7 Replies Latest reply on Oct 26, 2012 3:27 AM by pbcpbt

    new HD7970 loses GPU Device

    kbrafford

      I have a new HD7970, and after awhile the GPU device disappears from the OpenCL device list.  Here's what clinfo says when that happens:

       

      Number of platforms:                             1
        Platform Profile:                              FULL_PROFILE
        Platform Version:                              OpenCL 1.2 AMD-APP (923.1)
        Platform Name:                                 AMD Accelerated Parallel Proces
      sing
        Platform Vendor:                               Advanced Micro Devices, Inc.
        Platform Extensions:                           cl_khr_icd cl_amd_event_callbac
      k cl_amd_offline_devices cl_khr_d3d10_sharing
      
      
        Platform Name:                                 AMD Accelerated Parallel Proces
      sing
      Number of devices:                               1
        Device Type:                                   CL_DEVICE_TYPE_CPU
        Device ID:                                     4098
        Board name:
        Max compute units:                             4
        Max work items dimensions:                     3
          Max work items[0]:                           1024
          Max work items[1]:                           1024
          Max work items[2]:                           1024
        Max work group size:                           1024
        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:                 0
        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:                    0
        Max clock frequency:                           3010Mhz
        Address bits:                                  64
        Max memory allocation:                         2147483648
        Image support:                                 Yes
        Max number of images read arguments:           128
        Max number of images write arguments:          8
        Max image 2D width:                            8192
        Max image 2D height:                           8192
        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:                   4096
        Alignment (bits) of base address:              1024
        Minimum alignment (bytes) for any datatype:    128
        Single precision floating point capability
          Denorms:                                     Yes
          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:                                    65536
        Global memory size:                            8581414912
        Constant buffer size:                          65536
        Max number of constant args:                   8
        Local memory type:                             Global
        Local memory size:                             32768
        Kernel Preferred work group size multiple:     1
        Error correction support:                      0
        Unified memory for Host and Device:            1
        Profiling timer resolution:                    340
        Device endianess:                              Little
        Available:                                     Yes
        Compiler available:                            Yes
        Execution capabilities:
          Execute OpenCL kernels:                      Yes
          Execute native function:                     Yes
        Queue properties:
          Out-of-Order:                                No
          Profiling :                                  Yes
        Platform ID:                                   000007FED9012A08
        Name:                                          AMD Phenom(tm) II X4 940 Proces
      sor
        Vendor:                                        AuthenticAMD
        Device OpenCL C version:                       OpenCL C 1.2
        Driver version:                                2.0 (sse2)
        Profile:                                       FULL_PROFILE
        Version:                                       OpenCL 1.2 AMD-APP (923.1)
        Extensions:                                    cl_khr_fp64 cl_amd_fp64 cl_khr_
      global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int3
      2_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_
      khr_int64_extended_atomics cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ex
      t_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_
      media_ops cl_amd_popcnt cl_khr_d3d10_sharing
      

       

      It doesn't do this upon a fresh reboot.  It's only after some amount of time that at some point, the GPU is just gone. 

       

      Also (maybe related?) the machine now sometimes doesn't let me wake it back up after it has turned off the monitors.  I have found that with the new Radeon drivers for the new card that I have to disable the "turn off monitors" in the Power settings for the computer to keep working when I leave it alone for a few hours.

       

      Any idea what's going on?

       

      --Keith Brafford

        • Re: new HD7970 loses GPU Device
          pbcpbt

          I have similar problem with two HD 7970.

          Normally clinfo shows only CPU and one of the cards.

           

          When I issue:

               export COMPUTE=:0

          it shows all three  OpenCL devices - CPU and both GPUs.

            • Re: new HD7970 loses GPU Device
              ED1980

              pbcpbt wrote:

               

              I have similar problem with two HD 7970.

              Normally clinfo shows only CPU and one of the cards.

               

              When I issue:

                   export COMPUTE=:0

              it shows all three  OpenCL devices - CPU and both GPUs.

