Blogya.de | 1 Oct 16:29 2009
Picon

Error

Hi,

after some time (around 2 hours) i get this error:

1334412 chains done, current rate 141.42 chains/sec (interval: 00:01:00)
../tmto/device/cuda/host_side_methods.hpp(76)[void 
tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch 
failure

this happens only on 1 process, other processes on this machine are 
still running..
Sascha Krissler | 2 Oct 01:02 2009
Picon

Re: Error

gotta love those specific cuda error codes.
does it happen more than just once?
did you use any form of signaling through the fifo, like change number of operations?
(if it happens more frequently) does it always happen on the same card?
at which positions? (chains done).

> Hi,
> 
> after some time (around 2 hours) i get this error:
> 
> 1334412 chains done, current rate 141.42 chains/sec (interval: 00:01:00)
> ../tmto/device/cuda/host_side_methods.hpp(76)[void 
> tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch 
> failure
> 
> this happens only on 1 process, other processes on this machine are 
> still running..
> 
> _______________________________________________
> A51 mailing list
> A51@...
> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
> 

______________________________________________________
GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://movieflat.web.de
p q | 3 Oct 07:34 2009
Picon

Re: Fwd: all tables

i see the sample tables in data folder and the test application but couldnt figure out after all how the test scenario works . would you explain how this test vector works and test what against what ?
thanks




---------- Forwarded message ----------
From: Sascha Krissler <sascha.krissler-S0/GAf8tV78@public.gmane.org>
Date: Tue, Sep 29, 2009 at 10:56 PM
Subject: Re: [A51] Fwd: all tables
To: a51-Gjhu/N1EzaPLZEeaCYvZmUEOCMrvLtNR@public.gmane.org




thanks , thats what i was looking for . so with a HP super computer
> consist of :
> SSD + i7 quad Core + 3* GTX 295 we will have nearly 1000 chains per
> second and two of these computers equal all the computing resource
> that we have on this project now ? am i correct ? after all , does

this is correct from the point of view of the network server, which only
sees nodes that report status.


> overclocking the GPUs help ? i have also another important question .

you can get 20% increase from overclocking, at least with a single gtx260 in
an open case, ensuring proper cooling.


> assuming i have produced several chains is there anyway i can test
> see with an imaginary known plain text there are chances to find it
> in the limited produced chains ? how one can be sure the tables that
> are being built are correct , other than following project's
> instructions?

you can download one of the a5/1 implementations that are not from our
project and then generate some ciphertext. also read the reference implementation
in svn://reference/a51.cpp to verify that the tables produce data to speed up
a reverse function of A5/1. if you assume that the reference implementation is
correct then you can verify the actual generated table as described here:
http://reflextor.com/trac/a51/wiki/RunningTheProgram#Checkingvaluesagainstthereferenceimplementation


>
> bests
>
> On Tue, Sep 29, 2009 at 7:34 PM, Sascha Krissler <sascha.krissler <at> web.
> de> wrote:
> dividing the number of chains needed by the available resources gives
> you the time needed to finish the tables. so given 2000 chains/sec
> which
> is the speed of all nodes reporting status, and 2^37 chains needed,
> that would be: 105 weeks. if we want to be done by xmas, we need
> 8 times as much power.
>
> a gtx260 (700mhz) with 216 cores gives
> 162 chains/sec peak, a 9600M-GT (500mhz) with 32 cores gives
> 20 chains peak. so you get around 0.00107 (gtx260) and 0.00125(9600)
> chains per (core * mhz * second). although the frequency is not
> really the core frequency,
> but since shader freq is usually linked to GPU freq, i got used to
> calculate with the
> GPU freq.
> more new text below.
>
> > i really didnt understand your answer . anyway according to table
> > structure can we divide the amount of chains needed to produce with
> > the amount of computing resource ( Cores , any other factor ? ) come
> > up with a parametric number ?
> >
> > ---------- Forwarded message ----------
> > From: *Sascha Krissler*<sascha.krissler-S0/GAf8tV78@public.gmane.org>
> >
> > since the tables will be uploaded, there is no need to do this.
>
> it does not make sense to compute the tables for yourself, since they
> will
> already be produced with the current network.
>
> > if you want to decrypt messages without the network, you will
> probably
> > want to use an FPGA with the proper size and you would need some
> > very fast SSDs. take a look at the TableStructure node in the trac
> > wiki
>
> with the network that is proposed, you distribute the precomputation
> time
> and disk accesses across several nodes. if you wanted to do this all
> on your
> own, you would need much computing power and hardware that can do
> many IO Operations per unit of time. If you want to do all the
> precomputation
> yourself, you would need 380 fast gpus, which will need 38 kW of
> power.
> and you would have to do 2,5 million disk accesses which would take
> half an hour with one hard disk (assuming 1ms access time).
>
> > for some computation. if you used a hundred GPUs to do the
> precalculati
> > on
> > during the lookup, you would need a several kW power line.
> >
> > if somebody wants to build all the tables in house how to compute
> > > needed resources and time ? i want to simplify things by having a
> > > formula around to put the amount of cores , frequency (
> considering
> > > overclocking is possible and this is also a variable ) and other
> > > factors all together . all ideas are appreciated
> > >
> >
>
> > _______________________________________________ A51 mailing list
> A51 <at>
> > lists.reflextor.comhttp://lists.lists.reflextor.com/cgi-bin/mailman/

