<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
<style type="text/css" style="display:none;"> P {margin-top:0;margin-bottom:0;} </style>
</head>
<body dir="ltr">
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
The total number of VCIs are configured with <code>--with-ch4-max-vcis=#</code>. The maximum is 64. The default used to be 1, but it is changed to 64 in 4.0b1 release. There is also an option to control the vci assignment method:
<code>--enable-ch4-vci-method={communicator,tag,implicit}</code>. The default is
<code>communicator</code>, with which we assign vci to communicators in a round-robin fashion. If you create communicators consecutively, they are expected to have different VCIs. The other
<code>vci-method</code>s are at the experimental stage. If the communicator method is insufficient for your application, it may be worth a try. We'd like to understand your use case better before pointing you that way.<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
I am not exactly understanding your question. The vci locks are local process locks, so if you have N VCIs, you will have N channels for each process. With
<code>vci-method=communicator</code>, the vcis are one-to-one matched, i.e. rank 1 vci 1 only communicates to rank 2 (any ranks with the same communicator) vci 1.</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
<br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
-- <br>
</div>
<div style="font-family: Calibri, Arial, Helvetica, sans-serif; font-size: 12pt; color: rgb(0, 0, 0);">
Hui Zhou<br>
</div>
<div id="appendonsend"></div>
<hr style="display:inline-block;width:98%" tabindex="-1">
<div id="divRplyFwdMsg" dir="ltr"><font face="Calibri, sans-serif" style="font-size:11pt" color="#000000"><b>From:</b> Guilherme Valarini via discuss <discuss@mpich.org><br>
<b>Sent:</b> Monday, December 6, 2021 10:10 AM<br>
<b>To:</b> discuss@mpich.org <discuss@mpich.org><br>
<b>Cc:</b> Guilherme Valarini <guilherme.a.valarini@gmail.com><br>
<b>Subject:</b> [mpich-discuss] How locking on multi-VCI works</font>
<div> </div>
</div>
<div>
<div dir="ltr">
<div>Hello everyone,</div>
<div><br>
</div>
<div>I got one question regarding the multi-VCI support and possible locking contentions of MPICH on multi-threaded environments.</div>
<div><br>
</div>
<div>I understand that there is a direct mapping between a VCI and a communicator, so global locking is avoided on a multi-threaded application. But I wanted to know: how do these VCIs work? When I have N VCIs, do I have N virtual channels per rank (thus, one
global lock per VCI-rank pair) or only 2 channels at all (one lock per VCI)? I was wondering if, for example, two MPI_Sends targeting different ranks on the same comm might need to be synchronized using such a global lock.<br>
</div>
<div><br>
</div>
<div>Thanks for the help!</div>
<div>Guilherme Valarini</div>
</div>
</div>
</body>
</html>