clinfo.exe wrong values for CL_DEVICE_ADDRESS_BITS

Message boards : GPUs : clinfo.exe wrong values for CL_DEVICE_ADDRESS_BITS
Message board moderation

To post messages, you must log in.

AuthorMessage
Nikolay Polyarniy

Send message
Joined: 9 Jan 17
Posts: 3
Russia
Message 75159 - Posted: 9 Jan 2017, 18:07:38 UTC

On 64-bit Windows clinfo.exe outputs strange values for "Address bits" (CL_DEVICE_ADDRES_BITS):

14757395255531667520 and 14757395255531667488

While expected: 64 and 32.

I notice, that:
14757395255531667520 = 0b1100110011001100110011001100110000000000000000000000000001000000
14757395255531667488 = 0b1100110011001100110011001100110000000000000000000000000000100000

Also google returns a lot of results with outputs with the same values.

So upper bits are seems to be uninitialized. May be your clinfo reads CL_DEVICE_ADDRES_BITS into size_t value? (While should read into cl_uint, according to documentation - https://www.khronos.org/registry/OpenCL/sdk/1.0/docs/man/xhtml/clGetDeviceInfo.html)

Full output:
Number of platforms:                             2
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 1.1 CUDA 6.0.1
  Platform Name:                                 NVIDIA CUDA
  Platform Vendor:                               NVIDIA Corporation
  Platform Extensions:                           cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_
sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query
cl_nv_pragma_unroll
  Platform Profile:                              FULL_PROFILE
  Platform Version:                              OpenCL 1.2
  Platform Name:                                 Intel(R) OpenCL
  Platform Vendor:                               Intel(R) Corporation
  Platform Extensions:                           cl_intel_dx9_media_sharing cl_k
hr_3d_image_writes cl_khr_byte_addressable_store cl_khr_d3d11_sharing cl_khr_dep
th_images cl_khr_dx9_media_sharing cl_khr_gl_sharing cl_khr_global_int32_base_at
omics cl_khr_global_int32_extended_atomics cl_khr_icd cl_khr_local_int32_base_at
omics cl_khr_local_int32_extended_atomics cl_khr_spir


  Platform Name:                                 NVIDIA CUDA
Number of devices:                               1
  Device Type:                                   CL_DEVICE_TYPE_GPU
  Device ID:                                     4318
  Max compute units:                             2
  Max work items dimensions:                     3
    Max work items[0]:                           1024
    Max work items[1]:                           1024
    Max work items[2]:                           64
  Max work group size:                           1024
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 1
  Max clock frequency:                           705Mhz
  Address bits:                                  14757395255531667488
  Max memory allocation:                         536870912
  Image support:                                 Yes
  Max number of images read arguments:           256
  Max number of images write arguments:          16
  Max image 2D width:                            32768
  Max image 2D height:                           32768
  Max image 3D width:                            4096
  Max image 3D height:                           4096
  Max image 3D depth:                            4096
  Max samplers within kernel:                    32
  Max size of kernel argument:                   4352
  Alignment (bits) of base address:              4096
  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:                               128
  Cache size:                                    32768
  Global memory size:                            2147483648
  Constant buffer size:                          65536
  Max number of constant args:                   9
  Local memory type:                             Scratchpad
  Local memory size:                             49152
  Error correction support:                      0
  Profiling timer resolution:                    1000
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     No
  Queue properties:
    Out-of-Order:                                Yes
    Profiling :                                  Yes
  Platform ID:                                   00811B38
  Name:                                          Quadro K1100M
  Vendor:                                        NVIDIA Corporation
  Driver version:                                331.65
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 1.1 CUDA
  Extensions:                                    cl_khr_byte_addressable_store c
l_khr_icd cl_khr_gl_sharing cl_nv_d3d9_sharing cl_nv_d3d10_sharing cl_khr_d3d10_
sharing cl_nv_d3d11_sharing cl_nv_compiler_options cl_nv_device_attribute_query
cl_nv_pragma_unroll  cl_khr_global_int32_base_atomics cl_khr_global_int32_extend
ed_atomics cl_khr_local_int32_base_atomics cl_khr_local_int32_extended_atomics c
l_khr_fp64


