Accelerated processing unit
http://en.wikipedia.org/wiki/Accelerated_processing_unit
Accelerated processing unit
![]() |
This article needs additional citations for verification. Please help improve this article by adding citations to reliable sources. Unsourced material may be challenged and removed. (September 2011) |
An accelerated processing unit (APU, also Advanced Processing Unit) is a computer's main processing unit that includes additional processing capability designed to accelerate one or more types of computations outside of a central processing unit (CPU). This may include a graphics processing unit (GPU) used for general-purpose computing (GPGPU), a field-programmable gate array (FPGA), or similar specialized processing system. Variations on the usage of this term include a variation in which the APU is described as a processing device which integrates a CPU and an OpenCL compatible GPU on the same die, thus improvingdata transfer rates between these components while reducing power consumption by upwards of 50% with current technology over traditional architecture.[1] APUs can also include video processing and other application-specific accelerators. Examples include AMD Accelerated Processing Unit, Cell, Intel HD Graphics, andNVIDIA's Project Denver.
The term accelerated processing unit was first used in a public context with respect to accelerated computing in 2006,[2] and prior to that in various presentations and business plans written by Joe Landman[3] of Scalable Informatics.[4] Other uses include Xilinx using the term for an auxiliary processor unit.
See also[edit]
Accelerated processing unit的更多相关文章
- Method of offloading iSCSI TCP/IP processing from a host processing unit, and related iSCSI TCP/IP offload engine
A method of offloading, from a host data processing unit (205), iSCSI TCP/IP processing of data stre ...
- 计算机系统概论之CPU(central processing unit)
CPI表示每条指令(Instruction)周期数,即执行一条指令所需的平均时钟周期数.可用下式计算: CPI=执行某段程序所需的CPU(Centrol Processing Unit)时钟周期数/程 ...
- 视频处理单元Video Processing Unit
视频处理单元Video Processing Unit VPU处理全局视频处理,它包括时钟门.块复位线和电源域的管理. 缺少什么: •完全重置整个视频处理硬件块 •VPU时钟的缩放和设置 •总线时钟门 ...
- CPU:Central Processing Unit
CPU执行计算任务时都需要遵从一定的规范,程序在被执行前都需要先翻译为CPU可以理解的语言.这种规范或语言就是指令集(ISA,Instruction Set Architecture). CPU 架构 ...
- Intel graphics processing units
http://en.wikipedia.org/wiki/Comparison_of_Intel_graphics_processing_units Comparison of Intel graph ...
- PC硬件之我见——CPU篇
写在最前面: 最近身边很多朋友都购置电脑的想法,往往也会选择性价比较高的DIY攒机方式.不幸的是,并不是所有人都对电脑硬件有一定的了解的,何况在现在这种社会风气下,盲目的相信商家是不明智的.所 ...
- vimperator
racedu http://www.cnblogs.com/rocedu/p/6673380.html 首先这篇答案是用All-in-One Sidebar打开侧栏照打的...以下addons是经过自 ...
- X_PU
通俗易懂告诉你CPU/GPU/TPU/NPU...XPU都是些什么鬼?[附把妹秘籍] 2017-10-27 19:54移动芯片/谷歌 作者:iot101君 物联网智库 原创 转载请注明来源和出处 现在 ...
- APU (美国AMD公司研发的加速处理器)
APU(Accelerated Processing Unit)中文名字叫加速处理器,是AMD“融聚未来”理念的产品,它第一次将中央处理器和独显核心做在一个晶片上,它同时具有高性能处理器和最新独立显卡 ...
随机推荐
- wp8.1 sdk preview 预览版
http://pan.baidu.com/s/1hqyusja?qq-pf-to=pcqq.c2c#dir/path=%2FWPSDK%208.1%20DevPreview%20Installerwp ...
- 二、harbor部署之部署harbor
1 harbor部署之安装docker 1.yum install -y docker #安装docker 2 harbor部署之安装docker-compose 1.首先检查centos有没有安装p ...
- Leetcode 410.分割数组的最大值
分割数组的最大值 给定一个非负整数数组和一个整数 m,你需要将这个数组分成 m 个非空的连续子数组.设计一个算法使得这 m 个子数组各自和的最大值最小. 注意:数组长度 n 满足以下条件: 1 ≤ n ...
- Git x SVN rebase事故
Git x SVN rebase事故 @author ixenos 2019-01-09 14:21:21 前言: 昨天在Git x SVN 中进行git svn dcommit的时候,提示需要再进行 ...
- POJ 2106-Boolean Expressions,双栈运用类似表达式求值!
Boolean Expressions 首先声明此题后台可能极水(毕竟这种数据不好造!).昨天写了一天却总是找不到bug,讨论区各种数据都过了,甚至怀疑输入有问题,但看到gets也可以过,难道是思路错 ...
- 九度oj 题目1091:棋盘游戏
题目描述: 有一个6*6的棋盘,每个棋盘上都有一个数值,现在又一个起始位置和终止位置,请找出一个从起始位置到终止位置代价最小的路径: 1.只能沿上下左右四个方向移动 2.总代价是没走一步的 ...
- iOS学习笔记17-FMDB
上一节我已经介绍了SQLite的简单使用,不了解的可以提前去看一下iOS学习笔记16-数据库SQLite,这节我们来讲下FMDB. 一.FMDB介绍 FMDB是一种第三方的开源库,FMDB就是对SQL ...
- Codeforces Round #361 (Div. 2)——B. Mike and Shortcuts(BFS+小坑)
B. Mike and Shortcuts time limit per test 3 seconds memory limit per test 256 megabytes input standa ...
- BZOJ 3518 点组计数 ——莫比乌斯反演
要求$ans=\sum_{i=1}^n \sum_{j=1}^m (n-i)(m-j)(gcd(i,j)-1)$ 可以看做枚举矩阵的大小,然后左下右上必须取的方案数. 这是斜率单增的情况 然后大力反演 ...
- [BZOJ4756] [Usaco2017 Jan]Promotion Counting(线段树合并)
传送门 此题很有意思,有多种解法 1.用天天爱跑步的方法,进入子树的时候ans-query,出去子树的时候ans+query,query可以用树状数组或线段树来搞 2.按dfs序建立主席树 3.线段树 ...