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 techreportVolta 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


NVIDIA GeForce GTX 750 Ti global performance

 

Tesla-> Fermi (550Ti) -> Kepler(680) -> Maxwell (750Ti) -> Volta(was Pascal)

时间: 2024-08-08 05:10:59

Tesla-> Fermi (550Ti) -> Kepler(680) -> Maxwell (750Ti) -> Volta(was Pascal)的相关文章

CUDA 5 ---- 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 cores Shared Memory/L1Cache Register File Load/Store Units Special Function Units Warp Scheduler GPU中每个SM都设计成支持数以百计的线程并行执行,并且每个GPU都包含了很多的SM,所以GPU支持成百上千的

Nvidia GPU 上的 CNN 计算速度变迁

笔者从 2012 年初开始接触 GPU 编程,2014 年上半年开始接触 Caffe,可以毫不谦虚地说是"一天天看着 Nvidia GPU 和 Caffe 长大的". Nvidia GPU 架构经历了 Fermi.Kepler.Maxwell.Pascal(都是著名物理学家:特斯拉.费米.开普勒.麦克斯韦.帕斯卡.还未发布的 Volta 伏打--),硬件版本号从 1.x 到现在的 6.x,CUDA Toolkit 从 3.x 到现在 8.x,cuDNN 也从 v1 升级到 v5.1.

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,能够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,Stephen R. Covey提出的七个习惯是否就是万应良药虽然不一定,但是这些习惯的贯彻一定会是一个好的开始. [Android 开发]Android 系统中,那些能大幅提高工作效率的 API 汇总 作者:亦枫Blog "条条大路通罗马."工作中,实现某个需求的方式往往不是唯一的,这些不同实现

【转】Life of a triangle - NVIDIA's logical pipeline

From:https://developer.nvidia.com/content/life-triangle-nvidias-logical-pipeline Since the release of the ground breaking Fermi architecture almost 5 years have gone by, it might be time to refresh the principle graphics architecture beneath it. Ferm

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 logical pipeline Facebook Twitter LinkedIn Google+ By Christoph Kubisch, posted Mar 16 2015 at 12:52PM Tags: GameWorks GameWorks Expert Developer DX12 DX

OpenGL book list

? Learning Modern OpenGL ? A little guide about modern OpenGL and why it gives us so much value. Shaders + Cube Env Map + Phong Lighting Introduction Ok... so you want to learn modern OpenGL. Great! But what does it really mean and what options are a

Voting and Shuffling to Optimize Atomic Operations

2iSome years ago I started work on my first CUDA implementation of the Multiparticle Collision Dynamics (MPC) algorithm, a particle-in-cell code used to simulate hydrodynamic interactions between solvents and solutes. As part of this algorithm, a num

CUDA 6 ---- Warp解析

Warp 逻辑上,所有thread是并行的,但是,从硬件的角度来说,实际上并不是所有的thread能够在同一时刻执行,接下来我们将解释有关warp的一些本质. Warps and Thread Blocks warp是SM的基本执行单元.一个warp包含32个并行thread,这32个thread执行于SMIT模式.也就是说所有thread执行同一条指令,并且每个thread会使用各自的data执行该指令. block可以是一维二维或者三维的,但是,从硬件角度看,所有的thread都被组织成一维

CUDA编程

目录: 1.什么是CUDA 2.为什么要用到CUDA 3.CUDA环境搭建 4.第一个CUDA程序 5. CUDA编程 5.1. 基本概念 5.2. 线程层次结构 5.3. 存储器层次结构 5.4. 运行时API 5.4.1. 初始化 5.4.2. 设备管理 5.4.3. 存储器管理 5.4.3.1. 共享存储器 5.4.3.2. 常量存储器 5.4.3.3. 线性存储器 5.4.3.4. CUDA数组 5.4.4. 流管理 5.4.5. 事件管理 5.4.6. 纹理参考管理 5.4.6.1.