[Cryptography] Speculation considered harmful?
Bill Frantz
frantz at pwpconsult.com
Mon Jan 15 18:22:21 EST 2018
Forward from Mill Computing:
A White Paper covering how the Mill CPU is affected by the
recently disclosed Spectre and Meltdown exploits is available
here (https://millcomputing.com/blog/wp-content/uploads/2018/01/Spectre.03.pdf).
Cheers - Bill
On 1/10/18 at 2:41 PM, frantz at pwpconsult.com (Bill Frantz) wrote:
>On 1/10/18 at 8:02 AM, nico at cryptonector.com (Nico Williams) wrote:
>
>>On Tue, Jan 09, 2018 at 05:46:07PM -0500, Theodore Ts'o wrote:
>>>Yet another problem with VLIW is that the optimizations tend to be
>>>horribly architecture specific. If you change the number of various
>>>functional units, but you want to keep the instruction set backwards
>>>compatibility, that's possible --- but if the compiler has to know how
>>>the instructions will be scheduled, not only is it slow to compile,
>>>but what is optimized for a particular version of Itanic might have be
>>>terribe performance on a different version of the Itanic.
>>
>>VLIW == no stable ABI. We'd have to ship bitcode and re-optimize,
>>assemble, and link for every VLIW CPU model.
>>
>>It wouldn't be the end of the world. But first we'd need the compilers
>>that could handle it.
>
>For people interested in new approaches to hardware
>architecture, the Mill might be interesting
><https://millcomputing.com/> The Technology->docs/videos/slides
>page is a good place to learn about the technology.
>
>Full disclosure: I worked briefly for Mill Computing on a sweat
>equity basis. I still have a claim on a small bit of equity. I
>stopped working because I didn't think I was contributing much
>of value. I still wish them well because they have interesting ideas.
>
>Cheers - Bill
-----------------------------------------------------------------------
Bill Frantz | There's nothing so clear as | Periwinkle
(408)356-8506 | a design you haven't written | 16345
Englewood Ave
www.pwpconsult.com | down. - Dean Tribble | Los Gatos,
CA 95032
More information about the cryptography
mailing list