Mercurial > sdl-ios-xcode
view src/thread/pthread/SDL_syssem.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 | dc6b59e925a2 |
children | aee7ea396f59 |
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 <semaphore.h> #include "SDL_thread.h" #include "SDL_timer.h" /* Wrapper around POSIX 1003.1b semaphores */ #ifdef __MACOSX__ #define USE_NAMED_SEMAPHORES 1 #include <unistd.h> #endif struct SDL_semaphore { sem_t *sem; #if !USE_NAMED_SEMAPHORES sem_t sem_data; #endif }; /* Create a semaphore, initialized with value */ SDL_sem *SDL_CreateSemaphore(Uint32 initial_value) { SDL_sem *sem = (SDL_sem *) SDL_malloc(sizeof(SDL_sem)); if ( sem ) { #if USE_NAMED_SEMAPHORES static int semnum = 0; char name[32]; SDL_snprintf(name, SDL_arraysize(name), "/SDL_sem-%d-%4.4d", getpid(), semnum++); sem->sem = sem_open(name, O_CREAT, 0600, initial_value); if ( sem->sem == (sem_t *)SEM_FAILED ) { SDL_SetError("sem_open(%s) failed", name); SDL_free(sem); sem = NULL; } else { sem_unlink(name); } #else if ( sem_init(&sem->sem_data, 0, initial_value) < 0 ) { SDL_SetError("sem_init() failed"); SDL_free(sem); sem = NULL; } else { sem->sem = &sem->sem_data; } #endif /* USE_NAMED_SEMAPHORES */ } else { SDL_OutOfMemory(); } return sem; } void SDL_DestroySemaphore(SDL_sem *sem) { if ( sem ) { #if USE_NAMED_SEMAPHORES sem_close(sem->sem); #else sem_destroy(sem->sem); #endif SDL_free(sem); } } int SDL_SemTryWait(SDL_sem *sem) { int retval; if ( ! sem ) { SDL_SetError("Passed a NULL semaphore"); return -1; } retval = SDL_MUTEX_TIMEDOUT; if ( sem_trywait(sem->sem) == 0 ) { retval = 0; } return retval; } int SDL_SemWait(SDL_sem *sem) { int retval; if ( ! sem ) { SDL_SetError("Passed a NULL semaphore"); return -1; } retval = sem_wait(sem->sem); if ( retval < 0 ) { SDL_SetError("sem_wait() failed"); } return retval; } int SDL_SemWaitTimeout(SDL_sem *sem, Uint32 timeout) { int retval; if ( ! sem ) { SDL_SetError("Passed a NULL semaphore"); return -1; } /* Try the easy cases first */ if ( timeout == 0 ) { return SDL_SemTryWait(sem); } if ( timeout == SDL_MUTEX_MAXWAIT ) { return SDL_SemWait(sem); } /* Ack! We have to busy wait... */ timeout += SDL_GetTicks(); do { retval = SDL_SemTryWait(sem); if ( retval == 0 ) { break; } SDL_Delay(1); } while ( SDL_GetTicks() < timeout ); return retval; } Uint32 SDL_SemValue(SDL_sem *sem) { int ret = 0; if ( sem ) { sem_getvalue(sem->sem, &ret); if ( ret < 0 ) { ret = 0; } } return (Uint32)ret; } int SDL_SemPost(SDL_sem *sem) { int retval; if ( ! sem ) { SDL_SetError("Passed a NULL semaphore"); return -1; } retval = sem_post(sem->sem); if ( retval < 0 ) { SDL_SetError("sem_post() failed"); } return retval; }