[cairo-commit] papers/opengl_freenix04 ChangeLog,1.7,1.8 opengl_freenix04.bib,1.2,1.3 opengl_freenix04.tex,1.6,1.7

Peter Nilsson commit at pdx.freedesktop.org
Tue Dec 16 07:23:28 PST 2003


Committed by: peter

Update of /cvs/cairo/papers/opengl_freenix04
In directory pdx:/tmp/cvs-serv16057

Modified Files:
	ChangeLog opengl_freenix04.bib opengl_freenix04.tex 
Log Message:
Addressed some more notes

Index: ChangeLog
===================================================================
RCS file: /cvs/cairo/papers/opengl_freenix04/ChangeLog,v
retrieving revision 1.7
retrieving revision 1.8
diff -C2 -d -r1.7 -r1.8
*** ChangeLog	16 Dec 2003 01:23:09 -0000	1.7
--- ChangeLog	16 Dec 2003 15:23:26 -0000	1.8
***************
*** 1,12 ****
  2003-12-16  Peter Nilsson  <c99pnn at cs.umu.se>
!          * layers.png:
!          * layers.eps: Added a sketch diagram
!          * opengl_freenix04.tex: Restructured and rewrote a lot
  
  2003-12-15  Peter Nilsson  <c99pnn at cs.umu.se>
! 	 * cairo-demo-glc.png:
!          * cairo-demo-glc.eps:
!          * cairo-demo-xrender.png:
!          * cairo-demo-xrender.eps: Images have new colors and resolution
  
  2003-12-15  Carl Worth  <cworth at east.isi.edu>
--- 1,16 ----
  2003-12-16  Peter Nilsson  <c99pnn at cs.umu.se>
! 	* opengl_freenix04.tex: Changed the text about Render / XAA and 
! 	some more
! 			
! 2003-12-16  Peter Nilsson  <c99pnn at cs.umu.se>
! 	* layers.png:
! 	* layers.eps: Added a sketch diagram
! 	* opengl_freenix04.tex: Restructured and rewrote a lot
  
  2003-12-15  Peter Nilsson  <c99pnn at cs.umu.se>
! 	* cairo-demo-glc.png:
! 	* cairo-demo-glc.eps:
! 	* cairo-demo-xrender.png:
! 	* cairo-demo-xrender.eps: Images have new colors and resolution
  
  2003-12-15  Carl Worth  <cworth at east.isi.edu>

Index: opengl_freenix04.bib
===================================================================
RCS file: /cvs/cairo/papers/opengl_freenix04/opengl_freenix04.bib,v
retrieving revision 1.2
retrieving revision 1.3
diff -C2 -d -r1.2 -r1.3
*** opengl_freenix04.bib	15 Dec 2003 14:29:38 -0000	1.2
--- opengl_freenix04.bib	16 Dec 2003 15:23:26 -0000	1.3
***************
*** 14,17 ****
--- 14,23 ----
   note		= "\url{http://www.apple.com/macosx/features/quartzextreme}"},
  
+ @misc{imlib2,
+  title		= "Imlib2: An image processing library",
+  author		= "Rasterman and the imlib2 development team",
+  year		= 2003,
+  note		= "\url{http://www.enlightenment.org/pages/imlib2.html}"},
+ 
  @misc{longhorn,
   title		= "Online Resources: Windows Longhorn",

Index: opengl_freenix04.tex
===================================================================
RCS file: /cvs/cairo/papers/opengl_freenix04/opengl_freenix04.tex,v
retrieving revision 1.6
retrieving revision 1.7
diff -C2 -d -r1.6 -r1.7
*** opengl_freenix04.tex	16 Dec 2003 01:23:09 -0000	1.6
--- opengl_freenix04.tex	16 Dec 2003 15:23:26 -0000	1.7
***************
*** 49,53 ****
    
    \section{Introduction}
-   \edannote{Is this introduction easier to follow now?}
    Originally the X Window System wasn't designed for any of the advanced graphics
    that can bee seen on modern desktops today. For a long time it suffered from 
--- 49,52 ----
***************
*** 68,87 ****
    consistent model throughout the rendering system. 
  
