platform/upstream/pixman.git
15 years agoEnable sse2CombineAddU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:52 +0000 (01:00 -0400)]
Enable sse2CombineAddU

15 years agoEnable sse2CombineAtopXorU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:47 +0000 (01:00 -0400)]
Enable sse2CombineAtopXorU

15 years agoEnable sse2CombineAtopReverseU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:39 +0000 (01:00 -0400)]
Enable sse2CombineAtopReverseU

15 years agoEnable sse2CombineAtopU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:33 +0000 (01:00 -0400)]
Enable sse2CombineAtopU

15 years agoEnable sse2CombineOutReverseU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:26 +0000 (01:00 -0400)]
Enable sse2CombineOutReverseU

15 years agoEnable sse2CombineOutU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:20 +0000 (01:00 -0400)]
Enable sse2CombineOutU

15 years agoEnable sse2CombineInReverseU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:12 +0000 (01:00 -0400)]
Enable sse2CombineInReverseU

15 years agoEnable sse2CombineInU
Søren Sandmann Pedersen [Fri, 1 May 2009 05:00:07 +0000 (01:00 -0400)]
Enable sse2CombineInU

15 years agoEnable sse2CombineOverReverseU
Søren Sandmann Pedersen [Fri, 1 May 2009 04:59:59 +0000 (00:59 -0400)]
Enable sse2CombineOverReverseU

15 years agoEnable sse2CombineOverU
Søren Sandmann Pedersen [Fri, 1 May 2009 04:59:51 +0000 (00:59 -0400)]
Enable sse2CombineOverU

15 years agoImplement the sse2 combiners with masks (disabled)
Søren Sandmann Pedersen [Fri, 1 May 2009 04:59:29 +0000 (00:59 -0400)]
Implement the sse2 combiners with masks (disabled)

15 years agoUse memcpy() in fbCombineSrcU when there is no mask
Søren Sandmann Pedersen [Fri, 1 May 2009 04:58:38 +0000 (00:58 -0400)]
Use memcpy() in fbCombineSrcU when there is no mask

15 years agoHave the generic code go through the component alpha path always
Søren Sandmann Pedersen [Thu, 30 Apr 2009 21:59:09 +0000 (17:59 -0400)]
Have the generic code go through the component alpha path always

15 years agoGet rid of separate combineU and combineC types
Søren Sandmann Pedersen [Thu, 30 Apr 2009 21:53:48 +0000 (17:53 -0400)]
Get rid of separate combineU and combineC types

15 years agoChange type of combineU to take a mask
Søren Sandmann Pedersen [Thu, 30 Apr 2009 21:14:04 +0000 (17:14 -0400)]
Change type of combineU to take a mask

15 years agoMake combineC function type take const args
Søren Sandmann Pedersen [Thu, 30 Apr 2009 23:50:24 +0000 (19:50 -0400)]
Make combineC function type take const args

Fix type of mmx component alpha combiners

Fix type of sse2 component alpha combiners

Fix type of vmx component alpha combiners

15 years agoRemove accessor version of pixman-compose.c
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:54:32 +0000 (02:54 -0400)]
Remove accessor version of pixman-compose.c

15 years agoRemove unused xoff/yoff variables
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:51:09 +0000 (02:51 -0400)]
Remove unused xoff/yoff variables

15 years agoMove store logic into pixman-image.c
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:50:18 +0000 (02:50 -0400)]
Move store logic into pixman-image.c

15 years agoMove fetch logic to pixman-image.c
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:42:47 +0000 (02:42 -0400)]
Move fetch logic to pixman-image.c

15 years agoSimplify logic to compute store function
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:25:48 +0000 (02:25 -0400)]
Simplify logic to compute store function

15 years agoFormatting
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:14:13 +0000 (02:14 -0400)]
Formatting

15 years agoFactor out duplicated fetcher finding code
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:08:44 +0000 (02:08 -0400)]
Factor out duplicated fetcher finding code

15 years agoGet rid of SOURCE_IMAGE_CLASS_NEITHER again
Søren Sandmann Pedersen [Thu, 30 Apr 2009 06:03:03 +0000 (02:03 -0400)]
Get rid of SOURCE_IMAGE_CLASS_NEITHER again

15 years agoMore refactoring notes
Søren Sandmann Pedersen [Thu, 30 Apr 2009 05:49:13 +0000 (01:49 -0400)]
More refactoring notes

15 years agoAdd notes on how Render actually works
Søren Sandmann Pedersen [Thu, 30 Apr 2009 03:13:14 +0000 (23:13 -0400)]
Add notes on how Render actually works

15 years agoMove calls of the classification out of the if statements.
Søren Sandmann Pedersen [Thu, 30 Apr 2009 00:15:20 +0000 (20:15 -0400)]
Move calls of the classification out of the if statements.

