FFmpeg: libavcodec/x86/mpegvideoencdsp_init.c Source File

FFmpeg

[フレーム]

mpegvideoencdsp_init.c

Go to the documentation of this file.

1 /*

2 * This file is part of FFmpeg.

3 *

4 * FFmpeg is free software; you can redistribute it and/or

5 * modify it under the terms of the GNU Lesser General Public

6 * License as published by the Free Software Foundation; either

7 * version 2.1 of the License, or (at your option) any later version.

8 *

9 * FFmpeg is distributed in the hope that it will be useful,

10 * but WITHOUT ANY WARRANTY; without even the implied warranty of

11 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU

12 * Lesser General Public License for more details.

13 *

14 * You should have received a copy of the GNU Lesser General Public

15 * License along with FFmpeg; if not, write to the Free Software

16 * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA

17 */

19 #include "libavutil/attributes.h"

20 #include "libavutil/avassert.h"

21 #include "libavutil/cpu.h"

22 #include "libavutil/x86/cpu.h"

23 #include "libavcodec/avcodec.h"

24 #include "libavcodec/mpegvideoencdsp.h"

26 int ff_pix_sum16_mmx(uint8_t *pix, int line_size);

27 int ff_pix_sum16_mmxext(uint8_t *pix, int line_size);

28 int ff_pix_sum16_sse2(uint8_t *pix, int line_size);

29 int ff_pix_sum16_xop(uint8_t *pix, int line_size);

30 int ff_pix_norm1_mmx(uint8_t *pix, int line_size);

31 int ff_pix_norm1_sse2(uint8_t *pix, int line_size);

33 #if HAVE_INLINE_ASM

35 #define PHADDD(a, t) \

36 "movq " #a ", " #t " \n\t" \

37 "psrlq 32,ドル " #a " \n\t" \

38 "paddd " #t ", " #a " \n\t"

40 /*

41 * pmulhw: dst[0 - 15] = (src[0 - 15] * dst[0 - 15])[16 - 31]

42 * pmulhrw: dst[0 - 15] = (src[0 - 15] * dst[0 - 15] + 0x8000)[16 - 31]

43 * pmulhrsw: dst[0 - 15] = (src[0 - 15] * dst[0 - 15] + 0x4000)[15 - 30]

44 */

45 #define PMULHRW(x, y, s, o) \

46 "pmulhw " #s ", " #x " \n\t" \

47 "pmulhw " #s ", " #y " \n\t" \

48 "paddw " #o ", " #x " \n\t" \

49 "paddw " #o ", " #y " \n\t" \

50 "psraw 1,ドル " #x " \n\t" \

51 "psraw 1,ドル " #y " \n\t"

52 #define DEF(x) x ## _mmx

53 #define SET_RND MOVQ_WONE

54 #define SCALE_OFFSET 1

56 #include "mpegvideoenc_qns_template.c"

58 #undef DEF

59 #undef SET_RND

60 #undef SCALE_OFFSET

61 #undef PMULHRW

63 #define DEF(x) x ## _3dnow

64 #define SET_RND(x)

65 #define SCALE_OFFSET 0

66 #define PMULHRW(x, y, s, o) \

67 "pmulhrw " #s ", " #x " \n\t" \

68 "pmulhrw " #s ", " #y " \n\t"

70 #include "mpegvideoenc_qns_template.c"

72 #undef DEF

73 #undef SET_RND

74 #undef SCALE_OFFSET

75 #undef PMULHRW

77 #if HAVE_SSSE3_INLINE

78 #undef PHADDD

79 #define DEF(x) x ## _ssse3

80 #define SET_RND(x)

81 #define SCALE_OFFSET -1

83 #define PHADDD(a, t) \

84 "pshufw 0ドルx0E, " #a ", " #t " \n\t" \

85 /* faster than phaddd on core2 */ \

86 "paddd " #t ", " #a " \n\t"

88 #define PMULHRW(x, y, s, o) \

89 "pmulhrsw " #s ", " #x " \n\t" \

90 "pmulhrsw " #s ", " #y " \n\t"

