optimize ping pong with graviton3 intrinsics

[welly87]

current result without arm compiler flags

#[Mean    =       11.498, StdDeviation   =       21.781]
#[Max     =    14901.247, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 85,475.067415 RTTs/sec

[welly87]

before adding flags

from vscode

#[Mean    =        9.599, StdDeviation   =       18.778]
#[Max     =    12918.783, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 103,119.784649 RTTs/sec

#[Mean    =        9.470, StdDeviation   =       18.620]
#[Max     =     9052.159, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 104,518.685563 RTTs/sec

#[Mean    =        9.808, StdDeviation   =       21.577]
#[Max     =    20103.167, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 100,940.492482 RTTs/sec

after adding flags

#[Mean    =       16.056, StdDeviation   =       23.649]
#[Max     =     8388.607, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 60,870.374780 RTTs/sec

using release run

#[Mean    =        9.839, StdDeviation   =       17.878]
#[Max     =    12017.663, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 100,630.186374 RTTs/sec

once again

#[Mean    =        9.691, StdDeviation   =       16.324]
#[Max     =     5853.183, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 102,155.608562 RTTs/sec

#[Mean    =        9.448, StdDeviation   =       16.813]
#[Max     =     5849.087, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]
Throughput of 104,747.479048 RTTs/sec

[welly87]

another try with different process

#[Mean    =       16.920, StdDeviation   =       18.266]
#[Max     =    11706.367, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]

#[Mean    =       18.682, StdDeviation   =       31.254]
#[Max     =    22904.831, Total count    =     10000000]
#[Buckets =           24, SubBuckets     =         2048]