* MMX and SSE2 optimized snow DSP utils
* Copyright (c) 2005-2006 Robert Edele <yartrebo@earthlink.net>
*
- * 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
*/
+#include "libavutil/cpu.h"
#include "libavutil/x86_cpu.h"
#include "libavcodec/avcodec.h"
#include "libavcodec/snow.h"
+#include "libavcodec/dwt.h"
+#include "dsputil_mmx.h"
-void ff_snow_horizontal_compose97i_sse2(IDWTELEM *b, int width){
+static void ff_snow_horizontal_compose97i_sse2(IDWTELEM *b, int width){
const int w2= (width+1)>>1;
DECLARE_ALIGNED(16, IDWTELEM, temp)[width>>1];
const int w_l= (width>>1);
}
}
-void ff_snow_horizontal_compose97i_mmx(IDWTELEM *b, int width){
+static void ff_snow_horizontal_compose97i_mmx(IDWTELEM *b, int width){
const int w2= (width+1)>>1;
IDWTELEM temp[width >> 1];
const int w_l= (width>>1);
"movdqa %%"s2", %%"t2" \n\t"\
"movdqa %%"s3", %%"t3" \n\t"
-void ff_snow_vertical_compose97i_sse2(IDWTELEM *b0, IDWTELEM *b1, IDWTELEM *b2, IDWTELEM *b3, IDWTELEM *b4, IDWTELEM *b5, int width){
+static void ff_snow_vertical_compose97i_sse2(IDWTELEM *b0, IDWTELEM *b1, IDWTELEM *b2, IDWTELEM *b3, IDWTELEM *b4, IDWTELEM *b5, int width){
x86_reg i = width;
while(i & 0x1F)
"movq %%"s3", %%"t3" \n\t"
-void ff_snow_vertical_compose97i_mmx(IDWTELEM *b0, IDWTELEM *b1, IDWTELEM *b2, IDWTELEM *b3, IDWTELEM *b4, IDWTELEM *b5, int width){
+static void ff_snow_vertical_compose97i_mmx(IDWTELEM *b0, IDWTELEM *b1, IDWTELEM *b2, IDWTELEM *b3, IDWTELEM *b4, IDWTELEM *b5, int width){
x86_reg i = width;
while(i & 15)
{
#define snow_inner_add_yblock_sse2_end_8\
"sal $1, %%"REG_c" \n\t"\
- "add $"PTR_SIZE"*2, %1 \n\t"\
+ "addl $"PTR_SIZE"*2, %1 \n\t"\
snow_inner_add_yblock_sse2_end_common1\
"sar $1, %%"REG_c" \n\t"\
"sub $2, %2 \n\t"\
snow_inner_add_yblock_sse2_end_common2
#define snow_inner_add_yblock_sse2_end_16\
- "add $"PTR_SIZE"*1, %1 \n\t"\
+ "addl $"PTR_SIZE"*1, %1 \n\t"\
snow_inner_add_yblock_sse2_end_common1\
"dec %2 \n\t"\
snow_inner_add_yblock_sse2_end_common2
"add %%"REG_c", "PTR_SIZE"*2(%%"REG_a");\n\t"\
"add %%"REG_c", "PTR_SIZE"*1(%%"REG_a");\n\t"\
"add %%"REG_c", (%%"REG_a") \n\t"\
- "add $"PTR_SIZE"*1, %1 \n\t"\
+ "add"OPSIZE " $"PTR_SIZE"*1, %1 \n\t"\
"add %%"REG_c", %0 \n\t"\
"dec %2 \n\t"\
"jnz 1b \n\t"\
snow_inner_add_yblock_mmx_end("32")
}
-void ff_snow_inner_add_yblock_sse2(const uint8_t *obmc, const int obmc_stride, uint8_t * * block, int b_w, int b_h,
+static void ff_snow_inner_add_yblock_sse2(const uint8_t *obmc, const int obmc_stride, uint8_t * * block, int b_w, int b_h,
int src_x, int src_y, int src_stride, slice_buffer * sb, int add, uint8_t * dst8){
if (b_w == 16)
ff_snow_inner_add_yblock(obmc, obmc_stride, block, b_w, b_h, src_x,src_y, src_stride, sb, add, dst8);
}
-void ff_snow_inner_add_yblock_mmx(const uint8_t *obmc, const int obmc_stride, uint8_t * * block, int b_w, int b_h,
+static void ff_snow_inner_add_yblock_mmx(const uint8_t *obmc, const int obmc_stride, uint8_t * * block, int b_w, int b_h,
int src_x, int src_y, int src_stride, slice_buffer * sb, int add, uint8_t * dst8){
if (b_w == 16)
inner_add_yblock_bw_16_obmc_32_mmx(obmc, obmc_stride, block, b_w, b_h, src_x,src_y, src_stride, sb, add, dst8);
else
ff_snow_inner_add_yblock(obmc, obmc_stride, block, b_w, b_h, src_x,src_y, src_stride, sb, add, dst8);
}
+
+void ff_dwt_init_x86(DWTContext *c)
+{
+ int mm_flags = av_get_cpu_flags();
+
+ if (mm_flags & AV_CPU_FLAG_MMX) {
+ if(mm_flags & AV_CPU_FLAG_SSE2 & 0){
+ c->horizontal_compose97i = ff_snow_horizontal_compose97i_sse2;
+#if HAVE_7REGS
+ c->vertical_compose97i = ff_snow_vertical_compose97i_sse2;
+#endif
+ c->inner_add_yblock = ff_snow_inner_add_yblock_sse2;
+ }
+ else{
+ if(mm_flags & AV_CPU_FLAG_MMX2){
+ c->horizontal_compose97i = ff_snow_horizontal_compose97i_mmx;
+#if HAVE_7REGS
+ c->vertical_compose97i = ff_snow_vertical_compose97i_mmx;
+#endif
+ }
+ c->inner_add_yblock = ff_snow_inner_add_yblock_mmx;
+ }
+ }
+}