All apps were updated to v3.8.21

Only 2 things were fixed:

No new feature in this LLR version, but the AVX threading bug is here fixed.
This bug caused often false results after an error recovery, due to a misuse of the POSTFFT feature while calling gwstartnextft() function.

This LLR version is linked with the Version 28.14 of George Woltman's gwnum library.
The only thing new from 28.13 is better FFT selections for AMD Ryzen CPUs.

Pls note that the FLOPs are back to 0. This means inaccurate runtimes at the beginning. After some reported results the runtime will be correct again.

If you find any errors pls report them here. More work will be added soon.

More...