LZ4 is lossless compression algorithm, providing compression speed at 400 MB/s per core (0.16 Bytes/cycle). It also features an extremely fast decoder, with speed in multiple GB/s per core (0.71 Bytes/cycle). A high compression derivative, called LZ4_HC, is also provided. It trades CPU time for compression ratio.
This benchmark simulates simple "static content transfer" scenario such as OS Kernel compression or video game's static assets (text/images/tables/scripts/etc) which loading from Flash Memory / HDD / SSD.
In this case, compression time is completely ignored. Because only content developers compress the data at once and usually they don't care about its computational cost. But they always care enduser's experience a.k.a. "loading time" and bandwidth.
Please pay attention to "LZ4HC -9" which is quite faster than other methods.
This benchmark simulates "dynamic content transfer" scenario such as filesystems, caches, network packets, IPC/RPCs, and databases.
In this case, both compression and decompression times are important. You can observe "Fast compression algorithms" are better than traditional algorithms such as DEFLATE (zlib).