[cairo] Very slow performance

[Owen Taylor]

On Tue, 2004-12-28 at 12:05 -0800, Keith Packard wrote:
> Around 18 o'clock on Dec 28, Soeren Sandmann wrote:
> 
> > In my tests when I did the MMX stuff in xorg, 128 bit reads/writes
> > were not an improvement over 64 bit read/writes on the systems I
> > tested on. On some - but not all - systems, 64 bit was an improvement
> > over 32 bit.
> 
> Were these tests to AGP or PCI video memory?  Or main machine memory?  I 
> have been lead to believe that MMX/SSE copy and fill code can run faster 
> than regular instructions because of the way they connect to the main 
> memory interface.

I haven't seen any real difference in fill speed depending on the width
of the writes for cached writes. You can in some cases get huge
performance speedups for "non-temporal" writes that bypass the cache.

The difference between filling at 300meg/s or 1gig/s may be gilding the
lilly. 
Unless fills are going through a function-call-per-pixel slow path, they
are unlikely to be the bottleneck.

Regards,
						Owen

-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 189 bytes
Desc: This is a digitally signed message part
Url : http://lists.freedesktop.org/archives/cairo/attachments/20041228/7a69a31c/attachment.pgp