phc-discussions - Re: [PHC] A (naively?) simple PHC submission using hash chains

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite for Android: free password hash cracker in your pocket

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date: Wed, 7 Aug 2013 03:01:08 -0500 (CDT)
From: Steve Thomas <steve@...tu.com>
To: discussions@...sword-hashing.net
Subject: Re: [PHC] A (naively?) simple PHC submission using hash chains

> 

I should say I'm mostly thinking of the case of a website/server login.

> On August 7, 2013 at 2:44 AM Tony Arcieri <tony.arcieri@...il.com> wrote:
>  On Wed, Aug 7, 2013 at 12:39 AM, Steve Thomas <steve@...tu.com
> <mailto:steve@...tu.com> >wrote:
>    > >    You shouldn't rely on threading as it can cause problems
> >  > 
>  What problems?
> 
>    > >    and extra resources.
> >  > 
>  Like multiple CPU cores?
> 

Creating/destroying threads is costly (time and memory). You can avoid some of
this overhead if you have a service/daemon running and take requests.

> 
>    > >    If anything it should be nice for vector instructions (SSE2, AVX,
>    > > AVX2, AVX512)
> >  > 
>  How would these help leverage multicore CPUs?
> 

It won't but the multiple concurrent requests to login will.

> 
>    > >    Anyone know if the AES-NI run in constant time?
> >  > 
>  It'd be pretty facepalm if it wasn't. That said AES-NI would be an
> interesting way to get speedups on x86 CPUs at least
> 
I agree but I don't like to assume.
Content of type "text/html" skipped