[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CAKGDhHV18fCw-xGNMYqKx48u5gcbbny7RT8D0KAzrdr-eowd5w@mail.gmail.com>
Date: Thu, 16 Jul 2015 10:25:14 +0200
From: Agnieszka Bielec <bielecagnieszka8@...il.com>
To: john-dev@...ts.openwall.com
Subject: Re: PHC: Lyra2 on GPU
2015-07-14 1:18 GMT+02:00 magnum <john.magnum@...hmail.com>:
> On 2015-07-13 20:28, Agnieszka Bielec wrote:
>>
>> 2015-07-13 19:31 GMT+02:00 Solar Designer <solar@...nwall.com>:
>>>>
>>>> and I discovered now that the best number of lws also differ for
>>>> various costs but it isn't autotuned
>>>
>>>
>>> Why isn't it auto-tuned?
>>
>>
>> Do john support lws auto tuning? We only have get_default_workgroup()
>> function which is called somewhere.
>
>
> Unless none were given, autotune_run() will auto-tune GWS first (using an
> LWS of NULL during that process). Then it will auto-tune LWS using the
> previously established GWS.
works in Lyra2 but in yescrypt doesn't work
I added printf here
static void create_clobj(size_t gws, struct fmt_main *self)
{
printf("gws=%llu\n",gws);
and the output is:
none@...e ~/Desktop/job/run $ ./john --test --format=yescrypt-opencl --v=4
Benchmarking: yescrypt-opencl [Salsa20/8 OpenCL (inefficient,
development use only)]... Device 0: GeForce GTX 960M
Options used: -I ./kernels -cl-mad-enable -cl-nv-verbose
-DDEVICE_INFO=8210 -D_OPENCL_COMPILER -DDEV_VER_MAJOR=352
-DDEV_VER_MINOR=21 -DBINARY_SIZE=32 -DSALT_SIZE=64
-DPLAINTEXT_LENGTH=125 -DHASH_SIZE=44
memory per hash : 2.10 MB
Calculating best global worksize (GWS); max. 1s single kernel invocation.
gws=256
gws=0
OpenCL error (CL_INVALID_BUFFER_SIZE) in file
(opencl_yescrypt_fmt_plug.c) at line (163) - (Error creating device
buffer)
I changed get_default_workgroup() to return 0 in lyra and yescrypt
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.
