Malte Cornils wrote:
Hi,
I'm having a visual problem with an application (NWN under Wine) - it works
fine with LIBGL_ALWAYS_INDIRECT=true but displays the problem (some textures
flicker and show wrong colours) with hardware-accelerated r200.
How can I selectively disable/enable hardware accelera
On Wed, Oct 23, 2002 at 01:01:39AM +0100, Alan Cox wrote:
> ...
> Prefetching tends to be a win. What to prefetch is a harder question
> normally solved by benchmarking. When the card does DMA access to a
> buffer it will suck it from the processor L2 caches.
Pleaes define "suck" in this scenario.
Ian Romanick wrote:
On Wed, Oct 23, 2002 at 12:27:57AM +0200, Charl P. Botha wrote:
On Tue, Oct 22, 2002 at 03:12:52PM -0700, Ian Romanick wrote:
On Tue, Oct 22, 2002 at 12:46:27AM +0200, Charl P. Botha wrote:
Run glthreads with something like: glthreads -n 5
Here's an additional data poi
Around 1 o'clock on Oct 23, Alan Cox wrote:
> Uncached writes on PC hardware are almost always a complete loss. You
> want the writeback caching so you are writing to the PCI bridge or sdram
> in the largest chunk sizes possible.
The problem with cached writes is that each cacheline will be brou
Hi,
My configuration file is just a basic config file with no fancy stuff
(i attached a copy of it).
I don't see any errors in the log. The most weird thing is that i talk with some
people on #xfree86 (opn) and they don't have any problems.
I still have those even on a complete freshly reinstalle
Alan Hourihane wrote:
On Tue, Oct 22, 2002 at 12:21:00 -0700, Ian Romanick wrote:
Current CVS will not build. It dies trying to link
../../../../extras/freetype2/src/base/ftbase.c to lib/font/FreeType/module/.
I know that some merging is under way from XFree86 CVS. Could that effort
finish to
Allen Akin wrote:
On Tue, Oct 22, 2002 at 11:56:19AM -0700, Ian Romanick wrote:
|
| After the meeting, I thought of another possible usage. A number of
| companies, most notably id Software, are using home-grown shading languages.
| Depending on the set of available hardware features, they pick
On Wed, Oct 23, 2002 at 01:01:39AM +0100, Alan Cox wrote:
On Wed, 2002-10-23 at 00:19, José Fonseca wrote:
[...]
I'm not sure what you mean with "cache" above, but the Mach64 has a ring
buffer with all the pending DMA buffers, so there will be DMA transfer
simultaneously with the copy/verify, bu
On Tue, Oct 22, 2002 at 11:56:19AM -0700, Ian Romanick wrote:
|
| After the meeting, I thought of another possible usage. A number of
| companies, most notably id Software, are using home-grown shading languages.
| Depending on the set of available hardware features, they pick a different
| back-
On Wed, 2002-10-23 at 00:19, José Fonseca wrote:
> >Is it neccessary to copy all the data then DMA it or can you pipeline it
> >so that the DMA is writing out some of the cache while you copy data in
> >and verify it ?
>
> I'm not sure what you mean with "cache" above, but the Mach64 has a ring
>
On Tue, Oct 22, 2002 at 12:21:00 -0700, Ian Romanick wrote:
> Current CVS will not build. It dies trying to link
> ../../../../extras/freetype2/src/base/ftbase.c to lib/font/FreeType/module/.
> I know that some merging is under way from XFree86 CVS. Could that effort
> finish to a point where DRI
loser look at the radeon driver this weekend so that
he's happy with the merge. But if anyone does find problems - please
report them, or the other CVS committers can fix it up as they need.
I've tagged the trunk before I started with the tag 'trunk-20021022' and
after the m
On Wed, 23 Oct 2002 00:37:47 +0200
Malte Cornils <[EMAIL PROTECTED]> wrote:
> Hi,
>
> I'm having a visual problem with an application (NWN under Wine) - it works
> fine with LIBGL_ALWAYS_INDIRECT=true but displays the problem (some textures
> flicker and show wrong colours) with hardware-accelera
On Tue, Oct 22, 2002 at 10:24:04PM +0100, Alan Cox wrote:
[...]
