📄 node37.htm

📁 空间物理学研究需要有并行的环境
💻 HTM
字号:
<HTML>
<HEAD>
<!-- This file was generated by tohtml from mpichntman.tex -->
<!-- with the command
tohtml -default -dosnl -gaudy -basedef mpiman.def mpichntman.tex 
-->
<TITLE>Runtime environment variable options</TITLE>
</HEAD>
<BODY BGCOLOR="#FFFFFF">
<HR><H2><A NAME="Node37">Runtime environment variable options</a></H2>
<A HREF="node33.htm#Node36"><IMG WIDTH=16 HEIGHT=16 SRC="previous.xbm"></A><A HREF="node23.htm#Node23"><IMG WIDTH=16 HEIGHT=16 SRC="up.xbm"></A><A HREF="node38.htm#Node38"><IMG WIDTH=16 HEIGHT=16 SRC="next.xbm"></A><BR>
<b>Up: </b><A HREF="node23.htm#Node23"> Tools</a>
<b>Next: </b><A HREF="node38.htm#Node38"> Job manager tool</a>
<b>Previous: </b><A HREF="node33.htm#Node36"> Apply the updates</a>
<P>
There are some lesser used options available to MPICH which can be used to fine   
tune the performance to a specific machine.  The following environment variables   
may be used to set runtime options:  
<P> 
<dl> 
 
<dt> 
<b></b><tt>MPICH_NETMASK</tt></b><dd> 
<BR>  
Set this variable to the subnet ip address and mask you want to use to select the   
appropriate network adaptor on multi-nic hosts.  The form is: IP/Mask, eg 192.0.0.0/8.    
The subnet ip address is the partial ip address specifying which bits represent the   
subnet part of an ip address.  The mask part represents which bits are signifigant   
to determine the subnet.  For example, 20 = 255.255.240.0  
<P> 
 
<dt> 
<b></b><tt>MPICH_USE_POLLING</tt></b><dd> 
<BR>  
Set this variable to 1 to enable polling.  The default is to use event objects   
to wait on.  Polling has lower latency but burns the CPU and can decrease performance   
in certain situations.  
<P> 
 
<dt> 
<b></b><tt>MPICH_SINGLETHREAD</tt></b><dd> 
<BR>  
Set this variable to 1 to cause the shared memory and via devices to be single threaded.    
Single threaded devices have much lower latency but they obey different progress   
rules than the multithreaded versions.  They only make progress on messge passing   
when MPI calls are made.  The multi-threaded devices make progress on messages   
asynchronously when the message arives.  
<P> 
 
<dt> 
<b></b><tt>MPICH_SHMQSIZE</tt></b><dd> 
<BR>  
This value is the size, in bytes, of the shared memory queue for each process.   
The default value is 1MB.  
<P> 
 
<dt> 
<b></b><tt>MPICH_MAXSHMMSG</tt></b><dd> 
<BR>  
This value is the largest message, measured in bytes, that can be put in the shared   
memory queue.  This value must be less than or equal to <tt>MPICH_SHMQSIZE</tt>.  Messages   
larger than this value are copied directly from the address space of the sender to   
the receiver. The default value is 15k.  
<P> 
 
<dt> 
<b></b><tt>MPICH_LONGVLONGTHRESH</tt></b><dd> 
 
<dt> 
<b></b><tt>MPICH_TCPLONGVLONGTHRESH</tt></b><dd> 
 
<dt> 
<b></b><tt>MPICH_SHMLONGVLONGTHRESH</tt></b><dd> 
<BR>  
This value is the message size, in bytes, when the message sending protocol changes   
from eager to rendezvous. The default value is for shm is 20k and tcp is 100k.  Use   
the first variable to set both thresholds or use the protocol specific version to set   
an individual threshold.  
<P> 
 
<dt> 
<b></b><tt>MPICH_NUMCOMMPORTS</tt></b><dd> 
<BR>  
This value is the number of completion port threads that will be launched by each   
process to handle all socket communication. The default is 2.  
<P> 
 
<dt> 
<b></b><tt>MPICH_VI_USE_POLLING</tt></b><dd> 
<BR>  
Set this variable to 1 to enable polling in the VIA device.  The default is to use   
the wait interface.  Polling has lower latency but burns the CPU and can decrease   
performance in certain situations.  
<P> 
 
<dt> 
<b></b><tt>MPICH_VERBOSE</tt></b><dd> 
<BR>  
Set this variable to 1 to cause <TT>mpich</TT> to spit out loads of internal state as the   
application runs.  This would be useful to report suspected bugs in <TT>mpich</TT>.  
</dl> 
<BR> 
 Examples:  
<P> 
 High performance ping pong shared memory test:  
<BR> 
<pre><tt>mpirun -localonly 2  
  -env "MPICH_USE_POLLING=1|MPICH_SINGLETHREAD=1"  
  netpipe.exe 
</tt></pre> 
 High performance ping pong via test  
<BR> 
<pre><tt>mpirun -np 2  
  -env "MPICH_USE_POLLING=1|MPICH_SINGLETHREAD=1|MPICH_VI_CLIQUES=*"  
  netpipe.exe 
</tt></pre> 

<P>
<HR>
<A HREF="node33.htm#Node36"><IMG WIDTH=16 HEIGHT=16 SRC="previous.xbm"></A><A HREF="node23.htm#Node23"><IMG WIDTH=16 HEIGHT=16 SRC="up.xbm"></A><A HREF="node38.htm#Node38"><IMG WIDTH=16 HEIGHT=16 SRC="next.xbm"></A><BR>
<b>Up: </b><A HREF="node23.htm#Node23"> Tools</a>
<b>Next: </b><A HREF="node38.htm#Node38"> Job manager tool</a>
<b>Previous: </b><A HREF="node33.htm#Node36"> Apply the updates</a>
<P>
</BODY>
</HTML>
⌨️ 快捷键说明

复制代码 Ctrl + C
搜索代码 Ctrl + F
全屏模式 F11
切换主题 Ctrl + Shift + D
显示快捷键 ?
增大字号 Ctrl + =
减小字号 Ctrl + -