[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CA+E3k91wX8=iaANXpMk8ANCq+AQT8JpQrZAsS9vRzVMSLz5gJQ@mail.gmail.com>
Date: Tue, 16 Sep 2014 23:38:21 -0800
From: Royce Williams <royce@...ho.org>
To: john-users@...ts.openwall.com
Subject: Re: nVidia Maxwell support (especially descrypt)?
On Thu, Sep 11, 2014 at 7:37 AM, Royce Williams <royce@...ho.org> wrote:
> On Thu, Sep 11, 2014 at 12:57 AM, Solar Designer <solar@...nwall.com> wrote:
>> For now, I think someone with a Maxwell GPU should try building and
>> benchmarking our descrypt-opencl on it with the S-boxes that use
>> bitselect().
>
> Unless someone else can do it faster, I'll acquire a card -- but will
> need some help wrangling the S-boxes.
I now have a 750 Ti installed, and also have the latest bleeding-jumbo
source staged locally. If my setup can help test what Solar suggested
above, I am ready to do so.
In an interesting side note, for some reason, some device specs are
mismatched in the --list output. I double-checked against temperature
and fan speed and they're definitely swapped. The 750s are known for
running much cooler than older nvidias, for example.
$ ./john --list=opencl-devices
Platform #0 name: NVIDIA CUDA
Platform version: OpenCL 1.1 CUDA 6.5.14
Device #0 (0) name: GeForce GTX 750 Ti
Device vendor: NVIDIA Corporation
Device type: GPU (LE)
Device version: OpenCL 1.1 CUDA
Driver version: 340.32
Native vector widths: char 1, short 1, int 1, long 1
Preferred vector width: char 1, short 1, int 1, long 1
Global Memory: 1.0 GB
Global Memory Cache: 80.0 KB
Local Memory: 47.0 KB (Local)
Max memory alloc. size: 511.5 MB
Max clock (MHz): 1137
Profiling timer res.: 1000 ns
Max Work Group Size: 1024
Parallel compute cores: 5
Warp size: 32
Max. GPRs/work-group: 65536
Kernel exec. timeout: yes
Fan speed: 66%
Temperature: 88°C
Device #1 (1) name: GeForce GTX 480
Device vendor: NVIDIA Corporation
Device type: GPU (LE)
Device version: OpenCL 1.1 CUDA
Driver version: 340.32
Native vector widths: char 1, short 1, int 1, long 1
Preferred vector width: char 1, short 1, int 1, long 1
Global Memory: 1.0 GB
Global Memory Cache: 240.2 KB
Local Memory: 47.0 KB (Local)
Max memory alloc. size: 383.3 MB
Max clock (MHz): 1401
Profiling timer res.: 1000 ns
Max Work Group Size: 1024
Parallel compute cores: 15
Stream processors: 480 (15 x 32)
Warp size: 32
Max. GPRs/work-group: 32768
Kernel exec. timeout: yes
Fan speed: 32%
Temperature: 44°C
... whereas nvidia-smi shows the expected fan and temps:
$ nvidia-smi
Tue Sep 16 23:35:06 2014
+------------------------------------------------------+
| NVIDIA-SMI 340.32 Driver Version: 340.32 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 480 Off | 0000:01:00.0 N/A | N/A |
| 67% 90C P0 N/A / N/A | 470MiB / 1535MiB | N/A Default |
+-------------------------------+----------------------+----------------------+
| 1 GeForce GTX 750 Ti Off | 0000:02:00.0 N/A | N/A |
| 32% 48C P0 N/A / N/A | 307MiB / 2047MiB | N/A Default |
+-------------------------------+----------------------+----------------------+
Royce
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.
