Mercurial > sdl-ios-xcode
view src/video/x11/SDL_x11dyn.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 | 1f4f09641645 |
children | 3ba88cb7eb1b |
line wrap: on
line source
/* SDL - Simple DirectMedia Layer Copyright (C) 1997-2004 Sam Lantinga This library is free software; you can redistribute it and/or modify it under the terms of the GNU Library General Public License as published by the Free Software Foundation; either version 2 of the License, or (at your option) any later version. This library is distributed in the hope that it will be useful, but WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU Library General Public License for more details. You should have received a copy of the GNU Library General Public License along with this library; if not, write to the Free Foundation, Inc., 59 Temple Place, Suite 330, Boston, MA 02111-1307 USA Sam Lantinga slouken@libsdl.org */ #include "SDL_config.h" #ifndef _SDL_x11dyn_h #define _SDL_x11dyn_h #include <X11/Xlib.h> #include <X11/Xutil.h> #include <X11/Xatom.h> #include <X11/Xlibint.h> #include <X11/Xproto.h> #include "../Xext/extensions/extutil.h" #ifndef NO_SHARED_MEMORY #include <sys/ipc.h> #include <sys/shm.h> #include <X11/extensions/XShm.h> #endif /* * Never reference Xlib directly...we might load it dynamically at runtime. * Even if we don't, for readability, we still use the function pointers * (although the symbol resolution will be done by the loader in that case). * * We define SDL_X11_SYM and include SDL_x11sym.h to accomplish various * goals, without having to duplicate those function signatures. */ #ifdef __cplusplus extern "C" { #endif #ifdef __osf__ extern int _XData32(Display *,register long *,unsigned); extern void _XRead32(Display *,register long *,long); extern void _SmtBufferOverflow(Display *,register smtDisplayPtr); extern void _SmtIpError(Display *,register smtDisplayPtr, int); extern int ipAllocateData(ChannelPtr, IPCard, IPDataPtr *); extern int ipUnallocateAndSendData(ChannelPtr, IPCard); #endif /* evil function signatures... */ typedef Bool (*SDL_X11_XESetWireToEventRetType)(Display*,XEvent*,xEvent*); typedef int (*SDL_X11_XSynchronizeRetType)(Display*); typedef Status (*SDL_X11_XESetEventToWireRetType)(Display*,XEvent*,xEvent*); typedef int (*SDL_X11_XSetExtensionErrorHandlerType)(Display *,char *,char *); #define SDL_X11_SYM(req,ret,fn,params) extern ret (*p##fn) params; #include "SDL_x11sym.h" #undef SDL_X11_SYM /* Macro in the xlib headers, not an actual symbol... */ #define pXDestroyImage XDestroyImage /* Workaround code in headers... */ #if !__SDL_NO_REDEFINE_X11_HEADER_SYMS #define _XFlush p_XFlush #define _XFlushGCCache p_XFlushGCCache #define _XReply p_XReply #define _XSend p_XSend #define XFree pXFree #define _XData32 p_XData32 #if defined(__osf__) #define _SmtBufferOverflow p_SmtBufferOverflow #define _SmtIpError p_SmtIpError #define ipAllocateData pipAllocateData #define ipUnallocateAndSendData pipUnallocateAndSendData #endif #endif /* !__SDL_NO_REDEFINE_X11_HEADER_SYMS */ int SDL_X11_LoadSymbols(void); void SDL_X11_UnloadSymbols(void); #ifdef __cplusplus } #endif #endif /* !defined _SDL_x11dyn_h */