[FFmpeg-devel] [PATCH v2 5/5] avcodec/x86/hevc_mc: add qpel_h64_8_avx512icl

[jianhua.wu at intel.com]

From: Wu Jianhua <jianhua.wu at intel.com>

ff_hevc_put_hevc_qpel_h64_8_sse4       56782981
ff_hevc_put_hevc_qpel_h64_8_avx2       40097816
ff_hevc_put_hevc_qpel_h64_8_avx512icl  25488576

Signed-off-by: Wu Jianhua <jianhua.wu at intel.com>
---
 libavcodec/x86/hevc_mc.asm    | 10 +++++++++-
 libavcodec/x86/hevcdsp.h      |  1 +
 libavcodec/x86/hevcdsp_init.c |  1 +
 3 files changed, 11 insertions(+), 1 deletion(-)

diff --git a/libavcodec/x86/hevc_mc.asm b/libavcodec/x86/hevc_mc.asm
index fc3faac376..c07948dd9b 100644
--- a/libavcodec/x86/hevc_mc.asm
+++ b/libavcodec/x86/hevc_mc.asm
@@ -92,6 +92,7 @@ QPEL_TABLE  8, 1, b, avx512icl_h
 QPEL_TABLE  8, 1, d, avx512icl_v
 QPEL_TABLE 16, 1, b, avx512icl_h
 QPEL_TABLE 32, 1, b, avx512icl_h
+QPEL_TABLE 64, 1, b, avx512icl_h
 
 pb_qpel_shuffle_index: db  0,  1,  2,  3
                        db  1,  2,  3,  4
@@ -1767,9 +1768,15 @@ cglobal hevc_put_hevc_qpel_h%1_%2, 5, 6, 8, dst, src, srcstride, height, mx, tmp
 %else
     vpmovdw          [dstq], m6
 %endif
-%if %1 == 32
+%if %1 > 16
     QPEL_H_LOAD_COMPUTE   7, src, 16
     vpmovdw     [dstq + 32], m7
+%endif
+%if %1 > 32
+    QPEL_H_LOAD_COMPUTE   6, src, 32
+    QPEL_H_LOAD_COMPUTE   7, src, 48
+    vpmovdw     [dstq + 64], m6
+    vpmovdw     [dstq + 96], m7
 %endif
     LOOP_END            dst, src, srcstride
     RET
@@ -1848,6 +1855,7 @@ HEVC_PUT_HEVC_QPEL_HV_AVX512ICL 8, 8
 INIT_ZMM avx512icl
 HEVC_PUT_HEVC_QPEL_AVX512ICL 16, 8
 HEVC_PUT_HEVC_QPEL_AVX512ICL 32, 8
+HEVC_PUT_HEVC_QPEL_AVX512ICL 64, 8
 
 %endif
 %endif
diff --git a/libavcodec/x86/hevcdsp.h b/libavcodec/x86/hevcdsp.h
index 8d3c3cc75f..24e35bc032 100644
--- a/libavcodec/x86/hevcdsp.h
+++ b/libavcodec/x86/hevcdsp.h
@@ -237,6 +237,7 @@ void ff_hevc_put_hevc_qpel_h4_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t
 void ff_hevc_put_hevc_qpel_h8_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
 void ff_hevc_put_hevc_qpel_h16_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
 void ff_hevc_put_hevc_qpel_h32_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
+void ff_hevc_put_hevc_qpel_h64_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
 void ff_hevc_put_hevc_qpel_hv8_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
 
 ///////////////////////////////////////////////////////////////////////////////
diff --git a/libavcodec/x86/hevcdsp_init.c b/libavcodec/x86/hevcdsp_init.c
index ce5902c693..f3061bda84 100644
--- a/libavcodec/x86/hevcdsp_init.c
+++ b/libavcodec/x86/hevcdsp_init.c
@@ -883,6 +883,7 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
             c->put_hevc_qpel[3][0][1] = ff_hevc_put_hevc_qpel_h8_8_avx512icl;
             c->put_hevc_qpel[5][0][1] = ff_hevc_put_hevc_qpel_h16_8_avx512icl;
             c->put_hevc_qpel[7][0][1] = ff_hevc_put_hevc_qpel_h32_8_avx512icl;
+            c->put_hevc_qpel[9][0][1] = ff_hevc_put_hevc_qpel_h64_8_avx512icl;
             c->put_hevc_qpel[3][1][1] = ff_hevc_put_hevc_qpel_hv8_8_avx512icl;
         }
     } else if (bit_depth == 10) {
-- 
2.17.1