I can believe there are objects in 3D rendering big enough to be worth
mapping but I'd be guessing to name a size. Linus as a chip hacker might
actually have more detailed numbers.
At least with the Mach64 is very rare for this to
On Wed, Oct 23, 2002 at 12:27:57AM +0200, Charl P. Botha wrote:
> On Tue, Oct 22, 2002 at 03:12:52PM -0700, Ian Romanick wrote:
> > On Tue, Oct 22, 2002 at 12:46:27AM +0200, Charl P. Botha wrote:
> >
> > > Run glthreads with something like: glthreads -n 5
> >
> > Here's an additional data point.
Hi,
I'm having a visual problem with an application (NWN under Wine) - it works
fine with LIBGL_ALWAYS_INDIRECT=true but displays the problem (some textures
flicker and show wrong colours) with hardware-accelerated r200.
How can I selectively disable/enable hardware acceleration for certain
OpenG
On Tue, Oct 22, 2002 at 03:12:52PM -0700, Ian Romanick wrote:
> On Tue, Oct 22, 2002 at 12:46:27AM +0200, Charl P. Botha wrote:
>
> > Run glthreads with something like: glthreads -n 5
>
> Here's an additional data point. If you move the call to glXDestroyContext
> to the end of draw_loop (and d
On Tue, Oct 22, 2002 at 12:46:27AM +0200, Charl P. Botha wrote:
> Run glthreads with something like: glthreads -n 5
Here's an additional data point. If you move the call to glXDestroyContext
to the end of draw_loop (and delete the other two calls), the program works
as expected on the Radeon.
On Tue, Oct 22, 2002 at 01:48:35PM -0700, Keith Packard wrote:
>
> Around 13 o'clock on Oct 22, Ian Romanick wrote:
>
> > I would recommend an audit then a copy, with the DMA buffer being setup as
> > non-cached, write combining memory (like AGP mapped memory).
>
> Non-cached write combining mem
Hi,
On Tue, Oct 22, 2002 at 01:07:24PM +0200, Michel Dänzer wrote:
> The gotcha about TREE is that you have to provide the include directory, so
> you'd have to use TREE=/home/mcornils/kernel-source-2.4.18/include in this case.
Errm, is this documented somewhere? Couldn't this be part of the inst
On Tue, 2002-10-22 at 21:51, Keith Packard wrote:
> How expensive is it on a uniprocessor system? Copying data prior to DMA
> is not free, especially if the buffers span a significant fraction of
> the cache size.
Its actually very hard to measure, because the impact is felt down the
line not i
Around 21 o'clock on Oct 22, Alan Cox wrote:
> Unmapping something, especially with threaded apps on SMP boxes is
> really really expensive. If you do the audit as you copy the data it may
> well actually cost no more than a single copy
How expensive is it on a uniprocessor system? Copying data
Around 13 o'clock on Oct 22, Ian Romanick wrote:
> I would recommend an audit then a copy, with the DMA buffer being setup as
> non-cached, write combining memory (like AGP mapped memory).
Non-cached write combining memory doesn't go through the regular cache
buffers and is significantly slower
On Tue, 2002-10-22 at 21:13, Frank C. Earl wrote:
> On Tuesday 22 October 2002 03:00 pm, you wrote:
>
> > But wouldnt it be nice to allow the graphics card to directly access
> > the data from user space ?
> > It seems to defeat the whole point of DMA, if you have to do multiple
> > copies of the
On Tue, Oct 22, 2002 at 03:13:09PM -0500, Frank C. Earl wrote:
> On Tuesday 22 October 2002 03:00 pm, you wrote:
>
> > But wouldnt it be nice to allow the graphics card to directly access
> > the data from user space ?
> > It seems to defeat the whole point of DMA, if you have to do multiple
> > c
On Tuesday 22 October 2002 03:00 pm, you wrote:
> But wouldnt it be nice to allow the graphics card to directly access
> the data from user space ?
> It seems to defeat the whole point of DMA, if you have to do multiple
> copies of the data.
