Re: [libav-devel] [PATCH 6/6] arm: vp9lpf: Implement the mix2_44 function with one single filter pass

[Martin Storsjö]

On Fri, 10 Feb 2017, Janne Grunau wrote:

On 2017-01-15 22:55:52 +0200, Martin Storsjö wrote:
For this case, with 8 inputs but only changing 4 of them, we can fit
all 16 input pixels into a q register, and still have enough temporary
registers for doing the loop filter.
The wd=8 filters would require too many temporary registers for
processing all 16 pixels at once though.

Before:                          Cortex A7      A8     A9     A53
vp9_loop_filter_mix2_v_44_16_neon:   289.7   256.2  237.5   181.2
After:
vp9_loop_filter_mix2_v_44_16_neon:   221.2   150.5  177.7   138.0
---
 libavcodec/arm/vp9dsp_init_arm.c |   7 +-
 libavcodec/arm/vp9lpf_neon.S     | 191 +++++++++++++++++++++++++++++++++++++++
 2 files changed, 195 insertions(+), 3 deletions(-)

diff --git a/libavcodec/arm/vp9dsp_init_arm.c b/libavcodec/arm/vp9dsp_init_arm.c
index e99d931..1ede170 100644
--- a/libavcodec/arm/vp9dsp_init_arm.c
+++ b/libavcodec/arm/vp9dsp_init_arm.c
@@ -194,6 +194,8 @@ define_loop_filters(8, 8);
 define_loop_filters(16, 8);
 define_loop_filters(16, 16);

+define_loop_filters(44, 16);
+
 #define lf_mix_fn(dir, wd1, wd2, stridea)                                      
                   \
 static void loop_filter_##dir##_##wd1##wd2##_16_neon(uint8_t *dst,             
                   \
                                                      ptrdiff_t stride,         
                   \
@@ -207,7 +209,6 @@ static void 
loop_filter_##dir##_##wd1##wd2##_16_neon(uint8_t *dst,
     lf_mix_fn(h, wd1, wd2, stride) \
     lf_mix_fn(v, wd1, wd2, sizeof(uint8_t))

-lf_mix_fns(4, 4)
 lf_mix_fns(4, 8)
 lf_mix_fns(8, 4)
 lf_mix_fns(8, 8)
@@ -227,8 +228,8 @@ static av_cold void 
vp9dsp_loopfilter_init_arm(VP9DSPContext *dsp)
         dsp->loop_filter_16[0] = ff_vp9_loop_filter_h_16_16_neon;
         dsp->loop_filter_16[1] = ff_vp9_loop_filter_v_16_16_neon;

-        dsp->loop_filter_mix2[0][0][0] = loop_filter_h_44_16_neon;
-        dsp->loop_filter_mix2[0][0][1] = loop_filter_v_44_16_neon;
+        dsp->loop_filter_mix2[0][0][0] = ff_vp9_loop_filter_h_44_16_neon;
+        dsp->loop_filter_mix2[0][0][1] = ff_vp9_loop_filter_v_44_16_neon;
         dsp->loop_filter_mix2[0][1][0] = loop_filter_h_48_16_neon;
         dsp->loop_filter_mix2[0][1][1] = loop_filter_v_48_16_neon;
         dsp->loop_filter_mix2[1][0][0] = loop_filter_h_84_16_neon;
diff --git a/libavcodec/arm/vp9lpf_neon.S b/libavcodec/arm/vp9lpf_neon.S
index e31c807..12984a9 100644
--- a/libavcodec/arm/vp9lpf_neon.S
+++ b/libavcodec/arm/vp9lpf_neon.S
@@ -44,6 +44,109 @@
         vtrn.8          \r2,  \r3
 .endm

+@ The input to and output from this macro is in the registers q8-q15,
+@ and q0-q7 are used as scratch registers.
+@ p3 = q8, p0 = q11, q0 = q12, q3 = q15
+.macro loop_filter_q
+        vdup.u8         d0,  r2          @ E
+        lsr             r2,  r2,  #8
+        vdup.u8         d2,  r3          @ I
+        lsr             r3,  r3,  #8
+        vdup.u8         d1,  r2          @ E
+        vdup.u8         d3,  r3          @ I

I tried implementing your suggestion with uzp here, but it ended up being 
slower actually. With the version of the patch I posted here:

vp9_loop_filter_mix2_v_44_16_neon:   221.2   150.5  185.0   139.0

With this block replaced with this:

        vdup.u16        q0,  r2          @ E
        vdup.u16        q1,  r3          @ I
        vuzp.u8         d0,  d1          @ E
        vuzp.u8         d2,  d3          @ I

I get the following:

vp9_loop_filter_mix2_v_44_16_neon:   223.2   150.5  186.1   142.0

I.e. 1-3 cycles slower on A7, A9 and A53, identical on A8.

// Martin
_______________________________________________
libav-devel mailing list
libav-devel@libav.org
https://lists.libav.org/mailman/listinfo/libav-devel