Re: First-Part-Done (was Re: Byte Addressability And Beyond)

According to Lawrence D'Oliveiro  <ldo@nz.invalid>:

On Thu, 30 May 2024 14:42:14 -0000 (UTC), John Levine wrote:
>

The condition code tells you which it was.  If it was an interrupt, you
just branch back and keep going.

>
Does it really hurt performance for the CPU to keep track of the fact that
an instruction has to be restarted after an interrupt?

I should have been clearer, it's not just an interrupt. The CPU does
some maximum amount of work for the instruction, and sets the
condition code if it didn't do the whole string. Maybe it was an
interrupt, maybe it just hit the limit. Many other instructions that
process long chunks of data work the same way.

On the old VAX, there was a processor status bit called “First Part Done”,

Actually that was the PDP-6 and -10 for the byte instructions,

--
Regards,
John Levine, johnl@taugh.com, Primary Perpetrator of "The Internet for Dummies",
Please consider the environment before reading this e-mail. https://jl.ly