avcodec/mips: [loongson] optimize put_hevc_qpel_bi_hv_8 with mmi.

Optimize put_hevc_qpel_bi_hv_8 with mmi in the case width=4/8/12/16/24/32/48/64.
This optimization improved HEVC decoding performance 11.4%(2.01x to 2.24x, tested on loongson 3A3000).
Signed-off-by: Michael Niedermayer <michael@niedermayer.cc>

libavcodec/mips/hevcdsp_init_mips.c

@@ -34,6 +34,15 @@ static av_cold void hevc_dsp_init_mmi(HEVCDSPContext *c,
         c->put_hevc_qpel[8][1][1] = ff_hevc_put_hevc_qpel_hv48_8_mmi;
         c->put_hevc_qpel[9][1][1] = ff_hevc_put_hevc_qpel_hv64_8_mmi;
 
+        c->put_hevc_qpel_bi[1][1][1] = ff_hevc_put_hevc_qpel_bi_hv4_8_mmi;
+        c->put_hevc_qpel_bi[3][1][1] = ff_hevc_put_hevc_qpel_bi_hv8_8_mmi;
+        c->put_hevc_qpel_bi[4][1][1] = ff_hevc_put_hevc_qpel_bi_hv12_8_mmi;
+        c->put_hevc_qpel_bi[5][1][1] = ff_hevc_put_hevc_qpel_bi_hv16_8_mmi;
+        c->put_hevc_qpel_bi[6][1][1] = ff_hevc_put_hevc_qpel_bi_hv24_8_mmi;
+        c->put_hevc_qpel_bi[7][1][1] = ff_hevc_put_hevc_qpel_bi_hv32_8_mmi;
+        c->put_hevc_qpel_bi[8][1][1] = ff_hevc_put_hevc_qpel_bi_hv48_8_mmi;
+        c->put_hevc_qpel_bi[9][1][1] = ff_hevc_put_hevc_qpel_bi_hv64_8_mmi;
+
         c->put_hevc_qpel_bi[3][0][0] = ff_hevc_put_hevc_pel_bi_pixels8_8_mmi;
         c->put_hevc_qpel_bi[5][0][0] = ff_hevc_put_hevc_pel_bi_pixels16_8_mmi;
         c->put_hevc_qpel_bi[6][0][0] = ff_hevc_put_hevc_pel_bi_pixels24_8_mmi;

libavcodec/mips/hevcdsp_mips.h

@@ -502,7 +502,7 @@ void ff_hevc_put_hevc_##PEL##_bi_##DIR##WIDTH##_8_##TYPE(uint8_t *dst,
                                                          ptrdiff_t dst_stride,  \
                                                          uint8_t *src,          \
                                                          ptrdiff_t src_stride,  \
-                                                         int16_t *src_16bit,    \
+                                                         int16_t *src2,         \
                                                          int height,            \
                                                          intptr_t mx,           \
                                                          intptr_t my,           \
@@ -514,5 +514,15 @@ L_BI_MC(pel, pixels, 24, mmi);
 L_BI_MC(pel, pixels, 32, mmi);
 L_BI_MC(pel, pixels, 48, mmi);
 L_BI_MC(pel, pixels, 64, mmi);
+
+L_BI_MC(qpel, hv, 4, mmi);
+L_BI_MC(qpel, hv, 8, mmi);
+L_BI_MC(qpel, hv, 12, mmi);
+L_BI_MC(qpel, hv, 16, mmi);
+L_BI_MC(qpel, hv, 24, mmi);
+L_BI_MC(qpel, hv, 32, mmi);
+L_BI_MC(qpel, hv, 48, mmi);
+L_BI_MC(qpel, hv, 64, mmi);
+
 #undef L_BI_MC
 #endif  // #ifndef AVCODEC_MIPS_HEVCDSP_MIPS_H