> >
> > listinfo/a51
>


_______________________________________________
A51 mailing list
A51@...
http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
p q | 3 Oct 07:55 2009
Picon

known plain text

are we certain there is always 4 frames of known plain text available thus we always have 204 known key streams ? is this documented somewhere ? are we always having SACCH data available ? which side of the traffic , up link or down link ? to my understanding this attack is based on dividing the whole key space to the amount of known key streams , is that right ? so can we use different sources of known plain texts and put them together ? for example i see there is also known plain text in LAPDm , and maybe in other places . is it possible to put them together somehow ? is there a list know known plain texts of the algorithm ? and finally , those known 4 frames should be continues in the real traffic ? sorry to ask a lot of questions . i'm learning :)


_______________________________________________
A51 mailing list
A51@...
http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
Sascha Krissler | 3 Oct 12:04 2009
Picon

Re: known plain text

> are we certain there is always 4 frames of known plain text available 
> thus we always have 204 known key streams ? is this documented 
this is not always the case. if you have receive errors then depending on
whether you know at which bit they occur
1) you do not know where but how many: you would have to do 2^n * 204 lookups
    (n == number of flipped bits)
2) you know where: 2^n lookups (try both 0 and 1)
so 1) makes the capture attempt practically impossible.

another case where you do not have enough plaintext is when the network changes
the message format, e.g. include some optional information elements in a message
or pad the message with random data instead of 0x2b 0x2b 0x2b.
whether this can be done and is done is beyond my knowledge.

> somewhere ? are we always having SACCH data available ? which side of

we are sucking data out of the SDCCH during call setup.

> the traffic , up link or down link ? to my understanding this attack 

there is a CIPHER MODE COMPLETE message that is sent from handset to network
whose plaintext can be guessed completely.

> is based on dividing the whole key space to the amount of known key 
> streams , is that right ? so can we use different sources of known
> plain texts and put them together ? for example i see there is also 

this is true. a simple division.

> known plain text in LAPDm , and maybe in other places . is it 

the CIPHER MODE COMPLETE is an LAPDm frame. there are certainly
many spot to extract known plaintext and since each LAPDm frame is
padded, once the padding is 6 bytes large, you get a whole burst
with 114 bits of known keystream, allowing for 51 lookups.
you could also work with say 60 bits of known keystream and guess
the missing 4 bits, where you would need to do between 1 and 16 lookups,
8 on average, till you find a Kc value that decrypts the other traffic.

> possible to put them together somehow ? is there a list know known 

they have to have 64 bits of consecutive plaintext. i once saw somewhere
another method taking advantage of FEC which uses known bits in other patterns
which i did not try to understand (found in the 2003 paper)

> plain texts of the algorithm ? and finally , those known 4 frames 
> should be continues in the real traffic ? sorry to ask a lot of 

they have to be continuous in the SDCCH since they are the 4 parts of
an LAPDm frame.

