ffmpeg/tests/ref/seek/vsynth_lena-mjpeg
Ramiro Polla 384fe39623 swscale/range_convert: fix mpeg ranges in yuv range conversion for non-8-bit pixel formats
There is an issue with the constants used in YUV to YUV range conversion,
where the upper bound is not respected when converting to mpeg range.

With this commit, the constants are calculated at runtime, depending on
the bit depth. This approach also allows us to more easily understand how
the constants are derived.

For bit depths <= 14, the number of fixed point bits has been set to 14
for all conversions, to simplify the code.
For bit depths > 14, the number of fixed points bits has been raised and
set to 18, to allow for the conversion to be accurate enough for the mpeg
range to be respected.

The convert functions now take the conversion constants (coeff and offset)
as function arguments.
For bit depths <= 14, coeff is unsigned 16-bit and offset is 32-bit.
For bit depths > 14, coeff is unsigned 32-bit and offset is 64-bit.

x86_64:
chrRangeFromJpeg8_1920_c:    2127.4   2125.0  (1.00x)
chrRangeFromJpeg16_1920_c:   2325.2   2127.2  (1.09x)
chrRangeToJpeg8_1920_c:      3166.9   3168.7  (1.00x)
chrRangeToJpeg16_1920_c:     2152.4   3164.8  (0.68x)
lumRangeFromJpeg8_1920_c:    1263.0   1302.5  (0.97x)
lumRangeFromJpeg16_1920_c:   1080.5   1299.2  (0.83x)
lumRangeToJpeg8_1920_c:      1886.8   2112.2  (0.89x)
lumRangeToJpeg16_1920_c:     1077.0   1906.5  (0.56x)

aarch64 A55:
chrRangeFromJpeg8_1920_c:   28835.2  28835.6  (1.00x)
chrRangeFromJpeg16_1920_c:  28839.8  32680.8  (0.88x)
chrRangeToJpeg8_1920_c:     23074.7  23075.4  (1.00x)
chrRangeToJpeg16_1920_c:    17318.9  24996.0  (0.69x)
lumRangeFromJpeg8_1920_c:   15389.7  15384.5  (1.00x)
lumRangeFromJpeg16_1920_c:  15388.2  17306.7  (0.89x)
lumRangeToJpeg8_1920_c:     19227.8  19226.6  (1.00x)
lumRangeToJpeg16_1920_c:    15387.0  21146.3  (0.73x)

aarch64 A76:
chrRangeFromJpeg8_1920_c:    6324.4   6268.1  (1.01x)
chrRangeFromJpeg16_1920_c:   6339.9  11521.5  (0.55x)
chrRangeToJpeg8_1920_c:      9656.0   9612.8  (1.00x)
chrRangeToJpeg16_1920_c:     6340.4  11651.8  (0.54x)
lumRangeFromJpeg8_1920_c:    4422.0   4420.8  (1.00x)
lumRangeFromJpeg16_1920_c:   4420.9   5762.0  (0.77x)
lumRangeToJpeg8_1920_c:      5949.1   5977.5  (1.00x)
lumRangeToJpeg16_1920_c:     4446.8   5946.2  (0.75x)

NOTE: all simd optimizations for range_convert have been disabled.
      they will be re-enabled when they are fixed for each architecture.

NOTE2: the same issue still exists in rgb2yuv conversions, which is not
       addressed in this commit.
2024-12-05 21:10:29 +01:00

47 lines
2.7 KiB
Plaintext

ret: 0 st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos: 5652 size: 11224
ret: 0 st:-1 flags:0 ts:-1.000000
ret: 0 st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos: 5652 size: 11224
ret: 0 st:-1 flags:1 ts: 1.894167
ret: 0 st: 0 flags:1 dts: 1.880000 pts: 1.880000 pos: 592510 size: 14069
ret: 0 st: 0 flags:0 ts: 0.800000
ret: 0 st: 0 flags:1 dts: 0.800000 pts: 0.800000 pos: 232724 size: 12267
ret:-1 st: 0 flags:1 ts:-0.320000
ret:-1 st:-1 flags:0 ts: 2.576668
ret: 0 st:-1 flags:1 ts: 1.470835
ret: 0 st: 0 flags:1 dts: 1.480000 pts: 1.480000 pos: 453244 size: 13732
ret: 0 st: 0 flags:0 ts: 0.360000
ret: 0 st: 0 flags:1 dts: 0.360000 pts: 0.360000 pos: 104162 size: 11211
ret:-1 st: 0 flags:1 ts:-0.760000
ret:-1 st:-1 flags:0 ts: 2.153336
ret: 0 st:-1 flags:1 ts: 1.047503
ret: 0 st: 0 flags:1 dts: 1.040000 pts: 1.040000 pos: 307478 size: 12725
ret: 0 st: 0 flags:0 ts:-0.040000
ret: 0 st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos: 5652 size: 11224
ret: 0 st: 0 flags:1 ts: 2.840000
ret: 0 st: 0 flags:1 dts: 1.960000 pts: 1.960000 pos: 620688 size: 14145
ret: 0 st:-1 flags:0 ts: 1.730004
ret: 0 st: 0 flags:1 dts: 1.720000 pts: 1.720000 pos: 536394 size: 13965
ret: 0 st:-1 flags:1 ts: 0.624171
ret: 0 st: 0 flags:1 dts: 0.640000 pts: 0.640000 pos: 184556 size: 11973
ret: 0 st: 0 flags:0 ts:-0.480000
ret: 0 st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos: 5652 size: 11224
ret: 0 st: 0 flags:1 ts: 2.400000
ret: 0 st: 0 flags:1 dts: 1.960000 pts: 1.960000 pos: 620688 size: 14145
ret: 0 st:-1 flags:0 ts: 1.306672
ret: 0 st: 0 flags:1 dts: 1.320000 pts: 1.320000 pos: 399054 size: 13347
ret: 0 st:-1 flags:1 ts: 0.200839
ret: 0 st: 0 flags:1 dts: 0.200000 pts: 0.200000 pos: 59930 size: 10980
ret: 0 st: 0 flags:0 ts:-0.920000
ret: 0 st: 0 flags:1 dts: 0.000000 pts: 0.000000 pos: 5652 size: 11224
ret: 0 st: 0 flags:1 ts: 2.000000
ret: 0 st: 0 flags:1 dts: 1.960000 pts: 1.960000 pos: 620688 size: 14145
ret: 0 st:-1 flags:0 ts: 0.883340
ret: 0 st: 0 flags:1 dts: 0.880000 pts: 0.880000 pos: 257278 size: 12415
ret:-1 st:-1 flags:1 ts:-0.222493
ret:-1 st: 0 flags:0 ts: 2.680000
ret: 0 st: 0 flags:1 ts: 1.560000
ret: 0 st: 0 flags:1 dts: 1.560000 pts: 1.560000 pos: 480846 size: 13843
ret: 0 st:-1 flags:0 ts: 0.460008
ret: 0 st: 0 flags:1 dts: 0.480000 pts: 0.480000 pos: 137982 size: 11451
ret:-1 st:-1 flags:1 ts:-0.645825