@@ -91,6 +91,7 @@ QPEL_TABLE 4, 1, b, avx512icl_h
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
pb_qpel_shuffle_index: db 0, 1, 2, 3
db 1, 2, 3, 4
@@ -1765,6 +1766,11 @@ cglobal hevc_put_hevc_qpel_h%1_%2, 5, 6, 8, dst, src, srcstride, height, mx, tmp
%else
vpmovdw ym6, m6
movu [dstq], ym6
+%endif
+%if %1 == 32
+ QPEL_H_LOAD_COMPUTE 7, srcq + 16 - 3
+ vpmovdw ym7, m7
+ movu [dstq + 32], ym7
%endif
LOOP_END dst, src, srcstride
RET
@@ -1843,6 +1849,7 @@ 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
%endif
%endif
@@ -236,6 +236,7 @@ WEIGHTING_PROTOTYPES(12, sse4);
void ff_hevc_put_hevc_qpel_h4_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_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_hv8_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
///////////////////////////////////////////////////////////////////////////////
@@ -882,6 +882,7 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
c->put_hevc_qpel[1][0][1] = ff_hevc_put_hevc_qpel_h4_8_avx512icl;
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[3][1][1] = ff_hevc_put_hevc_qpel_hv8_8_avx512icl;
}
} else if (bit_depth == 10) {