Tesla-> Fermi (550Ti) -> Kepler(680) -> Maxwell (750Ti) -> Volta(was Pascal)
Pascal GPU
Pascal (from French mathematician Blaise Pascal) is Maxwell successor. In this news, we learnt that Volta was the post-Maxwell architecture, but it seems that Pascal is the new official name. One of the main feature of the Pascal architecture is the 3D memory or stacked DRAM that should provide terabyte bandwidth.
Update (2014.03.26): according to techreport, Volta is the successor of Pascal:
Turns out Volta remains on the roadmap, but it comes after Pascal and will evidently include more extensive changes to Nvidia’s core GPU architecture.
Maxwell GPU architecture (post-Kepler) is not available yet, but NVIDIA is already talking, at GTC 2013, about post-Maxwell architecture called Volta that features 3D stacked DRAM in order to provide terabyte bandwidth.
According to the guys at videocardz, NVIDIA Maxwell GM107 features 128 CUDA cores per SMX (streaming multiprocessor) against 192 for a Kepler-based GPU. The GeForce GTX 750 Ti has 5 SMX (640 cores) while the GTX 750 packs 512 cores in 4 SMX. The L2 cache has also received some changes: in Kepler the L2 cache has 256KB while on Maxwell, the cache has 2MB!
In the power consumption side, the GM107 has a TDP of 60W. And to finish, the GM107 will offer at least the same level (if not better) of performance than the GF100, the GPU behind the old good GTX 480.
Update (2013.03.20)
NVIDIA has just launched the first graphics cards based on Maxwell, NVIDIA’s new GPU architecture. TheGeForce GTX 750 Ti and GeForce GTX 750 are both powered by a GM107, a cut down version of an upcoming flagship (GM110 ?) GPU. The Maxwell architecture is focused on power efficiency:
Kepler SMXs (streaming multiprocessors) are now replaced by Maxwell SMMs. A SMM packs 128 CUDA cores(SMX = 192 cores). The L2 cache size has been increased from 256KB in Kepler to 2048KB in Maxwell.
The new GTX 750 and GTX 750 Ti targets the old GeForce GTX 650 Ti and the recently launched AMD Radeon R7 265.
GeForce GTX 750 Ti specifications
- GPU: GM107 @ 1020MHz (base) / 1085MHz (boost), 28nm
- Cores: 640 (5 SMMs)
- Texture units: 40
- ROPs: 16
- Memory: 2048MB @ 5.4GHz GDDR5, 128-bit
- TDP: 60W
- Price: USD $149
GeForce GTX 750 specifications
- GPU: GM107 @ 1020MHz (base) / 1085MHz (boost), 28nm
- Cores: 512 (4 SMMs)
- Texture units: 32
- ROPs: 16
- Memory: 1024MB @ 5.0GHz GDDR5, 128-bit
- TDP: 55W
- Price: USD $119
Related Articles and Reviews
- 5 Things You Should Know About the New Maxwell GPU Architecture
- NVIDIA GeForce GTX 750 Ti whitepaper
- Nvidia lance les GeForce GTX 750 Ti / 750 Maxwell
- NVIDIA GeForce GTX 750 Ti Review – Maxwell Architecture debuts at $150
- The NVIDIA GeForce GTX 750 Ti and GTX 750 Review: Maxwell Makes Its Move
- NVIDIA GeForce GTX 750 Ti 2 GB
NVIDIA GeForce GTX 750 Ti global performance
Tesla-> Fermi (550Ti) -> Kepler(680) -> Maxwell (750Ti) -> Volta(was Pascal)的更多相关文章
- CUDA ---- GPU架构(Fermi、Kepler)
GPU架构 SM(Streaming Multiprocessors)是GPU架构中非常重要的部分,GPU硬件的并行性就是由SM决定的. 以Fermi架构为例,其包含以下主要组成部分: CUDA co ...
- NVIDIA GPU架构与原理分析(一)——GPU简介与主流Fermi、Kepler架构GPU概述
1 GPU简介 图形处理单元GPU英文全称Graphic Processing Unit,GPU是相对于CPU的一个概念,NVIDIA公司在1999年发布GeForce256图形处理芯片时首先提出GP ...
- AI芯片
课程作业,正好自己也在学深度学习,正好有所帮助,做了深度学习的AI芯片调研,时间比较短,写的比较仓促,大家随便看看 近年来,深度学习技术,如卷积神经网络(CNN).递归神经网络(RNN)等,成为计算机 ...
