Report an Error

NVIDIA GK110B

Default
GK110B
GK110-300-B1
GK110-300-B1
GK110-301-B1
GK110-301-B1
GK110-350-B1
GK110-350-B1
GK110-425-B1
GK110-425-B1
GK110-430-B1
GK110-430-B1
GK110-890-B1
GK110-890-B1
Die Shot
Fritzchens Fritz
Die Shot
Block Diagram
Block Diagram
SMX Diagram
SMX Diagram
NVIDIA's GK110B 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. GK110B supports DirectX 12.0 (Feature Level 11_1). It features 2880 shading units, 240 texture mapping units and 48 ROPs.
Further reading: GK110B Compute Architecture Whitepaper

Graphics Processor

GPU Name
GK110B
Architecture
Kepler
Foundry
TSMC
Process Size
28 nm
Transistors
7,080 million
Density
12.6M / mm²
Die Size
561 mm²
Codename
NVF1
Released
Jul 23rd, 2013

Graphics Features

DirectX
12.0 (11_1)
OpenGL
4.6
OpenCL
1.2
Vulkan
1.1.103
CUDA
3.5
Shader Model
5.1
PureVideo HD
VP5
VDPAU
Feature Set D

Render Config

Shading Units
2880
TMUs
240
ROPs
48
SMX Count
15
GPCs
5
SFUs
480
DPUs
960
Tex L1 Cache
48 KB per SMX
L1 Cache
16 KB per SMX
L2 Cache
1536 KB
Max. TDP
375 W

All Kepler GPUs

Graphics cards using the NVIDIA GK110B GPU

Name Chip Memory Shaders TMUs ROPs GPU Clock Boost Clock Memory Clock
NVIDIA Quadro K6000 GK110-890-B1 12 GB 2880 240 48 797 MHz 902 MHz 1502 MHz
NVIDIA GeForce GTX 780 Ti GK110-425-B1 3 GB 2880 240 48 875 MHz 928 MHz 1753 MHz
NVIDIA GeForce GTX 780 Rev. 2 GK110-300-B1 3 GB 2304 192 48 863 MHz 902 MHz 1502 MHz
NVIDIA Tesla K40s 12 GB 2880 240 48 745 MHz 876 MHz 1502 MHz
NVIDIA Tesla K40m 12 GB 2880 240 48 745 MHz 876 MHz 1502 MHz
NVIDIA Tesla K40st 12 GB 2880 240 48 575 MHz 1502 MHz
NVIDIA GeForce GTX TITAN BLACK GK110-430-B1 6 GB 2880 240 48 889 MHz 980 MHz 1750 MHz
NVIDIA GeForce GTX TITAN Z GK110-350-B1 6 GB 2880 240 48 705 MHz 876 MHz 1750 MHz
NVIDIA Quadro K5200 8 GB 2304 192 48 667 MHz 771 MHz 1502 MHz
NVIDIA GeForce GTX 780 6 GB GK110-301-B1 6 GB 2304 192 48 863 MHz 902 MHz 1502 MHz
NVIDIA GeForce GTX 780 Ti 6 GB 6 GB 2880 240 48 875 MHz 928 MHz 1753 MHz
NVIDIA Tesla K40d 12 GB 2880 240 48 745 MHz 876 MHz 1502 MHz
NVIDIA Tesla K40t 12 GB 2880 240 48 745 MHz 876 MHz 1502 MHz

GK110B GPU Notes

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

GK110 chips have 5 Rasterizers each capable of 8 pixels per clock and are limited 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.
Luckily, additional ROPs can be used when for example MSAA is enabled (because it doesn't require additional data from rasterizers, while giving more work to ROPs).