Buildbot: ffmpegsos-solaris10-sparc Build #13553

Results:

Failed shell_2 shell_3 shell_4 shell_5

SourceStamp:

Project	ffmpeg
Repository	https://git.ffmpeg.org/ffmpeg.git
Branch	master
Revision	d9e2239f3c5e17d908db0b79f68ff06ee1867828
Got Revision	d9e2239f3c5e17d908db0b79f68ff06ee1867828
Changes	7 changes

BuildSlave:

unstable10s

Reason:

The SingleBranchScheduler scheduler named 'schedule-ffmpegsos-solaris10-sparc' triggered this build

Steps and Logfiles:

git update ( 6 secs )
1. stdio
shell 'gsed -i ...' ( 0 secs )
1. stdio
shell_1 'gsed -i ...' ( 0 secs )
1. stdio
shell_2 'gsed -i ...' failed ( 0 secs )
1. stdio
shell_3 './configure --samples="../../../ffmpeg/fate-suite" ...' failed ( 8 secs )
1. stdio
2. config.log
shell_4 'gmake fate-rsync' failed ( 0 secs )
1. stdio
shell_5 '../../../ffmpeg/fate.sh ../../../ffmpeg/fate_config_sos.sh' failed ( 0 secs )

Build Properties:

Name	Value	Source
branch	master	Build
builddir	/export/home/buildbot-unstable10s/slave/ffmpegsos-solaris10-sparc	slave
buildername	ffmpegsos-solaris10-sparc	Builder
buildnumber	13553	Build
codebase		Build
got_revision	d9e2239f3c5e17d908db0b79f68ff06ee1867828	Git
project	ffmpeg	Build
repository	https://git.ffmpeg.org/ffmpeg.git	Build
revision	d9e2239f3c5e17d908db0b79f68ff06ee1867828	Build
scheduler	schedule-ffmpegsos-solaris10-sparc	Scheduler
slavename	unstable10s	BuildSlave
workdir	/export/home/buildbot-unstable10s/slave/ffmpegsos-solaris10-sparc	slave (deprecated)

Forced Build Properties:

Name	Label	Value

Responsible Users:

DROOdotFOO
drewohnoyoudont@axol.io

Timing:

Start	Sat Jun 6 19:53:50 2026
End	Sat Jun 6 19:54:07 2026
Elapsed	16 secs

All Changes:

:

Change #269648

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	e0fa6412408fd776776d9571e4ca79f630a13e14

Comments

swscale/aarch64/yuv2rgb_neon: chroma-preserve compute_rgb
Macro writes per-luma sums into the destination registers, leaving
v20-v25 (chroma -> RGB offsets) intact for the 2-line callers. Takes
bare register names. compute_rgba and compute_rgba_alpha follow suit.

Single-row callers reload v20-v25 each iteration via
chroma_to_rgb_offsets, so the change is a no-op for them: Apple M1
width=1920 mean -0.54% across 55 paths, within bench noise.

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Change #269649

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	8dbc7299509f7e30530ded2ea868249e05ff54e8

Comments

swscale/aarch64/yuv2rgb_neon: name registers
the loop body. .text byte-identical.

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Change #269650

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	11b1721b11becf9692d855802b990cb032de6f3c

Comments

swscale/aarch64/yuv2rgb_neon: reorder params, unify signature
Pass src[]/srcStride[] as arrays (x5/x6), move y_offset/y_coeff into
register args (w2/w3). Only int-after-pointer stack args remain, so
Apple and AAPCS64 lay them out identically; every __APPLE__ is gone.
nv12/nv21/yuv420p/yuv422p/yuva420p share one signature.

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/swscale_unscaled.c
libswscale/aarch64/yuv2rgb_neon.S

Change #269651

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	4bfe7efd0c3ffa35a39d34af25c4c64ac484fe95

Comments

swscale/aarch64/yuv2rgb_neon: 2 lines at a time, packed RGB
Vertically-subsampled inputs (nv12, nv21, yuv420p) share a chroma
row across two output rows; compute the chroma -> RGB offsets once
and apply to both luma rows. Covers argb/rgba/abgr/bgra/rgb24/bgr24.

