[Libre-soc-dev] LD/ST Elwidth Overrides

lkcl luke.leighton at gmail.com
Thu Sep 2 11:55:32 BST 2021

On September 1, 2021 8:48:43 PM UTC, Jacob Lifshay <programmerjake at gmail.com> wrote:

>idk, but the point is the encoding supports it, so we have to account
>malicious programmers.

thought about it: no *we*, as spec writers, do not. the *hardware implementors* have to take responsibility for that.

in many cases when writing specifications the delineation and separation between those two responsibilities is not at all clear, in fact the total opposite, they are very closely interrelated. however in this unique and special case they are separatable.

implementors in this particular unique special case *may* choose to terminate fail-first at any point.

thus, for high security scenarios they *may* choose simply to disable ffirst entirely, causing programs to fall back to VL=1 a hundred percent of the time.

clearly, performance will suck.

preventing and prohibiting the possibility for hardware implementors to choose between performance and security makes for a really bad specification, given that security may be achieved through means OTHER than forcibly lobotomising the hardware.

such means include locking the hardware in high security vaults, disconnecting it from the internet entirely, security-vetting users and then trusting them with the responsibility of executing pre-vetted applications.

i am outlining this in some detail so that you do not conflate the role and responsibility of writing specifications with the role and responsibility of hardware implementors.

the two are completely separate and distinct.


More information about the Libre-soc-dev mailing list