Hi Augusto,
You can post my reply and Jim's as comments in the bug parade. Jim
will probably be closing that bug soon with the more detailed explanation.
He has already started opening many more specific bugs for the various
drawImage problems. It's hard to say what percent of the problem is
fixed in Kestrel FCS. Do you mean for the specific Plasma demo that is
mentioned in that bug report? Jim did make changes in that Plasma demo to
generate numbers that were more predictable (for instance not using drawString
to draw the perf numbers on the image). I believe that if there is no scaling
of the image, the numbers are almost comparable with 1.1.8. With scaling,
1.1.8 is still quite a bit faster (I don't have the numbers and Jim
is out for a couple of days).
jeannette
> Date: Tue, 07 Sep 1999 13:11:15 -0400
> From: Augusto Sellhorn <[EMAIL PROTECTED]>
> X-Accept-Language: en
> MIME-Version: 1.0
> To: Jeannette Hung <[EMAIL PROTECTED]>
> CC: [EMAIL PROTECTED]
> Subject: Re: [JAVA2D] Hardware Acceleration
> Content-Transfer-Encoding: 7bit
> Content-Transfer-Encoding: 7bit
>
> Hi Jeannette;
>
> Thanks for answering my question. Of course, we would all like drawImage
> to be fixed
> as soon as possible, but your explination is very good. Two questions;
>
> 1) Can I post your reply as a comment in the bug parade ? People are
> dying for
> more info on this.
>
> 2) Approximately what percent of the problem do the "noticeable changes"
> in Kestrel
> FCS fix (20%, 50%, 80%) ?
>
> Thanks
>
> BTW - It seems a lot of the performance work falls on Jim. Can we send
> him food ,
> money, code, greeting cards, etc. to make him happier/work faster
> ??? :)
>
> Augusto
>
> Jeannette Hung wrote:
> >
> > Hi Augusto,
> > There are a number of reasons that drawImage in JDK1.2+ is slower than
> > JDK1.1. We are trying to address some of the problems but it will not
> > be solved for Kestrel. One reason is that we currently do not store the
> > image into hardware buffers. That is an optimization that we still hope
> > to implement but have not as yet. (It might be easier to do so when
> > Jim finishes the new pipeline architecture -- however that is slated for
> > the next major release after Kestrel.) Another big reason is that we
> > are slow when we scale images. JDK1.1 scaled images directly into
> > the pixmap. We currently scale images into a BufferedImage and then
> > blit it so we have a lot more overhead. Getting rid of the extra
> > BufferedImage will be easier with Jim's new architecture. Another reason is
> > that there is a lot of overhead in our rendering pipeline (and Jim's work
will
> > have cleaned that up). Jim has made some of our blitting loops more
> > efficient (and these changes will be in Kestrel FCS) so there will be
> > some noticeable changes there.
> >
> > jeannette
> --
> - Augusto Sellhorn
===========================================================================
To unsubscribe, send email to [EMAIL PROTECTED] and include in the body
of the message "signoff JAVA2D-INTEREST". For general help, send email to
[EMAIL PROTECTED] and include in the body of the message "help".
