← Back to context

Comment by lolsowrong

6 hours ago

I saw the paper from Google last year and thought something in it aligned with not everything running through the microcode engine, though I could be wrong.

Might well be the case. I don't think I'm familiar with the paper you're referring to; any chance of at least a vague description?

  • Can’t find the pdf, but it’s all related to the zentool stuff:

    https://github.com/google/security-research/blob/master/pocs...

    Tavis spells it out there pretty quickly:

    “ The simplest instructions (add, sub, mov, etc) are all implemented in hardware. The more complicated instructions like rdrand, fpatan and cmpxchg are microcoded. You can think of them as a bit like calling into a library of functions written in that RISC-like code.”