NVIDIA G96

G96

TPC Diagram

NVIDIA's G96 GPU uses the Tesla architecture and is made using a 65 nm production process at UMC. With a die size of 144 mm² and a transistor count of 314 million it is a small chip. G96 supports DirectX 11.1 (Feature Level 10_0). For GPU compute applications, OpenCL version 1.1 and CUDA 1.1 can be used. It features 32 shading units, 16 texture mapping units and 8 ROPs.

Further reading: Tesla Architecture Whitepaper

Graphics Processor

Released: Jun 3rd, 2008

GPU Name: G96

Codename: NV96

Architecture: Tesla

Foundry: UMC

Process Size: 65 nm

Transistors: 314 million

Density: 2.2M / mm²

Die Size: 144 mm²

Graphics Features

DirectX: 11.1 (10_0)

OpenGL: 3.3

OpenCL: 1.1

Vulkan: N/A

CUDA: 1.1

Shader Model: 4.0

WDDM: 1.2

PureVideo HD: VP3

VDPAU: Feature Set B

Render Config

Shading Units: 32

TMUs: 16

ROPs: 8

SM Count: 4

SFUs: 8

TPCs: 2

Tex L1 Cache: 16 KB per TPC

L2 Cache: 32 KB

Max. TDP: 50 W

All Tesla 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 G96 GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	GPU Clock	Memory Clock
NVIDIA Quadro FX 380		256 MB	16	8	8	450 MHz	700 MHz
NVIDIA Quadro FX 1700M	NB9P-GLM	512 MB	32	16	8	625 MHz	800 MHz
NVIDIA Quadro FX 770M	G96-975-A1	512 MB	32	16	8	500 MHz	800 MHz
NVIDIA GeForce 9700M GT	NB9E-GE	512 MB	32	16	8	625 MHz	800 MHz
NVIDIA GeForce 9500M G	NB9P-GE	512 MB	16	8	8	500 MHz	800 MHz
NVIDIA GeForce 9500 GS	G96-259-A1	512 MB	32	16	8	550 MHz	504 MHz
NVIDIA GeForce 9500 GT		512 MB	32	16	8	600 MHz	1000 MHz