Re: [RFC PATCH 00/16] PTI support for x86-32

[Alan Cox]

> of timing requirements vs complexity.  At least theoretically one could
> imagine a machine which would take the trap after the speculative
> machine had already chased the pointer loop several levels down; this
> would most likely mean separate uops to allow for the existing
> out-of-order machine to do the bookkeeping.

It's not quite the same but in the IA-64 case you can write itanium code
that does exactly that. The speculation is expressed in software not
hardware (because you can trigger a load, then check later if it worked
out and respond appripriately).

Alan