Follow @Openwall on Twitter for new release announcements and other news
[<prev] [next>] [thread-next>] [day] [month] [year] [list]
Date: Wed, 17 Dec 2014 06:24:29 -0900
From: Royce Williams <>
Subject: bleeding-jumbo test fails at RAKP-opencl

Latest bleeding-jumbo fails at this writing with:

$ ./john --test --format=RAKP-opencl
OpenCL error (CL_INVALID_DEVICE) in file (common-opencl.c) at line (1918) -

I discovered this in a general test run.  All previous tests succeeded.
All non-GPU tests came first, and this one died in the middle of the GPU
tests.  No further tests are performed once this one dies.

The test system contains five GTX 970s, and I believe that the first device
is used during a --test run.  This is the first device:

Platform #0 name: NVIDIA CUDA
Platform version: OpenCL 1.1 CUDA 7.0.15
        Device #0 (0) name:     GeForce GTX 970
        Device vendor:          NVIDIA Corporation
        Device type:            GPU (LE)
        Device version:         OpenCL 1.1 CUDA
        Driver version:         346.22
        Native vector widths:   char 1, short 1, int 1, long 1
        Preferred vector width: char 1, short 1, int 1, long 1
        Global Memory:          3.0 GB
        Global Memory Cache:    208.2 KB
        Local Memory:           47.0 KB (Local)
        Max memory alloc. size: 1023.10 MB
        Max clock (MHz):        1316
        Profiling timer res.:   1000 ns
        Max Work Group Size:    1024
        Parallel compute cores: 13
        Stream processors:      1664  (13 x 128)
        Warp size:              32
        Max. GPRs/work-group:   65536
        Compute capability:     5.2 (sm_52)
        Kernel exec. timeout:   no
        PCI device topology:    01:00.0
        NVML id:                0
        Fan speed:              0%
        Temperature:            60°C
        Utilization:            n/a


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.