博客
关于我
强烈建议你试试无所不能的chatGPT,快点击我
Tesla-> Fermi (550Ti) -> Kepler(680) -> Maxwell (750Ti) -> Volta(was Pascal)
阅读量:6915 次
发布时间:2019-06-27

本文共 2390 字,大约阅读时间需要 7 分钟。

 

 

Pascal GPU

Pascal (from French mathematician Blaise Pascal) is Maxwell successor. In , 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 , 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.

 

NVIDIA Pascal GPU, 3D memory

NVIDIA GPU roadmap 2014

 

 

 

GPU-Z 0.6.9

 

Maxwell GPU architecture (post-Kepler) is not available yet, but NVIDIA is already talking, at , about post-Maxwell architecture called Volta that features 3D stacked DRAM in order to provide terabyte bandwidth.

 

 

 

GTC 2013 - NVIDIA GPU roadmap

 

 

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 Maxwell GPU, SMM vs SMX

 

 

 

NVIDIA has just launched the first graphics cards based on Maxwell, NVIDIA’s new GPU architecture. The and  are both powered by a GM107, a cut down version of an upcoming flagship (GM110 ?) GPU. The Maxwell architecture is focused on power efficiency:

 

NVIDIA Maxwell GPU

 

 

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.

 

NVIDIA Maxwell GPU, SMM vs SMX

 

 

The new GTX 750 and GTX 750 Ti targets the old GeForce GTX 650 Ti and the recently launched .

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

 

 

NVIDIA Maxwell GPU, GPU-Z

 

 

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

 

 

NVIDIA GeForce GTX 750 Ti global performance

NVIDIA GeForce GTX 750 Ti global performance

 

 

转载于:https://www.cnblogs.com/kylegui/p/3855743.html

你可能感兴趣的文章
《开源思索集》一开放源码是开源软件吗? - 简书
查看>>
Ubuntu Touch将支持用户数据加密:目前暂无时间表
查看>>
《金蝶ERP—K/3标准财务模拟实训(11.X版)》——导读
查看>>
开发者必备:基于 Linux 生态的十大AI开源框架盘
查看>>
《基于ArcGIS的Python编程秘笈(第2版)》——2.10 更新图层的符号系统
查看>>
SAP的ABAP屏幕程序如何使用Table Control进行数据交互
查看>>
Visual Studio 将集成 Cordova 支持跨平台开发
查看>>
这些方法助你优化 Android 启动速度
查看>>
《简明电路分析》——2.4节单口网络
查看>>
《动手玩转Arduino》——10.4 作品36:做一个三区域触摸开关
查看>>
《位置大数据隐私管理》—— 导读
查看>>
如何在 Ubuntu 以及 Debian 中安装 DHCP 服务器
查看>>
《图数据库》——2.1 关系型数据库缺少联系
查看>>
16万Facebook数据告诉你,单身狗更爱养猫
查看>>
《JUnit实战(第2版)》—— 1.6 使用JUnit测试
查看>>
C++程序设计:原理与实践(进阶篇)17.6 Shape
查看>>
《JavaScript设计模式》——1.3 用对象收编变量
查看>>
《HTML5+CSS3网页设计入门必读》——1.6 再次联手
查看>>
永远不要在Linux执行的10个最危险的命令
查看>>
Discretized Streams, 离散化的流数据处理
查看>>