add support for am processor, and option to use arm performance library

[juntangc]

Arm based processors has been gaining popularity in HPC because its power efficiency. There are also substantial work to improve the performance like NEON and SVE technology and arm performance library (armpl).

This PR added configuration to allow the user to compile and run HPCCG on latest arm processor with auto-vectorization. Another improvement is to enable the user to use sparse matrix operations from armpl.

The recommended compilers (for arm) are gcc 10.2 or arm compiler for linux (acfl). Acfl can be obtained from https://developer.arm.com/downloads/-/arm-compiler-for-linux.

example compile commands:

gcc compiler (make COMPILER=gnu LIBRARY=none)
acfl compiler (make COMPILER=arm LIBRARY=none)
gcc compiler with armpl (make COMPILER=gnu LIBRARY=armpl)
acfl with armpl (make COMPILER=arm LIBRARY=armpl)

Please feel free to contact me for more information.

Regards,

Jun