[felice2011]

I place an quick test of compression and decompression with enwik8, with and without cls.dll, with a block of memory resident in the 16384k heap, to equal the same compression ratio in response to the use of zstd without the cls.

I also tried to use 8 threads, the speed of compression increases considerably, but the cpu ... squirts to hell, with freeze pc if not adequately cooled.

zstd without cls

-↓- [ CMD Bench.Test.Info v0.0.6c ] -↓- Compressed Archive Completed At -↓- 22/08/2016 19:18:24
==================================================================================================================================
 ○ [ ALGORITHM ] ○ [ INPUT SIZE ] ○ [ OUTPUT SIZE ] ○ [ RATIO.% ] ○ [ ARCHIVED FILES ] ○ [ COMP.TIME ] ○ [ ARGUMENTS - OPTIONS ] ○

             Arc          95,4°MB           26,2°MB       27,46 %              1°Files     00:00:42:60   a -ma9 -ds -lc1024 -ld1024 -ep1 -di -i2 -ed -r -w.\
                                                                                                         -mzstd
==================================================================================================================================

-↓- [ CMD Bench.Test.Info v0.0.6c ] -↓- Decompressed Archive Completed At -↓- 22/08/2016 19:20:16
==================================================================================================================================
 ○ [ ALGORITHM ] ○ [ ARCHIVE NAME ] ○ [ INPUT SIZE ] ○ [ DECOMP.TIME ] ○ [ ARGUMENTS - OPTIONS ] ○

             Arc   ...\zstd_exe.arc          26,2°MB       00:00:00:36              x -o+ -w.\  
==================================================================================================================================

zstd only cls

-↓- [ CMD Bench.Test.Info v0.0.6c ] -↓- Compressed Archive Completed At -↓- 22/08/2016 19:28:24
==================================================================================================================================
 ○ [ ALGORITHM ] ○ [ INPUT SIZE ] ○ [ OUTPUT SIZE ] ○ [ RATIO.% ] ○ [ ARCHIVED FILES ] ○ [ COMP.TIME ] ○ [ ARGUMENTS - OPTIONS ] ○

             Arc          95,4°MB           26,1°MB       27,36 %              1°Files     00:00:18:57   a -ma9 -ds -lc1024 -ld1024 -ep1 -di -i2 -ed -r -w.\ 
                                                                                                         -mzstd
==================================================================================================================================

-↓- [ CMD Bench.Test.Info v0.0.6c ] -↓- Decompressed Archive Completed At -↓- 22/08/2016 19:31:16
==================================================================================================================================
 ○ [ ALGORITHM ] ○ [ ARCHIVE NAME ] ○ [ INPUT SIZE ] ○ [ DECOMP.TIME ] ○ [ ARGUMENTS - OPTIONS ] ○

             Arc   ...\zstd_cls.arc          26,1°MB       00:00:00:43              x -o+ -w.\  
==================================================================================================================================

[CLS]
Level=22
ChunkSize=16384k
Threads=4

With the use of the cls the compression time decreases by almost 60% while maintaining the same compression ratio with and without cls.
On the contrary, the decompression time has a lower speed of 15-17% with the use of cls, but in this case I think you should test larger files.
These dll alternative by razor are a real boon from sky ...