Wed, 15 Mar 2006 15:39:29 +0000 Fixed bug #15
Sam Lantinga <slouken@libsdl.org> [Wed, 15 Mar 2006 15:39:29 +0000] rev 1542
Fixed bug #15 SDL_blit_A.mmx-speed.patch.txt -- Speed improvements and a bugfix for the current GCC inline mmx asm code: - Changed some ops and removed some resulting useless ones. - Added some instruction parallelism (some gain) The resulting speed on my Xeon improved upto 35% depending on the function (measured in fps). - Fixed a bug where BlitRGBtoRGBSurfaceAlphaMMX() was setting the alpha component on the destination surfaces (to opaque-alpha) even when the surface had none. SDL_blit_A.mmx-msvc.patch.txt -- MSVC mmx intrinsics version of the same GCC asm code. MSVC compiler tries to parallelize the code and to avoid register stalls, but does not always do a very good job. Per-surface blending MSVC functions run quite a bit faster than their pure-asm counterparts (upto 55% faster for 16bit ones), but the per-pixel blending runs somewhat slower than asm. - BlitRGBtoRGBSurfaceAlphaMMX and BlitRGBtoRGBPixelAlphaMMX (and all variants) can now also handle formats other than (A)RGB8888. Formats like RGBA8888 and some quite exotic ones are allowed -- like RAGB8888, or actually anything having channels aligned on 8bit boundary and full 8bit alpha (for per-pixel alpha blending). The performance cost of this change is virtually 0 for per-surface alpha blending (no extra ops inside the loop) and a single non-MMX op inside the loop for per-pixel blending. In testing, the per-pixel alpha blending takes a ~2% performance hit, but it still runs much faster than the current code in CVS. If necessary, a separate function with this functionality can be made. This code requires Processor Pack for VC6.
Wed, 15 Mar 2006 05:52:31 +0000 Quartz implementation for SDL_DisplayYUVOverlay() was returning non-zero on
Ryan C. Gordon <icculus@icculus.org> [Wed, 15 Mar 2006 05:52:31 +0000] rev 1541
Quartz implementation for SDL_DisplayYUVOverlay() was returning non-zero on error, instead of zero, contrary to documentation. Fixes Bugzilla #165.
Wed, 15 Mar 2006 04:32:49 +0000 Added disk/dummy audio and dummy video to the Visual CE projects
Sam Lantinga <slouken@libsdl.org> [Wed, 15 Mar 2006 04:32:49 +0000] rev 1540
Added disk/dummy audio and dummy video to the Visual CE projects
Wed, 15 Mar 2006 04:29:35 +0000 *** empty log message ***
Sam Lantinga <slouken@libsdl.org> [Wed, 15 Mar 2006 04:29:35 +0000] rev 1539
*** empty log message ***
Wed, 15 Mar 2006 03:50:34 +0000 *** empty log message ***
Sam Lantinga <slouken@libsdl.org> [Wed, 15 Mar 2006 03:50:34 +0000] rev 1538
*** empty log message ***
Tue, 14 Mar 2006 19:12:49 +0000 Corrected dummy audio callback firing to be realistic, cleaned up tabs.
Ryan C. Gordon <icculus@icculus.org> [Tue, 14 Mar 2006 19:12:49 +0000] rev 1537
Corrected dummy audio callback firing to be realistic, cleaned up tabs.
Tue, 14 Mar 2006 17:33:33 +0000 WIN32 is no longer defined on Windows builds
Sam Lantinga <slouken@libsdl.org> [Tue, 14 Mar 2006 17:33:33 +0000] rev 1536
WIN32 is no longer defined on Windows builds
Tue, 14 Mar 2006 17:21:49 +0000 Added disk and dummy drivers to the Visual C++ projects
Sam Lantinga <slouken@libsdl.org> [Tue, 14 Mar 2006 17:21:49 +0000] rev 1535
Added disk and dummy drivers to the Visual C++ projects
Tue, 14 Mar 2006 16:20:28 +0000 *** empty log message ***
Sam Lantinga <slouken@libsdl.org> [Tue, 14 Mar 2006 16:20:28 +0000] rev 1534
*** empty log message ***
Tue, 14 Mar 2006 16:19:32 +0000 By default all the real targets have dummy audio/video and disk audio.
Sam Lantinga <slouken@libsdl.org> [Tue, 14 Mar 2006 16:19:32 +0000] rev 1533
By default all the real targets have dummy audio/video and disk audio.
(0) -1000 -300 -100 -10 +10 +100 +300 +1000 +3000 tip