5 Replies Latest reply on Oct 1, 2015 2:26 AM by dipak

    Which version of driver can enable the A10-7870K to support SVM/OpenCL 2.0


      Hi guys,

      I want to use APU's(A10-7870K) SVM ability.

      I installed the latest driver(15.20.1046) and the SDK3.0, however, the clinfo show the supported Opencl version is 1.2 and the SVM is not supported.

      Actuallly, the GPU is not detected, right?

      I'm sure the spec of 7870K show the APU can support OPENCL2.0, right?

      The OS which I use is OpenSuse 13.2, and I also try the ubuntu 15, 14, and Windows 10.

      Windows 10 can detect the GPU and support SVM, so the setting of BIOS should be OK.

      I have tried AMD OpenCL™ 2.0 Driver , however, the version seem too old for Opensuse 13.2.








      Append the output of clinfo


        Platform Name:                           AMD Accelerated Parallel Processing
      Number of devices:                         1
        Device Type:                             CL_DEVICE_TYPE_CPU
        Vendor ID:                               1002h
        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:            8
        Preferred vector width double:           4
        Native vector width char:                16
        Native vector width short:               8
        Native vector width int:                 4
        Native vector width long:                2
        Native vector width float:               8
        Native vector width double:              4
        Max clock frequency:                     1700Mhz
        Address bits:                            64
        Max memory allocation:                   8154801152
        Image support:                           Yes
        Max number of images read arguments:     128
        Max number of images write arguments:    64
        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:                              16384
        Global memory size:                      32619204608
        Constant buffer size:                    65536
        Max number of constant args:             8
        Local memory type:                       Global
        Local memory size:                       32768
        Max pipe arguments:                      16
        Max pipe active reservations:            16
        Max pipe packet size:                    3859833856
        Max global variable size:                1879048192
        Max global variable preferred total size:1879048192
        Max read/write image args:               64
        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:1
        Error correction support:                0
        Unified memory for Host and Device:      1
        Profiling timer resolution:              1
        Device endianess:                        Little
        Available:                               Yes
        Compiler available:                      Yes
        Execution capabilities:                        
      Execute OpenCL kernels:                Yes
      Execute native function:               Yes
        Queue on Host properties:                      
      Out-of-Order:                          No
      Profiling :                            Yes
        Queue on Device properties:                    
      Out-of-Order:                          No
      Profiling :                            No
        Platform ID:                             0x7f585bfaa430
        Name:                                    AMD A10-7870K Radeon R7, 12 Compute Cores 4C+8G
        Vendor:                                  AuthenticAMD
        Device OpenCL C version:                 OpenCL C 1.2
        Driver version:                          1800.5 (sse2,avx,fma4)
        Profile:                                 FULL_PROFILE
        Version:                                 OpenCL 1.2 AMD-APP (1800.5)
        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_ext_device_fission cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_spir cl_khr_gl_event