Go Back   nV News Forums > Linux Support Forums > NVIDIA Linux

Newegg Daily Deals

Reply
 
Thread Tools
Old 01-06-06, 09:23 AM   #13
zander
NVIDIA Corporation
 
zander's Avatar
 
Join Date: Aug 2002
Posts: 3,740
Default Re: horrible 2D performance

@PrakashP: current NVIDIA Linux drivers use the processor's PAT to mark frame buffer and/or AGP aperture mappings write-combined, a MTRR is not installed for the relevant I/O apertures.
zander is offline   Reply With Quote
Old 01-06-06, 09:48 AM   #14
Enverex
Registered User
 
Join Date: Jan 2006
Location: Worcester, UK
Posts: 29
Default Re: horrible 2D performance

hmm, Turning Render Accell on got me down to 3.66 in Monochrome AA mode, but the same 10.X score with Subpixel Hinting turned on. My machine also hardlocked after a while of using Cedega with RenderAccel turned on (it's never locked before). So it seems I'd only gain when using not AA'd fonts anyway.
Enverex is offline   Reply With Quote
Old 01-06-06, 11:19 AM   #15
PrakashP
gentoo ~x86_64 user
 
PrakashP's Avatar
 
Join Date: Jul 2004
Location: Germania
Posts: 213
Default Re: horrible 2D performance

Quote:
Originally Posted by zander
@PrakashP: current NVIDIA Linux drivers use the processor's PAT to mark frame buffer and/or AGP aperture mappings write-combined, a MTRR is not installed for the relevant I/O apertures.
Interesting, I thought you needed kernel support for that? I read in the mailing list archive that Terrence Ripperda once posted a patch for PAT in the kernel, but it wasn't merged because of Intel erratas or alike.
PrakashP is offline   Reply With Quote
Old 01-06-06, 11:27 AM   #16
zander
NVIDIA Corporation
 
zander's Avatar
 
Join Date: Aug 2002
Posts: 3,740
Default Re: horrible 2D performance

@PrakashP: ideally the kernel would configure and support a WC entry in the PAT, but in addition to basic support that's trivial to implement on Linux (even taking into account the errata you refer to), there's been interest in establishing a mechanism to prevent the creation of mappings with conflicting memory types. This is relatively simple for the NVIDIA driver to ensure internally, but non-trivial to implement globally.
zander is offline   Reply With Quote
Old 01-06-06, 11:43 AM   #17
PrakashP
gentoo ~x86_64 user
 
PrakashP's Avatar
 
Join Date: Jul 2004
Location: Germania
Posts: 213
Default Re: horrible 2D performance

@zander

Good to know, maybe you want to put that info into the README that the user doesn't need to mess around with mtrr anymore then. At least I couldn't find anything about this issue there...
PrakashP is offline   Reply With Quote
Old 01-06-06, 11:51 AM   #18
zander
NVIDIA Corporation
 
zander's Avatar
 
Join Date: Aug 2002
Posts: 3,740
Default Re: horrible 2D performance

@PrakashP: on most systems, it was very rarely necessary to manually adjust the MTRR configuration established by the NVIDIA Linux graphics driver even before the transition to using the PAT. The official NVIDIA README never suggested this in the first place. ;)
zander is offline   Reply With Quote
Old 01-06-06, 12:25 PM   #19
ppd
Registered User
 
Join Date: Jan 2006
Posts: 6
Default Re: horrible 2D performance

I think I'll stay with the nv driver.
The latest nvidia driver feels extremely unsnappy, at least after a suspend to disk. The 7667 is smooth and fast, but it won't work with suspend2.
The nv driver is slow, the gnome rubberband lags, but it works a million times better with suspend to disk than the nvidia driver and 2d performance is acceptable compared to the latest nvidia driver.

max
ppd is offline   Reply With Quote
Old 01-06-06, 04:32 PM   #20
ViRgiLiO
Registered User
 
Join Date: Jul 2003
Posts: 21
Default Re: horrible 2D performance

zander, I know you heard this question several times, but will we have a subpixel AA in the next release?
ViRgiLiO is offline   Reply With Quote

Old 01-06-06, 06:13 PM   #21
AaronP
NVIDIA Corporation
 
AaronP's Avatar
 
Join Date: Mar 2005
Posts: 2,487
Default Re: horrible 2D performance

Quote:
Originally Posted by ViRgiLiO
zander, I know you heard this question several times, but will we have a subpixel AA in the next release?
ViRgiLiO,
I'm aware of the issues involved and hope to get acceleration for it into the next release, but I'll have to do some more testing and unfortunately can't make any promises.
AaronP is offline   Reply With Quote
Old 01-06-06, 08:14 PM   #22
ViRgiLiO
Registered User
 
Join Date: Jul 2003
Posts: 21
Default Re: horrible 2D performance

Ok, thanks AaronP for your quick answer. I'm glad to hear that someone is working on that problem. I really hope that you find the solution.
ViRgiLiO is offline   Reply With Quote
Reply


Thread Tools

Posting Rules
You may not post new threads
You may not post replies
You may not post attachments
You may not edit your posts

BB code is On
Smilies are On
[IMG] code is On
HTML code is Off
Forum Jump


Similar Threads
Thread Thread Starter Forum Replies Last Post
Disk Performance Expectations vs. Reality News Archived News Items 0 05-27-12 04:00 PM
Boost Your Performance Goals 10x ' This Week on inside* Publications News Archived News Items 0 05-13-12 06:20 PM
NVIDIA Unleashes the GeForce GTX 670 Graphics Card ' Performance Perfected (WCCFTECH) News GeForce GTX 670 Reviews 0 05-10-12 09:40 AM
My UT2003 Tweak Guide DXnfiniteFX Gaming Central 48 10-31-02 12:59 AM
so let's try this again in the new forum - bad performance with correctly inst.driver neutrino NVIDIA Linux 11 08-01-02 05:19 PM

All times are GMT -5. The time now is 08:43 AM.


Powered by vBulletin® Version 3.7.1
Copyright ©2000 - 2014, Jelsoft Enterprises Ltd.
Copyright 1998 - 2014, nV News.