  Platform Name:                                 Intel(R) OpenCL
Number of devices:                               2
  Device Type:                                   CL_DEVICE_TYPE_CPU
  Device ID:                                     32902
  Max compute units:                             8
  Max work items dimensions:                     3
    Max work items[0]:                           8192
    Max work items[1]:                           8192
    Max work items[2]:                           8192
  Max work group size:                           8192
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 1
  Max clock frequency:                           2200Mhz
  Address bits:                                  14757395255531667488
  Max memory allocation:                         536838144
  Image support:                                 Yes
  Max number of images read arguments:           480
  Max number of images write arguments:          480
  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:                    480
  Max size of kernel argument:                   3840
  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:                               No
    Round to +ve and infinity:                   No
    IEEE754-2008 fused multiply-add:             No
  Cache type:                                    Read/Write
  Cache line size:                               64
  Cache size:                                    262144
  Global memory size:                            2147352576
  Constant buffer size:                          131072
  Max number of constant args:                   480
  Local memory type:                             Global
  Local memory size:                             32768
  Error correction support:                      0
  Profiling timer resolution:                    466
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     Yes
  Queue properties:
    Out-of-Order:                                Yes
    Profiling :                                  Yes
  Platform ID:                                   00702CA8
  Name:                                          Intel(R) Core(TM) i7-4702HQ CPU
 @ 2.20GHz
  Vendor:                                        Intel(R) Corporation
  Driver version:                                4.2.0.148
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 1.2 (Build 148)
  Extensions:                                    cl_khr_icd cl_khr_global_int32_
base_atomics cl_khr_global_int32_extended_atomics cl_khr_local_int32_base_atomic
s cl_khr_local_int32_extended_atomics cl_khr_byte_addressable_store cl_khr_spir
cl_intel_exec_by_local_thread cl_khr_depth_images cl_khr_3d_image_writes cl_khr_
fp64 cl_intel_dx9_media_sharing cl_khr_dx9_media_sharing cl_khr_d3d11_sharing cl
_khr_gl_sharing


  Device Type:                                   CL_DEVICE_TYPE_GPU
  Device ID:                                     32902
  Max compute units:                             20
  Max work items dimensions:                     3
    Max work items[0]:                           512
    Max work items[1]:                           512
    Max work items[2]:                           512
  Max work group size:                           512
  Preferred vector width char:                   1
  Preferred vector width short:                  1
  Preferred vector width int:                    1
  Preferred vector width long:                   1
  Preferred vector width float:                  1
  Preferred vector width double:                 0
  Max clock frequency:                           600Mhz
  Address bits:                                  14757395255531667520
  Max memory allocation:                         373712486
  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:              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:                               Yes
    Round to +ve and infinity:                   Yes
    IEEE754-2008 fused multiply-add:             No
  Cache type:                                    Read/Write
  Cache line size:                               64
  Cache size:                                    2097152
  Global memory size:                            1494849946
  Constant buffer size:                          65536
  Max number of constant args:                   8
  Local memory type:                             Scratchpad
  Local memory size:                             65536
  Error correction support:                      0
  Profiling timer resolution:                    80
  Device endianess:                              Little
  Available:                                     Yes
  Compiler available:                            Yes
  Execution capabilities:
    Execute OpenCL kernels:                      Yes
    Execute native function:                     No
  Queue properties:
    Out-of-Order:                                No
    Profiling :                                  Yes
  Platform ID:                                   00702CA8
  Name:                                          Intel(R) HD Graphics 4600
  Vendor:                                        Intel(R) Corporation
  Driver version:                                10.18.14.4112
  Profile:                                       FULL_PROFILE
  Version:                                       OpenCL 1.2
  Extensions:                                    cl_intel_accelerator cl_intel_a
dvanced_motion_estimation cl_intel_ctz cl_intel_d3d11_nv12_media_sharing cl_inte
l_dx9_media_sharing cl_intel_motion_estimation cl_intel_simultaneous_sharing cl_
intel_subgroups cl_khr_3d_image_writes cl_khr_byte_addressable_store cl_khr_d3d1
0_sharing cl_khr_d3d11_sharing cl_khr_depth_images cl_khr_dx9_media_sharing cl_k
hr_gl_depth_images cl_khr_gl_event cl_khr_gl_msaa_sharing cl_khr_gl_sharing cl_k
hr_global_int32_base_atomics cl_khr_global_int32_extended_atomics cl_khr_icd cl_
khr_image2d_from_buffer cl_khr_local_int32_base_atomics cl_khr_local_int32_exten
ded_atomics cl_khr_spir


P.S. I didn't found source code for clinfo on github - https://github.com/BOINC, may be you will upload it there?
ID: 75159 · Report as offensive
Profile Agentb
Help desk expert
Avatar

Send message
Joined: 30 May 15
Posts: 265
United Kingdom
Message 75161 - Posted: 9 Jan 2017, 19:28:25 UTC - in response to Message 75159.  
Last modified: 9 Jan 2017, 19:29:12 UTC

Welcome to the BOINC forums

Most of these questions need to be raised with nVidia. nVidia's support for OpenCL is at best average.

