NVIDIA GK106S

GK106S

GK106S BGA

Die Shot

Block Diagram

SM Diagram

NVIDIA's GK106S GPU uses the Kepler architecture and is made using a 28 nm production process at TSMC. With a die size of 221 mm² and a transistor count of 2,540 million it is a medium-sized chip. GK106S supports DirectX 12 (Feature Level 11_0). For GPU compute applications, OpenCL version 3.0 and CUDA 3.0 can be used. It features 768 shading units, 64 texture mapping units and 16 ROPs.

Graphics Processor

Released: Oct 9th, 2012

GPU Name: GK106S

Codename: NVE6

Architecture: Kepler

Foundry: TSMC

Process Size: 28 nm

Transistors: 2,540 million

Density: 11.5M / mm²

Die Size: 221 mm²

Package: BGA-908

Graphics Features

DirectX: 12 (11_0)

OpenGL: 4.6

OpenCL: 3.0

Vulkan: 1.2.175

CUDA: 3.0

Shader Model: 6.5 (5.1)

WDDM: 3.0

NVENC: 1st Gen

NVDEC: 1st Gen

PureVideo HD: VP5

VDPAU: Feature Set D

Render Config

Shading Units: 768

TMUs: 64

ROPs: 16

SMX Count: 4

SFUs: 128

GPCs: 3

Tex L1 Cache: 48 KB per SMX

L1 Cache: 16 KB per SMX

L2 Cache: 256 KB

Max. TDP: 110 W

All Kepler 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 GK106S GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	GPU Clock	Memory Clock
NVIDIA GeForce GTX 650 Ti	GK106-220-A1	1024 MB	768	64	16	928 MHz	1350 MHz
NVIDIA GeForce GTX 760M	N14E-GL-A1	2 GB	768	64	16	628 MHz	1002 MHz
NVIDIA GeForce GTX 645 OEM	GK106-200-A1	1024 MB	576	48	16	824 MHz	1000 MHz
NVIDIA Quadro K2100M	N15P-Q3-A1	2 GB	576	48	16	667 MHz	752 MHz
NVIDIA GeForce GT 740 OEM		1024 MB	384	32	16	1006 MHz	1253 MHz
NVIDIA GeForce GT 740 OEM		1024 MB	384	32	16	980 MHz	1253 MHz