Report an Error

AMD Navi 32

Default
Navi 32
Navi 32 XT
Navi 32 XT
AMD's Navi 32 GPU uses the RDNA 3.0 architecture and is made using a 5 nm production process at TSMC. With a die size of 346 mm² and a transistor count of 28,100 million it is a large chip. Navi 32 supports DirectX 12 Ultimate (Feature Level 12_2). For GPU compute applications, OpenCL version 2.2 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 3840 shading units, 192 texture mapping units and 128 ROPs. The GPU also contains 60 raytracing acceleration cores.
Further reading: RDNA Whitepaper , RDNA3 ISA

Graphics Processor

Released
Aug 25th, 2023
GPU Name
Navi 32
Codename
Wheat Nas
Generation
Navi III
Architecture
RDNA 3.0
Foundry
TSMC
Process Size
5 nm
MCD Process
6 nm
Process Type
N5 / N6 FinFET
Transistors
28,100 million
Density
81.2M / mm²
Die Size
346 mm²
GCD Size
200mm²
MCD Size
36.6 mm² x4
Package
MCM
Package Size
40mm × 40mm

Graphics Features

DirectX
12 Ultimate (12_2)
OpenGL
4.6
OpenCL
2.2
Vulkan
1.3
Shader Model
6.7
WDDM
3.1
GC
11.0.3
Shader ISA
GFX11.0 (gfx1101)
DCN
3.2
VCN
4.0

Render Config

Shading Units
3840
TMUs
192
ROPs
128
Compute Units
60
RT Cores
60
L0 Cache
64 KB per WGP
L1 Cache
256 KB per Array
L2 Cache
4096 KB
L3 Cache
64 MB
Max. TDP
263 W

All RDNA 3.0 GPUs

AMD GPU Architecture History

Graphics cards using the AMD Navi 32 GPU

Name Chip Memory Shaders TMUs ROPs Base Clock Boost Clock Memory Clock
AMD Radeon RX 7800 XT
Navi 32 XT 16 GB 3840 240 96 1295 MHz 2430 MHz 2438 MHz
AMD Radeon RX 7700 XT
Navi 32 XL 12 GB 3456 216 96 1435 MHz 2544 MHz 2250 MHz
AMD Radeon RX 7700
Navi 32 12 GB 3072 192 96 1900 MHz 2600 MHz 2250 MHz
AMD Radeon PRO W7700
Navi 32 16 GB 3072 192 96 1900 MHz 2600 MHz 2250 MHz

Navi 32 GPU Notes

Generation: Navi III
Codename: Wheat Nas
Ray Tracing Cores: 2nd Gen
Infinity Cache: 2nd Gen
Graphics/Compute: 11.0.3
Shader ISA: GFX11.0 (gfx1101)
Display Core Next: 3.2
Video Core Next: 4.0

Per SIMD32:
- 10 KB Scalar Register File

Per CU:
- 16 KB Vector Data Cache
- 64 KB Local Data Share (GCN-Mode)

Per WGP:
- 16 KB Scalar Data Cache / K Cache
- 32 KB Instruction Cache
- 128 KB Local Data Share
May 3rd, 2024 06:27 EDT change timezone

Latest GPU Drivers

New Forum Posts

Popular Reviews

Controversial News Posts