Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-09-04 Thread Søren Sandmann
Siarhei Siamashka siarhei.siamas...@gmail.com writes: On Thu, 29 Aug 2013 05:59:26 +0200 sandm...@cs.au.dk (Søren Sandmann) wrote: Siarhei Siamashka siarhei.siamas...@gmail.com writes: With this new alignment assumption, such an optimization becomes even more impossible,

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-09-04 Thread Bill Spitzak
Søren Sandmann wrote: Here is another proposal, but I'm not sure it's really better: - The combiners are made to return a buffer. The returned buffer is expected to contain the combined result and may be any of the passed src/mask/dest buffers. Almost all combiners will continue to combine

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-09-01 Thread Siarhei Siamashka
On Thu, 29 Aug 2013 05:59:26 +0200 sandm...@cs.au.dk (Søren Sandmann) wrote: Siarhei Siamashka siarhei.siamas...@gmail.com writes: With this new alignment assumption, such an optimization becomes even more impossible, Implementing this optimization does not seem to be too difficult in

[Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-08-28 Thread Søren Sandmann
From: Søren Sandmann Pedersen s...@redhat.com Now that the general implementation guarantees that the iter buffers are aligned to 16 bytes, there is no longer any reason for the initial loop to bring the destination buffer up to an aligned position. --- pixman/pixman-mmx.c | 20

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-08-28 Thread Siarhei Siamashka
On Wed, 28 Aug 2013 16:01:27 -0400 Søren Sandmann sandm...@cs.au.dk wrote: From: Søren Sandmann Pedersen s...@redhat.com Now that the general implementation guarantees that the iter buffers are aligned to 16 bytes, there is no longer any reason for the initial loop to bring the destination

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-08-28 Thread Søren Sandmann
Siarhei Siamashka siarhei.siamas...@gmail.com writes: On Wed, 28 Aug 2013 16:01:27 -0400 Søren Sandmann sandm...@cs.au.dk wrote: From: Søren Sandmann Pedersen s...@redhat.com Now that the general implementation guarantees that the iter buffers are aligned to 16 bytes, there is no longer

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-08-28 Thread Siarhei Siamashka
On Thu, 29 Aug 2013 01:27:08 +0200 sandm...@cs.au.dk (Søren Sandmann) wrote: Siarhei Siamashka siarhei.siamas...@gmail.com writes: On Wed, 28 Aug 2013 16:01:27 -0400 Søren Sandmann sandm...@cs.au.dk wrote: From: Søren Sandmann Pedersen s...@redhat.com Now that the general

Re: [Pixman] [PATCH 2/2] sse2, mmx: Remove initial unaligned loops in fetchers

2013-08-28 Thread Søren Sandmann
Siarhei Siamashka siarhei.siamas...@gmail.com writes: With this new alignment assumption, such an optimization becomes even more impossible, Implementing this optimization does not seem to be too difficult in principle. I tried to hack a bit and here is the result: