Updated results for Version 2.0 Eval 03
Yeah, there is some progress...
Results for my primary sample set:
AMD Sempron 2.2 GHz
Preset Compression Enco-Speed Deco-Speed
1.1.2 2.0 Win 1.1.2 2.0 Win 1.1.2 2.0 Win
-p0 58.83 58,74 0,09 264.10 290,95 10,17% 283.52 294,06 3,72%
-p1 57.98 57,66 0,32 193.18 192,05 -0,58% 275.80 285,83 3,64%
-p2 57.07 56,93 0,14 131.39 135,30 2,98% 250.36 258,87 3,40%
-p3 56.52 56,40 0,12 55.97 61,18 9,31% 190.88 218,93 14,70%
-p4 56.16 56,08 0,08 32.07 33,83 5,49% 166.89 176,69 5,87%
-p4m 56.07 55,93 0,14 17.81 14,43 -18,98%
Intel Pentium Dual Core 2 GHz
Preset Compression Enco-Speed Deco-Speed
1.1.2 2.0 Win 1.1.2 2.0 Win 1.1.2 2.0 Win
-p0 58.83 58,74 0,09 261.83 284,54 8,67% 298.67 311,81 4,40%
-p1 57.98 57,66 0,32 201.75 201,09 -0,33% 291.72 304,66 4,44%
-p2 57.07 56,93 0,14 146.14 148,89 1,88% 262.58 271,37 3,35%
-p3 56.52 56,40 0,12 64.64 69,37 7,32% 214.36 240,48 12,19%
-p4 56.16 56,08 0,08 36.90 37,86 2,60% 193.97 205,73 6,06%
-p4m 56.07 55,93 0,14 21.07 16,68 -20,84%
Compression is relative to the original file size, Enco- and Deco-Speed expressed as multiple of real time.
Some results for LossyWav:
Quality Preset Compression
1.1.2 2.0 Win
-q00 -p2m 19.37 18,92 0,45
-q25 -p2m 26.38 26,00 0,38
-q50 -p2m 32.34 31,97 0,37
Some remarks:
- Again some tiny compression improvements.
- Again -p0 is encoding significantly faster. Encoding is now nearly as fast as decoding on the Sempron.
- I have deceided, to make -p1 stronger, therefore it's now encoding a bit slower.
Thomas