11 Replies Latest reply on Sep 13, 2017 1:32 AM by daisuken

    OpenCL clCreateCommandQueue() fails with error -6(out of host memory) on Ubuntu 16.04.3 64 bit, AMDGPUPRO driver 17.30 465504

    daisuken

      Hello,

      I'm trying to use OpenCL 1.2 on the following environment:

      - DELL Workstation T7910

      - AMD FirePro W4100

      - Ubuntu 16.04.3 (upgraded from 16.04.2)

      - amdgpu-pro driver 17.30-465504 for Ubuntu 16.04.3 (the latest one which fixed incompatibility issue between Ubuntu 16.04.3 and amdgpu-driver 17.30)

      - AMD-APP-SDK-v3.0.130.136-GA-linux64

       

      On this system, 'clinfo' shows 2 platforms 'Clover/Mesa' and 'AMD Accelerated Parallel Processing/Advanced Micro Devices, Inc.'.

       

      A simple OpenCL program which just does clCreateCommandQueue() with the AMD GPU Pro platform fails with error code '-6' (out of host memory), while it succeeds with Clover.

      The system has plenty of RAM (64GB), and it looks unlikely to be lacking host memory.

       

      Is the latest AMD GPU PRO driver for Ubuntu successfully supporting the FirePro W4100 graphics board? (I have already confirmed the board is in the supported list of the driver, though)

      Or, does something look wrong with any part of configuration or installation?

      At least, I can use the Ubuntu's desktop without problem so far.

       

       

      - The simple test program to reproduce the issue:

      #include <stdio.h>

      #include <stdlib.h>

      #include <CL/cl.h>

       

       

      static void print_device_info(cl_device_id device_id, cl_device_info info_name, const char* label);

      static void print_platform_info(cl_platform_id platform_id, cl_platform_info info_name, const char* label);

       

       

      int main(int argc, char** argv) {

       

       

          cl_platform_id *platform_ids = NULL;

          cl_device_id *device_ids = NULL;

          cl_context context = NULL;

          cl_command_queue command_queue = NULL;

          cl_uint ndevices;

          cl_uint nplatforms;

          cl_int ret;

          int i, j;

       

       

          if (clGetPlatformIDs(0, NULL, &nplatforms) != CL_SUCCESS) {

              fprintf(stderr, "failed to get platforms count\n");

              exit(1);

          }

          fprintf(stdout, "nplatforms=%d\n\n", nplatforms);

       

       

          platform_ids = (cl_platform_id *)malloc(nplatforms * sizeof(cl_platform_id));

          if (clGetPlatformIDs(nplatforms, platform_ids, NULL) != CL_SUCCESS) {

              fprintf(stderr, "failed to get platform ids\n");

              exit(1);

          }

       

       

          for (i = 0; i < nplatforms; i++) {

              fprintf(stdout, "Platform[%d]:\n", i);

       

       

              print_platform_info(platform_ids[i], CL_PLATFORM_NAME, "Platform Name");

              print_platform_info(platform_ids[i], CL_PLATFORM_PROFILE, "Platform Profile");

              print_platform_info(platform_ids[i], CL_PLATFORM_VERSION, "Platform Version");

              print_platform_info(platform_ids[i], CL_PLATFORM_VENDOR, "Platform Vendor");

              print_platform_info(platform_ids[i], CL_PLATFORM_EXTENSIONS, "Platform Extensions");

       

       

              if (clGetDeviceIDs(platform_ids[i], CL_DEVICE_TYPE_GPU, 0, NULL, &ndevices) != CL_SUCCESS) {

                  fprintf(stderr, "failed to get devices count\n");

                  continue;

              }

              fprintf(stdout, "ndevices=%d\n", ndevices);

       

       

              device_ids = (cl_device_id *)malloc(ndevices * sizeof(cl_device_id));

              if (clGetDeviceIDs(platform_ids[i], CL_DEVICE_TYPE_GPU, ndevices, device_ids, NULL) != CL_SUCCESS) {

                  fprintf(stderr, "failed to get device ids\n");

                  continue;

              }

       

       

              for (j = 0; j < ndevices; j++) {

                  fprintf(stdout, "Device[%d]:\n", j);

