NVIDIA GK180

GK180-425-A1

GK180-890-A1

Die Shot

Block Diagram

SMX Diagram

NVIDIA's GK180 GPU uses the Kepler architecture and is made using a 28 nm production process at TSMC. With a die size of 561 mm² and a transistor count of 7,080 million it is a very big chip. GK180 supports DirectX 12 (Feature Level 11_0). For GPU compute applications, OpenCL version 3.0 and CUDA 3.5 can be used. It features 2880 shading units, 240 texture mapping units and 48 ROPs.

Further reading: GK180 Compute Architecture Whitepaper

Graphics Processor

Released: Oct 8th, 2013

GPU Name: GK180

Architecture: Kepler

Foundry: TSMC

Process Size: 28 nm

Transistors: 7,080 million

Density: 12.6M / mm²

Die Size: 561 mm²

Package: BGA-2152

Graphics Features

DirectX: 12 (11_0)

OpenGL: 4.6

OpenCL: 3.0

Vulkan: 1.2.175

CUDA: 3.5

Shader Model: 5.1

WDDM: 3.0

NVENC: 1st Gen

NVDEC: 1st Gen

PureVideo HD: VP5

VDPAU: Feature Set D

Render Config

Shading Units: 2880

TMUs: 240

ROPs: 48

SMX Count: 15

DPUs: 960

SFUs: 480

GPCs: 5

PPC: 8 per Rasterizer

Tex L1 Cache: 48 KB per SMX

L1 Cache: 16 KB per SMX

L2 Cache: 1536 KB

Max. TDP: 250 W

All Kepler 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 GK180 GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	Base Clock	Boost Clock	Memory Clock
NVIDIA Tesla K40c	GK180-890-A1	12 GB	2880	240	48	745 MHz	876 MHz	1502 MHz
NVIDIA GeForce GTX 780 Ti Engineering Sample	GK180-425-A1	3 GB	2880	240	48	875 MHz	928 MHz	1753 MHz

GK180 GPU Notes

NVENC: 1st Gen
NVDEC: 1st Gen
PureVideo HD: VP5
VDPAU: Feature Set D

L1 Cache is configurable from 16 KB up to 48 KB per SMX

GK180 has 5 GPCs each capable of 8 pixels per clock. This limits complete GPU to 40 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

04:40 by KrazyT
Horizontal black lines popping up on my screen? (7)
04:37 by Chomiq
What's your latest tech purchase? (20343)
04:27 by GreiverBlade
TPU's Nostalgic Hardware Club (18471)
04:22 by FoulOnWhite
What are you playing? (20531)
03:50 by Keullo-e
Which new games will you be buying? (320)
03:46 by BoggledBeagle
Alphacool CORE 1 CPU block - bulging with danger of splitting? (21)
02:57 by Keullo-e
Best SSD for system drive (82)
02:51 by Arjai
What phone you use as your daily driver? And, a discussion of them. (1484)
01:53 by tpa-pr
AMD RX 7000 series GPU Owners' Club (1087)
01:48 by unclewebb
im new to throttelstop and i think i messed it up by copying others any hints would be very much aprreciated (3)