OpenCL

[meriken]

With Radeon Software Adrenaline 17.12.2, calls to clGetDeviceInfo with CL_DEVICE_TOPOLOGY_AMD always return wrong results. You can easily see this with clinfo:

Device Topology: PCI[ B#0, D#0, F#1 ]

The results are always the same regardless of actual topology. I confirmed this bug with RX 480/470 and 7990. This horrendous bug renders AMD Display Library completely useless as there is now no way to match OpenCL devices with ADL adapters reliably. No temperature monitoring, no fan control, nothing! Please fix this bug ASAP!

[dipak]

Thanks for reporting it. From the above description, the issue seems related to base driver. I'll report it to concerned team. Please share OS information and clinfo output.

[meriken]

Microsoft Windows [Version 10.0.16299.125]

(c) 2017 Microsoft Corporation. All rights reserved.

C:\Users\me>clinfo

Number of platforms:                             1

  Platform Profile:                              FULL_PROFILE

  Platform Version:                              OpenCL 2.1 AMD-APP (2527.7)

  Platform Name:                                 AMD Accelerated Parallel Processing

  Platform Vendor:                               Advanced Micro Devices, Inc.

  Platform Extensions:                           cl_khr_icd cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_amd_event_callback cl_amd_offline_devices

  Platform Name:                                 AMD Accelerated Parallel Processing

Number of devices:                               5

  Device Type:                                   CL_DEVICE_TYPE_GPU

  Vendor ID:                                     1002h

  Board name:                                    Radeon (TM) RX 480 Graphics

  Device Topology:                               PCI[ B#0, D#0, F#1 ]

  Max compute units:                             36

  Max work items dimensions:                     3

    Max work items[0]:                           1024

    Max work items[1]:                           1024

    Max work items[2]:                           1024

  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:                           1288Mhz

  Address bits:                                  64

  Max memory allocation:                         4244635648

  Image support:                                 Yes

  Max number of images read arguments:           128

  Max number of images write arguments:          64

  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:                            8589934592

  Constant buffer size:                          4244635648

  Max number of constant args:                   8

  Local memory type:                             Scratchpad

  Local memory size:                             32768

  Max pipe arguments:                            16

  Max pipe active reservations:                  16

  Max pipe packet size:                          4244635648

  Max global variable size:                      3820172032

  Max global variable preferred total size:      8589934592

  Max read/write image args:                     64

  Max on device events:                          1024

  Queue on device max size:                      8388608

  Max on device queues:                          1

  Queue on device preferred size:                262144

  SVM capabilities:

    Coarse grain buffer:                         Yes

    Fine grain buffer:                           Yes

    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:                                Yes

    Profiling :                                  Yes

  Platform ID:                                   00007FFC54A94AB0

  Name:                                          Ellesmere

  Vendor:                                        Advanced Micro Devices, Inc.

  Device OpenCL C version:                       OpenCL C 2.0

  Driver version:                                2527.7

  Profile:                                       FULL_PROFILE

  Version:                                       OpenCL 2.0 AMD-APP (2527.7)

  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_fp16 cl_khr_gl_sharing cl_khr_gl_depth_images cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_subgroups cl_khr_gl_event cl_khr_depth_images cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_amd_liquid_flash

  Device Type:                                   CL_DEVICE_TYPE_GPU

  Vendor ID:                                     1002h

  Board name:                                    AMD Radeon HD 7900 Series

  Device Topology:                               PCI[ B#0, D#0, F#1 ]

  Max compute units:                             32

  Max work items dimensions:                     3

    Max work items[0]:                           1024

    Max work items[1]:                           1024

    Max work items[2]:                           1024

  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:                           1000Mhz

  Address bits:                                  32

  Max memory allocation:                         2952790016

  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:                            3221225472

  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:                                   00007FFC54A94AB0

  Name:                                          Tahiti

  Vendor:                                        Advanced Micro Devices, Inc.

  Device OpenCL C version:                       OpenCL C 1.2

  Driver version:                                2527.7

  Profile:                                       FULL_PROFILE

  Version:                                       OpenCL 1.2 AMD-APP (2527.7)

  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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event cl_amd_liquid_flash

  Device Type:                                   CL_DEVICE_TYPE_GPU

  Vendor ID:                                     1002h

  Board name:                                    AMD Radeon HD 7900 Series

  Device Topology:                               PCI[ B#0, D#0, F#1 ]

  Max compute units:                             32

  Max work items dimensions:                     3

    Max work items[0]:                           1024

    Max work items[1]:                           1024

    Max work items[2]:                           1024

  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:                           1000Mhz

  Address bits:                                  32

  Max memory allocation:                         2952790016

  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:                            3221225472

  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:                                   00007FFC54A94AB0

  Name:                                          Tahiti

  Vendor:                                        Advanced Micro Devices, Inc.