              Add the "export COMPUTE =: 0" in the file / etc / environment and all of OpenCL devices will be continuously visible in the system (only in my HD7970 connected to a monitor, a second HD6950 ... )

            • Re: new HD7970 loses GPU Device
              ED1980

              kbrafford wrote:

               

              I have a new HD7970, and after awhile the GPU device disappears from the OpenCL device list.  Here's what clinfo says when that happens:

               

              Number of platforms:                             1
                Platform Profile:                              FULL_PROFILE
                Platform Version:                              OpenCL 1.2 AMD-APP (923.1)
                Platform Name:                                 AMD Accelerated Parallel Proces
              sing
                Platform Vendor:                               Advanced Micro Devices, Inc.
                Platform Extensions:                           cl_khr_icd cl_amd_event_callbac
              k cl_amd_offline_devices cl_khr_d3d10_sharing
              
              
                Platform Name:                                 AMD Accelerated Parallel Proces
              sing
              Number of devices:                               1
                Device Type:                                   CL_DEVICE_TYPE_CPU
                Device ID:                                     4098
                Board name:
                Max compute units:                             4
                Max work items dimensions:                     3
                  Max work items[0]:                           1024
                  Max work items[1]:                           1024
                  Max work items[2]:                           1024
                Max work group size:                           1024
                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:                 0
                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:                    0
                Max clock frequency:                           3010Mhz
                Address bits:                                  64
                Max memory allocation:                         2147483648
                Image support:                                 Yes
                Max number of images read arguments:           128
                Max number of images write arguments:          8
                Max image 2D width:                            8192
                Max image 2D height:                           8192
                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:                   4096
                Alignment (bits) of base address:              1024
                Minimum alignment (bytes) for any datatype:    128
                Single precision floating point capability
                  Denorms:                                     Yes
                  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:                                    65536
                Global memory size:                            8581414912
                Constant buffer size:                          65536
                Max number of constant args:                   8
                Local memory type:                             Global
                Local memory size:                             32768
                Kernel Preferred work group size multiple:     1
                Error correction support:                      0
                Unified memory for Host and Device:            1
                Profiling timer resolution:                    340
                Device endianess:                              Little
                Available:                                     Yes
                Compiler available:                            Yes
                Execution capabilities:
                  Execute OpenCL kernels:                      Yes
                  Execute native function:                     Yes
                Queue properties:
                  Out-of-Order:                                No
                  Profiling :                                  Yes
                Platform ID:                                   000007FED9012A08
                Name:                                          AMD Phenom(tm) II X4 940 Proces
              sor
                Vendor:                                        AuthenticAMD
                Device OpenCL C version:                       OpenCL C 1.2
                Driver version:                                2.0 (sse2)
                Profile:                                       FULL_PROFILE
                Version:                                       OpenCL 1.2 AMD-APP (923.1)
                Extensions:                                    cl_khr_fp64 cl_amd_fp64 cl_khr_
              global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int3
              2_base_atomics cl_khr_local_int32_extended_atomics cl_khr_int64_base_atomics cl_
              khr_int64_extended_atomics cl_khr_byte_addressable_store cl_khr_gl_sharing cl_ex
              t_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_
              media_ops cl_amd_popcnt cl_khr_d3d10_sharing
              

               

              It doesn't do this upon a fresh reboot.  It's only after some amount of time that at some point, the GPU is just gone.

               

              Also (maybe related?) the machine now sometimes doesn't let me wake it back up after it has turned off the monitors.  I have found that with the new Radeon drivers for the new card that I have to disable the "turn off monitors" in the Power settings for the computer to keep working when I leave it alone for a few hours.

               

              Any idea what's going on?

               

              --Keith Brafford

              I think it works Technology AMD Zero Core, breaking graphics card when idle

              • Re: new HD7970 loses GPU Device
                kbrafford

                Ok, I rebooted again, and now I have no GPU context at all, even from the beginning of a session.

                 

                What gives?  How do I fix my setup?

                 

                --Keith Brafford

                • Re: new HD7970 loses GPU Device
                  pbcpbt

                  Same problem again with two HD 7970.

                  clinfo shows only CPU and one of the cards.

                   

                  When I issue:

                       export COMPUTE=:0

                   

                  NOTHING CHANGES!

                  file etc/environment has that line as well...

                   

                  This time it's Ubuntu 12.04