DMA allows you to do other things while the display chi
Current CVS will not build. It dies trying to link
../../../../extras/freetype2/src/base/ftbase.c to lib/font/FreeType/module/.
I know that some merging is under way from XFree86 CVS. Could that effort
finish to a point where DRI CVS will at least build? :)
--
Smile! http://antwrp.gsfc.nasa.go
On Mon, Oct 21, 2002 at 04:28:12PM -0700, Allen Akin wrote:
> One open question is the usage model for such an extension. Keith
> suggested that developers will write a small number of code paths, and
> then the app will choose one of these at runtime. Typically it'll
> choose the "grooviest" pa
On Tue, Oct 22, 2002 at 11:31:00AM +0100, José Fonseca wrote:
> On Tue, Oct 22, 2002 at 10:34:58AM +0100, Alan Hourihane wrote:
> >I'm about to start a merge of the XFree86 CVS and bring that into
> >the DRI CVS trunk. No doubt with the trees diverging quite a bit, that
> >there will undoubtably be
On Die, 2002-10-22 at 02:43, Malte Cornils wrote:
> On Mon, Oct 21, 2002 at 08:08:20PM +0200, Benjamin Herrenschmidt wrote:
> > >[using /usr/include/linux etc symlinks]
> > >Worked for ages.
> >
> > Well, maybe, but it has always been the wrong thing to do,
> > at least according to Linus, and th
On Mon, 2002-10-21 at 16:17, Keith Whitwell wrote:
> Michel Dänzer wrote:
> > On Sam, 2002-10-19 at 08:10, Allen Akin wrote:
> >
> >>On Fri, Oct 18, 2002 at 07:48:53PM -0700, Ian Romanick wrote:
> >>|
> >>| I had never run glean before, but all I can say is, "Wow!" Without this
> >>| second pat
On Die, 2002-10-22 at 00:36, Felix Kühling wrote:
>
> as a conclusion from the "gcc-3.2 problems" thread a week ago, here is a
> patch that fixes inconsistent type aliasing in the radeon and r200
> drivers. Can someone with CVS access commit this please?
Done, thanks.
--
Earthling Michel Dänze
On Mon, 2002-10-21 at 21:07, Kees Cook wrote:
> On Mon, Oct 21, 2002 at 07:53:13PM +0200, Michel Dänzer wrote:
> > FWIW, I have an AGP 7000 running with PCI GART right now. It has locked
>
> Which binaries need to be replaced?
radeon_drv.o (the 2D driver) and radeon.o (the DRM).
> I built the d
On Son, 2002-10-20 at 08:15, Matthieu Bonetti wrote:
>
> I am running the lastest dri drivers for my ati radeon 7500 on a X 4.2.1
>
> When I want to play a video with Xv or to play a 3D games (2D games work
> fine ?!) the part of the screen where the movie/game is is covered by
> some "color" do
On Tue, Oct 22, 2002 at 10:34:58AM +0100, Alan Hourihane wrote:
I'm about to start a merge of the XFree86 CVS and bring that into
the DRI CVS trunk. No doubt with the trees diverging quite a bit, that
there will undoubtably be some build bustage along the way.
I'll be bringing it across in stages
On Die, 2002-10-22 at 11:34, Alan Hourihane wrote:
> I'm about to start a merge of the XFree86 CVS and bring that into
> the DRI CVS trunk. No doubt with the trees diverging quite a bit, that
> there will undoubtably be some build bustage along the way.
>
> I'll be bringing it across in stages to
I'm about to start a merge of the XFree86 CVS and bring that into
the DRI CVS trunk. No doubt with the trees diverging quite a bit, that
there will undoubtably be some build bustage along the way.
I'll be bringing it across in stages to try and minimize the disruption.
Jose - it may be worth disa
On Tue, Oct 22, 2002 at 12:35:45AM +0100, José Fonseca wrote:
> ..
> > I think we'll need a set of private buffers equivalent to what
> >we use now (2MB), but we could probably get away with a smaller set of
> >client buffers.
>
> I agree. In principle, each client could even use the same buff
38 matches
Mail list logo
