phc-discussions - RE: [PHC] Is bandwidth all that counts?

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]

Message-ID: <e67f54d5f4ae4645bb11ac0d60a3e66d@SN2PR03MB080.namprd03.prod.outlook.com>
Date: Wed, 12 Feb 2014 01:23:39 +0000
From: Marsh Ray <maray@...rosoft.com>
To: "discussions@...sword-hashing.net" <discussions@...sword-hashing.net>
Subject: RE: [PHC] Is bandwidth all that counts?

From: Peter Maxwell [mailto:peter@...icient.co.uk]
> My problem is understanding why memory bandwidth is the critical
> factor - is memory bandwidth inherently more expensive than the actual DRAM?

It’s something that depends on MACROscopic hardware, which imposes physical limits to growth. It grows much slower that Moore’s law.

Yet commodity hardware comes very highly optimized for memory bandwidth, so in effect defenders collectively participate in a big economy of scale. An attacker may be able to do get a better price/performance with custom hardware, but probably not by much (on the log2 scale).

In short, we can expect that an attacker could fit 512 parallel instances of MD5 on a custom silicon chip. But it’s probably also a reasonable assumption that no one has an external RAM subsystem that’s 512 times more efficient than the latest DDR chips.

- Marsh
----------------------------
My own opinions, usual disclaimers apply.

Content of type "text/html" skipped