Test Name                                A55-gcc            M1-clang             A76-gcc
----------------------------------------------------------------------------------------
nv12_to_argb_neon                21647.2 (1.16x)        40.1 (1.24x)     13813.3 (1.16x)
nv12_to_rgba_neon                21653.7 (1.16x)        40.8 (1.32x)     14105.0 (1.13x)
nv12_to_abgr_neon                22122.2 (1.15x)        40.3 (1.27x)     14100.2 (1.16x)
nv12_to_bgra_neon                22121.6 (1.15x)        39.6 (1.24x)     14125.9 (1.16x)
nv12_to_rgb24_neon               19842.0 (1.18x)        33.4 (1.28x)     12868.9 (1.17x)
nv12_to_bgr24_neon               20318.0 (1.18x)        34.6 (1.23x)     12868.8 (1.17x)
nv21_to_argb_neon                21648.5 (1.16x)        41.0 (1.29x)     13978.5 (1.14x)
nv21_to_rgba_neon                21653.0 (1.16x)        41.3 (1.21x)     14173.5 (1.11x)
nv21_to_abgr_neon                22120.6 (1.15x)        41.1 (1.20x)     14505.4 (1.14x)
nv21_to_bgra_neon                22120.8 (1.15x)        41.0 (1.22x)     14520.1 (1.14x)
nv21_to_rgb24_neon               19830.5 (1.19x)        35.1 (1.28x)     12832.4 (1.17x)
nv21_to_bgr24_neon               20317.1 (1.18x)        34.6 (1.27x)     12833.1 (1.17x)
yuv420p_to_argb_neon             21450.2 (1.15x)        39.2 (1.19x)     14118.3 (1.12x)
yuv420p_to_rgba_neon             21447.2 (1.15x)        38.8 (1.24x)     14326.0 (1.14x)
yuv420p_to_abgr_neon             21927.0 (1.15x)        38.9 (1.25x)     14826.6 (1.13x)
yuv420p_to_bgra_neon             21930.8 (1.15x)        41.4 (1.18x)     14822.9 (1.13x)
yuv420p_to_rgb24_neon            19365.5 (1.17x)        33.5 (1.25x)     13291.8 (1.16x)
yuv420p_to_bgr24_neon            19848.8 (1.16x)        34.1 (1.35x)     13292.8 (1.16x)

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Change #269652

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	dad212060c777ad21a8f785ba11f1add3a15e432

Comments

swscale/aarch64/yuv2rgb_neon: 2 lines at a time, gbrp
Six dst pointers exhaust the caller-saved registers; spill x19/x20.
yuva420p_to_gbrp_neon is routed through the yuv420p path by the
dispatcher (gbrp has no alpha channel).

Test Name                                A55-gcc            M1-clang             A76-gcc
----------------------------------------------------------------------------------------
nv12_to_gbrp_neon                20017.8 (1.15x)        32.8 (1.34x)     10658.0 (1.27x)
nv21_to_gbrp_neon                20020.9 (1.15x)        32.5 (1.36x)     10691.1 (1.26x)
yuv420p_to_gbrp_neon             19856.3 (1.14x)        31.4 (1.34x)     10348.0 (1.37x)
yuva420p_to_gbrp_neon            19859.8 (1.14x)        30.9 (1.27x)     10350.9 (1.37x)

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Change #269653

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	4b6f7c2a05f456cc27241f6ed1e44e77aa7861d6

Comments

swscale/aarch64/yuv2rgb_neon: 2 lines at a time, rgb16
pack_rgb16_2l uses v26-v29 as scratch (luma temps, dead by then)
instead of v20-v23, so v20-v25 chroma survives the pack step. A
.error trips if yuva420p hits rgb16 (v28/v29 would clobber alpha);
the dispatcher routes that combination through yuv420p anyway.