It looks like you are running an old version see http://www.nvidia.co.uk/Download/index.aspx?lang=en-uk
ID: 75161 · Report as offensive
Nikolay Polyarniy

Send message
Joined: 9 Jan 17
Posts: 3
Russia
Message 75162 - Posted: 9 Jan 2017, 19:32:45 UTC - in response to Message 75161.  

I am sure, that driver for Intel HD 4600 is actual (I installed it today from my notebook vendor site).
Moreover - the problem exists for CPU too.
ID: 75162 · Report as offensive
Juha
Volunteer developer
Volunteer tester
Help desk expert

Send message
Joined: 20 Nov 12
Posts: 737
Finland
Message 75164 - Posted: 9 Jan 2017, 21:40:55 UTC - in response to Message 75159.  

If you are referring to the clinfo.exe downloadable from http://boinc.berkeley.edu/dl/clinfo.zip it is not made by BOINC developers. I am not sure of its origin but looking at the strings inside the file it probably comes from ATI Stream SDK samples.
ID: 75164 · Report as offensive
Nikolay Polyarniy

Send message
Joined: 9 Jan 17
Posts: 3
Russia
Message 75170 - Posted: 10 Jan 2017, 9:08:47 UTC - in response to Message 75164.  

Ok, thanks!
ID: 75170 · Report as offensive
Profile Agentb
Help desk expert
Avatar

Send message
Joined: 30 May 15
Posts: 265
United Kingdom
Message 75178 - Posted: 10 Jan 2017, 20:08:27 UTC - in response to Message 75170.  

That zip file dates back to 30-Mar-2011 13:52, so i would suggest you would be better off deleting it.
ID: 75178 · Report as offensive
Profile Ageless
Volunteer moderator
Project administrator
Volunteer tester
Help desk expert
Avatar

Send message
Joined: 29 Aug 05
Posts: 12495
Netherlands
Message 75180 - Posted: 10 Jan 2017, 20:29:50 UTC

Check in %SYSTEMDRIVE%:\Windows\System32 as there may be a more up-to-date clinfo.exe in there, deposited by the Nvidia or Intel drivers.
Jord
Please do not private message me for tech support. Use the forums for that. Tech PMs will be ignored.

quote: "Isn't the best defense always a good attack?"
ID: 75180 · Report as offensive
Claggy
Volunteer tester
Help desk expert

Send message
Joined: 23 Apr 07
Posts: 1112
United Kingdom
Message 75184 - Posted: 10 Jan 2017, 23:39:56 UTC - in response to Message 75180.  

Check in %SYSTEMDRIVE%:\Windows\System32 as there may be a more up-to-date clinfo.exe in there, deposited by the Nvidia or Intel drivers.

Or AMD, I'm sure it's an AMD file.

Claggy
ID: 75184 · Report as offensive
Profile Ageless
Volunteer moderator
Project administrator
Volunteer tester
Help desk expert
Avatar

Send message
Joined: 29 Aug 05
Posts: 12495
Netherlands
Message 75186 - Posted: 10 Jan 2017, 23:41:42 UTC - in response to Message 75184.  

Yes, for me it's deposited there by my AMD GPU drivers, but since the OP only has an Intel and Nvidia GPU, either drivers may have done the same thing.
Jord
Please do not private message me for tech support. Use the forums for that. Tech PMs will be ignored.

quote: "Isn't the best defense always a good attack?"
ID: 75186 · Report as offensive

Message boards : GPUs : clinfo.exe wrong values for CL_DEVICE_ADDRESS_BITS

Copyright © 2018 University of California. Permission is granted to copy, distribute and/or modify this document under the terms of the GNU Free Documentation License, Version 1.2 or any later version published by the Free Software Foundation.