@@ -89,6 +89,7 @@ QPEL_TABLE 10, 8, w, avx2
QPEL_TABLE 8, 1, b, avx512icl_h
QPEL_TABLE 8, 1, d, avx512icl_v
+QPEL_TABLE 16, 1, b, avx512icl_h
pb_qpel_shuffle_index: db 0, 1, 2, 3
db 1, 2, 3, 4
@@ -98,6 +99,14 @@ pb_qpel_shuffle_index: db 0, 1, 2, 3
db 5, 6, 7, 8
db 6, 7, 8, 9
db 7, 8, 9, 10
+ db 8, 9, 10, 11
+ db 9, 10, 11, 12
+ db 10, 11, 12, 13
+ db 11, 12, 13, 14
+ db 12, 13, 14, 15
+ db 13, 14, 15, 16
+ db 14, 15, 16, 17
+ db 15, 16, 17, 18
db 4, 5, 6, 7
db 5, 6, 7, 8
db 6, 7, 8, 9
@@ -106,6 +115,14 @@ pb_qpel_shuffle_index: db 0, 1, 2, 3
db 9, 10, 11, 12
db 10, 11, 12, 13
db 11, 12, 13, 14
+ db 12, 13, 14, 15
+ db 13, 14, 15, 16
+ db 14, 15, 16, 17
+ db 15, 16, 17, 18
+ db 16, 17, 18, 19
+ db 17, 18, 19, 20
+ db 18, 19, 20, 21
+ db 19, 20, 21, 22
SECTION .text
@@ -1712,7 +1729,7 @@ HEVC_PUT_HEVC_QPEL_HV 16, 10
%macro QPEL_LOAD_SHUF 2
movu m%1, [pb_qpel_shuffle_index + 0]
- movu m%2, [pb_qpel_shuffle_index + 32]
+ movu m%2, [pb_qpel_shuffle_index + 64]
%endmacro
; required: m0-m5
@@ -1720,7 +1737,11 @@ HEVC_PUT_HEVC_QPEL_HV 16, 10
; %2: name for src
%macro QPEL_H_LOAD_COMPUTE 2
pxor m%1, m%1
- movu xm4, [%2q - 3]
+%if mmsize == 64
+ movu ym4, [%2]
+%else
+ movu xm4, [%2]
+%endif
vpermb m5, m2, m4
vpermb m4, m3, m4
vpdpbusd m%1, m5, m0
@@ -1732,9 +1753,14 @@ cglobal hevc_put_hevc_qpel_h%1_%2, 5, 6, 8, dst, src, srcstride, height, mx, tmp
QPEL_FILTER_H %1, mx, 0, 1, tmp
QPEL_LOAD_SHUF 2, 3
.loop:
- QPEL_H_LOAD_COMPUTE 6, src
+ QPEL_H_LOAD_COMPUTE 6, srcq - 3
+%if %1 == 8
vpmovdw xm6, m6
movu [dstq], xm6
+%else
+ vpmovdw ym6, m6
+ movu [dstq], ym6
+%endif
LOOP_END dst, src, srcstride
RET
%endmacro
@@ -1764,12 +1790,12 @@ cglobal hevc_put_hevc_qpel_hv%1_%2, 6, 7, 8, dst, src, srcstride, height, mx, my
%assign %%j %%j+1
%endrep
%rep %%extra
- QPEL_H_LOAD_COMPUTE %%i, src
+ QPEL_H_LOAD_COMPUTE %%i, srcq - 3
add srcq, srcstrideq
%assign %%i %%i+1
%endrep
.loop:
- QPEL_H_LOAD_COMPUTE %%i, src
+ QPEL_H_LOAD_COMPUTE %%i, srcq - 3
vpmulld m22, m14, m6
vpmulld m23, m15, m7
vpmulld m24, m16, m8
@@ -1807,5 +1833,8 @@ INIT_YMM avx512icl
HEVC_PUT_HEVC_QPEL_AVX512ICL 8, 8
HEVC_PUT_HEVC_QPEL_HV_AVX512ICL 8, 8
+INIT_ZMM avx512icl
+HEVC_PUT_HEVC_QPEL_AVX512ICL 16, 8
+
%endif
%endif
@@ -234,6 +234,7 @@ WEIGHTING_PROTOTYPES(10, sse4);
WEIGHTING_PROTOTYPES(12, sse4);
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_hv8_8_avx512icl(int16_t *dst, uint8_t *_src, ptrdiff_t _srcstride, int height, intptr_t mx, intptr_t my, int width);
///////////////////////////////////////////////////////////////////////////////
@@ -880,6 +880,7 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
}
if (EXTERNAL_AVX512ICL(cpu_flags)) {
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[3][1][1] = ff_hevc_put_hevc_qpel_hv8_8_avx512icl;
}
} else if (bit_depth == 10) {