[FFmpeg-devel] [PATCH] avcodec/aarch64/opusdsp_neon: Simplify opus_postfilter_neon

[Martin Storsjö]

On Sat, 8 Feb 2025, Krzysztof Pyrkosz via ffmpeg-devel wrote:

> On Sat, Feb 08, 2025 at 01:59:32AM +0100, Lynne wrote:
>> On 07/02/2025 20:42, Krzysztof Pyrkosz via ffmpeg-devel wrote:
>>> This change removes one extra floating point operation and simplifies
>>> load operations at the beginning of the loop by using dedicated register
>>> for each of the 5 pointers and interleaving it with calculations. The
>>> first case seems to be a bit slower, but the performance increase is
>>> substantial in the other two.
>>>
>>> A78 before:
>>> postfilter_15_neon:                                   1684.8 ( 4.23x)
>>> postfilter_512_neon:                                  1395.5 ( 5.10x)
>>> postfilter_1022_neon:                                 1357.0 ( 5.25x)
>>>
>>> After:
>>> postfilter_15_neon:                                   1742.2 ( 4.09x)
>>> postfilter_512_neon:                                  1169.8 ( 6.09x)
>>> postfilter_1022_neon:                                 1160.0 ( 6.12x)
>>>
>>>
>>> A72 before:
>>> postfilter_15_neon:                                   3144.8 ( 2.39x)
>>> postfilter_512_neon:                                  3141.2 ( 2.39x)
>>> postfilter_1022_neon:                                 3230.0 ( 2.33x)
>>>
>>> After:
>>> postfilter_15_neon:                                   2847.8 ( 2.64x)
>>> postfilter_512_neon:                                  2877.8 ( 2.61x)
>>> postfilter_1022_neon:                                 2837.2 ( 2.65x)
>>>
>>>
>>> x13s before:
>>> postfilter_15_neon:                                   1615.4 ( 2.61x)
>>> postfilter_512_neon:                                   963.1 ( 4.39x)
>>> postfilter_1022_neon:                                  963.6 ( 4.39x)
>>>
>>> After:
>>> postfilter_15_neon:                                   1749.6 ( 2.41x)
>>> postfilter_512_neon:                                   707.1 ( 5.97x)
>>> postfilter_1022_neon:                                  706.1 ( 5.99x)
>>>
>>>
>>> Krzysztof
>>>
>>> ---
>>>   libavcodec/aarch64/opusdsp_neon.S | 31 ++++++++++++-------------------
>>>   1 file changed, 12 insertions(+), 19 deletions(-)
>>>
>>> diff --git a/libavcodec/aarch64/opusdsp_neon.S b/libavcodec/aarch64/opusdsp_neon.S
>>> index 253825aa61..990fc44c70 100644
>>> --- a/libavcodec/aarch64/opusdsp_neon.S
>>> +++ b/libavcodec/aarch64/opusdsp_neon.S
>>> @@ -55,35 +55,28 @@ endfunc
>>>   function ff_opus_postfilter_neon, export=1
>>>           ld1             {v0.4s}, [x2]
>>> +        sub             x5, x0, w1, sxtw #2
>>> +        sub             x1, x5, #8
>>>           dup             v1.4s, v0.s[1]
>>>           dup             v2.4s, v0.s[2]
>>>           dup             v0.4s, v0.s[0]
>>> -        add             w1, w1, #2
>>> -        sub             x1, x0, x1, lsl #2
>>> -
>>> -        ld1             {v3.4s}, [x1]
>>> +        ld1             {v3.4s}, [x1], #16
>>> +        sub             x4, x5, #4
>>> +        add             x6, x5, #4
>>>           fmul            v3.4s, v3.4s, v2.4s
>>> -1:      add             x1, x1, #4
>>> -        ld1             {v4.4s}, [x1]
>>> -        add             x1, x1, #4
>>> -        ld1             {v5.4s}, [x1]
>>> -        add             x1, x1, #4
>>> -        ld1             {v6.4s}, [x1]
>>> -        add             x1, x1, #4
>>> -        ld1             {v7.4s}, [x1]
>>> -
>>> +1:      ld1             {v7.4s}, [x1], #16
>>> +        ld1             {v4.4s}, [x4], #16
>>>           fmla            v3.4s, v7.4s, v2.4s
>>> +        ld1             {v6.4s}, [x6], #16
>>> +        ld1             {v5.4s}, [x5], #16
>>>           fadd            v6.4s, v6.4s, v4.4s
>>> +        fmla            v3.4s, v5.4s, v0.4s
>>>           ld1             {v4.4s}, [x0]
>>> -        fmla            v4.4s, v5.4s, v0.4s
>>> -
>>> -        fmul            v6.4s, v6.4s, v1.4s
>>> -        fadd            v6.4s, v6.4s, v3.4s
>>> -
>>> -        fadd            v4.4s, v4.4s, v6.4s
>>> +        fmla            v3.4s, v6.4s, v1.4s
>>> +        fadd            v4.4s, v4.4s, v3.4s
>>>           fmul            v3.4s, v7.4s, v2.4s
>>>           st1             {v4.4s}, [x0], #16
>>
>> This function was written and optimized for A53 cores. The fmla chain is
>> very performance sensitive on in-order CPUs?
>> Could you post a perf difference from an in-order CPU?
>
> Here are my benchmarks on Raspberry Pi 3B+.
>
> Before:
> deemphasis_neon:                                      4121.8 ( 2.11x)
> postfilter_15_neon:                                   9405.2 ( 2.46x)
> postfilter_512_neon:                                  9457.0 ( 2.44x)
> postfilter_1022_neon:                                 9398.0 ( 2.46x)
>
> After:
> deemphasis_neon:                                      4135.8 ( 2.10x)
> postfilter_15_neon:                                   7967.2 ( 2.90x)
> postfilter_512_neon:                                  7980.2 ( 2.89x)
> postfilter_1022_neon:                                 7980.0 ( 2.89x)

I'm also getting similar numbers on another A53.

This patch looks good to me, so I pushed it. Thanks!

// Martin