[FFmpeg-devel] [PATCH v2 4/6] lavc/aarch64: add hevc sao edge 8x8

[J. Dekker]

--bench on AWS Graviton:

hevc_sao_edge_8x8_8_c: 516.0
hevc_sao_edge_8x8_8_neon: 81.0

Signed-off-by: J. Dekker <jdek at itanimul.li>
---
 libavcodec/aarch64/hevcdsp_init_aarch64.c |  3 ++
 libavcodec/aarch64/hevcdsp_sao_neon.S     | 51 +++++++++++++++++++++++
 2 files changed, 54 insertions(+)

 Used inline shift for ldr & escheduled uxtl/uxtl2 before zip/zip2.

diff --git a/libavcodec/aarch64/hevcdsp_init_aarch64.c b/libavcodec/aarch64/hevcdsp_init_aarch64.c
index 747ff0412d..b93cec9e44 100644
--- a/libavcodec/aarch64/hevcdsp_init_aarch64.c
+++ b/libavcodec/aarch64/hevcdsp_init_aarch64.c
@@ -59,6 +59,8 @@ void ff_hevc_sao_band_filter_8x8_8_neon(uint8_t *_dst, uint8_t *_src,
                                   int width, int height);
 void ff_hevc_sao_edge_filter_16x16_8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride_dst,
                                           int16_t *sao_offset_val, int eo, int width, int height);
+void ff_hevc_sao_edge_filter_8x8_8_neon(uint8_t *dst, uint8_t *src, ptrdiff_t stride_dst,
+                                          int16_t *sao_offset_val, int eo, int width, int height);
 
 av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
 {
@@ -76,6 +78,7 @@ av_cold void ff_hevc_dsp_init_aarch64(HEVCDSPContext *c, const int bit_depth)
         c->idct_dc[2]                  = ff_hevc_idct_16x16_dc_8_neon;
         c->idct_dc[3]                  = ff_hevc_idct_32x32_dc_8_neon;
         c->sao_band_filter[0]          = ff_hevc_sao_band_filter_8x8_8_neon;
+        c->sao_edge_filter[0]          = ff_hevc_sao_edge_filter_8x8_8_neon;
         c->sao_edge_filter[1]          =
         c->sao_edge_filter[2]          =
         c->sao_edge_filter[3]          =
diff --git a/libavcodec/aarch64/hevcdsp_sao_neon.S b/libavcodec/aarch64/hevcdsp_sao_neon.S
index f1b9ced93f..e844cc8980 100644
--- a/libavcodec/aarch64/hevcdsp_sao_neon.S
+++ b/libavcodec/aarch64/hevcdsp_sao_neon.S
@@ -150,3 +150,54 @@ function ff_hevc_sao_edge_filter_16x16_8_neon, export=1
        // no lines to filter
        ret
 endfunc
+
+// ff_hevc_sao_edge_filter_8x8_8_neon(char *dst, char *src, ptrdiff stride_dst,
+//                                    int16 *sao_offset_val, int eo, int width, int height)
+function ff_hevc_sao_edge_filter_8x8_8_neon, export=1
+       adr             x7, .Lsao_edge_pos
+       ldr             w4, [x7, w4, uxtw #2]
+       ld1             {v3.8h}, [x3]
+       mov             v3.h[7], v3.h[0]
+       mov             v3.h[0], v3.h[1]
+       mov             v3.h[1], v3.h[2]
+       mov             v3.h[2], v3.h[7]
+       uzp2            v1.16b, v3.16b, v3.16b
+       uzp1            v0.16b, v3.16b, v3.16b
+       movi            v2.16b, #2
+       add             x16, x0, x2
+       lsl             x2, x2, #1
+       mov             x15, #192
+       mov              x8, x1
+       sub              x9, x1, x4
+       add             x10, x1, x4
+       mov             x17, #4
+1:     ld1             {v3.d}[0], [ x8], x15
+       ld1             {v4.d}[0], [ x9], x15
+       ld1             {v5.d}[0], [x10], x15
+       ld1             {v3.d}[1], [ x8], x15
+       ld1             {v4.d}[1], [ x9], x15
+       ld1             {v5.d}[1], [x10], x15
+       cmhi            v16.16b, v4.16b, v3.16b
+       cmhi            v17.16b, v3.16b, v4.16b
+       cmhi            v18.16b, v5.16b, v3.16b
+       cmhi            v19.16b, v3.16b, v5.16b
+       sub             v20.16b, v16.16b, v17.16b
+       sub             v21.16b, v18.16b, v19.16b
+       add             v20.16b, v20.16b, v21.16b
+       add             v20.16b, v20.16b, v2.16b
+       tbl             v16.16b, {v0.16b}, v20.16b
+       tbl             v17.16b, {v1.16b}, v20.16b
+       uxtl            v20.8h, v3.8b
+       uxtl2           v21.8h, v3.16b
+       zip1            v18.16b, v16.16b, v17.16b
+       zip2            v19.16b, v16.16b, v17.16b
+       sqadd           v20.8h, v18.8h, v20.8h
+       sqadd           v21.8h, v19.8h, v21.8h
+       sqxtun          v6.8b, v20.8h
+       sqxtun          v7.8b, v21.8h
+       st1             {v6.8b}, [ x0], x2
+       st1             {v7.8b}, [x16], x2
+       subs            x17, x17, #1
+       b.ne            1b
+       ret
+endfunc
-- 
2.30.1 (Apple Git-130)