Report an Error

AMD Raphael

Default
Raphael
AMD's Raphael GPU uses the RDNA 2.0 architecture and is made using a 5 nm production process at TSMC. With a die size of 264 mm² and a transistor count of 3,400 million it is a medium-sized chip. Raphael supports DirectX 12 Ultimate (Feature Level 12_2). For GPU compute applications, OpenCL version 2.0 can be used. Additionally, the DirectX 12 Ultimate capability guarantees support for hardware-raytracing, variable-rate shading and more, in upcoming video games. It features 128 shading units, 8 texture mapping units and 8 ROPs. The GPU also contains 2 raytracing acceleration cores.
Further reading: RDNA Whitepaper

Graphics Processor

Released
Sep 27th, 2022
GPU Name
Raphael
Generation
Navi II
Architecture
RDNA 2.0
Foundry
TSMC
Process Size
5 nm
I/O Process
6 nm
Process Type
N5 / N6 FinFET
Transistors
3,400 million
Density
12.9M / mm²
Die Size
264 mm²
CCD Die Size
71 mm² x2
I/O Die Size
122 mm²
Package
LGA-1718

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.0
Vulkan
1.3
Shader Model
6.8
WDDM
3.2
GC
10.3.6
Shader ISA
GFX10.3 (gfx1036)
DCN
3.1.5
VCN
3.1.2
SDMA
5.2.6
MP0
13.0.5

Render Config

Shading Units
128
TMUs
8
ROPs
8
Compute Units
2
RT Cores
2
L0 Cache
32 KB per WGP
L1 Cache
128 KB per Array
L2 Cache
2048 KB
Max. TDP
15 W

All RDNA 2.0 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Raphael GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
AMD Radeon Graphics 128SP
System Shared 128 8 8 400 MHz 2200 MHz System Shared

Raphael GPU Notes

Generation: Navi II
Ray Tracing Cores: 1st Gen
Graphics/Compute: 10.3.6
Shader ISA: GFX10.3 (gfx1036)
Display Core Next: 3.1.5
Video Core Next: 3.1.2
System DMA: 5.2.6
Platform Security Processor: 13.0.5
Nov 12th, 2024 18:22 EST change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts