/*
* Copyright (C) 2004 the ffmpeg project
*
- * This file is part of FFmpeg.
+ * This file is part of Libav.
*
- * FFmpeg is free software; you can redistribute it and/or
+ * Libav 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.
*
- * FFmpeg is distributed in the hope that it will be useful,
+ * Libav 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 FFmpeg; if not, write to the Free Software
+ * License along with Libav; if not, write to the Free Software
* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
*/
/**
- * @file vp3dsp.c
+ * @file
* Standard C DSP-oriented functions cribbed from the original VP3
* source code.
*/
+#include "libavutil/attributes.h"
+#include "libavutil/common.h"
#include "avcodec.h"
#include "dsputil.h"
+#include "vp3dsp.h"
#define IdctAdjustBeforeShift 8
#define xC1S7 64277
static av_always_inline void idct(uint8_t *dst, int stride, int16_t *input, int type)
{
int16_t *ip = input;
- uint8_t *cm = ff_cropTbl + MAX_NEG_CROP;
int A, B, C, D, Ad, Bd, Cd, Dd, E, F, G, H;
int Ed, Gd, Add, Bdd, Fd, Hd;
ip[5*8] = (Fd + Bdd ) >> 4;
ip[6*8] = (Fd - Bdd ) >> 4;
}else if(type==1){
- dst[0*stride] = cm[(Gd + Cd ) >> 4];
- dst[7*stride] = cm[(Gd - Cd ) >> 4];
+ dst[0*stride] = av_clip_uint8((Gd + Cd ) >> 4);
+ dst[7*stride] = av_clip_uint8((Gd - Cd ) >> 4);
- dst[1*stride] = cm[(Add + Hd ) >> 4];
- dst[2*stride] = cm[(Add - Hd ) >> 4];
+ dst[1*stride] = av_clip_uint8((Add + Hd ) >> 4);
+ dst[2*stride] = av_clip_uint8((Add - Hd ) >> 4);
- dst[3*stride] = cm[(Ed + Dd ) >> 4];
- dst[4*stride] = cm[(Ed - Dd ) >> 4];
+ dst[3*stride] = av_clip_uint8((Ed + Dd ) >> 4);
+ dst[4*stride] = av_clip_uint8((Ed - Dd ) >> 4);
- dst[5*stride] = cm[(Fd + Bdd ) >> 4];
- dst[6*stride] = cm[(Fd - Bdd ) >> 4];
+ dst[5*stride] = av_clip_uint8((Fd + Bdd ) >> 4);
+ dst[6*stride] = av_clip_uint8((Fd - Bdd ) >> 4);
}else{
- dst[0*stride] = cm[dst[0*stride] + ((Gd + Cd ) >> 4)];
- dst[7*stride] = cm[dst[7*stride] + ((Gd - Cd ) >> 4)];
+ dst[0*stride] = av_clip_uint8(dst[0*stride] + ((Gd + Cd ) >> 4));
+ dst[7*stride] = av_clip_uint8(dst[7*stride] + ((Gd - Cd ) >> 4));
- dst[1*stride] = cm[dst[1*stride] + ((Add + Hd ) >> 4)];
- dst[2*stride] = cm[dst[2*stride] + ((Add - Hd ) >> 4)];
+ dst[1*stride] = av_clip_uint8(dst[1*stride] + ((Add + Hd ) >> 4));
+ dst[2*stride] = av_clip_uint8(dst[2*stride] + ((Add - Hd ) >> 4));
- dst[3*stride] = cm[dst[3*stride] + ((Ed + Dd ) >> 4)];
- dst[4*stride] = cm[dst[4*stride] + ((Ed - Dd ) >> 4)];
+ dst[3*stride] = av_clip_uint8(dst[3*stride] + ((Ed + Dd ) >> 4));
+ dst[4*stride] = av_clip_uint8(dst[4*stride] + ((Ed - Dd ) >> 4));
- dst[5*stride] = cm[dst[5*stride] + ((Fd + Bdd ) >> 4)];
- dst[6*stride] = cm[dst[6*stride] + ((Fd - Bdd ) >> 4)];
+ dst[5*stride] = av_clip_uint8(dst[5*stride] + ((Fd + Bdd ) >> 4));
+ dst[6*stride] = av_clip_uint8(dst[6*stride] + ((Fd - Bdd ) >> 4));
}
} else {
dst[4*stride]=
dst[5*stride]=
dst[6*stride]=
- dst[7*stride]= 128 + ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20);
+ dst[7*stride]= av_clip_uint8(128 + ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20));
}else{
if(ip[0*8]){
int v= ((xC4S4 * ip[0*8] + (IdctAdjustBeforeShift<<16))>>20);
- dst[0*stride] = cm[dst[0*stride] + v];
- dst[1*stride] = cm[dst[1*stride] + v];
- dst[2*stride] = cm[dst[2*stride] + v];
- dst[3*stride] = cm[dst[3*stride] + v];
- dst[4*stride] = cm[dst[4*stride] + v];
- dst[5*stride] = cm[dst[5*stride] + v];
- dst[6*stride] = cm[dst[6*stride] + v];
- dst[7*stride] = cm[dst[7*stride] + v];
