Mercurial > sdl-ios-xcode
view src/thread/pthread/SDL_sysmutex.c @ 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 a1b03ba2fcd0 |
line wrap: on
line source
/* SDL - Simple DirectMedia Layer Copyright (C) 1997-2006 Sam Lantinga This library is free software; you can redistribute it and/or modify it under the terms of the GNU Lesser General Public License as published by the Free Software Foundation; either version 2.1 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 Lesser General Public License for more details. You should have received a copy of the GNU Lesser General Public License along with this library; if not, write to the Free Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston, MA 02110-1301 USA Sam Lantinga slouken@libsdl.org */ #include "SDL_config.h" #include <pthread.h> #include "SDL_thread.h" #if !SDL_THREAD_PTHREAD_RECURSIVE_MUTEX && \ !SDL_THREAD_PTHREAD_RECURSIVE_MUTEX_NP #define FAKE_RECURSIVE_MUTEX #endif struct SDL_mutex { pthread_mutex_t id; #if FAKE_RECURSIVE_MUTEX int recursive; pthread_t owner; #endif }; SDL_mutex *SDL_CreateMutex (void) { SDL_mutex *mutex; pthread_mutexattr_t attr; /* Allocate the structure */ mutex = (SDL_mutex *)SDL_calloc(1, sizeof(*mutex)); if ( mutex ) { pthread_mutexattr_init(&attr); #if SDL_THREAD_PTHREAD_RECURSIVE_MUTEX pthread_mutexattr_settype(&attr, PTHREAD_MUTEX_RECURSIVE); #elif SDL_THREAD_PTHREAD_RECURSIVE_MUTEX_NP pthread_mutexattr_setkind_np(&attr, PTHREAD_MUTEX_RECURSIVE_NP); #else /* No extra attributes necessary */ #endif if ( pthread_mutex_init(&mutex->id, &attr) != 0 ) { SDL_SetError("pthread_mutex_init() failed"); SDL_free(mutex); mutex = NULL; } } else { SDL_OutOfMemory(); } return(mutex); } void SDL_DestroyMutex(SDL_mutex *mutex) { if ( mutex ) { pthread_mutex_destroy(&mutex->id); SDL_free(mutex); } } /* Lock the mutex */ int SDL_mutexP(SDL_mutex *mutex) { int retval; #if FAKE_RECURSIVE_MUTEX pthread_t this_thread; #endif if ( mutex == NULL ) { SDL_SetError("Passed a NULL mutex"); return -1; } retval = 0; #if FAKE_RECURSIVE_MUTEX this_thread = pthread_self(); if ( mutex->owner == this_thread ) { ++mutex->recursive; } else { /* The order of operations is important. We set the locking thread id after we obtain the lock so unlocks from other threads will fail. */ if ( pthread_mutex_lock(&mutex->id) == 0 ) { mutex->owner = this_thread; mutex->recursive = 0; } else { SDL_SetError("pthread_mutex_lock() failed"); retval = -1; } } #else if ( pthread_mutex_lock(&mutex->id) < 0 ) { SDL_SetError("pthread_mutex_lock() failed"); retval = -1; } #endif return retval; } int SDL_mutexV(SDL_mutex *mutex) { int retval; if ( mutex == NULL ) { SDL_SetError("Passed a NULL mutex"); return -1; } retval = 0; #if FAKE_RECURSIVE_MUTEX /* We can only unlock the mutex if we own it */ if ( pthread_self() == mutex->owner ) { if ( mutex->recursive ) { --mutex->recursive; } else { /* The order of operations is important. First reset the owner so another thread doesn't lock the mutex and set the ownership before we reset it, then release the lock semaphore. */ mutex->owner = 0; pthread_mutex_unlock(&mutex->id); } } else { SDL_SetError("mutex not owned by this thread"); retval = -1; } #else if ( pthread_mutex_unlock(&mutex->id) < 0 ) { SDL_SetError("pthread_mutex_unlock() failed"); retval = -1; } #endif /* FAKE_RECURSIVE_MUTEX */ return retval; }