SimGrid 模拟器安装与应用-高性能计算模拟器

目录

1.SimGrid简介

2.SimGrid安装

2.1 Binaries for Linux

2.2 Installing from the Source

3.SimGrid代码运行

3.1 代码下载

3.2 自己写C++代码并运行

参考文献

---

1.SimGrid简介

SimGrid是应用较为广的一个模拟器，其主页为[1] https://simgrid.org/doc/latest/Tutorial_Algorithms.html ，其简介如下：

简而言之，就它可以在单机上模拟分布式的一些应用，并且支持C++/Python3/JAVA的开发支持。应用的第一步就是安装，但目前网上关于SimGrid使用安装的中文资料很少，所以我在此做记录，供大家参考。我选择最为简单的Linux系统上进行安装。

2.SimGrid安装

2.1 Binaries for Linux

对于这种安装你可以按照网站上的步骤直接安装：

apt install libsimgrid-dev  # if you want to develop in C or C++
apt install simgrid-java    # if you want to develop in Java
apt install python3-simgrid # if you want to develop in Python

但这种安装的是3.18的版本，目前官网是上的demo都是3.22以上的所以这种安装不推荐。

2.2 Installing from the Source

其次可以源码安装，首先需要下载依赖（官网上有更详细步骤[2]，https://simgrid.org/doc/latest/Installing_SimGrid.html）

Getting the Dependencies
1. C++ compiler (either g++, clang, or icc).
   We use the C++11 standard, and older compilers tend to fail on us. It seems that g++  5.0 or higher is required nowadays (because of boost). SimGrid compiles well with clang or icc too.

2. Python 3.
   SimGrid should build without Python. That is only needed by our regression test suite.

3. cmake (v3.5).
   ccmake provides a nicer graphical interface compared to cmake. Press t in ccmake if you need to see absolutely all configuration options (e.g., if your Python installation is not standard).

4. boost (at least v1.48, v1.59 recommended)
   On Debian / Ubuntu: apt install libboost-dev libboost-context-dev
   On macOS with homebrew: brew install boost

5. Java (optional):
   Debian / Ubuntu: apt install default-jdk libgcj18-dev (or any version of libgcj)
   macO