https://en.wikipedia.org/wiki/Symmetric_multiprocessor_system

A symmetric multiprocessor system (SMP) is a multiprocessor system with centralized shared memory called main memory (MM) operating under a single operating system with two or more homogeneous processors—i.e., it is not a heterogeneous computing system.

More precisely, an SMP is a tightly coupled multiprocessor system with a pool of homogeneous processors running independently, each processor executing different programs and working on different data, with the capability to share resources (memory, I/O device, interrupt system, etc.), and connected using a system bus or a crossbar. An SMP attempts to balance workload across its processors in order to optimize performance. If performance improved with additional processors in a perfectly linear manner, two processors would run twice as fast as one and ten processors would run ten times as fast as a single processor. However, this performance increase is not necessarily linear due to critical sections in the operating system that must be executed serially. This limitation on speedup based on serial sections is represented in Amdahl's law.[1][2][3]

Each processor usually has an associated private high-speed memory known as cache memory (or cache) to speed-up the MM data access and to reduce the system bus traffic. These caches store values temporarily that may be accessed by a processor multiple times. This reduces latency by preventing multiple unnecessary memory accesses. A single cache can be used per processor, or multiple levels of cache memory may be employed to further increase efficiency.[3]

According to Flynn's taxonomy, a SMP is a type of multiple instruction, multiple data (MIMD) architecture with uniform memory access (UMA) since all processors have the same latency when accessing memory. It is important to note that the term SMP is sometimes loosely used to describe architectures where memory access does not differ by a significant amount (although it may differ somewhat). [4]

symmetric multiprocessor的更多相关文章

  1. Symmetric Multiprocessor Organization

    COMPUTER ORGANIZATION AND ARCHITECTURE DESIGNING FOR PERFORMANCE NINTH EDITION

  2. SYMMETRIC MULTIPROCESSORS

    COMPUTER ORGANIZATION AND ARCHITECTURE DESIGNING FOR PERFORMANCE NINTH EDITION As demands for perfor ...

  3. Extended symmetrical multiprocessor architecture

    An architecture for an extended multiprocessor (XMP) computer system is provided. The XMP computer s ...

  4. Power aware dynamic scheduling in multiprocessor system employing voltage islands

    Minimizing the overall power conservation in a symmetric multiprocessor system disposed in a system- ...

  5. SMP、NUMA、MPP(Teradata)体系结构介绍

    从系统架构来看,目前的商用服务器大体可以分为三类,即对称多处理器结构 (SMP : Symmetric Multi-Processor) ,非一致存储访问结构 (NUMA : Non-Uniform ...

  6. Oracle Tuning 基础概述01 - Oracle 常见等待事件

    对Oracle数据库整体性能的优化,首先要关注的是在有性能问题时数据库排名前几位等待事件是哪些.Oracle等待事件众多,随着版本的升级,数量还在不断增加,可以通过v$event_name查到当前数据 ...

  7. linux源码分析(三)-start_kernel

    前置:这里使用的linux版本是4.8,x86体系. start_kernel是过了引导阶段,进入到了内核启动阶段的入口.函数在init/main.c中. set_task_stack_end_mag ...

  8. SQL Server中的“最大并行度”的配置建议

    SQL Server中的最大并行度(max degree of parallelism)如何设置呢? 设置max degree of parallelism有什么好的建议和指导方针呢?在微软官方文档R ...

  9. [DPDK][转]DPDK编程开发(4)—lcore

    1.知识百科 返回值 操作函数 函数功能 RTE_DECLARE_PER_LCORE (unsigned, _lcore_id) RTE_DECLARE_PER_LCORE (rte_cpuset_t ...

随机推荐

  1. Redis开启持久化

    配置appendonly 打开redis.conf找到appendonly. 将 appendonly no 改为 appendonly yes 配置appendfsync appendfsync a ...

  2. 关于listView 中的聚焦问题

    我在使用listView+adapter 中,遇到一个问题,就是item项添加了若干个可以被监听的控件后 在listView中的setOnItemClickListener失效了 原因是焦点已经在it ...

  3. 【原】iOS学习之PCH文件

    1. PCH文件概述 PCH文件是一种预编译头文件(一般扩展名为.PCH),是把一个工程中较稳定的代码预先编译好放在一个文件(.PCH)里.这些预先编译好的代码可以是任何的C/C++代码--甚至可以是 ...

  4. [转]crontab命令指南

    原文链接:http://www.cnblogs.com/peida/archive/2013/01/08/2850483.html 前一天学习了 at 命令是针对仅运行一次的任务,循环运行的例行性计划 ...

  5. display:none 与 opacity:0

    display:none隐藏消失: opacity:0 只是透明:

  6. Leetcode Maximum Depth of Binary Tree

    Given a binary tree, find its maximum depth. The maximum depth is the number of nodes along the long ...

  7. ACM 括号配对问题

    括号配对问题 时间限制:3000 ms  |  内存限制:65535 KB 难度:3   描述 现在,有一行括号序列,请你检查这行括号是否配对.   输入 第一行输入一个数N(0<N<=1 ...

  8. window 安装Mysql 5.6 发生系统错误 1067

    问题: #安装MySQL服务:mysqld -install MySQL5 D:\Program Files\mysql_5.6.24_winx64\bin>mysqld -install My ...

  9. Linux文件锁flock

    Linux文件锁flock 在多个进程同时操作同一份文件的过程中,很容易导致文件中的数据混乱,需要锁操作来保证数据的完整性,这里介绍的针对文件的锁,称之为“文件锁”-flock. flock,建议性锁 ...

  10. Hibernate映射多对多双向关联关系(小案例)

    多对多双向关联关系(Project(工程)/Emp(员工)为案例): 步骤如下: 1.创建Project类,并需要定义集合类型的Emp属性 public class Project { //编号 pr ...