[gmpi] Re: Topic 7: Audio packaging

  • From: RonKuper@xxxxxxxxxxxx
  • To: gmpi@xxxxxxxxxxxxx
  • Date: Tue, 3 Jun 2003 08:40:51 -0400

>>>
you finally fall down in a trap ! :-) when Ron don't give numbers , you
believe it, when i give number you ask where they go from ! :-) If Ron
Measure something regarding optimization due to IsZero flag why doesn't he
give the result :
for exemple : "on a average montage 24 tracks , 150 clips, we have inserted
24 EQ+Compressor on console and other 40 special Fx on some clips. With the
"IsZero" opimization we have been able to insert 10 other plug-ins without
getting trouble. But we finnally get trouble after moving 20 clips on the
timeline". So Why Ron does not said it !? just because he didn't measure
something in real situation.
<<<

Are you calling me a liar?

First of all, the usage case you described is not what I was benchmarking
when I saw performance bottlenecks.  My usage case was simply a bunch of
audio tracks, with a the same amount of "blank space" between audio clips as
you would expect in any real-world project that had been edited a while.  No
effects were present in ths project; my goal was to simply benchmark the
performance of our mixing code.

In this test case, running under VTune, I saw performance "hotspots" in the
zero fill code.  In other words, we were zerofilling excessively, and it was
showing up in the CPU overhead.

An IsZero optimization will not give the kinds of gains as in your example.
But it will give some gains, and it is optional, and since this discussion
is about *requirements*, my stake in the ground is, "I require this."

----------------------------------------------------------------------
Generalized Music Plugin Interface (GMPI) public discussion list
Participation in this list is contingent upon your abiding by the
following rules:  Please stay on topic.  You are responsible for your own
words.  Please respect your fellow subscribers.  Please do not
redistribute anyone else's words without their permission.

Archive: //www.freelists.org/archives/gmpi
Email gmpi-request@xxxxxxxxxxxxx w/ subject "unsubscribe" to unsubscribe

Other related posts: