all tests got segmentation fault after launch

[arom4github]

Building process looks correct except some warnings. But after that all tests fail.

$ ./bench/bench-blas
Devices available:
------------------
[x] - gfx803 on AMD Accelerated Parallel Processing
------------------
BENCH   M       N       K       AT      BT      ISAAC
Segmentation fault (core dumped)

$ gdb $_
GNU gdb (Ubuntu 7.7.1-0ubuntu5~14.04.2) 7.7.1
......
Reading symbols from ./bench/bench-blas...(no debugging symbols found)...done.
(gdb) run
Starting program: /tmp/isaac/build/bench/bench-blas
Devices available:
------------------
Warning: couldn't activate thread debugging using libthread_db: Cannot find new threads: generic error
warning: File "/lib/x86_64-linux-gnu/libthread_db-1.0.so" auto-loading has been declined by your `auto-load safe-path' set to "$debugdir:$datadir/auto-load".
To enable execution of this file add
        add-auto-load-safe-path /lib/x86_64-linux-gnu/libthread_db-1.0.so
line to your configuration file "/var/data0/sandbox/user1/.gdbinit".
To completely disable this security protection add
        set auto-load safe-path /
line to your configuration file "/var/data0/sandbox/user1/.gdbinit".
For more information about this security protection see the
"Auto-loading safe path" section in the GDB manual.  E.g., run from the shell:
        info "(gdb)Auto-loading safe path"
warning: Unable to find libthread_db matching inferior's thread library, thread debugging will not be available.
[x] - gfx803 on AMD Accelerated Parallel Processing
------------------
BENCH   M       N       K       AT      BT      ISAAC

Program received signal SIGSEGV, Segmentation fault.
0x00007ffff7750a1d in isaac::runtime::profiles::value_type::init(isaac::runtime::execution_handler const&) () from /tmp/isaac/build/lib/libisaac.so
(gdb) where
#0  0x00007ffff7750a1d in isaac::runtime::profiles::value_type::init(isaac::runtime::execution_handler const&) () from /tmp/isaac/build/lib/libisaac.so
#1  0x00007ffff7751440 in isaac::runtime::profiles::value_type::execute(isaac::runtime::execution_handler const&) () from /tmp/isaac/build/lib/libisaac.so
#2  0x00007ffff775b71e in isaac::runtime::execute(isaac::runtime::execution_handler const&, std::map<std::pair<isaac::expression_type, isaac::numeric_type>, std::shared_ptr<isaac::runtime::profiles::value_type>, std::less<std::pair<isaac::expression_type, isaac::numeric_type> >, std::allocator<std::pair<std::pair<isaac::expression_type, isaac::numeric_type> const, std::shared_ptr<isaac::runtime::profiles::value_type> > > >&) () from /tmp/isaac/build/lib/libisaac.so
#3  0x00007ffff7741200 in isaac::array_base::operator=(isaac::runtime::execution_handler const&) () from /tmp/isaac/build/lib/libisaac.so
#4  0x00007ffff77419a7 in isaac::array_base::operator=(isaac::expression_tree const&) () from /tmp/isaac/build/lib/libisaac.so
#5  0x0000000000409c7e in double bench<void bench<float>(isaac::numeric_type, std::string)::{lambda()#8}, void bench<float>(isaac::numeric_type, std::string)::{lambda()#1}>(void bench<float>(isaac::numeric_type, std::string)::{lambda()#8} const&, void bench<float>(isaac::numeric_type, std::string)::{lambda()#1} const&) ()
#6  0x000000000040d4f8 in void bench<float>(isaac::numeric_type, std::string) ()
#7  0x0000000000405caf in main ()
(gdb)

[ptillet]

Hi,

Interesting, the OpenCL driver reports gfx803 instead of Fiji. What is the GPU and driver version?

[ptillet]

Also, can you retry now with the latest version of origin/master?

[arom4github]

Hi,

Updated version works much better now

$ ./bench-blas
Devices available:
------------------
[x] - gfx803 on AMD Accelerated Parallel Processing
------------------
BENCH   M       N       K       AT      BT      ISAAC
Deep    1760    16      1760    N       N       0.30
Deep    1760    32      1760    N       N       0.59
Deep    1760    64      1760    N       N       0.70
Deep    1760    128     1760    N       N       0.74
Deep    1760    7000    1760    N       N       1.27
Deep    2048    16      2048    N       N       0.34
Deep    2048    32      2048    N       N       0.66
Deep    2048    64      2048    N       N       0.80
Deep    2048    128     2048    N       N       0.81
Deep    2048    7000    2048    N       N       1.02
Deep    2560    16      2560    N       N       0.54
Deep    2560    32      2560    N       N       0.56
Deep    2560    64      2560    N       N       0.62
Deep    2560    128     2560    N       N       0.81
Deep    2560    7000    2560    N       N       1.09
Deep    1760    16      1760    T       N       0.28
Deep    1760    32      1760    T       N       0.55
Deep    1760    64      1760    T       N       1.01
Deep    1760    128     1760    T       N       1.13
Deep    1760    7000    1760    T       N       1.58
Deep    2048    16      2048    T       N       0.07
Deep    2048    32      2048    T       N       0.11
Deep    2048    64      2048    T       N       0.38
Deep    2048    128     2048    T       N       0.28
Deep    2048    7000    2048    T       N       0.50
Deep    2560    16      2560    T       N       0.25
Deep    2560    32      2560    T       N       0.48
Deep    2560    64      2560    T       N       0.53
Deep    2560    128     2560    T       N       0.98
Deep    2560    7000    2560    T       N       0.83
Deep    1760    7133    1760    N       T       0.98
Memory access fault by GPU node-1 on address 0x916cf2000. Reason: Page not present or supervisor privilege.
Aborted (core dumped)

The error I see is not benchmark error I guess. clBLAS tests throw the same error. Probably it's on driver side.

I have RX 480 installed

01:00.0 VGA compatible controller: Advanced Micro Devices, Inc. [AMD/ATI] Device 67df (rev c7)

I'm also confused by this "gfx803". I use driver from ROCm.

$ uname -r
4.6.0-kfd-compute-rocm-rel-1.4-16
$ /opt/rocm/opencl/bin/x86_64/clinfo
Number of platforms:                             1
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 2.0 AMD-APP (2300.5)
  Platform Name:                                 AMD Accelerated Parallel Processing
  Platform Vendor:                               Advanced Micro Devices, Inc.
  Platform Extensions:                           cl_khr_icd cl_amd_event_callback cl_amd_offline_devices


  Platform Name:                                 AMD Accelerated Parallel Processing
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_GPU
  Vendor ID:                                     1002h
  Board name:                                    Device 67df
  Device Topology:                               PCI[ B#1, D#0, F#0 ]
  Max compute units:                             36
...
  Platform ID:                                   0x7f32f2e9f198
  Name:                                          gfx803
  Vendor:                                        Advanced Micro Devices, Inc.
  Device OpenCL C version:                       OpenCL C 2.0
  Driver version:                                1.1 (HSA,LC)
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 1.2
...

[ptillet]

Glad that it solved your problem.

So gfx803 is actually Polaris? The performance is very poor (1.6TFLOPS vs 5.0TFLOPS peak). Is it an R480m or the full desktop version? I get 70-75% of the peak on R9 Fury so that's a little odd.