  Device OpenCL C version:                       OpenCL C 1.2

  Driver version:                                2527.7

  Profile:                                       FULL_PROFILE

  Version:                                       OpenCL 1.2 AMD-APP (2527.7)

  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_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_gl_event cl_amd_liquid_flash

  Device Type:                                   CL_DEVICE_TYPE_GPU

  Vendor ID:                                     1002h

  Board name:                                    Radeon (TM) RX 470 Graphics

  Device Topology:                               PCI[ B#0, D#0, F#1 ]

  Max compute units:                             32

  Max work items dimensions:                     3

    Max work items[0]:                           1024

    Max work items[1]:                           1024

    Max work items[2]:                           1024

  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:                           1226Mhz

  Address bits:                                  64

  Max memory allocation:                         4026531840

  Image support:                                 Yes

  Max number of images read arguments:           128

  Max number of images write arguments:          64

  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:                            4294967296

  Constant buffer size:                          4026531840

  Max number of constant args:                   8

  Local memory type:                             Scratchpad

  Local memory size:                             32768

  Max pipe arguments:                            16

  Max pipe active reservations:                  16

  Max pipe packet size:                          4026531840

  Max global variable size:                      3623878656

  Max global variable preferred total size:      4294967296

  Max read/write image args:                     64

  Max on device events:                          1024

  Queue on device max size:                      8388608

  Max on device queues:                          1

  Queue on device preferred size:                262144

  SVM capabilities:

    Coarse grain buffer:                         Yes

    Fine grain buffer:                           Yes

    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:                                Yes

    Profiling :                                  Yes

  Platform ID:                                   00007FFC54A94AB0

  Name:                                          Ellesmere

  Vendor:                                        Advanced Micro Devices, Inc.

  Device OpenCL C version:                       OpenCL C 2.0

  Driver version:                                2527.7

  Profile:                                       FULL_PROFILE

  Version:                                       OpenCL 2.0 AMD-APP (2527.7)

  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_fp16 cl_khr_gl_sharing cl_khr_gl_depth_images cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_d3d10_sharing cl_khr_d3d11_sharing cl_khr_dx9_media_sharing cl_khr_image2d_from_buffer cl_khr_spir cl_khr_subgroups cl_khr_gl_event cl_khr_depth_images cl_khr_mipmap_image cl_khr_mipmap_image_writes cl_amd_liquid_flash

  Device Type:                                   CL_DEVICE_TYPE_CPU

  Vendor ID:                                     1002h

  Board name:

  Max compute units:                             12

  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:                           3398Mhz

  Address bits:                                  64

  Max memory allocation:                         8566595584

  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:                                    32768

  Global memory size:                            34266382336

  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:                          4271628288

  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:                    301

  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:                                   00007FFC54A94AB0

  Name:                                          Intel(R) Core(TM) i7-6800K CPU @ 3.40GHz

  Vendor:                                        GenuineIntel

  Device OpenCL C version:                       OpenCL C 1.2

  Driver version:                                2527.7 (sse2,avx)

  Profile:                                       FULL_PROFILE

  Version:                                       OpenCL 1.2 AMD-APP (2527.7)

  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_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_d3d10_sharing cl_khr_spir cl_khr_gl_event

[meriken]

[dipak]

Thanks for sharing those information. I've opened a ticket against this bug.

[meriken]

Do you have an ETA at all for this issue?

My holiday vacation went down into toilet implementing a workaround for this issue, and it is by no means perfect.

I don't mean to be rude, but it really shouldn't take this long to fix this problem, should it?

[dipak]

Sorry, I'm unable to give an ETA at this moment. The issue is still under investigation. Once I get any update from the concerned team, I'll let you know.

[meriken]

Release notes say the problem is fixed in Adrenalin 18.1.1.

I am downloading the new driver now...

Edit: The problem is indeed gone with the new driver! Thank you so much. This is a wonderful news!

[dipak]

Thanks for the confirmation.