15 years agoMove SourcePictClassify into pixman-image.c
Søren Sandmann Pedersen [Wed, 29 Apr 2009 23:55:19 +0000 (19:55 -0400)]
Move SourcePictClassify into pixman-image.c

In preparation for making pixman_image_t more of a real object, move
SourcePictClassify into pixman-image.c and expose it through a
function pointer. Later, this function will be split into smaller
functions depending on the exact type of the image.

15 years agoMore refactoring notes
Søren Sandmann Pedersen [Wed, 29 Apr 2009 05:44:56 +0000 (01:44 -0400)]
More refactoring notes

15 years agoAdd refactoring notes
Søren Sandmann Pedersen [Wed, 29 Apr 2009 03:02:49 +0000 (23:02 -0400)]
Add refactoring notes

15 years agoMention utils.h in test/Makefile.am so that make dist will pick it up
Søren Sandmann Pedersen [Mon, 4 May 2009 22:54:27 +0000 (18:54 -0400)]
Mention utils.h in test/Makefile.am so that make dist will pick it up

Pointed out by Julien Cristau.

15 years agoMove all the GTK+ test code into its own file, utils.c
Søren Sandmann Pedersen [Mon, 4 May 2009 22:34:54 +0000 (18:34 -0400)]
Move all the GTK+ test code into its own file, utils.c

15 years agoInclude string.h and fix warning in trap-test.c
Søren Sandmann Pedersen [Wed, 29 Apr 2009 02:49:31 +0000 (22:49 -0400)]
Include string.h and fix warning in trap-test.c

15 years agoAdd solaris-hwcap.mapfile to EXTRA_DIST
Alan Coopersmith [Tue, 28 Apr 2009 15:44:47 +0000 (08:44 -0700)]
Add solaris-hwcap.mapfile to EXTRA_DIST

Signed-off-by: Alan Coopersmith <alan.coopersmith@sun.com>
15 years agoUpdated scaling test to support rgb565, source clipping, etc.
Siarhei Siamashka [Mon, 20 Apr 2009 13:13:44 +0000 (16:13 +0300)]
Updated scaling test to support rgb565, source clipping, etc.

Now test provides better coverage for various image scaling
cases. Unused byte for x8r8g8b8 format is ignored. Running
the test program without any command line options provides
a PASS/FAIL verdict based on the precalculated crc32 value
for using pixman with all the fastpath functions disabled,
which should simplify testing for correcteness.

15 years agoAdd trap-crasher.c test program
Søren Sandmann Pedersen [Sat, 25 Apr 2009 01:35:46 +0000 (21:35 -0400)]
Add trap-crasher.c test program

Based off of Pavel Kankovsky's test case in bug 16560.

15 years agoEnable fbCompositeSolidMask_nx8x8888neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:38 +0000 (17:32 -0400)]
Enable fbCompositeSolidMask_nx8x8888neon

15 years agoEnable fbCompositeSolidMask_nx8x0565neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:38 +0000 (17:32 -0400)]
Enable fbCompositeSolidMask_nx8x0565neon

15 years agoEnable fbCompositeSrc_8888x8x8888neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:38 +0000 (17:32 -0400)]
Enable fbCompositeSrc_8888x8x8888neon

15 years agoEnable fbCompositeSrc_8888x8888neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:38 +0000 (17:32 -0400)]
Enable fbCompositeSrc_8888x8888neon

15 years agoEnable fbCompositeSrc_x888x0565neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:37 +0000 (17:32 -0400)]
Enable fbCompositeSrc_x888x0565neon

15 years agoEnable fbCompositeSrcAdd_8000x8000neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:37 +0000 (17:32 -0400)]
Enable fbCompositeSrcAdd_8000x8000neon

