Handle compute packets that are split between the ends of two command buffers

[kalaposfos13]

For some reason P.T. submits compute command buffers that are not aligned at instruction ends, so some instructions end up having data in two buffers. This PR fixes the issue, by doing the following:

• If an instruction is longer than the remaining buffer size, we copy the incomplete part out to a buffer
• When the next instrucion buffer arrives, we check if there were any "leftovers" from the previous one, and if so, do the following:
• Check that if we took the appropriate amount of commands from the start of the buffer, the next data is a valid instruction
• If so, we finish setting up the command by copying the remaining data to the end of the previous one, then execute this command
• We then finish handling this new buffer, starting from the appropriate offset.

If any of these fail, we proceed to handle the new buffer as normal.

[raphaelthegreat]

I dont really like this approach too much, it feels very hacky

[kalaposfos13]

Any ideas as to how else could it be done? I agree that it's a bit too hacky, that's why I initially didn't release it

[raphaelthegreat]

It depends on the details of the problem. So first submit ends at the middle of a PM4 packet and next one starts right after the previous? Is there some padding in-between? If you could give a real example with addresses would be helpful