> questions . i'm learning :)
> 

all the information is second hand and i did not verify it with experiments.
________________________________________________________________
Neu: WEB.DE Doppel-FLAT mit Internet-Flatrate + Telefon-Flatrate
für nur 19,99 Euro/mtl.!* http://produkte.web.de/go/02/
p q | 3 Oct 12:25 2009
Picon

Fwd: known plain text

thanks ,

so your suggestion is to capture SDCCH which goes from MS to BTS and use its 4-bursts as the source of known plain text . according to um interface wiki , SACCH is also sent on every call and it certainly has 4 bursts thus the know plain text which i saw it on the other papers too . can we use both of these sources to decrease the amount of tests we need to do ?



--
From: Sascha Krissler <sascha.krissler <at> web.de>
Date: Sat, Oct 3, 2009 at 1:34 PM
Subject: Re: [A51] known plain text
To: a51 <a51-Gjhu/N1EzaPLZEeaCYvZmUEOCMrvLtNR@public.gmane.org>


> are we certain there is always 4 frames of known plain text available
> thus we always have 204 known key streams ? is this documented
this is not always the case. if you have receive errors then depending on
whether you know at which bit they occur
1) you do not know where but how many: you would have to do 2^n * 204 lookups
   (n == number of flipped bits)
2) you know where: 2^n lookups (try both 0 and 1)
so 1) makes the capture attempt practically impossible.

another case where you do not have enough plaintext is when the network changes
the message format, e.g. include some optional information elements in a message
or pad the message with random data instead of 0x2b 0x2b 0x2b.
whether this can be done and is done is beyond my knowledge.

> somewhere ? are we always having SACCH data available ? which side of

we are sucking data out of the SDCCH during call setup.

> the traffic , up link or down link ? to my understanding this attack

there is a CIPHER MODE COMPLETE message that is sent from handset to network
whose plaintext can be guessed completely.

> is based on dividing the whole key space to the amount of known key
> streams , is that right ? so can we use different sources of known
> plain texts and put them together ? for example i see there is also

this is true. a simple division.

> known plain text in LAPDm , and maybe in other places . is it

the CIPHER MODE COMPLETE is an LAPDm frame. there are certainly
many spot to extract known plaintext and since each LAPDm frame is
padded, once the padding is 6 bytes large, you get a whole burst
with 114 bits of known keystream, allowing for 51 lookups.
you could also work with say 60 bits of known keystream and guess
the missing 4 bits, where you would need to do between 1 and 16 lookups,
8 on average, till you find a Kc value that decrypts the other traffic.

> possible to put them together somehow ? is there a list know known

they have to have 64 bits of consecutive plaintext. i once saw somewhere
another method taking advantage of FEC which uses known bits in other patterns
which i did not try to understand (found in the 2003 paper)

> plain texts of the algorithm ? and finally , those known 4 frames
> should be continues in the real traffic ? sorry to ask a lot of

they have to be continuous in the SDCCH since they are the 4 parts of
an LAPDm frame.

> questions . i'm learning :)
>

all the information is second hand and i did not verify it with experiments.
________________________________________________________________

_______________________________________________
A51 mailing list
A51@...
http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
Sascha Krissler | 3 Oct 12:32 2009
Picon

Re: Fwd: known plain text


thanks ,
> so your suggestion is to capture SDCCH which goes from MS to BTS and 
> use its 4-bursts as the source of known plain text . according to um 
> interface wiki , SACCH is also sent on every call and it certainly 
> has 4 bursts thus the know plain text which i saw it on the other 
> papers too . can we use both of these sources to decrease the amount 
> of tests we need to do ?

yes we can!

________________________________________________________________
Neu: WEB.DE Doppel-FLAT mit Internet-Flatrate + Telefon-Flatrate
für nur 19,99 Euro/mtl.!* http://produkte.web.de/go/02/
Christoffer Jerkeby | 4 Oct 18:25 2009
Picon

Re: Error

Hi I got the same error, I was using the configuration generated from
http://reflextor.com/cgi-bin/a51/a51id.cgi .

