Mercurial > sdl-ios-xcode
view src/thread/beos/SDL_systhread.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" /* BeOS thread management routines for SDL */ #include <stdio.h> #include <signal.h> #include <be/kernel/OS.h> #include "SDL_mutex.h" #include "SDL_thread.h" #include "../SDL_thread_c.h" #include "../SDL_systhread.h" static int sig_list[] = { SIGHUP, SIGINT, SIGQUIT, SIGPIPE, SIGALRM, SIGTERM, SIGWINCH, 0 }; void SDL_MaskSignals(sigset_t *omask) { sigset_t mask; int i; sigemptyset(&mask); for ( i=0; sig_list[i]; ++i ) { sigaddset(&mask, sig_list[i]); } sigprocmask(SIG_BLOCK, &mask, omask); } void SDL_UnmaskSignals(sigset_t *omask) { sigprocmask(SIG_SETMASK, omask, NULL); } static int32 RunThread(void *data) { SDL_RunThread(data); return(0); } int SDL_SYS_CreateThread(SDL_Thread *thread, void *args) { /* Create the thread and go! */ thread->handle=spawn_thread(RunThread, "SDL", B_NORMAL_PRIORITY, args); if ( (thread->handle == B_NO_MORE_THREADS) || (thread->handle == B_NO_MEMORY) ) { SDL_SetError("Not enough resources to create thread"); return(-1); } resume_thread(thread->handle); return(0); } void SDL_SYS_SetupThread(void) { /* Mask asynchronous signals for this thread */ SDL_MaskSignals(NULL); } Uint32 SDL_ThreadID(void) { return((Uint32)find_thread(NULL)); } void SDL_SYS_WaitThread(SDL_Thread *thread) { status_t the_status; wait_for_thread(thread->handle, &the_status); } void SDL_SYS_KillThread(SDL_Thread *thread) { kill_thread(thread->handle); }