       

       

                  print_device_info(device_ids[j], CL_DEVICE_NAME, "Device Name");

                  print_device_info(device_ids[j], CL_DEVICE_PROFILE, "Device Profile");

                  print_device_info(device_ids[j], CL_DEVICE_VERSION, "Device Version");

                  print_device_info(device_ids[j], CL_DRIVER_VERSION, "Driver Version");

                  print_device_info(device_ids[j], CL_DEVICE_VENDOR, "Device Vendor");

                  print_device_info(device_ids[j], CL_DEVICE_OPENCL_C_VERSION, "OpenCL C Version");

                  print_device_info(device_ids[j], CL_DEVICE_EXTENSIONS, "Device Extensions");

       

       

                  context = clCreateContext(NULL, 1, &device_ids[j], NULL, NULL, &ret);

                  fprintf(stdout, "CreateContext: ret=%d\n", ret);

       

       

                  command_queue = clCreateCommandQueue(context, device_ids[j], 0, &ret);

                  fprintf(stdout, "CreateCommandQueue: ret=%d\n", ret);

       

       

                  if (command_queue != NULL) {

                      clReleaseCommandQueue(command_queue);

                  }

                  if (context != NULL) {

                      clReleaseContext(context);

                  }

              }

       

       

              if (device_ids != NULL) {

                  free(device_ids);

              }

       

       

              fprintf(stdout, "\n");

          }

       

       

          if (platform_ids != NULL) {

              free(platform_ids);

          }

       

       

          return 0;

      }

       

       

      static void print_device_info(cl_device_id device_id, cl_device_info info_name, const char* label) {

          char* data;

          size_t datasize;

          clGetDeviceInfo(device_id, info_name, 0, NULL, &datasize);

          data = (char*)malloc(datasize);

          clGetDeviceInfo(device_id, info_name, datasize, data, NULL);

          fprintf(stdout, "%s: %s\n", label, data);

          free(data);

      }

       

       

      static void print_platform_info(cl_platform_id platform_id, cl_platform_info info_name, const char* label) {

          char* data;

          size_t datasize;

          clGetPlatformInfo(platform_id, info_name, 0, NULL, &datasize);

          data = (char*)malloc(datasize);

          clGetPlatformInfo(platform_id, info_name, datasize, data, NULL);

          fprintf(stdout, "%s: %s\n", label, data);

          free(data);

      }

       

      - How to build the simple test program:

      gcc -I /opt/amdgpu-pro/include -L/opt/amdgpu-pro/lib/x86_64-linux-gnu -o cltest cltest.c -Wl,-rpath,/opt/amdgpu-pro/lib/x86_64-linux-gnu -lOpenCL

       

      - Output of the simple test program:

       

      nplatforms=2

       

       

      Platform[0]:

      Platform Name: Clover

      Platform Profile: FULL_PROFILE

      Platform Version: OpenCL 1.1 Mesa 17.0.7

      Platform Vendor: Mesa

      Platform Extensions: cl_khr_icd

      ndevices=1

      Device[0]:

      Device Name: AMD CAPE VERDE (DRM 3.16.0 / 4.10.0-33-generic, LLVM 4.0.0)

      Device Profile: FULL_PROFILE

      Device Version: OpenCL 1.1 Mesa 17.0.7

      Driver Version: 17.0.7

      Device Vendor: AMD

      OpenCL C Version: OpenCL C 1.1

      Device Extensions: cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_fp64

      CreateContext: ret=0

      CreateCommandQueue: ret=0

       

       

      Platform[1]:

      Platform Name: AMD Accelerated Parallel Processing

      Platform Profile: FULL_PROFILE

      Platform Version: OpenCL 2.0 AMD-APP (2442.7)

      Platform Vendor: Advanced Micro Devices, Inc.

      Platform Extensions: cl_khr_icd cl_amd_event_callback cl_amd_offline_devices

      ndevices=1

      Device[0]:

      Device Name: Capeverde

      Device Profile: FULL_PROFILE

      Device Version: OpenCL 1.2 AMD-APP (2442.7)

      Driver Version: 2442.7

      Device Vendor: Advanced Micro Devices, Inc.

