Openwall GNU/*/Linux - a small security-enhanced Linux distro for servers
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Sun, 6 Sep 2015 22:59:51 +0300
From: Solar Designer <solar@...nwall.com>
To: john-dev@...ts.openwall.com
Subject: SIMD_PARA_SHA256

magnum -

We should increase SIMD_PARA_SHA256 from 1 to 2 at least for XOP builds.
With 1, I am getting:

Benchmarking: sha256crypt, crypt(3) $5$ (rounds=5000) [SHA256 128/128 XOP 4x]... (8xOMP) DONE
Speed for cost 1 (iteration count) of 5000
Raw:    4602 c/s real, 648 c/s virtual

Benchmarking: PBKDF2-HMAC-SHA256 [PBKDF2-SHA256 128/128 XOP 4x]... (8xOMP) DONE
Speed for cost 1 (iteration count) of 1000
Raw:    20608 c/s real, 2569 c/s virtual

with 2, I am getting:

Benchmarking: sha256crypt, crypt(3) $5$ (rounds=5000) [SHA256 128/128 XOP 4x2]... (8xOMP) DONE
Speed for cost 1 (iteration count) of 5000
Raw:    5789 c/s real, 817 c/s virtual

(it varies from 5708 to 6001 across several runs), and:

Benchmarking: PBKDF2-HMAC-SHA256 [PBKDF2-SHA256 128/128 XOP 4x2]... (8xOMP) DONE
Speed for cost 1 (iteration count) of 1000
Raw:    26112 c/s real, 3247 c/s virtual

I didn't test this on other machines (nor without XOP).

Alexander

Powered by blists - more mailing lists

Your e-mail address:

Confused about mailing lists and their use? Read about mailing lists on Wikipedia and check out these guidelines on proper formatting of your messages.