | Boost Clock | Memory Clock |
|---|---|---|---|---|---|---|---|---|
AMD Radeon Instinct MI100
|
Arcturus XL | 32 GB | 7680 | 480 | 64 | 1000 MHz | 1502 MHz | 1200 MHz |
Arcturus GPU Notes
| Architecture Codename: Graphics/Compute: GFX9 (gfx908) |