NVIDIA GF100

GF100

GF100-030-A3

GF100-275-A3

GF100-375-A3

GF100-850-A3

Block Diagram

SM Diagram

Fritzchens Fritz

Die Shot

NVIDIA's GF100 GPU uses the Fermi architecture and is made using a 40 nm production process at TSMC. With a die size of 529 mm² and a transistor count of 3,100 million it is a very big chip. GF100 supports DirectX 12 (Feature Level 11_0). For GPU compute applications, OpenCL version 1.1 and CUDA 2.0 can be used. It features 512 shading units, 64 texture mapping units and 48 ROPs.

Further reading: Fermi Compute Architecture

Graphics Processor

Released: Mar 26th, 2010

GPU Name: GF100

Codename: NVC0

Architecture: Fermi

Foundry: TSMC

Process Size: 40 nm

Transistors: 3,100 million

Density: 5.9M / mm²

Die Size: 529 mm²

Package: BGA-1980

Graphics Features

DirectX: 12 (11_0)

OpenGL: 4.6

OpenCL: 1.1

Vulkan: N/A

CUDA: 2.0

Shader Model: 5.1

WDDM: 2.3

PureVideo HD: VP4

VDPAU: Feature Set C

Render Config

Shading Units: 512

TMUs: 64

ROPs: 48

SM Count: 16

SFUs: 64

GPCs: 4

L1 Cache: 64 KB per SM

L2 Cache: 768 KB

Max. TDP: 900 W

All Fermi GPUs

NVIDIA GPU Architecture History

2024 Blackwell
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 GF100 GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	GPU Clock	Memory Clock
NVIDIA GeForce GTX 465	GF100-030-A3	1024 MB	352	44	32	608 MHz	802 MHz
NVIDIA GeForce GTX 470	GF100-275-A3	1280 MB	448	56	40	608 MHz	837 MHz
NVIDIA GeForce GTX 480	GF100-375-A3	1536 MB	480	60	48	701 MHz	924 MHz
NVIDIA Quadro 6000	GF100-850-A3	6 GB	448	56	48	574 MHz	747 MHz
NVIDIA Quadro 5000	GF100-850-A3	2.5 GB	352	44	40	513 MHz	750 MHz
NVIDIA Quadro 4000	GF100-825-A3	2 GB	256	32	32	475 MHz	702 MHz
NVIDIA Quadro 4000 Mac Edition		1792 MB	256	32	32	475 MHz	702 MHz
NVIDIA Tesla C2050	GF100-850-A3	3 GB	448	56	48	574 MHz	750 MHz
NVIDIA Tesla C2070		6 GB	448	56	48	574 MHz	747 MHz
NVIDIA GeForce GTX 480M	N11E-GTX-A3	2 GB	352	44	32	425 MHz	600 MHz
NVIDIA Quadro 5000M	N10E-GLM5-A3	2 GB	320	40	32	405 MHz	600 MHz
NVIDIA Tesla M2050		3 GB	448	56	48	574 MHz	773 MHz
NVIDIA Tesla M2070		6 GB	448	56	48	574 MHz	783 MHz
NVIDIA Tesla M2070-Q	GF100-876-A1	6 GB	448	56	48	574 MHz	783 MHz
NVIDIA Tesla S2050		3 GB	448	56	48	574 MHz	773 MHz
NVIDIA GeForce GTX 480 Core 512	GF100-ES-DT1-A2	1536 MB	512	64	48	527 MHz	700 MHz
NVIDIA GeForce GTX 470 PhysX Edition	GF100-275-A3	1280 MB	448	56	40	608 MHz	837 MHz
NVIDIA Tesla X2070	GF100-876-A3	6 GB	448	56	48	651 MHz	924 MHz
NVIDIA Quadro 6000 SDI		6 GB	448	56	48	574 MHz	747 MHz
NVIDIA Quadro 5000 SDI	GF100-850-A3	2.5 GB	352	44	40	513 MHz	750 MHz
NVIDIA GeForce GTX 470 X2	GF100-030-A3	1024 MB	352	44	32	608 MHz	837 MHz
NVIDIA GeForce GTX 490	GF100-375-A3	1536 MB	480	60	48	608 MHz	854 MHz

GF100 GPU Notes

PureVideo HD: VP4
VDPAU: Feature Set C

GF100 has 4 GPCs each capable of 8 pixels per clock. This limits complete GPU to 32 pixels per clock and because of that it can't feed all 48 ROPs when they all require data at the same time.
Additional ROPs however can be used for MSAA (because it doesn't require additional data from rasterizers, while giving more work to ROPs.)

New Forum Posts

18:49 by Finnedsgang
Gigabyte am5 motherboard ddr5 not posting when rebooting (9)
18:47 by njoyyoursalad
Free Games Thread (3818)
18:43 by alwayssts
What's your latest tech purchase? (20618)
18:31 by Keullo-e
Post Your TIMESPY, PCMARK10 & FIRESTRIKE SCORES! (2019) (227)
18:19 by LiKenun
For general use - moving files around and playing games, would you have an Optane boot drive or PCie gen 5? (73)
18:08 by riserser
Can't set PROCHOT offset (0)
18:07 by ty_ger
Help to identify component at position U14 on Gigabyte PCB (1)
17:51 by deepy
CUSTOM RES NOT WORKING AT 144HZ (AMD GPU) (0)
17:50 by Noci
3DMARK "LEGENDARY" (193)
17:41 by Turmeric
Would you pay more for hardware with AI capabilities? (54)