<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
<head>
<meta content="text/html;charset=ISO-8859-1" http-equiv="Content-Type">
<title></title>
</head>
<body bgcolor="#ffffff" text="#000000">
<br>
<blockquote cite="mid200811121729.18763.arnd@arndb.de" type="cite">
<blockquote type="cite">
<blockquote type="cite">
<pre wrap=""> PID TID USERNAME S F %SPU SPE TIME BINARY
24429 24443 user002 U 0.2 4 14.230 mono
24429 24442 user002 U 0.2 5 14.231 mono
24429 24441 user002 U 0.2 6 14.232 mono
24429 24440 user002 U 0.2 7 14.232 mono
24429 24439 user002 L 0.0 -1 14.305 mono
24429 24438 user002 L 0.0 -1 14.305 mono
24429 24437 user002 L 0.0 -1 14.306 mono
24429 24436 user002 L 0.0 -1 14.308 mono
24429 24435 user002 U 0.2 0 14.342 mono
24429 24434 user002 U 0.2 1 14.343 mono
24429 24433 user002 U 0.2 2 14.345 mono
24429 24432 user002 U 0.2 3 14.347 mono
</pre>
</blockquote>
<pre wrap="">What does these values mean ?
</pre>
</blockquote>
<pre wrap=""><!---->
-1 means that the context is currently not loaded to any SPU.
</pre>
</blockquote>
But what can be the reason of that ?<br>
In fact, I am running my program on QS22 server with 16 SPUs <br>
and the program works well until 8 threads/SPUs.<br>
Trying to run it on more than 8 SPUs, leads to "extra" processes are in
the "-1" state initially<br>
though a time goes by for them:<br>
<blockquote type="cite">
<pre wrap="">L 0.0 -1 <b><big><big>14.308</big></big></b> mono
U 0.2 0 14.342 mono</pre>
</blockquote>
How it's possible at all ?<br>
<blockquote cite="mid200811121729.18763.arnd@arndb.de" type="cite">
<pre wrap="">
</pre>
<blockquote type="cite">
<pre wrap="">Also, in SDK 3.1 top-spu gives incorrect values in %SPU column.
</pre>
</blockquote>
<pre wrap=""><!---->
Incorrect in what way?</pre>
</blockquote>
Please, let's see that again:<br>
<blockquote type="cite">spu-top: Context View
<br>
Cpu(s) load avg: 0.09, 0.13, 0.22
<br>
Spu(s) load avg: 3.43, 1.60, 1.18
<br>
Cpu(s): 0.1%us, 0.3%sys, 0.2%wait, 0.0%nice, 99.4%idle
<br>
Spu(s): 49.9%us, 0.1%sys, 0.0%wait, 50.0%idle
<br>
<br>
PID TID USERNAME S F %SPU SPE TIME BINARY
<br>
24429 24443 user002 U 0.2 4 14.230 mono
<br>
24429 24442 user002 U 0.2 5 14.231 mono
<br>
24429 24441 user002 U 0.2 6 14.232 mono
<br>
24429 24440 user002 U 0.2 7 14.232 mono
<br>
24429 24439 user002 L 0.0 -1 14.305 mono
<br>
24429 24438 user002 L 0.0 -1 14.305 mono
<br>
24429 24437 user002 L 0.0 -1 14.306 mono
<br>
24429 24436 user002 L 0.0 -1 14.308 mono
<br>
24429 24435 user002 U 0.2 0 14.342 mono
<br>
24429 24434 user002 U 0.2 1 14.343 mono
<br>
24429 24433 user002 U 0.2 2 14.345 mono
<br>
24429 24432 user002 U 0.2 3 14.347 mono
</blockquote>
In fact, real workload is 100% for each SPU (except processes with
"-1"),<br>
and a total workload ( for 8 SPUs) is near 50 %:<br>
<blockquote type="cite">Spu(s): <big><big><b>49.9%us</b></big></big>,
0.1%sys, 0.0%wait, 50.0%idle</blockquote>
Thanks.<br>
<br>
Yury<br>
<br>
<br>
<br>
</body>
</html>