NVIDIA GP102

GP102

GP102-350-K1-A1

GP102-350-K2-A1

GP102-350-K3-A1

GP102-350-K4-A1

GP102-351-K1-A1

GP102-400-A1

GP102-450-A1

Fritzchens Fritz

Die Shot

Block Diagram

SM Diagram

NVIDIA's GP102 GPU uses the Pascal architecture and is made using a 16 nm production process at TSMC. With a die size of 471 mm² and a transistor count of 11,800 million it is a very big chip. GP102 supports DirectX 12 (Feature Level 12_1). For GPU compute applications, OpenCL version 3.0 and CUDA 6.1 can be used. It features 3840 shading units, 240 texture mapping units and 96 ROPs.

Graphics Processor

Released: Aug 2nd, 2016

GPU Name: GP102

Codename: NV132

Architecture: Pascal

Foundry: TSMC

Process Size: 16 nm

Transistors: 11,800 million

Density: 25.1M / mm²

Die Size: 471 mm²

Package: BGA-2397

Graphics Features

DirectX: 12 (12_1)

OpenGL: 4.6

OpenCL: 3.0

Vulkan: 1.3

CUDA: 6.1

Shader Model: 6.8

WDDM: 3.2

NVENC: 6th Gen

NVDEC: 3rd Gen

PureVideo HD: VP8

VDPAU: Feature Set H

Render Config

Shading Units: 3840

TMUs: 240

ROPs: 96

SM Count: 30

SFUs: 960

TPCs: 30

GPCs: 6

L1 Cache: 48 KB per SM

L2 Cache: 3072 KB

Max. TDP: 250 W

All Pascal GPUs

NVIDIA GPU Architecture History

2025 Blackwell 2.0
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 GP102 GPU

Name	Chip	Memory	Shaders	TMUs	ROPs	Base Clock	Boost Clock	Memory Clock
NVIDIA TITAN X Pascal	GP102-400-A1	12 GB	3584	224	96	1417 MHz	1531 MHz	1251 MHz
NVIDIA Quadro P6000	GP102-875-A1	24 GB	3840	240	96	1506 MHz	1645 MHz	1127 MHz
NVIDIA GeForce GTX 1080 Ti	GP102-350-K1-A1	11 GB	3584	224	88	1481 MHz	1582 MHz	1376 MHz
NVIDIA Tesla P40		24 GB	3840	240	96	1303 MHz	1531 MHz	1808 MHz
NVIDIA TITAN Xp	GP102-450-A1	12 GB	3840	240	96	1405 MHz	1582 MHz	1426 MHz
NVIDIA P102-100	GP102-100-A1	5 GB	3200	200	80	1582 MHz	1683 MHz	1376 MHz
NVIDIA P102-101	GP102-101-A1	10 GB	3200	200	80	1557 MHz	1670 MHz	2002 MHz
NVIDIA GeForce GTX 1080 Ti 10 GB		10 GB	3200	200	80	1557 MHz	1670 MHz	1376 MHz
NVIDIA Tesla P10		24 GB	3840	240	96	1025 MHz	1493 MHz	1808 MHz
NVIDIA GeForce GTX 1080 Ti 12 GB		12 GB	3200	200	80	1557 MHz	1670 MHz	1376 MHz

GP102 GPU Notes

NVENC: 6th Gen
NVDEC: 3rd Gen
PureVideo HD: VP8
VDPAU: Feature Set H

Latest Drivers:
Windows 7 / 8 / 8.1 (x32 / x64):
GeForce Release 391.35 / 474.89
Quadro Release R390 U9 (392.37) / R440 U4 (441.66)
Data Center Release 427.11

Windows 10 / 11 (x32 / x64):
GeForce Release 391.35 / Latest
Quadro Release R390 U9 (392.37) / Latest
Data Center Release: Latest

New Forum Posts

17:53 by dirtyferret
psu calculator. sites that have their personal interests vs honest sites (99)
17:45 by A Computer Guy
It checks out as authentic (24)
17:41 by eidairaman1
[newegg] B550 Motherboard and Ryzen 7 5700x combo for $279.99 (4)
17:41 by Krit
Case cooling fans (12)
17:40 by eidairaman1
how probable/difficult is it to flash a 6000fx cpu to to be an 8320fx ? (10)
17:39 by Super Firm Tofu
Intel Core "Special Edition" Owners' Club (173)
17:38 by wheresmycar
Is Microsoft Deliberately Limiting AMD CPU Performance? (0)
17:36 by phanbuey
Why everyone say Zen 5 is bad ? (785)
17:33 by Beginner Macro Devic...
Technical Issues - TPU Main Site & Forum (2024) (277)
17:25 by yzonker
Star Wars Outlaws (16)