15 years agoEnable fbCompositeSrcAdd_8888x8x8neon
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:37 +0000 (17:32 -0400)]
Enable fbCompositeSrcAdd_8888x8x8neon

15 years agoAdd support for ARM NEON fast paths
Ian Rickards [Tue, 21 Apr 2009 21:32:36 +0000 (17:32 -0400)]
Add support for ARM NEON fast paths

Currently disabled

15 years agoAdd support for doing ARM simd detection on Windows
Jeff Muizelaar [Tue, 21 Apr 2009 21:32:36 +0000 (17:32 -0400)]
Add support for doing ARM simd detection on Windows

15 years agoAdd support for doing ARM simd detection on Windows
Jeff Muizelaar [Wed, 15 Apr 2009 14:38:37 +0000 (10:38 -0400)]
Add support for doing ARM simd detection on Windows

15 years agoPost-release version bump
Søren Sandmann Pedersen [Fri, 10 Apr 2009 00:38:53 +0000 (20:38 -0400)]
Post-release version bump

15 years agoPre-release version bump pixman-0.15.2
Søren Sandmann Pedersen [Thu, 9 Apr 2009 20:38:05 +0000 (16:38 -0400)]
Pre-release version bump

15 years agoFix search and replace issue
Søren Sandmann Pedersen [Mon, 6 Apr 2009 19:25:03 +0000 (15:25 -0400)]
Fix search and replace issue

15 years agoReplace custom type ullong with standard uint64_t in pixman-mmx.c
Alan Coopersmith [Fri, 3 Apr 2009 20:02:37 +0000 (13:02 -0700)]
Replace custom type ullong with standard uint64_t in pixman-mmx.c

Signed-off-by: Alan Coopersmith <alan.coopersmith@sun.com>
15 years agoFix MMX & SSE intrinsics to work with Sun compilers & Solaris
Alan Coopersmith [Fri, 3 Apr 2009 19:40:10 +0000 (12:40 -0700)]
Fix MMX & SSE intrinsics to work with Sun compilers & Solaris

Signed-off-by: Alan Coopersmith <alan.coopersmith@sun.com>
15 years agoFix pixbuf_from_argb32() to take premultiplied alpha into account
Søren Sandmann Pedersen [Sat, 4 Apr 2009 10:04:42 +0000 (06:04 -0400)]
Fix pixbuf_from_argb32() to take premultiplied alpha into account

15 years agoAdd a new trap-test test program.
Søren Sandmann Pedersen [Sat, 4 Apr 2009 09:57:20 +0000 (05:57 -0400)]
Add a new trap-test test program.

Also some tweaks to the build system in the test directory to make it
build non-gtk+-using application when use of gtk+ is disabled.

15 years agoSet srcRepeat = False when using fbCompositeSrcScaleNearest
Siarhei Siamashka [Wed, 1 Apr 2009 22:26:24 +0000 (18:26 -0400)]
Set srcRepeat = False when using fbCompositeSrcScaleNearest

NORMAL repeat was broken (the optimized function can handle repeat operation
itself and can be screwed up if 'pixman_walk_composite_region' tries to help it
by splitting the work into handling multiple separate areas).

Splitting work into handling different areas does not work right for the
transform case (and it is never used for generic path).  The point is that this
splitting only has full pixel precision at the moment, while correct blitting
needs to preserve some fractional part in calculations when moving from one
"tile" to another.

15 years agoImage scaling regression test script
Siarhei Siamashka [Tue, 31 Mar 2009 17:58:56 +0000 (20:58 +0300)]
Image scaling regression test script

This test script can help in finding regressions in image scaling
fastpath implementations. It uses test program compiled with
and without fastpath code and can compare results of execution
for different pseudorandom compositing operations involving scaling.

Signed-off-by: Søren Sandmann Pedersen <sandmann@redhat.com>
15 years agoAdd support for BGRA and BGRx formats.
Mark Kettenis [Tue, 24 Mar 2009 18:28:38 +0000 (14:28 -0400)]
Add support for BGRA and BGRx formats.

15 years agoCheck for failure when intersecting regions.
Chris Wilson [Tue, 17 Mar 2009 13:28:31 +0000 (13:28 +0000)]
Check for failure when intersecting regions.