+ dst[0*stride] = av_clip_uint8(dst[0*stride] + v);
+ dst[1*stride] = av_clip_uint8(dst[1*stride] + v);
+ dst[2*stride] = av_clip_uint8(dst[2*stride] + v);
+ dst[3*stride] = av_clip_uint8(dst[3*stride] + v);
+ dst[4*stride] = av_clip_uint8(dst[4*stride] + v);
+ dst[5*stride] = av_clip_uint8(dst[5*stride] + v);
+ dst[6*stride] = av_clip_uint8(dst[6*stride] + v);
+ dst[7*stride] = av_clip_uint8(dst[7*stride] + v);
}
}
}
}
}
-void ff_vp3_idct_c(DCTELEM *block/* align 16*/){
- idct(NULL, 0, block, 0);
-}
-
-void ff_vp3_idct_put_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
+static void vp3_idct_put_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
idct(dest, line_size, block, 1);
+ memset(block, 0, sizeof(*block) * 64);
}
-void ff_vp3_idct_add_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
+static void vp3_idct_add_c(uint8_t *dest/*align 8*/, int line_size, DCTELEM *block/*align 16*/){
idct(dest, line_size, block, 2);
+ memset(block, 0, sizeof(*block) * 64);
+}
+
+static void vp3_idct_dc_add_c(uint8_t *dest/*align 8*/, int line_size,
+ DCTELEM *block/*align 16*/){
+ int i, dc = (block[0] + 15) >> 5;
+
+ for(i = 0; i < 8; i++){
+ dest[0] = av_clip_uint8(dest[0] + dc);
+ dest[1] = av_clip_uint8(dest[1] + dc);
+ dest[2] = av_clip_uint8(dest[2] + dc);
+ dest[3] = av_clip_uint8(dest[3] + dc);
+ dest[4] = av_clip_uint8(dest[4] + dc);
+ dest[5] = av_clip_uint8(dest[5] + dc);
+ dest[6] = av_clip_uint8(dest[6] + dc);
+ dest[7] = av_clip_uint8(dest[7] + dc);
+ dest += line_size;
+ }
+ block[0] = 0;
+}
+
+static void vp3_v_loop_filter_c(uint8_t *first_pixel, int stride,
+ int *bounding_values)
+{
+ unsigned char *end;
+ int filter_value;
+ const int nstride= -stride;
+
+ for (end= first_pixel + 8; first_pixel < end; first_pixel++) {
+ filter_value =
+ (first_pixel[2 * nstride] - first_pixel[ stride])
+ +3*(first_pixel[0 ] - first_pixel[nstride]);
+ filter_value = bounding_values[(filter_value + 4) >> 3];
+ first_pixel[nstride] = av_clip_uint8(first_pixel[nstride] + filter_value);
+ first_pixel[0] = av_clip_uint8(first_pixel[0] - filter_value);
+ }
+}
+
+static void vp3_h_loop_filter_c(uint8_t *first_pixel, int stride,
+ int *bounding_values)
+{
+ unsigned char *end;
+ int filter_value;
+
+ for (end= first_pixel + 8*stride; first_pixel != end; first_pixel += stride) {
+ filter_value =
+ (first_pixel[-2] - first_pixel[ 1])
+ +3*(first_pixel[ 0] - first_pixel[-1]);
+ filter_value = bounding_values[(filter_value + 4) >> 3];
+ first_pixel[-1] = av_clip_uint8(first_pixel[-1] + filter_value);
+ first_pixel[ 0] = av_clip_uint8(first_pixel[ 0] - filter_value);
+ }
+}
+
+static void put_no_rnd_pixels_l2(uint8_t *dst, const uint8_t *src1,
+ const uint8_t *src2, ptrdiff_t stride, int h)
+{
+ int i;
+
+ for (i = 0; i < h; i++) {
+ uint32_t a, b;
+
+ a = AV_RN32A(&src1[i * stride]);
+ b = AV_RN32A(&src2[i * stride]);
+ AV_WN32A(&dst[i * stride], no_rnd_avg32(a, b));
+ a = AV_RN32A(&src1[i * stride + 4]);
+ b = AV_RN32A(&src2[i * stride + 4]);
+ AV_WN32A(&dst[i * stride + 4], no_rnd_avg32(a, b));
+ }
+}
+
+av_cold void ff_vp3dsp_init(VP3DSPContext *c, int flags)
+{
+ c->put_no_rnd_pixels_l2 = put_no_rnd_pixels_l2;
+
+ c->idct_put = vp3_idct_put_c;
+ c->idct_add = vp3_idct_add_c;
+ c->idct_dc_add = vp3_idct_dc_add_c;
+ c->v_loop_filter = vp3_v_loop_filter_c;
+ c->h_loop_filter = vp3_h_loop_filter_c;
+
+ c->idct_perm = FF_NO_IDCT_PERM;
+
+ if (ARCH_ARM)
+ ff_vp3dsp_init_arm(c, flags);
+ if (ARCH_PPC)
+ ff_vp3dsp_init_ppc(c, flags);
+ if (ARCH_X86)
+ ff_vp3dsp_init_x86(c, flags);
}