Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Date: Thu, 9 Jul 2015 12:00:41 +0800
From: Lei Zhang <>
Subject: Re: JtR on Power

> On Jul 1, 2015, at 10:39 PM, Solar Designer <> wrote:
> You'll need to post benchmarks once you've added some basic SIMD
> support.  Right now, I guess you got SIMD for some DES-based formats only.

Alright, I've got a working set of AltiVec intrinsics now, and JtR could pass all self-tests with AltiVec (with 3 formats disabled though, which I'll handle later).

I pick a few representative formats here to demonstrate the difference after using AltiVec:


Benchmarking: Raw-MD4 [MD4 32/64]... DONE
Raw:	3987K c/s real, 3987K c/s virtual

Benchmarking: Raw-MD5 [MD5 32/64]... DONE
Raw:	3023K c/s real, 3023K c/s virtual

Benchmarking: Raw-SHA1 [SHA1 32/64]... DONE
Raw:	4065K c/s real, 4106K c/s virtual

Benchmarking: Raw-SHA256 [SHA256 32/64 OpenSSL]... (152xOMP) DONE
Raw:	14319K c/s real, 321644 c/s virtual

Benchmarking: Raw-SHA512 [SHA512 32/64 OpenSSL]... (152xOMP) DONE
Raw:	13385K c/s real, 268735 c/s virtual


Benchmarking: Raw-MD4 [MD4 128/128 AltiVec 4x]... DONE
Raw:	7826K c/s real, 7826K c/s virtual

Benchmarking: Raw-MD5 [MD5 128/128 AltiVec 4x]... DONE
Raw:	1694K c/s real, 1711K c/s virtual

Benchmarking: Raw-SHA1 [SHA1 128/128 AltiVec 4x]... DONE
Raw:	6515K c/s real, 6515K c/s virtual

Benchmarking: Raw-SHA256 [SHA256 128/128 AltiVec 4x]... (152xOMP) DONE
Raw:	8146K c/s real, 458028 c/s virtual

Benchmarking: Raw-SHA512 [SHA512 128/128 AltiVec 4x]... (152xOMP) DONE
Raw:	1353K c/s real, 19260 c/s virtual

Strangely, MD5, SHA256 and SHA512 become even slower. Currently there're some inefficient emulation for several intrinsics, notably int64 shift, which very likely slows down SHA512 here. I try to do some optimization and see how it goes.


Powered by blists - more mailing lists

Your e-mail address:

Powered by Openwall GNU/*/Linux - Powered by OpenVZ