Need to check and report the failure of intersecting the rectangle with
the clip region during pixman_image_fill_rectangles().

15 years agoCheck for allocation errors during pixman_op()
Chris Wilson [Tue, 17 Mar 2009 08:39:48 +0000 (08:39 +0000)]
Check for allocation errors during pixman_op()

Propagate the error returns from pixman_rect_alloc().

15 years agoRemove stale comment
Søren Sandmann Pedersen [Wed, 11 Feb 2009 00:47:19 +0000 (19:47 -0500)]
Remove stale comment

15 years agoAdd license and copyright holders to COPYING
Søren Sandmann Pedersen [Sat, 7 Feb 2009 00:41:24 +0000 (19:41 -0500)]
Add license and copyright holders to COPYING

15 years agoImplement PIXMAN_REPEAT_REFLECT for images
Thomas Jaeger [Tue, 20 Jan 2009 23:40:46 +0000 (18:40 -0500)]
Implement PIXMAN_REPEAT_REFLECT for images

15 years agoReinstate SrcScaledNearest optimization
Søren Sandmann Pedersen [Fri, 6 Feb 2009 23:03:31 +0000 (18:03 -0500)]
Reinstate SrcScaledNearest optimization

15 years agoBump version number post-release
Søren Sandmann Pedersen [Fri, 6 Feb 2009 23:01:57 +0000 (18:01 -0500)]
Bump version number post-release

15 years agoBump version number pre release pixman-0.14.0
Søren Sandmann Pedersen [Fri, 6 Feb 2009 22:31:32 +0000 (17:31 -0500)]
Bump version number pre release

15 years agoComment out SrcScaledNearest optimization that hasn't been tested much
Søren Sandmann Pedersen [Fri, 6 Feb 2009 22:30:24 +0000 (17:30 -0500)]
Comment out SrcScaledNearest optimization that hasn't been tested much

15 years agoFix release targets to remove all hashfiles before generating tar balls
Søren Sandmann Pedersen [Fri, 6 Feb 2009 22:29:04 +0000 (17:29 -0500)]
Fix release targets to remove all hashfiles before generating tar balls

15 years agoAdd pixman-matrix.c to Makefile.win32
Jeff Muizelaar [Fri, 9 Jan 2009 17:48:22 +0000 (12:48 -0500)]
Add pixman-matrix.c to Makefile.win32

15 years agoConditionally include config.h in pixman-matrix.c to fix win32 build
Jeff Muizelaar [Fri, 9 Jan 2009 17:48:20 +0000 (12:48 -0500)]
Conditionally include config.h in pixman-matrix.c to fix win32 build

15 years agoFix pixman-1-uninstalled.pc to point to the libtool library
Chris Wilson [Sat, 20 Dec 2008 17:18:51 +0000 (17:18 +0000)]
Fix pixman-1-uninstalled.pc to point to the libtool library

Otherwise we fail to link when compiling cairo against the uninstalled
library.

15 years agoAllocate initial array of RegionInfo on the stack.
Chris Wilson [Fri, 21 Nov 2008 01:20:38 +0000 (01:20 +0000)]
Allocate initial array of RegionInfo on the stack.

The region validate() code is frequently called by cairo as it is used to
extract regions from the trapezoids for fast-paths through the drawing
code and also for fast-path clipping and the RegionInfo allocation (as
well as the pixman_rect_alloc during the final union) appears as a hot
spot on application memory profiles.

15 years agoDon't treat PIXMAN_TYPE_YUY2 and PIXMAN_TYPE_YV12 as PIXMAN_FORMAT_COLOR.
Aaron Plattner [Wed, 17 Dec 2008 18:35:03 +0000 (10:35 -0800)]
Don't treat PIXMAN_TYPE_YUY2 and PIXMAN_TYPE_YV12 as PIXMAN_FORMAT_COLOR.

Various pieces of code expect PIXMAN_FORMAT_COLOR (and its less cool older
brother, PICT_FORMAT_COLOR) formats to have ARGB bits, and the YUV formats do
not.

15 years ago[arm-simd] Add a comment about aligning source and destination pointers.
Jeff Muizelaar [Fri, 5 Dec 2008 17:01:03 +0000 (12:01 -0500)]
[arm-simd] Add a comment about aligning source and destination pointers.