      OpenCL C Version: OpenCL C 1.2

      Device Extensions: cl_khr_fp64 cl_amd_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event

      CreateContext: ret=0

      CreateCommandQueue: ret=-6

       

      - 'ldd' output:

              linux-vdso.so.1 =>  (0x00007fffd06f8000)

              libOpenCL.so.1 => /opt/amdgpu-pro/lib/x86_64-linux-gnu/libOpenCL.so.1 (0x00007fe7fee52000)

              libc.so.6 => /lib/x86_64-linux-gnu/libc.so.6 (0x00007fe7fea6a000)

              librt.so.1 => /lib/x86_64-linux-gnu/librt.so.1 (0x00007fe7fe861000)

              libm.so.6 => /lib/x86_64-linux-gnu/libm.so.6 (0x00007fe7fe558000)

              libdl.so.2 => /lib/x86_64-linux-gnu/libdl.so.2 (0x00007fe7fe354000)

              libpthread.so.0 => /lib/x86_64-linux-gnu/libpthread.so.0 (0x00007fe7fe136000)

              /lib64/ld-linux-x86-64.so.2 (0x000055d0668e1000)

       

      - Output of 'clinfo':

      Number of platforms:                             2

        Platform Profile:                              FULL_PROFILE

        Platform Version:                              OpenCL 1.1 Mesa 17.0.7

        Platform Name:                                 Clover

        Platform Vendor:                               Mesa

        Platform Extensions:                           cl_khr_icd

        Platform Profile:                              FULL_PROFILE

        Platform Version:                              OpenCL 2.0 AMD-APP (2442.7)

        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:                                 Clover

      Number of devices:                               1

        Device Type:                                   CL_DEVICE_TYPE_GPU

        Vendor ID:                                     1002h

        Max compute units:                             8

        Max work items dimensions:                     3

          Max work items[0]:                           256

          Max work items[1]:                           256

          Max work items[2]:                           256

        Max work group size:                           256

        Preferred vector width char:                   16

        Preferred vector width short:                  8

        Preferred vector width int:                    4

        Preferred vector width long:                   2

        Preferred vector width float:                  4

        Preferred vector width double:                 2

        Native vector width char:                      16

        Native vector width short:                     8

        Native vector width int:                       4

        Native vector width long:                      2

        Native vector width float:                     4

        Native vector width double:                    2

        Max clock frequency:                           630Mhz

        Address bits:                                  64

        Max memory allocation:                         1918531584

        Image support:                                 No

        Max size of kernel argument:                   1024

        Alignment (bits) of base address:              1024

        Minimum alignment (bytes) for any datatype:    128

        Single precision floating point capability

          Denorms:                                     No

          Quiet NaNs:                                  Yes

          Round to nearest even:                       Yes

          Round to zero:                               No

          Round to +ve and infinity:                   No

          IEEE754-2008 fused multiply-add:             No

        Cache type:                                    None

        Cache line size:                               0

        Cache size:                                    0

        Global memory size:                            3220066304

        Constant buffer size:                          1918531584

        Max number of constant args:                   16

        Local memory type:                             Scratchpad

        Local memory size:                             32768

        Kernel Preferred work group size multiple:     64

        Error correction support:                      0

        Unified memory for Host and Device:            1

        Profiling timer resolution:                    0

        Device endianess:                              Little

        Available:                                     Yes

        Compiler available:                            Yes

        Execution capabilities:

          Execute OpenCL kernels:                      Yes

          Execute native function:                     No

        Queue on Host properties:

          Out-of-Order:                                No

          Profiling :                                  Yes

        Platform ID:                                   0x7f6f0863ae40

        Name:                                          AMD CAPE VERDE (DRM 3.16.0 / 4.10.0-33-generic, LLVM 4.0.0)

        Vendor:                                        AMD

        Device OpenCL C version:                       OpenCL C 1.1

        Driver version:                                17.0.7

        Profile:                                       FULL_PROFILE

        Version:                                       OpenCL 1.1 Mesa 17.0.7

        Extensions:                                    cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_fp64

       

       

       

       

        Platform Name:                                 AMD Accelerated Parallel Processing

