[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKGDhHVX58+PdrG_Rn-qdCE_tqgOKABEmJmV2xwyuZm9iFNp7Q@mail.gmail.com>
Date: Wed, 22 Jul 2015 21:11:48 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: yescrypt on GPU
2015-07-22 4:06 GMT+02:00 Agnieszka Bielec <bielecagnieszka8@...il.com>:
> 2015-07-21 21:00 GMT+02:00 Agnieszka Bielec <bielecagnieszka8@...il.com>:
>> hi, I discovered right now that benchmarks for yescrypt should be done
>> using every password different like in pomelo (I don't know why, there
>> is no coalescing), I could testing it in cracking mode but I wasn't
>> doing this, and hence is the strange thing with estimating GWS
>>
>> you should forget about previous benchmarks, sorry that I didn't
>> discovered this earlier
>
> I reverted back my changes in kernel what I did last week and I didn't
> gained any speed at all
sorry for making a chaos but now turned out that when I was testing
speed of 2 versions of john with this optimization and without speed
was the same but I didn't remove this optimization properly I have in
the code #define SP_COPY 1 but I'm using #ifdef SP_COPY - I forgot
about that this looks like here and I changed only 1 to 0 instead
remove whole #define and even it's slower with this optimization
Powered by blists - more mailing lists
Confused about mailing lists and their use?
Read about mailing lists on Wikipedia
and check out these
guidelines on proper formatting of your messages.