15 years agoCheck alignment of 'src' pointer in optimized ARM routines
Jeff Muizelaar [Fri, 5 Dec 2008 16:45:03 +0000 (11:45 -0500)]
Check alignment of 'src' pointer in optimized ARM routines

fbCompositeSrcAdd_8000x8000arm() tries to align 'dst' already but must check
'src' too.  Otherwise, the next 4-byte copy loop might access an odd 'src' address
causing an alignment trap.

Patch from Enrico Scholz

15 years agoMerge commit 'origin/master'
Keith Packard [Wed, 26 Nov 2008 06:04:29 +0000 (22:04 -0800)]
Merge commit 'origin/master'

15 years agoBump to 0.13.3 after 0.13.2 release
Keith Packard [Wed, 26 Nov 2008 06:03:55 +0000 (22:03 -0800)]
Bump to 0.13.3 after 0.13.2 release

15 years agoBump version to 0.13.2 for release pixman-0.13.2
Keith Packard [Wed, 26 Nov 2008 05:37:54 +0000 (21:37 -0800)]
Bump version to 0.13.2 for release

15 years agoMove matrix operations from X server to pixman
Keith Packard [Mon, 24 Nov 2008 19:49:32 +0000 (11:49 -0800)]
Move matrix operations from X server to pixman

Signed-off-by: Keith Packard <keithp@keithp.com>
15 years agoOptimize rectilinear nearest-neighbour scaling
Jeff Muizelaar [Mon, 24 Nov 2008 20:11:24 +0000 (15:11 -0500)]
Optimize rectilinear nearest-neighbour scaling

Add a special case for a source transformation that is only a scale and
preserves rectangular pixels and doesn't rotate the image. Currently, only
SOURCE is special cased, however I plan to do more work in this area as needed.
The biggest advantage the specialization currently has is writing directly to
the destination surface instead of a temporary scanline buffer. However, it is
still pretty unoptimized but I want to keep things simple for now.

15 years agoUnify scanline buffer types
Jeff Muizelaar [Sat, 22 Nov 2008 02:35:30 +0000 (21:35 -0500)]
Unify scanline buffer types

Change the type of the stack based scanline buffer to uint8_t to match the rest
of the variables. Also premultiply the scanline buffer size by sizeof(uint32_t)
because the bpp can be either sizeof(uint32_t) or sizeof(uint64_t).

15 years ago[arm-simd] Fix typo found by 王新拓
Jeff Muizelaar [Thu, 20 Nov 2008 15:41:40 +0000 (10:41 -0500)]
[arm-simd] Fix typo found by 王新拓

'and r7, %[upper_component_mask]' appears to by a short hand for
'and r7, %[upper_component_mask], %[upper_component_mask]'. Use
the explicit form to avoid any confusion.

15 years agoLess fragile Linux altivec detection
David Woodhouse [Tue, 18 Nov 2008 21:01:11 +0000 (16:01 -0500)]
Less fragile Linux altivec detection

Instead of using really fragile SIGILL trapping, use a more reliable
detection method by checking what the CPU really supports.

https://bugzilla.redhat.com/show_bug.cgi?id=472000
https://bugzilla.redhat.com/show_bug.cgi?id=451831

16 years agoMake comments about PIXMAN_REFLECT more useful
Søren Sandmann Pedersen [Tue, 11 Nov 2008 04:18:09 +0000 (23:18 -0500)]
Make comments about PIXMAN_REFLECT more useful

16 years agoVarious formatting fixes, and a simplification of the adjusting code
Søren Sandmann Pedersen [Thu, 6 Nov 2008 04:58:56 +0000 (23:58 -0500)]
Various formatting fixes, and a simplification of the adjusting code

16 years agoInline the fetchers
Søren Sandmann Pedersen [Wed, 5 Nov 2008 22:51:55 +0000 (17:51 -0500)]
Inline the fetchers

16 years agoUse fetch_nearest() instead of having duplicated code
Søren Sandmann Pedersen [Wed, 5 Nov 2008 22:23:45 +0000 (17:23 -0500)]
Use fetch_nearest() instead of having duplicated code

16 years agoDo the fetch_bilinear inline rather than in separate functions
Søren Sandmann Pedersen [Wed, 5 Nov 2008 22:12:22 +0000 (17:12 -0500)]
Do the fetch_bilinear inline rather than in separate functions