$ ./a51table --condition rounds:rounds=32 --roundfunc
xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
--implementation sharedmem --algorithm A51 --device
cuda:operations=512 --work random:prefix=11,0 --consume
file:prefix=data:append --logger normal generate --chains 380000000
--chainlength 3000000 --intermediate filter:runlength=512

Initialize implementation sharedmem...
148 chains done, current rate 2.47 chains/sec (interval: 00:01:00)
6639 chains done, current rate 108.18 chains/sec (interval: 00:01:00)
10356 chains done, current rate 61.95 chains/sec (interval: 00:01:00)
14655 chains done, current rate 71.65 chains/sec (interval: 00:01:00)
19769 chains done, current rate 85.23 chains/sec (interval: 00:01:00)
24015 chains done, current rate 70.77 chains/sec (interval: 00:01:00)
28610 chains done, current rate 76.58 chains/sec (interval: 00:01:00)
../tmto/device/cuda/host_side_methods.hpp(76)[void
tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
failure

Regards Kugg

On 10/2/09, Sascha Krissler <sascha.krissler@...> wrote:
> gotta love those specific cuda error codes.
> does it happen more than just once?
> did you use any form of signaling through the fifo, like change number of
> operations?
> (if it happens more frequently) does it always happen on the same card?
> at which positions? (chains done).
>
>> Hi,
>>
>> after some time (around 2 hours) i get this error:
>>
>> 1334412 chains done, current rate 141.42 chains/sec (interval: 00:01:00)
>> ../tmto/device/cuda/host_side_methods.hpp(76)[void
>> tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
>> failure
>>
>> this happens only on 1 process, other processes on this machine are
>> still running..
>>
>> _______________________________________________
>> A51 mailing list
>> A51@...
>> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
>>
>
>
> ______________________________________________________
> GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
> Jetzt freischalten unter http://movieflat.web.de
>
> _______________________________________________
> A51 mailing list
> A51@...
> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
>
Christoffer Jerkeby | 4 Oct 18:51 2009
Picon

Re: Error

Trying again gave me a similar error:
$ ./a51table --condition rounds:rounds=32 --roundfunc
xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
--implementation sharedmem --algorithm A51 --device
cuda:operations=512 --work random:prefix=11,0 --consume
file:prefix=data:append --logger normal generate --chains 380000000
--chainlength 3000000 --intermediate filter:runlength=512
Initialize implementation sharedmem...
106 chains done, current rate 1.77 chains/sec (interval: 00:01:00)
6633 chains done, current rate 108.78 chains/sec (interval: 00:01:00)
10350 chains done, current rate 61.95 chains/sec (interval: 00:01:00)
14632 chains done, current rate 71.37 chains/sec (interval: 00:01:00)
19810 chains done, current rate 86.30 chains/sec (interval: 00:01:00)
../tmto/device/cuda/working_set_methods.hpp(38)[void
tmto::device::cuda::working_set::simple_host<T,
Round>::copyToDevice(int) [with T =
tmto::device::combined_work_item<tmto::algorithm::A51::data_type,
tmto::configuration::state::state<void, void,
tmto::condition::tag::rounds,
tmto::round_function::arguments::selector<tmto::round_function::tag::xor_,
tmto::condition::tag::distinguished_point,
tmto::round_function::generator::tag::sharedmem<tmto::round_function::gen

Trying one more time I got
$ ./a51table --condition rounds:rounds=32 --roundfunc
xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
--implementation sharedmem --algorithm A51 --device
cuda:operations=512 --work random:prefix=11,0 --consume
file:prefix=data:append --logger normal generate --chains 380000000
--chainlength 3000000 --intermediate filter:runlength=512
NVIDIA: could not open the device file /dev/nvidia0 (Input/output error).
Initialize implementation sharedmem...
../tmto/round_function/generator/sharedmem_methods.hpp(12)[void
tmto::round_function::generator::host_part<tmto::round_function::generator::tag::sharedmem<Real>
>::copyToDevice() const [with Real =
tmto::round_function::generator::tag::lfsr]]: cuda error: no
CUDA-capable device is available

Im running on two GeForce GTX 260's

Regards Kugg

On 10/4/09, Christoffer Jerkeby <kugghjul@...> wrote:
> Hi I got the same error, I was using the configuration generated from
> http://reflextor.com/cgi-bin/a51/a51id.cgi .
>
> $ ./a51table --condition rounds:rounds=32 --roundfunc
> xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
> --implementation sharedmem --algorithm A51 --device
> cuda:operations=512 --work random:prefix=11,0 --consume
> file:prefix=data:append --logger normal generate --chains 380000000
> --chainlength 3000000 --intermediate filter:runlength=512
>
> Initialize implementation sharedmem...
> 148 chains done, current rate 2.47 chains/sec (interval: 00:01:00)
> 6639 chains done, current rate 108.18 chains/sec (interval: 00:01:00)
> 10356 chains done, current rate 61.95 chains/sec (interval: 00:01:00)
> 14655 chains done, current rate 71.65 chains/sec (interval: 00:01:00)
> 19769 chains done, current rate 85.23 chains/sec (interval: 00:01:00)
> 24015 chains done, current rate 70.77 chains/sec (interval: 00:01:00)
> 28610 chains done, current rate 76.58 chains/sec (interval: 00:01:00)
> ../tmto/device/cuda/host_side_methods.hpp(76)[void
> tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
> failure
>
> Regards Kugg
>
> On 10/2/09, Sascha Krissler <sascha.krissler@...> wrote:
>> gotta love those specific cuda error codes.
>> does it happen more than just once?
>> did you use any form of signaling through the fifo, like change number of
>> operations?
>> (if it happens more frequently) does it always happen on the same card?
>> at which positions? (chains done).
>>
>>> Hi,
>>>
>>> after some time (around 2 hours) i get this error:
>>>
>>> 1334412 chains done, current rate 141.42 chains/sec (interval: 00:01:00)
>>> ../tmto/device/cuda/host_side_methods.hpp(76)[void
>>> tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
>>> failure
>>>
>>> this happens only on 1 process, other processes on this machine are
>>> still running..
>>>
>>> _______________________________________________
>>> A51 mailing list
>>> A51@...
>>> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
>>>
>>
>>
>> ______________________________________________________
>> GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
>> Jetzt freischalten unter http://movieflat.web.de
>>
>> _______________________________________________
>> A51 mailing list
>> A51@...
>> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
>>
>
Sascha Krissler | 5 Oct 18:20 2009
Picon

Re: Error

i do not have a solution for this problem or a good guess what the problem
is, so i ask you to wait for the next release and if the problem remains i will
take a look at cuda-gdb and see whether it is usable or write a kernel that generates
more debugging information.
cuda-gdb should be able to print information about the error, so if you want to invest
time, you can try it out. it should be able to at least print the source file line number
of the instruction that was responsible for the error in the case of the failed cudaThreadSynchronize,
the error in the memcpy and the no_device_found are a different story as no code is
executed on the GPU in that case.
maybe your drivers are too old. also if you are on a 32bit system you have to compile
with -malign-double as enabled by default in the Makefile.local.dist.
Maybe you can post nvidia driver version, cpu arch and linux version.

