Probably the one test that concerns me is P7zip on Linux.
The disparity between the Linux fork (16.02) and the Windows version (19) keeps growing.
There are several documented enhancements in performance between the two releases. (Missing in the Linux fork)
The speed for LZMA/LZMA2 compressing was increased by 3-10%
The speed for LZMA/LZMA2 compressing was increased by 8% for fastest/fast compression levels and by 3% for normal/maximum compression levels. The vulnerability in RAR unpacking code was fixed (CVE-2018-10115)
The speed for single-thread LZMA/LZMA2 decoding was increased by 30% in x64 version and by 3% in x86 version
7-Zip now can use multi-threading for 7z/LZMA2 decoding, if there are multiple independent data chunks in LZMA2 stream.
7-Zip now can use multi-threading for xz decoding, if there are multiple blocks in xz stream
7-Zip now uses additional memory buffers for multi-block LZMA2 compression. CPU utilization was slightly improved.
Perhaps the use case for these enhancements are limited in the Linux world so their desire to have is very limited. For a cross platform benchmark, this can be disconcerting. (at last check. PTS uses the same version for both FWIW) Publications (ie: PC World) have moved on to the latest for Windows, so this make a compare difficult.
I wonder if a cash bounty for an update to the Linux fork is needed to help keep it current.
-
Phoronix Test Suite 8.8 Further Enhances Open-Source, Automated Windows Benchmarking
Phoronix: Phoronix Test Suite 8.8 Further Enhances Open-Source, Automated Windows Benchmarking
While we have endless passion and fun for Linux (and BSD) benchmarking, with Phoronix Test Suite 8.8 being released there are yet more improvements for our open-source, automated and repeatable benchmarking on Microsoft Windows...
Leave a comment: