Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CABob6iriH2Z7WDhnS348=7EB1adCPeUgx8E=c+rvHrbu0ujBMg@mail.gmail.com>
Date: Fri, 18 Jul 2014 02:49:56 +0200
From: Lukas Odzioba <lukas.odzioba@...il.com>
To: john-users@...ts.openwall.com
Subject: Re: Help Compiling John on ARM w/ MPI & CUDA

2014-07-17 18:03 GMT+02:00 Pyrex <pyrex@...networks.net>:

>  OK this is the output from configure, it crashed out when attempting to
> compile... Any feedback?
>


> nvcc fatal   : Value 'sm_10' is not defined for option 'gpu-architecture'
> make[1]: *** [cuda_common.o] Error 255
> make[1]: *** Waiting for unfinished jobs....
> make: *** [default] Error 2
>

Just for the record, modify Makefile.in:
NVCC_FLAGS = -c -Xptxas -v -fmad=true -arch sm_10
to
NVCC_FLAGS = -c -Xptxas -v -fmad=true -arch sm_32

and then ./configure --disable-mpi && make -s worked for me.

sm_20 seems to be enough to compile john, but with sm_32 you will likely
get better performance.
Example for phpass-cuda format:
sm_20:
Raw: 110276 c/s real, 110276 c/s virtual
sm_32:
Raw: 126030 c/s real, 127117 c/s virtual

Lukas

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.