92 #include "mpegvideoenc_qns_template.c"

94 #undef DEF

95 #undef SET_RND

96 #undef SCALE_OFFSET

97 #undef PMULHRW

98 #undef PHADDD

99 #endif /* HAVE_SSSE3_INLINE */

100

101 /* Draw the edges of width 'w' of an image of size width, height

102 * this MMX version can only handle w == 8 || w == 16. */

103 static void draw_edges_mmx(uint8_t *buf, int wrap, int width, int height,

104 int w, int h, int sides)

105 {

106 uint8_t *ptr, *last_line;

107 int i;

108

109 last_line = buf + (height - 1) * wrap;

110 /* left and right */

111 ptr = buf;

112 if (w == 8) {

113 __asm__ volatile (

114 "1: \n\t"

115 "movd (%0), %%mm0 \n\t"

116 "punpcklbw %%mm0, %%mm0 \n\t"

117 "punpcklwd %%mm0, %%mm0 \n\t"

118 "punpckldq %%mm0, %%mm0 \n\t"

119 "movq %%mm0, -8(%0) \n\t"

120 "movq -8(%0, %2), %%mm1 \n\t"

121 "punpckhbw %%mm1, %%mm1 \n\t"

122 "punpckhwd %%mm1, %%mm1 \n\t"

123 "punpckhdq %%mm1, %%mm1 \n\t"

124 "movq %%mm1, (%0, %2) \n\t"

125 "add %1, %0 \n\t"

126 "cmp %3, %0 \n\t"

127 "jb 1b \n\t"

128 : "+r" (ptr)

129 : "r" ((x86_reg) wrap), "r" ((x86_reg) width),

130 "r" (ptr + wrap * height));

131 } else if (w == 16) {

132 __asm__ volatile (

133 "1: \n\t"

134 "movd (%0), %%mm0 \n\t"

135 "punpcklbw %%mm0, %%mm0 \n\t"

136 "punpcklwd %%mm0, %%mm0 \n\t"

137 "punpckldq %%mm0, %%mm0 \n\t"

138 "movq %%mm0, -8(%0) \n\t"

139 "movq %%mm0, -16(%0) \n\t"

140 "movq -8(%0, %2), %%mm1 \n\t"

141 "punpckhbw %%mm1, %%mm1 \n\t"

142 "punpckhwd %%mm1, %%mm1 \n\t"

143 "punpckhdq %%mm1, %%mm1 \n\t"

144 "movq %%mm1, (%0, %2) \n\t"

145 "movq %%mm1, 8(%0, %2) \n\t"

146 "add %1, %0 \n\t"

147 "cmp %3, %0 \n\t"

148 "jb 1b \n\t"

149 : "+r"(ptr)

150 : "r"((x86_reg)wrap), "r"((x86_reg)width), "r"(ptr + wrap * height)

151 );

152 } else {

153 av_assert1(w == 4);

154 __asm__ volatile (

155 "1: \n\t"

156 "movd (%0), %%mm0 \n\t"

157 "punpcklbw %%mm0, %%mm0 \n\t"

158 "punpcklwd %%mm0, %%mm0 \n\t"

159 "movd %%mm0, -4(%0) \n\t"

160 "movd -4(%0, %2), %%mm1 \n\t"

161 "punpcklbw %%mm1, %%mm1 \n\t"

162 "punpckhwd %%mm1, %%mm1 \n\t"

163 "punpckhdq %%mm1, %%mm1 \n\t"

164 "movd %%mm1, (%0, %2) \n\t"

165 "add %1, %0 \n\t"

166 "cmp %3, %0 \n\t"

167 "jb 1b \n\t"

168 : "+r" (ptr)

169 : "r" ((x86_reg) wrap), "r" ((x86_reg) width),

170 "r" (ptr + wrap * height));

171 }

172

173 /* top and bottom (and hopefully also the corners) */

174 if (sides & EDGE_TOP) {

175 for (i = 0; i < h; i += 4) {

176 ptr = buf - (i + 1) * wrap - w;

177 __asm__ volatile (

178 "1: \n\t"

