On Sonntag, 3. März 2002 18:09:18, Gareth Hughes wrote:
> Dieter Nützel wrote:
> > Yes, SPECviewperf worked out of the box, GLperf never tried.
> > Got SPECviewperf running several times for testing the tdfx driver since
> > '2000.
> >
> > I only changed CDEBUGFLAGS in makefile.linux for better Athlon
> > optimization.
> >
> > CDEBUGFLAGS = -O -mcpu=k6 -pipe -mpreferred-stack-boundary=2
> > -malign-functions=4 -fschedule -insns2 -fexpensive-optimizations
>
> Hmmm, I'm not really sure that's legal (in terms of having reportable
> results with a binary compiled like that) :-)
He asked about self compiling...;-)))
Oh and I had forgotten to mention, that he should have a look into
~viewperf-6.2.1/docs/Linux_readme.html.
AMD 1 GHz Athlon II SlotA (0.18µm)
MSI MS-6167 Rev 1.0B (AMD 750, Irongate C4, without bypass)
640 MB PC100-2-2-2 SDRAM
Voodoo5 5500 AGP
DRI CVS trunk (Mesa-4.0.2)
Linux 2.4.19-pre2-ac2 (incl. O(1)-scheduler) + preemption + lock-break
I use the latest -aa VM stuff, too. It delivers much better throughput.
As I asked about latency and preemption before, it should be a design goal for
DRI, too.
If you ever get your hands on such a system, you will _NEVER_ use Linux
without...;-) --- I am under KDE-3.0 beta2, too and it flies!!!
Here are my numbers for AWadvs-04:
viewperf-6.2.1/AWadvs-04> ../tools/vpost.pl -v awadvs viewperf.log
Log file: viewperf.log
Advanced Visualizer (AWadvs-04) Viewset
-------------------------------------------------------------------------------
Test Weight Frames DList Visual Double Frame Buffer Accumulation
# % Per Sec Build ID Buffer R G B A Z Stencil R G B A
-------------------------------------------------------------------------------
1 21.00 15.50 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
2 21.00 14.90 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
3 14.00 20.90 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
4 14.00 21.50 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
5 6.00 14.70 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
6 5.00 15.70 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
7 5.00 14.70 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
8 4.00 18.00 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
9 4.00 16.90 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
10 3.00 17.50 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
11 3.00 16.60 0.000 0X29 True 8 8 8 8 24 8 0 0 0 0
--------------------------------------------------------------------------------
Weighted Geometric Mean = 16.948
Cheers,
Dieter
_______________________________________________
Dri-devel mailing list
[EMAIL PROTECTED]
https://lists.sourceforge.net/lists/listinfo/dri-devel
