NVIDIA NV38

NV38

FX 5950 Ultra

Die Shot

NVIDIA's NV38 GPU uses the Rankine architecture and is made using a 130 nm production process at TSMC. With a die size of 207 mm² and a transistor count of 135 million it is a medium-sized chip. NV38 supports DirectX 9.0a. For GPU compute applications, OpenCL version N/A can be used. It features 4 pixel shaders and 3 vertex shaders, 8 texture mapping units and 4 ROPs. Due to the lack of unified shaders you will not be able to run recent games at all (which require unified shader/DX10+ support).

Graphics Processor

Released: Oct 23rd, 2003

GPU Name: NV38

Architecture: Rankine

Foundry: TSMC

Process Size: 130 nm

Transistors: 135 million

Density: 652.2K / mm²

Die Size: 207 mm²

Graphics Features

DirectX: 9.0a

OpenGL: 1.5 (full)
2.0 (partial)

OpenCL: N/A

Vulkan: N/A

Pixel Shader: 2.0a

Vertex Shader: 2.0a

WDDM: 1.0

Render Config

Pixel Shaders: 4

Vertex Shaders: 3

TMUs: 8

ROPs: 4

Max. TDP: 74 W

All Rankine GPUs

NVIDIA GPU Architecture History

2023 Hopper
2022-2024 Ada Lovelace
2020-2024 Ampere
2018-2022 Turing
2017-2020 Volta
2016-2021 Pascal
2014-2019 Maxwell 2.0
2014-2017 Maxwell
2013-2015 Kepler 2.0
2012-2018 Kepler
2010-2016 Fermi 2.0
2010-2013 VLIW Vec4
2010-2016 Fermi
2007-2013 Tesla 2.0
2006-2010 Tesla
2003-2013 Curie
2003-2005 Rankine
2001-2003 Kelvin
1999-2005 Celsius
1998-2000 Fahrenheit

Graphics cards using the NVIDIA NV38 GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	GPU Clock	Memory Clock
NVIDIA GeForce PCX 5950		256 MB	4 / 3	8	4	475 MHz	425 MHz
NVIDIA GeForce FX 5950 Ultra	FX 5950 Ultra	256 MB	4 / 3	8	4	475 MHz	475 MHz
NVIDIA Quadro FX 1300	NV38 GL	128 MB	4 / 3	8	4	350 MHz	275 MHz