16 years agoMake use of fetch_bilinear() in the various bilinear implementations
Søren Sandmann Pedersen [Wed, 5 Nov 2008 21:59:56 +0000 (16:59 -0500)]
Make use of fetch_bilinear() in the various bilinear implementations

16 years agoAdd fetch_bilinear function
Søren Sandmann Pedersen [Wed, 5 Nov 2008 21:38:33 +0000 (16:38 -0500)]
Add fetch_bilinear function

16 years agoAdd missing pixman-arm-simd.[ch] files.
Søren Sandmann Pedersen [Mon, 3 Nov 2008 18:09:02 +0000 (13:09 -0500)]
Add missing pixman-arm-simd.[ch] files.

Pointed out by Chris Ball and Adrian Bunk.

16 years agoInlucde inttypes.h on digital Tru64
Søren Sandmann Pedersen [Fri, 31 Oct 2008 19:08:03 +0000 (15:08 -0400)]
Inlucde inttypes.h on digital Tru64

Bug 18007, reported by Joonas Pihlaja.

16 years agoRename the current ARM code to ARM SIMD
Adrian Bunk [Fri, 31 Oct 2008 18:59:30 +0000 (14:59 -0400)]
Rename the current ARM code to ARM SIMD

This code is only for CPUs supporting the SIMD instructions, not for all ARM
CPUs.

I stumbled above the recent commit with the ARM SIMD code while preparing a
patch that models the patch from #13445 after the MMX and SSE2 cases:

The ARM SIMD option currently uses --disable-arm, although this code is only
for CPUs >= ARMv6. That's as if one would call the option to disable the SSE2
code --disable-x86.

This patch therefore renames the configure option and the function and file
names to arm-simd/arm_simd.

16 years agoDefine force_inline for compilers other than gcc & MS Visual C
Alan Coopersmith [Thu, 30 Oct 2008 01:13:59 +0000 (18:13 -0700)]
Define force_inline for compilers other than gcc & MS Visual C

16 years agoCleanup inline definitions
Jeff Muizelaar [Thu, 30 Oct 2008 00:14:41 +0000 (17:14 -0700)]
Cleanup inline definitions

Replace all inline definitions with a common one in pixman-private.h. Also, add
'force_inline' and replace all existing uses of 'inline' as a forced inline
with 'force_inline'.

16 years agoRemove unused AddMul_256 macro
Søren Sandmann Pedersen [Wed, 15 Oct 2008 22:46:38 +0000 (18:46 -0400)]
Remove unused AddMul_256 macro

16 years agounswitch red and blue
Benjamin Otte [Sun, 12 Oct 2008 22:05:40 +0000 (00:05 +0200)]
unswitch red and blue

The previous code assumed a color format of ABGR when naming the
variables. The true color format is ARGB. This did not cause any bugs
because no functions rely on the order of colors so far. This patch
renames the variables just to avoid confusion.

16 years agoupdate .gitignore
Benjamin Otte [Wed, 8 Oct 2008 19:21:58 +0000 (21:21 +0200)]
update .gitignore

16 years agoforce alignment of arg pointer in potential SSE users
Benjamin Otte [Wed, 8 Oct 2008 19:18:12 +0000 (21:18 +0200)]
force alignment of arg pointer in potential SSE users

Fix for bug 17824

16 years agoMove _mm_empty() to correct place
David Müller [Tue, 23 Sep 2008 11:45:51 +0000 (07:45 -0400)]
Move _mm_empty() to correct place

The "fbComposeSetupSSE2()" function is guarding most of its code
depending on the capabilities of the CPU, but unfortunately the call
to "_mm_empty()" is not part of this code path but executed
unconditionally.  This results in a "illegal instruction" crash on
non-MMX / non-SSE capable CPUs caused by the the "emms" instruction
(embedded in "_mm_empty()").

Fix bug 17729.

16 years agoUpdate TODO
Søren Sandmann Pedersen [Sun, 21 Sep 2008 15:01:07 +0000 (11:01 -0400)]
Update TODO

16 years agoMake use of SSE2 blt/fill in more places
Søren Sandmann Pedersen [Sun, 21 Sep 2008 15:00:33 +0000 (11:00 -0400)]
Make use of SSE2 blt/fill in more places