Test Name                                A55-gcc            M1-clang             A76-gcc
----------------------------------------------------------------------------------------
nv12_to_rgb565le_neon            28531.9 (1.12x)        46.8 (1.28x)     19252.9 (1.09x)
nv12_to_bgr565le_neon            29018.1 (1.12x)        48.1 (1.17x)     19252.0 (1.09x)
nv12_to_rgb555le_neon            28531.3 (1.12x)        47.2 (1.24x)     19253.6 (1.09x)
nv12_to_bgr555le_neon            29012.1 (1.12x)        45.8 (1.22x)     19252.5 (1.09x)
nv21_to_rgb565le_neon            28532.3 (1.12x)        48.4 (1.15x)     19430.0 (1.09x)
nv21_to_bgr565le_neon            29013.8 (1.12x)        47.2 (1.21x)     19428.8 (1.09x)
nv21_to_rgb555le_neon            28533.3 (1.12x)        49.7 (1.16x)     19430.5 (1.09x)
nv21_to_bgr555le_neon            29011.4 (1.12x)        48.5 (1.18x)     19428.7 (1.09x)
yuv420p_to_rgb565le_neon         28351.9 (1.11x)        46.4 (1.18x)     19635.3 (1.08x)
yuv420p_to_bgr565le_neon         28831.8 (1.11x)        50.8 (1.09x)     19634.5 (1.08x)
yuv420p_to_rgb555le_neon         28351.3 (1.11x)        46.3 (1.23x)     19634.2 (1.08x)
yuv420p_to_bgr555le_neon         28829.1 (1.11x)        46.5 (1.21x)     19634.3 (1.08x)
yuva420p_to_rgb565le_neon        28349.5 (1.11x)        51.2 (1.06x)     19634.7 (1.08x)
yuva420p_to_bgr565le_neon        28833.1 (1.11x)        48.6 (1.17x)     19633.9 (1.08x)
yuva420p_to_rgb555le_neon        28351.6 (1.11x)        47.8 (1.16x)     19635.2 (1.08x)
yuva420p_to_bgr555le_neon        28831.5 (1.11x)        46.4 (1.14x)     19634.8 (1.08x)

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Change #269654

Category	ffmpeg
Changed by	DROOdotFOO <drewohnoyoudont@axol.io>
Changed at	Sat 06 Jun 2026 19:38:40
Repository	https://git.ffmpeg.org/ffmpeg.git
Project	ffmpeg
Branch	master
Revision	d9e2239f3c5e17d908db0b79f68ff06ee1867828

Comments

swscale/aarch64/yuv2rgb_neon: 2 lines at a time, yuva420p
Alpha is full resolution, so each row loads its own 16 alpha bytes
via process_row's \rsrcA arg.

Test Name                                A55-gcc            M1-clang             A76-gcc
----------------------------------------------------------------------------------------
yuva420p_to_argb_neon            22607.6 (1.16x)        39.2 (1.24x)     13631.6 (1.12x)
yuva420p_to_rgba_neon            22608.2 (1.16x)        38.3 (1.21x)     13912.8 (1.12x)
yuva420p_to_abgr_neon            23074.6 (1.16x)        38.8 (1.22x)     14492.1 (1.08x)
yuva420p_to_bgra_neon            23079.7 (1.16x)        39.9 (1.19x)     14472.6 (1.08x)

Co-authored-by: Ramiro Polla <ramiro.polla@gmail.com>
Signed-off-by: DROOdotFOO <drew@axol.io>

Changed files

libswscale/aarch64/yuv2rgb_neon.S

Builder ffmpegsos-solaris10-sparc Build #13553

Results:

SourceStamp:

BuildSlave:

Reason:

Steps and Logfiles:

Build Properties:

Forced Build Properties:

Responsible Users:

Timing:

All Changes:

:

Change #269648

Comments

Changed files

Change #269649

Comments

Changed files

Change #269650

Comments

Changed files

Change #269651

Comments

Changed files

Change #269652

Comments

Changed files

Change #269653

Comments

Changed files

Change #269654

Comments

Changed files