mirror of
https://github.com/gryf/wmaker.git
synced 2026-03-19 17:23:33 +01:00
ef1a504898
This patch is improving the alpha combine function by using int instead of float. That function is used for example in the switch panel to merge the transparency mask. The change is practically indistinguishable to the human eye for a single-pass blend but the performance gained is huge. I've been doing some benchmark of wrlib and even implemented AVX2 support. But the gain compared to the complexity of AVX2 is not worth, while having int usage in that specific function is a really good trade-off. Here the result: Alpha Blending Performance Test Image size: 1024x768 (786432 pixels) Iterations: 100 AVX2 support: YES === RGBA Source Test === Original (float): 2.540 ms/frame (393.8 FPS) Optimized (int): 1.983 ms/frame (504.2 FPS) [1.3x speedup] AVX2 optimized: 1.843 ms/frame (542.6 FPS) [1.4x speedup] By using int, the alpha blending in that use case is 28% faster.
71 lines
2.3 KiB
C
71 lines
2.3 KiB
C
/* alpha_combine.c - Alpha channel combination, based on Gimp 1.1.24
|
|
* The GIMP -- an image manipulation program
|
|
* Copyright (C) 1995 Spencer Kimball and Peter Mattis
|
|
*
|
|
* 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
|
|
* Software Foundation, Inc., 51 Franklin St, Fifth Floor, Boston,
|
|
* MA 02110-1301, USA.
|
|
*/
|
|
|
|
#include "config.h"
|
|
|
|
#include "wraster.h"
|
|
#include "wr_i18n.h"
|
|
|
|
|
|
void RCombineAlpha(unsigned char *d, unsigned char *s, int s_has_alpha,
|
|
int width, int height, int dwi, int swi, int opacity) {
|
|
int x, y;
|
|
unsigned char *dst = d;
|
|
unsigned char *src = s;
|
|
|
|
for (y = 0; y < height; y++) {
|
|
for (x = 0; x < width; x++) {
|
|
int sa = s_has_alpha ? src[3] : 255;
|
|
int t, alpha;
|
|
|
|
if (opacity != 255) {
|
|
t = sa * opacity + 0x80;
|
|
sa = ((t >> 8) + t) >> 8;
|
|
}
|
|
|
|
t = dst[3] * (255 - sa) + 0x80;
|
|
alpha = sa + (((t >> 8) + t) >> 8);
|
|
|
|
if (alpha == 0) {
|
|
dst[3] = 0;
|
|
} else if (sa == alpha) {
|
|
dst[0] = src[0];
|
|
dst[1] = src[1];
|
|
dst[2] = src[2];
|
|
dst[3] = alpha;
|
|
} else if (sa == 0) {
|
|
dst[3] = alpha;
|
|
} else {
|
|
int ratio = (sa << 8) / alpha;
|
|
int inv_ratio = 256 - ratio;
|
|
|
|
dst[0] = (dst[0] * inv_ratio + src[0] * ratio) >> 8;
|
|
dst[1] = (dst[1] * inv_ratio + src[1] * ratio) >> 8;
|
|
dst[2] = (dst[2] * inv_ratio + src[2] * ratio) >> 8;
|
|
dst[3] = alpha;
|
|
}
|
|
|
|
dst += 4;
|
|
src += s_has_alpha ? 4 : 3;
|
|
}
|
|
dst += dwi;
|
|
src += swi;
|
|
}
|
|
} |