- CUDA程序设计(一)
为什么需要GPU 几年前我启动并主导了一个项目,当时还在谷歌,这个项目叫谷歌大脑.该项目利用谷歌的计算基础设施来构建神经网络. 规模大概比之前的神经网络扩大了一百倍,我们的方法是用约一千台电脑.这确实 ...
- CSDN日报20170312——《成功人士的七个习惯》
[程序人生]成功人士的七个习惯 作者:liumiaocn 所谓温故而知新.重读往往会带来新的收获,即使没有新的收获,可以带来新的思考也是非常不错.在个人成长的历程中.习惯所扮演的角色不言而喻,Step ...
- 显卡,显卡驱动,nvcc, cuda driver,cudatoolkit,cudnn到底是什么?
在使用深度学习框架的过程中一定会经常碰到这些东西,虽然anaconda有时会帮助我们自动地解决这些设置,但是有些特殊的库却还是需要我们手动配置环境,但是我对标题上的这些名词其实并不十分清楚,所以老是被 ...
- CUDA Programming Guide 学习笔记
CUDA学习笔记 GPU架构 GPU围绕流式多处理器(SM)的可扩展阵列搭建,每个GPU有多个SM,每个SM支持数百个线程并发执行.目前Nvidia推出了6种GPU架构(按时间顺序,详见下图):Fer ...
- NVIDIA FFmpeg 转码技术分析
NVIDIA FFmpeg 转码技术分析 所有从 Kepler 一代开始的 NVIDIA GPUs 都支持完全加速的硬件视频编码,而从费米一代开始的所有 GPUs 都支持完全加速的硬件视频解码.截至 ...
- Life of a triangle - NVIDIA's logical pipeline
Home GameWorks Blog Life of a triangle - NVIDIA's logical pipeline Life of a triangle - NVIDIA's l ...
随机推荐
- July 17th, Week 30th Sunday, 2016
You are beautiful, but that is not why I love you. 你如此美丽,但我并非因此而爱你. Although we have always been tol ...
- 数列(codevs 1141)
题目描述 Description 给定一个正整数k(3≤k≤15),把所有k的方幂及所有有限个互不相等的k的方幂之和构成一个递增的序列,例如,当k=3时,这个序列是: 1,3,4,9,10,12,13 ...
- vs2013 error c4996: 'fopen': This function or varia
做opencv练习时,使用vs2013遇到如下错误: 错误1error C4996: 'fopen': This function or variable may be unsafe. Consid ...
- C++ friend
如果类A希望类B可以访问它的私有成员, 可以把类B设置为友元类. // 类A,希望把私有成员公开给类B class A { friend class B;// 把B设置为友元类 public: ...
- php 面向对象之继承、多态和静态方法
<?php //继承:子类可以继承父类的一切 //特点:单继承 //父类 class Ren { public $name; public $sex; public $yuyan; functi ...
- 修改iptables防火墙规则解决vsftp登录后不显示文件目录的问题
如果设置防火墙开端口可能只是常用的几个端口,这样很可能导vsftpd在被动模式时无法启动随机端口,从而造成客户端的FTP无法列出目录这样胡问题.解决方式很简单,给 vsftpd增加随机端口范围,然后把 ...
- navicat使用跳板机连接数据库-ssh
1. 目标数据库的域名/IP,端口,用户名,密码:如图1 2. 这时候不要点OK!选择SSH这个tab 3. 选中User SSH Tunnel:填写跳板机域名/IP,用户名,密码(注意:端口22不要 ...
- 好久没弄了,来个最简的centos下的Iptables文件存照吧。
有最基本的作用.. # Generated by iptables-save v1. :: *filter :INPUT ACCEPT [:] :FORWARD ACCEPT [:] :OUTPUT ...
- wp8 -- gameover
<phone:PhoneApplicationPage.Resources> <Storyboard x:Name="Storyboard1"> <D ...
- loj 1021(状压dp+记忆化搜索)
题目链接:http://acm.hust.edu.cn/vjudge/problem/viewProblem.action?id=25887 题目大意:给定的一个某进制下的排列,问它的全排列有多少个能 ...