[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-ID: <CA+E3k90qBEJN=ubHiT_EYFQQKhZmrLLEe18S-2Q+37Pfqm1LSw@mail.gmail.com>
Date: Fri, 10 Oct 2014 21:55:10 -0800
From: Royce Williams <royce@...ho.org>
To: john-users@...ts.openwall.com
Subject: Re: thanks for GPU temp and fan speed in status line
On Fri, Oct 10, 2014 at 6:11 PM, magnum <john.magnum@...hmail.com> wrote:
> On 2014-10-11 02:45, Royce Williams wrote:
>>
>> Just wanted to say thanks for the new GPU temperature and fan speed
>> info in the status line. Very handy!
>>
>> 341g 0:16:43:07 3/3 0.005665g/s 372158p/s 47519Kc/s 48154KC/s
>> GPU:60°C fan:46% fe3M2lz..fcpys92
>
> And it's actually fetched from the correct device! ;-) FYI you can set a
> max temperature in john.conf for safety; exceeding it will cause John to
> abort. It currently default to 95 degrees so you might want to decrease it
> to whatever is speced for nvidia. I do not think nvidias are prone to self
> destruction though.
The 750 Ti and the 970 in my other system are both quite happy
thermally, but the GTX 480 is pretty hot-headed, so this will be handy
- thanks.
> BTW could you please post the full output of --list=cuda-devices as well as
> --list=opencl-devices for the Maxwell card? I'd like to verify some recent
> tweaks for sm_50.
As of:
commit d243b8f06e45e411dc56bccab975b3b05243bca3
Author: magnum <john.magnum@...hmail.com>
Date: Sat Oct 11 05:03:38 2014 +0200
Add sm_50 SP multiplier for CUDA too (I did not remember we had to
calculate it from a table like in OpenCL).
... the opencl temp and fan still look like I expect it to for temp
and fan, but the cuda looks swapped:
$ ./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: 340.29
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
Stream processors: 640 (5 x 128)
Warp size: 32
Max. GPRs/work-group: 65536
Kernel exec. timeout: yes
PCI device topology: 02:00.0
NVML id: 1
Fan speed: 32%
Temperature: 28°C
Utilization: n/a
Device #1 (1) name: GeForce GTX 480
Device vendor: NVIDIA Corporation
Device type: GPU (LE)
Device version: OpenCL 1.1 CUDA
Driver version: 340.29
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
NVML id: 0
Fan speed: 48%
Temperature: 73°C
Utilization: n/a
$ ./john --list=cuda-devices
2 CUDA devices found:
CUDA Device #0
Name: GeForce GTX 750 Ti
Type: discrete
Compute capability: sm_50
Number of stream processors: 640 (5 x 128)
Clock rate: 1137 Mhz
Memory clock rate (peak) 2700 Mhz
Memory bus width 128 bits
Peak memory bandwidth: 86 GB/s
Total global memory: 1.0 GB
Total shared memory per block: 48.0 KB
Total constant memory: 64.0 KB
L2 cache size 2.0 MB
Kernel execution timeout: Yes
Concurrent copy and execution: One direction
Concurrent kernels support: Yes
Warp size: 32
Max. GPRs/thread block 65536
Max. threads per block 1024
Max. resident threads per MP 2048
PCI device topology: 02:00.0
NVML id: 1
Fan speed: 48%
GPU temp: 74°C
Utilization: n/a
CUDA Device #1
Name: GeForce GTX 480
Type: discrete
Compute capability: sm_20
Number of stream processors: 480 (15 x 32)
Clock rate: 1401 Mhz
Memory clock rate (peak) 1848 Mhz
Memory bus width 384 bits
Peak memory bandwidth: 177 GB/s
Total global memory: 1.0 GB
Total shared memory per block: 48.0 KB
Total constant memory: 64.0 KB
L2 cache size 768.7 KB
Kernel execution timeout: Yes
Concurrent copy and execution: One direction
Concurrent kernels support: Yes
Warp size: 32
Max. GPRs/thread block 32768
Max. threads per block 1024
Max. resident threads per MP 1536
PCI device topology: 01:00.0
NVML id: 0
Fan speed: 32%
GPU temp: 28°C
Utilization: n/a
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.
