Optimize put_hevc_pel_bi_pixels_8 with mmi in the case width=8/16/24/32/48/64.
This optimization improved HEVC decoding performance 2%(1.77x to 1.81x, tested
on loongson 3A3000).
---
libavcodec/mips/Makefile| 1 +
libavcodec/mips/hevcdsp_init_mips.c | 23 ++
libavcodec/mips/hevcdsp_mips.h | 19 +
libavcodec/mips/hevcdsp_mmi.c | 135
4 files changed, 178 insertions(+)
create mode 100644 libavcodec/mips/hevcdsp_mmi.c
diff --git a/libavcodec/mips/Makefile b/libavcodec/mips/Makefile
index 3571207..3029872 100644
--- a/libavcodec/mips/Makefile
+++ b/libavcodec/mips/Makefile
@@ -86,3 +86,4 @@ MMI-OBJS-$(CONFIG_VP8_DECODER)+= mips/vp8dsp_mmi.o
MMI-OBJS-$(CONFIG_HPELDSP)+= mips/hpeldsp_mmi.o
MMI-OBJS-$(CONFIG_VC1_DECODER)+= mips/vc1dsp_mmi.o
MMI-OBJS-$(CONFIG_WMV2DSP)+= mips/wmv2dsp_mmi.o
+MMI-OBJS-$(CONFIG_HEVC_DECODER) += mips/hevcdsp_mmi.o
diff --git a/libavcodec/mips/hevcdsp_init_mips.c
b/libavcodec/mips/hevcdsp_init_mips.c
index 776d13e..41c9001 100644
--- a/libavcodec/mips/hevcdsp_init_mips.c
+++ b/libavcodec/mips/hevcdsp_init_mips.c
@@ -20,6 +20,26 @@
#include "libavcodec/mips/hevcdsp_mips.h"
+#if HAVE_MMI
+static av_cold void hevc_dsp_init_mmi(HEVCDSPContext *c,
+ const int bit_depth)
+{
+if (8 == bit_depth) {
+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;
+c->put_hevc_qpel_bi[7][0][0] = ff_hevc_put_hevc_pel_bi_pixels32_8_mmi;
+c->put_hevc_qpel_bi[8][0][0] = ff_hevc_put_hevc_pel_bi_pixels48_8_mmi;
+c->put_hevc_qpel_bi[9][0][0] = ff_hevc_put_hevc_pel_bi_pixels64_8_mmi;
+
+c->put_hevc_epel_bi[3][0][0] = ff_hevc_put_hevc_pel_bi_pixels8_8_mmi;
+c->put_hevc_epel_bi[5][0][0] = ff_hevc_put_hevc_pel_bi_pixels16_8_mmi;
+c->put_hevc_epel_bi[6][0][0] = ff_hevc_put_hevc_pel_bi_pixels24_8_mmi;
+c->put_hevc_epel_bi[7][0][0] = ff_hevc_put_hevc_pel_bi_pixels32_8_mmi;
+}
+}
+#endif // #if HAVE_MMI
+
#if HAVE_MSA
static av_cold void hevc_dsp_init_msa(HEVCDSPContext *c,
const int bit_depth)
@@ -448,6 +468,9 @@ static av_cold void hevc_dsp_init_msa(HEVCDSPContext *c,
void ff_hevc_dsp_init_mips(HEVCDSPContext *c, const int bit_depth)
{
+#if HAVE_MMI
+hevc_dsp_init_mmi(c, bit_depth);
+#endif // #if HAVE_MMI
#if HAVE_MSA
hevc_dsp_init_msa(c, bit_depth);
#endif // #if HAVE_MSA
diff --git a/libavcodec/mips/hevcdsp_mips.h b/libavcodec/mips/hevcdsp_mips.h
index 1573d1c..ff9401c 100644
--- a/libavcodec/mips/hevcdsp_mips.h
+++ b/libavcodec/mips/hevcdsp_mips.h
@@ -479,4 +479,23 @@ void ff_hevc_addblk_32x32_msa(uint8_t *dst, int16_t
*pi16Coeffs,
ptrdiff_t stride);
void ff_hevc_idct_luma_4x4_msa(int16_t *pi16Coeffs);
+/* Loongson optimization */
+#define L_BI_MC(PEL, DIR, WIDTH, TYPE)
\
+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,
\
+int height,
\
+intptr_t mx,
\
+intptr_t my,
\
+int width)
+
+L_BI_MC(pel, pixels, 8, mmi);
+L_BI_MC(pel, pixels, 16, mmi);
+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);
+#undef L_BI_MC
#endif // #ifndef AVCODEC_MIPS_HEVCDSP_MIPS_H
diff --git a/libavcodec/mips/hevcdsp_mmi.c b/libavcodec/mips/hevcdsp_mmi.c
new file mode 100644
index 000..e9403c5
--- /dev/null
+++ b/libavcodec/mips/hevcdsp_mmi.c
@@ -0,0 +1,135 @@
+/*
+ * Copyright (c) 2019 Shiyou Yin (yinshiyou...@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
