Remove brand_code, model_bits and model_code fields, add a new brand sub-struct.
There fields were complicated to manage, adding complex functions to make it work.
amd_bits_t and intel_bits_t enums were truncated, I had to replace them with #define in 2e01aa0303.
Some of these #define were conflicting with other C headers (ctype.h on OpenBSD, corecrt_wctype.h on Windows), that is why I wanted to get rid of it.
I updated some CPU codenames meanwhile for more consistency.
Fix#212.
Since Zen-based CPUs, cpu_id_t::l3_cache is the size of the total L3 cache for the whole chip, while cpu_id_t::l1_cache and cpu_id_t::l2_cache are size for each instances.
This change provide L3 cache size per instance.
Since ff5aafb5f4, xeon-scalable-4114.test and qemu.test are failling because RAW came from a VM.
Since 2b8023f733, godavari-x4.test is failling due to the merge after 9710e7c0ba