!   Although Render can be accelerated by graphics hardware using XAA~\cite{xaa} 
!   to some extent, 
!   \edannote{To what extent? Can you be more specific here? Are 
!     there identifiable limitations in the XAA hooks for Render?} 
!   it requires graphics driver developers to add support for this it requires graphics 
!   driver developers to add support for this
!   in each driver. 
!   \edannote{Point out the problem here. Specifically that there is duplicated 
!     effort and that acceleration support for Render is inconsistent between drivers.}
!   It's probably fair to say that so far, the 
!   few drivers which do support this only do so with modest results. 
!   \edannote{As written, this is vague and unsubstantiated. Can you point to some specific 
!     benchmark? For example, didn't the rasterman run some Render benchmark not too long ago?}
!   Even though this has been sufficient for some time now, the graphical user 
!   interfaces seem to have gone into a new era with the presence of demanding 
!   visual effects like alpha blending, image transformations and anti-aliasing.
  
    Even with today's powerful computers these tasks constitute a heavy burden on 
--- 67,98 ----
    consistent model throughout the rendering system. 
  
!   Render uses the XFree86 Acceleration Architecture (XAA)~\cite{xaa} to achieve
!   hardware accelerated rendering. This requires graphics driver developers to add 
!   their own XAA render hooks in each driver to support it, which results in a 
!   duplicated effort. XAA breaks down complex render operations into simpler ones 
!   and accelerates them if support is provided by the driver, otherwise it falls 
!   back on software. Unfortunately not many drivers have much support for XAA at 
!   this point, which results in an inconsistent acceleration support for Render 
!   between different drivers and hardware.
! 
!   From the benchmarks made in the context of this project (see table 1, section 5)
!   the amount of accelerated rendering achieved by Render doesn't seem to be enough
!   for the complex visual effects addressed by this project. This perticular benchmark
!   is run on a Nvidia system but similar results were attained with Matrox drivers, 
!   which have been known for having the best acceleration support for Render in the past.
! 
!   There was also an other benchmark application called Renderbench released not 
!   too long ago by the people behind imlib2~\cite{imlib2} that compared the 
!   performance of Imlib2 to that of Render. Imlib2 is a image processing library 
!   that uses MMX among other things to accelerate render operations.
!   This benchmark attracted a lot of attention as it clearly shows the superior 
!   rendering performance of imlib2 compared to Render. A detailed comparison 
!   between Imlib2 and the software developed in this project will be presented in 
!   the full paper.
! 
!   The performance of Render has been quite sufficient for some time now, 
!   but in the past years graphical user interfaces seem to have gone into a 
!   new era with the presence of much more demanding visual effects like 
!   alpha blending, image transformations and anti-aliasing.
  
    Even with today's powerful computers these tasks constitute a heavy burden on 
***************
*** 138,142 ****
    \end{figure}
  
!   \edannote{I really dont know about this huge block diagram :)}
  
    The complete paper will present results from extensive research to find 
--- 149,153 ----
    \end{figure}
  
!   \edannote{I really dont know about the huge block diagram :)}
  
    The complete paper will present results from extensive research to find 
***************
*** 263,267 ****
    performance with Cairo, using the different output formats including xrender, 
    images (pure software) and the GL backend developed in this project. 
!   The benchmark application currently contains two separate tests. 
  
    The first 
--- 274,279 ----
    performance with Cairo, using the different output formats including xrender, 
    images (pure software) and the GL backend developed in this project. 
!   This benchmark application, called cairobench, currently contains two 
!   separate tests. 
  
    The first 
***************
*** 295,298 ****
--- 307,320 ----
    \end{table}
  
+   There has also been some benchmarking of imlib2 compared to the software
+   developed here. A benchmark utility called Renderbench was recently 
+   released that points out the superior rendering performance of imlib2
+   compared to that of Render. Renderbench has been ported to instead test 
+   the performance of imlib2 compared to the library developed here. 
+   Although imlib2 is very fast at some tasks, still in most cases it can't 
+   compare to the rendering capabilities of OpenGL. This paper currently lacks 
+   concrete results from these tests but a more detailed comparison will
+   be presented in the full paper.
+ 
    All these testing and benchmarking utilities can be downloaded from the 
    project web site (referenced in Section 7). The site also contains complete 
***************
*** 356,359 ****
--- 378,382 ----
    found at this location.
  
+   \newpage
    \bibliography{opengl_freenix04}
    \bibliographystyle{plain}





More information about the cairo-commit mailing list