avcodec/vc1: Arm 32-bit NEON deblocking filter fast paths

checkasm benchmarks on 1.5 GHz Cortex-A72 are as follows. Note that the C
version can still outperform the NEON version in specific cases. The balance
between different code paths is stream-dependent, but in practice the best
case happens about 5% of the time, the worst case happens about 40% of the
time, and the complexity of the remaining cases fall somewhere in between.
Therefore, taking the average of the best and worst case timings is
probably a conservative estimate of the degree by which the NEON code
improves performance.

vc1dsp.vc1_h_loop_filter4_bestcase_c: 19.0
vc1dsp.vc1_h_loop_filter4_bestcase_neon: 48.5
vc1dsp.vc1_h_loop_filter4_worstcase_c: 144.7
vc1dsp.vc1_h_loop_filter4_worstcase_neon: 76.2
vc1dsp.vc1_h_loop_filter8_bestcase_c: 41.0
vc1dsp.vc1_h_loop_filter8_bestcase_neon: 75.0
vc1dsp.vc1_h_loop_filter8_worstcase_c: 294.0
vc1dsp.vc1_h_loop_filter8_worstcase_neon: 102.7
vc1dsp.vc1_h_loop_filter16_bestcase_c: 54.7
vc1dsp.vc1_h_loop_filter16_bestcase_neon: 130.0
vc1dsp.vc1_h_loop_filter16_worstcase_c: 569.7
vc1dsp.vc1_h_loop_filter16_worstcase_neon: 186.7
vc1dsp.vc1_v_loop_filter4_bestcase_c: 20.2
vc1dsp.vc1_v_loop_filter4_bestcase_neon: 47.2
vc1dsp.vc1_v_loop_filter4_worstcase_c: 164.2
vc1dsp.vc1_v_loop_filter4_worstcase_neon: 68.5
vc1dsp.vc1_v_loop_filter8_bestcase_c: 43.5
vc1dsp.vc1_v_loop_filter8_bestcase_neon: 55.2
vc1dsp.vc1_v_loop_filter8_worstcase_c: 316.2
vc1dsp.vc1_v_loop_filter8_worstcase_neon: 72.7
vc1dsp.vc1_v_loop_filter16_bestcase_c: 62.2
vc1dsp.vc1_v_loop_filter16_bestcase_neon: 103.7
vc1dsp.vc1_v_loop_filter16_worstcase_c: 646.5
vc1dsp.vc1_v_loop_filter16_worstcase_neon: 110.7

Signed-off-by: Ben Avison <bavison@riscosopen.org>
Signed-off-by: Martin Storsjö <martin@martin.st>

1 files changed, 14 insertions, 0 deletions

diff --git a/libavcodec/arm/vc1dsp_init_neon.c b/libavcodec/arm/vc1dsp_init_neon.c
index 2cca784f5a..f5f5c702d7 100644
--- a/libavcodec/arm/vc1dsp_init_neon.c
+++ b/libavcodec/arm/vc1dsp_init_neon.c
@@ -32,6 +32,13 @@ void ff_vc1_inv_trans_4x8_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *bloc
 void ff_vc1_inv_trans_8x4_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
 void ff_vc1_inv_trans_4x4_dc_neon(uint8_t *dest, ptrdiff_t stride, int16_t *block);
 
+void ff_vc1_v_loop_filter4_neon(uint8_t *src, int stride, int pq);
+void ff_vc1_h_loop_filter4_neon(uint8_t *src, int stride, int pq);
+void ff_vc1_v_loop_filter8_neon(uint8_t *src, int stride, int pq);
+void ff_vc1_h_loop_filter8_neon(uint8_t *src, int stride, int pq);
+void ff_vc1_v_loop_filter16_neon(uint8_t *src, int stride, int pq);
+void ff_vc1_h_loop_filter16_neon(uint8_t *src, int stride, int pq);
+
 void ff_put_pixels8x8_neon(uint8_t *block, const uint8_t *pixels,
                            ptrdiff_t line_size, int rnd);
 
@@ -92,6 +99,13 @@ av_cold void ff_vc1dsp_init_neon(VC1DSPContext *dsp)
     dsp->vc1_inv_trans_8x4_dc = ff_vc1_inv_trans_8x4_dc_neon;
     dsp->vc1_inv_trans_4x4_dc = ff_vc1_inv_trans_4x4_dc_neon;
 
+    dsp->vc1_v_loop_filter4  = ff_vc1_v_loop_filter4_neon;
+    dsp->vc1_h_loop_filter4  = ff_vc1_h_loop_filter4_neon;
+    dsp->vc1_v_loop_filter8  = ff_vc1_v_loop_filter8_neon;
+    dsp->vc1_h_loop_filter8  = ff_vc1_h_loop_filter8_neon;
+    dsp->vc1_v_loop_filter16 = ff_vc1_v_loop_filter16_neon;
+    dsp->vc1_h_loop_filter16 = ff_vc1_h_loop_filter16_neon;
+
     dsp->put_vc1_mspel_pixels_tab[1][ 0] = ff_put_pixels8x8_neon;
     FN_ASSIGN(1, 0);
     FN_ASSIGN(2, 0);