[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: [Cryptography] Does RISC V solve Spectre ?



At 11:15 PM 3/24/2018, Bill Frantz wrote:
>People who are interested in these issues might be interested in looking at the Mill architecture.
>
><https://millcomputing.com/>
>
>The TLDR is: The mill is a family of statically scheduled chips with significant differences in number and type of functional units.
>
>Using them to best effect falls on the compiler and a post compiler phase called the specializer which prepares the program for specific chip.
>
>The web site has quite a bit about the technology, including videos of public presentations of the technology.

Indeed it does.

See this presentation in particular, where Mill claims that its processor is immune to Spectre/Meltdown, but that they *did* find a speculation bug in their software (which means that there are almost certainly equivalent bugs in compilers for other machines):

https://millcomputing.com/blog/wp-content/uploads/2018/01/Spectre.03.pdf

Spectre, Meltdown and the Mill CPU

Will Edwards will AT millcomputing.com

_______________________________________________
The cryptography mailing list
cryptography AT metzdowd.com
http://www.metzdowd.com/mailman/listinfo/cryptography