179 "movq (%1, %0), %%mm0 \n\t"

180 "movq %%mm0, (%0) \n\t"

181 "movq %%mm0, (%0, %2) \n\t"

182 "movq %%mm0, (%0, %2, 2) \n\t"

183 "movq %%mm0, (%0, %3) \n\t"

184 "add 8,ドル %0 \n\t"

185 "cmp %4, %0 \n\t"

186 "jb 1b \n\t"

187 : "+r" (ptr)

188 : "r" ((x86_reg) buf - (x86_reg) ptr - w),

189 "r" ((x86_reg) - wrap), "r" ((x86_reg) - wrap * 3),

190 "r" (ptr + width + 2 * w));

191 }

192 }

193

194 if (sides & EDGE_BOTTOM) {

195 for (i = 0; i < h; i += 4) {

196 ptr = last_line + (i + 1) * wrap - w;

197 __asm__ volatile (

198 "1: \n\t"

199 "movq (%1, %0), %%mm0 \n\t"

200 "movq %%mm0, (%0) \n\t"

201 "movq %%mm0, (%0, %2) \n\t"

202 "movq %%mm0, (%0, %2, 2) \n\t"

203 "movq %%mm0, (%0, %3) \n\t"

204 "add 8,ドル %0 \n\t"

205 "cmp %4, %0 \n\t"

206 "jb 1b \n\t"

207 : "+r" (ptr)

208 : "r" ((x86_reg) last_line - (x86_reg) ptr - w),

209 "r" ((x86_reg) wrap), "r" ((x86_reg) wrap * 3),

210 "r" (ptr + width + 2 * w));

211 }

212 }

213 }

214

215 #endif /* HAVE_INLINE_ASM */

216

217 av_cold void ff_mpegvideoencdsp_init_x86(MpegvideoEncDSPContext *c,

218 AVCodecContext *avctx)

219 {

220 int cpu_flags = av_get_cpu_flags();

221

222 #if ARCH_X86_32

223 if (EXTERNAL_MMX(cpu_flags)) {

224 c->pix_sum = ff_pix_sum16_mmx;

225 c->pix_norm1 = ff_pix_norm1_mmx;

226 }

227

228 if (EXTERNAL_MMXEXT(cpu_flags)) {

229 c->pix_sum = ff_pix_sum16_mmxext;

230 }

231 #endif

232

233 if (EXTERNAL_SSE2(cpu_flags)) {

234 c->pix_sum = ff_pix_sum16_sse2;

235 c->pix_norm1 = ff_pix_norm1_sse2;

236 }

237

238 if (EXTERNAL_XOP(cpu_flags)) {

239 c->pix_sum = ff_pix_sum16_xop;

240 }

241

242 #if HAVE_INLINE_ASM

243

244 if (INLINE_MMX(cpu_flags)) {

245 if (!(avctx->flags & CODEC_FLAG_BITEXACT)) {

246 c->try_8x8basis = try_8x8basis_mmx;

247 }

248 c->add_8x8basis = add_8x8basis_mmx;

249

250 if (avctx->bits_per_raw_sample <= 8) {

251 c->draw_edges = draw_edges_mmx;

252 }

253 }

254

255 if (INLINE_AMD3DNOW(cpu_flags)) {

256 if (!(avctx->flags & CODEC_FLAG_BITEXACT)) {

257 c->try_8x8basis = try_8x8basis_3dnow;

258 }

259 c->add_8x8basis = add_8x8basis_3dnow;

260 }

261

262 #if HAVE_SSSE3_INLINE

263 if (INLINE_SSSE3(cpu_flags)) {

264 if (!(avctx->flags & CODEC_FLAG_BITEXACT)) {

265 c->try_8x8basis = try_8x8basis_ssse3;

266 }

267 c->add_8x8basis = add_8x8basis_ssse3;

268 }

269 #endif /* HAVE_SSSE3_INLINE */

270

271 #endif /* HAVE_INLINE_ASM */

272 }

Generated on Sun Mar 8 2015 02:35:03 for FFmpeg by doxygen 1.8.2