> Trying again gave me a similar error:
> $ ./a51table --condition rounds:rounds=32 --roundfunc
> xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
> --implementation sharedmem --algorithm A51 --device
> cuda:operations=512 --work random:prefix=11,0 --consume
> file:prefix=data:append --logger normal generate --chains 380000000
> --chainlength 3000000 --intermediate filter:runlength=512
> Initialize implementation sharedmem...
> 106 chains done, current rate 1.77 chains/sec (interval: 00:01:00)
> 6633 chains done, current rate 108.78 chains/sec (interval: 00:01:00)
> 10350 chains done, current rate 61.95 chains/sec (interval: 00:01:00)
> 14632 chains done, current rate 71.37 chains/sec (interval: 00:01:00)
> 19810 chains done, current rate 86.30 chains/sec (interval: 00:01:00)
> ../tmto/device/cuda/working_set_methods.hpp(38)[void
> tmto::device::cuda::working_set::simple_host<T,
> Round>::copyToDevice(int) [with T =
> tmto::device::combined_work_item<tmto::algorithm::A51::data_type,
> tmto::configuration::state::state<void, void,
> tmto::condition::tag::rounds,
> tmto::round_function::arguments::selector<tmto::round_function::tag::xor_,
> tmto::condition::tag::distinguished_point,
> tmto::round_function::generator::tag::sharedmem<tmto::round_function::gen
> 
> Trying one more time I got
> $ ./a51table --condition rounds:rounds=32 --roundfunc
> xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
> --implementation sharedmem --algorithm A51 --device
> cuda:operations=512 --work random:prefix=11,0 --consume
> file:prefix=data:append --logger normal generate --chains 380000000
> --chainlength 3000000 --intermediate filter:runlength=512
> NVIDIA: could not open the device file /dev/nvidia0 (Input/output error).
> Initialize implementation sharedmem...
> ../tmto/round_function/generator/sharedmem_methods.hpp(12)[void
> tmto::round_function::generator::host_part<tmto::round_function::generator::tag::sharedmem<Real>
> >::copyToDevice() const [with Real =
> tmto::round_function::generator::tag::lfsr]]: cuda error: no
> CUDA-capable device is available
> 
> Im running on two GeForce GTX 260's
> 
> Regards Kugg
> 
> On 10/4/09, Christoffer Jerkeby <kugghjul@...> wrote:
> > Hi I got the same error, I was using the configuration generated from
> > http://reflextor.com/cgi-bin/a51/a51id.cgi .
> >
> > $ ./a51table --condition rounds:rounds=32 --roundfunc
> > xor:condition=distinguished_point::bits=15:generator=lfsr::tablesize=32::advance=139584
> > --implementation sharedmem --algorithm A51 --device
> > cuda:operations=512 --work random:prefix=11,0 --consume
> > file:prefix=data:append --logger normal generate --chains 380000000
> > --chainlength 3000000 --intermediate filter:runlength=512
> >
> > Initialize implementation sharedmem...
> > 148 chains done, current rate 2.47 chains/sec (interval: 00:01:00)
> > 6639 chains done, current rate 108.18 chains/sec (interval: 00:01:00)
> > 10356 chains done, current rate 61.95 chains/sec (interval: 00:01:00)
> > 14655 chains done, current rate 71.65 chains/sec (interval: 00:01:00)
> > 19769 chains done, current rate 85.23 chains/sec (interval: 00:01:00)
> > 24015 chains done, current rate 70.77 chains/sec (interval: 00:01:00)
> > 28610 chains done, current rate 76.58 chains/sec (interval: 00:01:00)
> > ../tmto/device/cuda/host_side_methods.hpp(76)[void
> > tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
> > failure
> >
> > Regards Kugg
> >
> > On 10/2/09, Sascha Krissler <sascha.krissler@...> wrote:
> >> gotta love those specific cuda error codes.
> >> does it happen more than just once?
> >> did you use any form of signaling through the fifo, like change number of
> >> operations?
> >> (if it happens more frequently) does it always happen on the same card?
> >> at which positions? (chains done).
> >>
> >>> Hi,
> >>>
> >>> after some time (around 2 hours) i get this error:
> >>>
> >>> 1334412 chains done, current rate 141.42 chains/sec (interval: 00:01:00)
> >>> ../tmto/device/cuda/host_side_methods.hpp(76)[void
> >>> tmto::device::cuda::cudaSynchronize()]: cuda error: unspecified launch
> >>> failure
> >>>
> >>> this happens only on 1 process, other processes on this machine are
> >>> still running..
> >>>
> >>> _______________________________________________
> >>> A51 mailing list
> >>> A51@...
> >>> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
> >>>
> >>
> >>
> >> ______________________________________________________
> >> GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
> >> Jetzt freischalten unter http://movieflat.web.de
> >>
> >> _______________________________________________
> >> A51 mailing list
> >> A51@...
> >> http://lists.lists.reflextor.com/cgi-bin/mailman/listinfo/a51
> >>
> >
> 

______________________________________________________
GRATIS für alle WEB.DE-Nutzer: Die maxdome Movie-FLAT!
Jetzt freischalten unter http://movieflat.web.de

Gmane