add neon instructions to kuznyechik

[alexzin04]

No description provided.

[alexzin04]

Bench before optimization (on Apple M1 Pro)
test kuznyechik_decrypt_block ... bench: 88,242.71 ns/iter (+/- 452.56) = 185 MB/s
test kuznyechik_decrypt_blocks ... bench: 88,452.09 ns/iter (+/- 1,017.96) = 185 MB/s
test kuznyechik_encrypt_block ... bench: 70,227.56 ns/iter (+/- 478.46) = 233 MB/s
test kuznyechik_encrypt_blocks ... bench: 45,962.28 ns/iter (+/- 872.57) = 356 MB/s
test result: ok. 0 passed; 0 failed; 0 ignored;4measured; 0 filtered out; finished in 2.17s

Bench after optimization with Neon
test kuznyechik_decrypt_block ... bench: 84,322.23 ns/iter (+/- 2,925.29) = 194 MB/s
test kuznyechik_decrypt_blocks ... bench: 31,483.26 ns/iter (+/- 263.59) = 520 MB/s
test kuznyechik_encrypt_block ... bench: 80,200.57 ns/iter (+/- 497.14) = 204 MB/s
test kuznyechik_encrypt_blocks ... bench: 27,858.40 ns/iter (+/- 142.16) = 588 MB/s
test result: ok. 0 passed; 0 failed; 0 ignored; 4 measured; 0 filtered out; finished in 2.63s

The speed after optimization increased by 2.81 times for decryption and by 1.6 times for encryption.

[newpavlov]

Thank you!