[FFmpeg-cvslog] avcodec/x86/hevc_mc: add qpel_h4_8_avx512icl
Wu Jianhua
git at videolan.org
Sun Apr 24 10:09:37 EEST 2022
ffmpeg | branch: master | Wu Jianhua <jianhua.wu at intel.com> | Fri Mar 11 15:52:11 2022 +0800| [6fbb8cc8ad8c406cec0d0eb0bb3078c2929109c8] | committer: Haihao Xiang
avcodec/x86/hevc_mc: add qpel_h4_8_avx512icl
ff_hevc_put_hevc_qpel_h4_8_sse4 993694
ff_hevc_put_hevc_qpel_h4_8_avx512icl 686647
Reviewed-by: Henrik Gramner <henrik at gramner.com>
Signed-off-by: Wu Jianhua <jianhua.wu at intel.com>
> http://git.videolan.org/gitweb.cgi/ffmpeg.git/?a=commit;h=6fbb8cc8ad8c406cec0d0eb0bb3078c2929109c8
---
libavcodec/x86/hevc_mc.asm | 9 +++++++++
libavcodec/x86/hevcdsp.h | 1 +
libavcodec/x86/hevcdsp_init.c | 1 +
3 files changed, 11 insertions(+)
diff --git a/libavcodec/x86/hevc_mc.asm b/libavcodec/x86/hevc_mc.asm
index 4e39cdd7fe..ff59ae3509 100644
--- a/libavcodec/x86/hevc_mc.asm
+++ b/libavcodec/x86/hevc_mc.asm
@@ -87,6 +87,7 @@ QPEL_TABLE 12, 4, w, sse4
QPEL_TABLE 8,16, b, avx2
QPEL_TABLE 10, 8, w, avx2
+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
@@ -1754,7 +1755,12 @@ cglobal hevc_put_hevc_qpel_h%1_%2, 5, 6, 8, dst, src, srcstride, height, mx, tmp
QPEL_LOAD_SHUF 2, 3
.loop:
QPEL_H_LOAD_COMPUTE 6, src
+%if %1 == 4
+ vpmovdw xm6, m6
+ movq [dstq], xm6
+%else
vpmovdw [dstq], m6
+%endif
LOOP_END dst, src, srcstride
RET
%endmacro
@@ -1822,6 +1828,9 @@ cglobal hevc_put_hevc_qpel_hv%1_%2, 6, 7, 27, dst, src, srcstride, height, mx, m
%if ARCH_X86_64
%if HAVE_AVX512ICL_EXTERNAL
+INIT_XMM avx512icl
+HEVC_PUT_HEVC_QPEL_AVX512ICL 4, 8
+
INIT_YMM avx512icl
HEVC_PUT_HEVC_QPEL_AVX512ICL 8, 8
HEVC_PUT_HEVC_QPEL_HV_AVX512ICL 8, 8
diff --git a/libavcodec/x86/hevcdsp.h b/libavcodec/x86/hevcdsp.h
index 6e3fc01ad0..51ffdc9628 100644
--- a/libavcodec/x86/hevcdsp.h
+++ b/libavcodec/x86/hevcdsp.h
@@ -233,6 +233,7 @@ WEIGHTING_PROTOTYPES(8, sse4);
WEIGHTING_PROTOTYPES(10, sse4);
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_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 a73c2e2bd9..58b91459ed 100644
--- a/libavcodec/x86/hevcdsp_init.c
+++ b/libavcodec/x86/hevcdsp_init.c
@@ -879,6 +879,7 @@ void ff_hevc_dsp_init_x86(HEVCDSPContext *c, const int bit_depth)
c->add_residual[3] = ff_hevc_add_residual_32_8_avx2;
}
if (EXTERNAL_AVX512ICL(cpu_flags) && ARCH_X86_64) {
+ 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[3][1][1] = ff_hevc_put_hevc_qpel_hv8_8_avx512icl;
More information about the ffmpeg-cvslog
mailing list