* Beginner question about fbdev performance
@ 2010-03-08 0:16 Egor Nogdor
2010-03-10 17:12 ` James Simmons
0 siblings, 1 reply; 2+ messages in thread
From: Egor Nogdor @ 2010-03-08 0:16 UTC (permalink / raw)
To: linux-fbdev
Hi,
Why is it that the unaccelerated framebuffer device is slower than
e.g. an accelerated X session when blitting data from main memory?
Shouldn't both cases involve simply copying data from RAM to VRAM?
What is the bottleneck in the former case?
Thanks,
Anders
^ permalink raw reply [flat|nested] 2+ messages in thread
* Re: Beginner question about fbdev performance
2010-03-08 0:16 Beginner question about fbdev performance Egor Nogdor
@ 2010-03-10 17:12 ` James Simmons
0 siblings, 0 replies; 2+ messages in thread
From: James Simmons @ 2010-03-10 17:12 UTC (permalink / raw)
To: linux-fbdev
> Hi,
>
> Why is it that the unaccelerated framebuffer device is slower than
> e.g. an accelerated X session when blitting data from main memory?
> Shouldn't both cases involve simply copying data from RAM to VRAM?
> What is the bottleneck in the former case?
Its all about the the transfer method. An unaccelerated draw transfers
image data over the pci bus pixel by pixel. The accelerated session
usually used a DMA transfer. Yes a framebuffer could use a DMA transfer in
the driver but that is only used internally by the console system. Its not
avaliable to userland for use.
^ permalink raw reply [flat|nested] 2+ messages in thread
end of thread, other threads:[~2010-03-10 17:12 UTC | newest]
Thread overview: 2+ messages (download: mbox.gz follow: Atom feed
-- links below jump to the message on this page --
2010-03-08 0:16 Beginner question about fbdev performance Egor Nogdor
2010-03-10 17:12 ` James Simmons
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).