#18744: Setup registers for GO message before waiting

[jbaumanTT]

Ticket

#18744

Problem description

Currently Done->GO message latency can be as high as around 950 cycles.

What's changed

If we setup all the registers for multicasting the GO message before we wait for workers, that can reduce the minimum latency for the GO message by about 80 cycles.

Checklist

• All post commit CI passes
• Blackhole Post commit CI passes (if applicable)
• Model regression CI passes (if applicable)
• Device performance regression CI passes (if applicable)
• (For models and ops writers) Full new models tests CI passes (if applicable)
• New/Existing tests provide coverage for changes