avcodec/mips: [loongson] optimize theora decoding in vp3dsp.

Optimize theora decoding with msa in functions:
1. ff_vp3_idct_add_msa
2. ff_vp3_idct_put_msa
3. ff_vp3_idct_dc_add_msa
4. ff_vp3_v_loop_filter_msa
5. ff_vp3_h_loop_filter_msa
6. ff_put_no_rnd_pixels_l2_msa

Theora decoding speed improved about 36%(from 22fps to 30fps, Tested on loongson 2K1000).

Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

1 files changed, 37 insertions, 0 deletions

diff --git a/libavcodec/mips/vp3dsp_mips.h b/libavcodec/mips/vp3dsp_mips.h
new file mode 100644
index 0000000000..7750d5c53d
--- /dev/null
+++ b/libavcodec/mips/vp3dsp_mips.h
@@ -0,0 +1,37 @@
+/*
+ * Copyright (c) 2018 gxw <guxiwei-hf@loongson.cn>
+ *
+ * This file is part of FFmpeg.
+ *
+ * FFmpeg 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,
+ * 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
+ * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
+ */
+
+#ifndef AVCODEC_MIPS_VP3DSP_MIPS_H
+#define AVCODEC_MIPS_VP3DSP_MIPS_H
+
+#include "libavcodec/vp3dsp.h"
+#include <string.h>
+
+void ff_vp3_idct_add_msa(uint8_t *dest, ptrdiff_t line_size, int16_t *block);
+void ff_vp3_idct_put_msa(uint8_t *dest, ptrdiff_t line_size, int16_t *block);
+void ff_vp3_idct_dc_add_msa(uint8_t *dest, ptrdiff_t line_size, int16_t *block);
+void ff_vp3_v_loop_filter_msa(uint8_t *first_pixel, ptrdiff_t stride,
+                              int *bounding_values);
+void ff_put_no_rnd_pixels_l2_msa(uint8_t *dst, const uint8_t *src1,
+                                 const uint8_t *src2, ptrdiff_t stride, int h);
+void ff_vp3_h_loop_filter_msa(uint8_t *first_pixel, ptrdiff_t stride,
+                              int *bounding_values);
+
+#endif /* #ifndef AVCODEC_MIPS_VP3DSP_MIPS_H */