      Number of devices:                               1

        Device Type:                                   CL_DEVICE_TYPE_GPU

        Vendor ID:                                     1002h

        Board name:                                    AMD FirePro W4100

        Device Topology:                               PCI[ B#3, D#0, F#0 ]

        Max compute units:                             4

        Max work items dimensions:                     3

          Max work items[0]:                           256

          Max work items[1]:                           256

          Max work items[2]:                           256

        Max work group size:                           256

        Preferred vector width char:                   4

        Preferred vector width short:                  2

        Preferred vector width int:                    1

        Preferred vector width long:                   1

        Preferred vector width float:                  1

        Preferred vector width double:                 1

        Native vector width char:                      4

        Native vector width short:                     2

        Native vector width int:                       1

        Native vector width long:                      1

        Native vector width float:                     1

        Native vector width double:                    1

        Max clock frequency:                           630Mhz

        Address bits:                                  32

        Max memory allocation:                         1408942080

        Image support:                                 Yes

        Max number of images read arguments:           128

        Max number of images write arguments:          8

        Max image 2D width:                            16384

        Max image 2D height:                           16384

        Max image 3D width:                            2048

        Max image 3D height:                           2048

        Max image 3D depth:                            2048

        Max samplers within kernel:                    16

        Max size of kernel argument:                   1024

        Alignment (bits) of base address:              2048

        Minimum alignment (bytes) for any datatype:    128

        Single precision floating point capability

          Denorms:                                     No

          Quiet NaNs:                                  Yes

          Round to nearest even:                       Yes

          Round to zero:                               Yes

          Round to +ve and infinity:                   Yes

          IEEE754-2008 fused multiply-add:             Yes

        Cache type:                                    Read/Write

        Cache line size:                               64

        Cache size:                                    16384

        Global memory size:                            2131243008

        Constant buffer size:                          65536

        Max number of constant args:                   8

        Local memory type:                             Scratchpad

        Local memory size:                             32768

        Max pipe arguments:                            0

        Max pipe active reservations:                  0

        Max pipe packet size:                          0

        Max global variable size:                      0

        Max global variable preferred total size:      0

        Max read/write image args:                     0

        Max on device events:                          0

        Queue on device max size:                      0

        Max on device queues:                          0

        Queue on device preferred size:                0

        SVM capabilities:

          Coarse grain buffer:                         No

          Fine grain buffer:                           No

          Fine grain system:                           No

          Atomics:                                     No

        Preferred platform atomic alignment:           0

        Preferred global atomic alignment:             0

        Preferred local atomic alignment:              0

        Kernel Preferred work group size multiple:     64

        Error correction support:                      0

        Unified memory for Host and Device:            0

        Profiling timer resolution:                    1

        Device endianess:                              Little

        Available:                                     Yes

        Compiler available:                            Yes

        Execution capabilities:

          Execute OpenCL kernels:                      Yes

          Execute native function:                     No

        Queue on Host properties:

          Out-of-Order:                                No

          Profiling :                                  Yes

        Queue on Device properties:

          Out-of-Order:                                No

          Profiling :                                  No

        Platform ID:                                   0x7f6ef66e7478

        Name:                                          Capeverde

        Vendor:                                        Advanced Micro Devices, Inc.

        Device OpenCL C version:                       OpenCL C 1.2

        Driver version:                                2442.7

        Profile:                                       FULL_PROFILE

        Version:                                       OpenCL 1.2 AMD-APP (2442.7)

        Extensions:                                    cl_khr_fp64 cl_amd_fp64 cl_khr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_khr_int64_extended_atomics cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_gl_sharing cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event

       

      - lshw -class display

       

        *-display

             description: VGA compatible controller

             product: Cape Verde GL [FirePro W4100]

             vendor: Advanced Micro Devices, Inc. [AMD/ATI]

             physical id: 0

             bus info: pci@0000:03:00.0

             version: 00

             width: 64 bits

             clock: 33MHz

             capabilities: pm pciexpress msi vga_controller bus_master cap_list rom

             configuration: driver=amdgpu latency=0

             resources: irq:42 memory:e0000000-efffffff memory:f7e00000-f7e3ffff ioport:d000(size=256) memory:f7e40000-f7e5ffff