avcodec/x86/hevc_mc: add qpel_h16_8_avx512icl

ff_hevc_put_hevc_qpel_h16_8_sse4       3290870
ff_hevc_put_hevc_qpel_h16_8_avx512icl  1730033

Reviewed-by: Henrik Gramner <henrik@gramner.com>
Signed-off-by: Wu Jianhua <jianhua.wu@intel.com>
This commit is contained in:
Wu Jianhua 2022-03-11 15:52:10 +08:00 committed by Haihao Xiang
parent d4cd8830bd
commit c1790b60d6
3 changed files with 27 additions and 1 deletions

View File

@ -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
%if mmsize == 64
movu ym4, [%2q - 3]
%else
movu xm4, [%2q - 3]
%endif
vpermb m5, m2, m4
vpermb m4, m3, m4
vpdpbusd m%1, m5, m0
@ -1805,5 +1826,8 @@ 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

View File

@ -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);
///////////////////////////////////////////////////////////////////////////////

View File

@ -880,6 +880,7 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
}
if (EXTERNAL_AVX512ICL(cpu_flags) && ARCH_X86_64) {
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) {