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
| ||
|
Date: Tue, 28 Apr 2015 14:36:47 +0200 From: Thomas Pornin <pornin@...et.org> To: discussions@...sword-hashing.net Subject: Re: [PHC] Optimized versions for ARM? On Mon, Apr 27, 2015 at 07:43:49PM -0700, Bill Cox wrote: > Milan is generously benchmarking on PowerPC, but isn't that a mostly dead > architecture? PowerPC is very common in the car and plane industries. Notably, if you want radiation-shielded chips to put in satellites, then you will find the "RAD" series, which are PowerPC. Whether such systems need to hash passwords, though, is unclear. Close-to-human-user devices (say, mobile phones), that store data and may use password-based encryption, tend to use ARM, x86 or Mips CPU. Notable cases are some game consoles. Xbox 360, PS3 and Wii were all PowerPC-based. While Microsoft (Xbox One) and Sony (PS4) switched to x86, Nintendo (Wii U) keeps on using PowerPC. This still represents a lot of consumer systems on which password hashing may be relevant. As was discussed earlier, embedded systems are not a target of choice for password hashing, since password hashing is all about muscle, that embedded systems lack. If you restrain yourself to _powerful_ CPU that are in common usage, then you and up with x86 and ARM, and also Mips (mostly in routers). Of course, all three have a lot of variants, in register size (32 or 64 bits), FPU, SIMD opcodes, RAM size and bandwidth... Big POWER chips are sure apt at hashing passwords, but they are expensive and rare. I similarly suggest to ignore high-end SPARC processors. --Thomas Pornin
Powered by blists - more mailing lists