Mercurial > sdl-ios-xcode
view src/hermes/HeadMMX.h @ 1542:a8bf1aa21020
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.
author | Sam Lantinga <slouken@libsdl.org> |
---|---|
date | Wed, 15 Mar 2006 15:39:29 +0000 |
parents | d910939febfa |
children | 782fd950bd46 c121d94672cb 39b9405d3cb6 |
line wrap: on
line source
/* Header definitions for the MMX routines for the HERMES library Copyright (c) 1998 Christian Nentwich (c.nentwich@cs.ucl.ac.uk) This source code is licensed under the GNU LGPL Please refer to the file COPYING.LIB contained in the distribution for licensing conditions */ #include "SDL_config.h" #ifndef __HERMES_HEAD_MMX__ #define __HERMES_HEAD_MMX__ /* If you cannot stand ifdefs, then please do not look into this file, it's going to end your life :) */ #ifdef X86_ASSEMBLER #ifdef __cplusplus extern "C" { #endif void STACKCALL ConvertMMX(HermesConverterInterface *); void STACKCALL ClearMMX_32(HermesClearInterface *); void STACKCALL ClearMMX_24(HermesClearInterface *); void STACKCALL ClearMMX_16(HermesClearInterface *); void STACKCALL ClearMMX_8(HermesClearInterface *); void ConvertMMXpII32_24RGB888(); void ConvertMMXpII32_16RGB565(); void ConvertMMXpII32_16BGR565(); void ConvertMMXpII32_16RGB555(); void ConvertMMXpII32_16BGR565(); void ConvertMMXpII32_16BGR555(); void ConvertMMXp32_16RGB555(); #ifdef __cplusplus } #endif /* Fix the underscore business with ELF compilers */ #if defined(__ELF__) && defined(__GNUC__) #ifdef __cplusplus extern "C" { #endif extern void _ConvertMMX(HermesConverterInterface *); extern void _ConvertMMXpII32_24RGB888(); extern void _ConvertMMXpII32_16RGB565(); extern void _ConvertMMXpII32_16BGR565(); extern void _ConvertMMXpII32_16RGB555(); extern void _ConvertMMXpII32_16BGR555(); #define ConvertMMX _ConvertMMX #define ConvertMMXpII32_24RGB888 _ConvertMMXpII32_24RGB888 #define ConvertMMXpII32_16RGB565 _ConvertMMXpII32_16RGB565 #define ConvertMMXpII32_16BGR565 _ConvertMMXpII32_16BGR565 #define ConvertMMXpII32_16RGB555 _ConvertMMXpII32_16RGB555 #define ConvertMMXpII32_16BGR555 _ConvertMMXpII32_16BGR555 #ifdef __cplusplus } #endif #endif /* ELF and GNUC */ /* Make it work with Watcom */ #ifdef __WATCOMC__ #pragma warning 601 9 #pragma aux ConvertMMX "_*" modify [EAX EBX ECX EDX ESI EDI] #pragma aux ClearMMX_32 "_*" modify [EAX EBX ECX EDX ESI EDI] #pragma aux ClearMMX_24 "_*" modify [EAX EBX ECX EDX ESI EDI] #pragma aux ClearMMX_16 "_*" modify [EAX EBX ECX EDX ESI EDI] #pragma aux ClearMMX_8 "_*" modify [EAX EBX ECX EDX ESI EDI] #pragma aux ConvertMMXpII32_24RGB888 "_*" #pragma aux ConvertMMXpII32_16RGB565 "_*" #pragma aux ConvertMMXpII32_16BGR565 "_*" #pragma aux ConvertMMXpII32_16RGB555 "_*" #pragma aux ConvertMMXpII32_16BGR555 "_*" #pragma aux ConvertMMXp32_16RGB555 "_*" #endif /* WATCOM */ #endif /* X86_ASSEMBLER */ #endif