Commit Graph

14 Commits

Author SHA1 Message Date
Zhao Zhili
eb14d45824 avfilter/vf_colordetect: add aarch64 asm
| rpi5 gcc 12  | m1 clang -fno-vectorize | m1 clang
---------------------------------------------------------------------------
alpha_8_full_c:        | 32159.2 ( 1.00x) | 135.8 ( 1.00x) |  26.4 ( 1.00x)
alpha_8_full_neon:     |  1266.0 (25.40x) |   8.0 (17.03x) |   8.4 ( 3.15x)
alpha_8_limited_c:     | 37561.9 ( 1.00x) | 169.1 ( 1.00x) |  47.7 ( 1.00x)
alpha_8_limited_neon:  |  3967.0 ( 9.47x) |  12.5 (13.53x) |  13.3 ( 3.59x)
alpha_16_full_c:       | 15867.9 ( 1.00x) |  64.5 ( 1.00x) |  13.7 ( 1.00x)
alpha_16_full_neon:    |  1256.9 (12.62x) |   7.9 ( 8.15x) |   8.3 ( 1.64x)
alpha_16_limited_c:    | 16723.7 ( 1.00x) |  88.7 ( 1.00x) | 103.3 ( 1.00x)
alpha_16_limited_neon: |  4031.3 ( 4.15x) |  12.5 ( 7.08x) |  13.2 ( 7.86x)
range_8_c:             | 21819.7 ( 1.00x) | 120.0 ( 1.00x) |   9.4 ( 1.00x)
range_8_neon:          |  1148.3 (19.00x) |   4.3 (27.60x) |   4.8 ( 1.97x)
range_16_c:            | 10757.1 ( 1.00x) |  45.7 ( 1.00x) |   7.9 ( 1.00x)
range_16_neon:         |  1141.5 ( 9.42x) |   4.4 (10.38x) |   4.6 ( 1.72x)
2025-09-01 15:35:16 +00:00
Timo Rothenpieler
262d41c804 all: fix typos found by codespell 2025-08-03 13:48:47 +02:00
Timo Rothenpieler
8d439b2483 all: fix whitespace/new-line issues 2025-08-03 13:48:47 +02:00
Martin Storsjö
93cda5a9c2 aarch64: Lowercase UXTW/SXTW and similar flags
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-10-21 23:25:23 +03:00
Martin Storsjö
184103b310 aarch64: Consistently use lowercase for vector element specifiers
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-10-21 23:25:18 +03:00
Andreas Rheinhardt
fa06f48371 avfilter/bwdifdsp: Constify
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2023-09-28 00:17:47 +02:00
Andreas Rheinhardt
80afcc8539 avfilter/bwdif: Add proper BWDIFDSPContext
This already avoids unnecessary indirectly included headers
in the arch-specific vf_bwdif_init.c files; it is also in
preparation for splitting the actual functions out of vf_bwdif.c.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2023-09-28 00:17:47 +02:00
John Cox
f00222e81f avfilter/vf_bwdif: Add neon for filter_line3
Signed-off-by: John Cox <jc@kynesim.co.uk>
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-07-06 00:21:05 +03:00
John Cox
94cb94a2c0 avfilter/vf_bwdif: Add neon for filter_line
Exports C filter_line needed for tail fixup of neon code
Adds neon for filter_line

Signed-off-by: John Cox <jc@kynesim.co.uk>
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-07-06 00:21:05 +03:00
John Cox
8130df83e0 avfilter/vf_bwdif: Add neon for filter_edge
Adds clip and spatial macros for aarch64 neon
Exports C filter_edge needed for tail fixup of neon code
Adds neon for filter_edge

Signed-off-by: John Cox <jc@kynesim.co.uk>
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-07-06 00:21:05 +03:00
John Cox
5075cfb4e6 avfilter/vf_bwdif: Add neon for filter_intra
Adds an outline for aarch neon functions
Adds common macros and consts for aarch64 neon
Exports C filter_intra needed for tail fixup of neon code
Adds neon for filter_intra

Signed-off-by: John Cox <jc@kynesim.co.uk>
Signed-off-by: Martin Storsjö <martin@martin.st>
2023-07-06 00:21:05 +03:00
Andreas Rheinhardt
f3c197b129 Include attributes.h directly
Some files currently rely on libavutil/cpu.h to include it for them;
yet said file won't use include it any more after the currently
deprecated functions are removed, so include attributes.h directly.

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>
2021-04-19 14:34:10 +02:00
Jan Ekström
eb94ec3257 lavfi/nlmeans: fix aarch64 assembly with clang
Clang is more strict about some things.
2018-07-28 17:41:19 +03:00
Clément Bœsch
5a71bce371 lavfi/nlmeans: add AArch64 SIMD for compute_safe_ssd_integral_image
ssd_integral_image_c: 49204.6
ssd_integral_image_neon: 28346.8
2018-05-08 10:28:06 +02:00