cancel
Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

duanrb
Journeyman III

two GPUs, samples do not work: CL_DEVICE_NOT_FOUND

Error: clCreateContextFromType failed. Error code : CL_DEVICE_NOT_FOUND

I have two GPUs on my workstation:

/sbin/lspci 

06:00.0 VGA compatible controller: nVidia Corporation GT200GL [Quadro FX 5800] (rev a1)

07:00.0 VGA compatible controller: ATI Technologies Inc Unknown device 6898



OS:CentOS release 5.5

After installed ATI driver and ati-stream-sdk-v2.2-lnx64, I can successfully run HelloCL and CLInfo, but cannot run others like ./BinarySearch. Always get error: 

Error: clCreateContextFromType failed. Error code : CL_DEVICE_NOT_FOUND 

========================

./CLInfo 

Number of platforms: 2

  Platform Profile: FULL_PROFILE

  Platform Version: OpenCL 1.1 ATI-Stream-v2.2 (302)

  Platform Name: ATI Stream

  Platform Vendor: Advanced Micro Devices, Inc.

  Platform Extensions: cl_khr_icd cl_amd_event_callback

  Platform Profile: FULL_PROFILE

  Platform Version: OpenCL 1.0 CUDA 3.1.1

  Platform Name: NVIDIA CUDA

  Platform Vendor: NVIDIA Corporation

  Platform Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll 

.............


========================

How can I solve this problem

Thanks replying.

0 Likes
19 Replies
nou
Exemplar

do you install catalyst? and did CLInfo report GPU device or only CPU? becuase samples default run on GPU. you need run them with -device cpu parameter.

0 Likes
duanrb
Journeyman III

I have installed catalyst. Without installing catalyst, I cannot compile the samples.

 

CLInfo only report GPU devices: both NVIDIA and ATI.

 

It runs well with -device cpu parameter, but cannot run on gpu.

0 Likes

how can it run on CPU device when CLInfo report only GPU? what ATI GPU do you have?

0 Likes

duanrb,

please post the complete clInfo output.

Some other people also faced problems with ATI+NVIDIA Gpu.These links might help you:

http://forums.amd.com/forum/messageview.cfm?catid=328&threadid=132643&enterthread=y

http://forums.amd.com/forum/messageview.cfm?catid=390&threadid=139508&forumid=9

0 Likes

 

./CLInfo

Number of platforms: 2

  Platform Profile: FULL_PROFILE

  Platform Version: OpenCL 1.1 ATI-Stream-v2.2 (302)

  Platform Name: ATI Stream

  Platform Vendor: Advanced Micro Devices, Inc.

  Platform Extensions: cl_khr_icd cl_amd_event_callback

  Platform Profile: FULL_PROFILE

  Platform Version: OpenCL 1.0 CUDA 3.1.1

  Platform Name: NVIDIA CUDA

  Platform Vendor: NVIDIA Corporation

  Platform Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll 

 

 

  Platform Name: ATI Stream

Number of devices: 1

  Device Type: CL_DEVICE_TYPE_CPU

  Device ID: 4098

  Max compute units: 16

  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

  Max clock frequency: 1596Mhz

  Address bits: 64

  Max memory allocation: 1073741824

  Image support: No

  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: No

  Cache type: Read/Write

  Cache line size: 64

  Cache size: 32768

  Global memory size: 3221225472

  Constant buffer size: 65536

  Max number of constant args: 8

  Local memory type: Global

  Local memory size: 32768

  Profiling timer resolution: 999848

  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: 0x2add11dbfb20

  Name: Intel(R) Xeon(R) CPU           W5590  @ 3.33GHz

  Vendor: GenuineIntel

  Driver version: 2.0

  Profile: FULL_PROFILE

  Version: OpenCL 1.1 ATI-Stream-v2.2 (302)

  Extensions: 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_byte_addressable_store cl_khr_gl_sharing cl_ext_device_fission cl_amd_device_attribute_query cl_amd_printf 

 

 

Passed!

  Platform Name: NVIDIA CUDA

Number of devices: 1

  Device Type: CL_DEVICE_TYPE_GPU

  Device ID: 4318

  Max compute units: 30

  Max work items dimensions: 3

    Max work items[0]: 512

    Max work items[1]: 512

    Max work items[2]: 64

  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: 1

  Max clock frequency: 1296Mhz

  Address bits: 32

  Max memory allocation: 1073659904

  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: 4352

  Alignment (bits) of base address: 256

  Minimum alignment (bytes) for any datatype: 16

  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: None

  Cache line size: 0

  Cache size: 0

  Global memory size: 4294639616

  Constant buffer size: 65536

  Max number of constant args: 9

  Local memory type: Scratchpad

  Local memory size: 16384

  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: 0x1e8392f0

  Name: Quadro FX 5800

  Vendor: NVIDIA Corporation

  Driver version: 256.35

  Profile: FULL_PROFILE

  Version: OpenCL 1.0 CUDA

  Extensions: cl_khr_byte_addressable_store cl_khr_icd cl_khr_gl_sharing cl_nv_compiler_options cl_nv_device_attribute_query cl_nv_pragma_unroll  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_fp64 

 

 

Error : atomics mismatch!

Error : Bytes mismatch!

Error : glSharing mismatch!

Error : images mismatch!

Error : printf mismatch!

Error : deviceAttributeQuery mismatch!

Failed!



0 Likes

According to the lspci output, the ATI GPU should be Radeon HD 5800 Series. 

/sbin/lspci | grep ATI

07:00.0 VGA compatible controller: ATI Technologies Inc Unknown device 6898

07:00.1 Audio device: ATI Technologies Inc Cypress HDMI Audio [Radeon HD 5800 Series]



0 Likes

so CLInfo report nVidia GPU and Intel CPU so it do not see ATI GPU. this is driver related issue. try run FindNumDevices from CAL samples of ATI SDK. most likely it will find 0 devices. that mean driver is not installed corectly.

0 Likes
duanrb
Journeyman III

yes you are right, nou. Do I need to reinstall ATI driver? I tried reinstalling it yesterday. Did I miss something?

./FindNumDevices 

Supported CAL Runtime Version: 1.3.185

Found CAL Runtime Version: 1.4.739

Use -? for help

CAL initialized.

Finding out number of devices :- 

Device Count = 0

CAL shutdown successful.

 

Press enter to exit...



0 Likes

you must have fglrx in xorg.conf so Xorg will load driver. and monitor plug into ATI card.

0 Likes
duanrb
Journeyman III

Is it necessary that monitor plug into ATI card? Because the server is on a remote site. I cannot do it for now. is there another solution without plugging monitor into ATI card?

0 Likes

on linux it is not necessary. but running Xserver is necessary with properly configured xorg.con throug aticonfig --initial

0 Likes
duanrb
Journeyman III

I have run the command: aticonfig --initial

but still doesn't work

0 Likes

did Xserver running and logged in under some user.

export DISPLAY=:0 to gain access to xsession and GPU. you must be logged in as same user as to X session.

best what you can is first started it localy with attached monitor and then remotely.

 

0 Likes
FD_CS
Journeyman III

I have similar issues:

I can reach the server station with an Ati Radeon and a geforce only remotely.

When i am the only user connected on say pts/0 , i can only see the Intel CPU with OpenCL.

After root connet in X (the root can physically connect the station) so the xserver is running, the root sees the 3 devices (Intel CPU + Ati GPU + Nvidia GPU ) whereas i can only see Intel CPU and Nvidia GPU.

Is there a way for me to use Ati card ?

Thank you very much for your time

 

 

 

 

0 Likes

ok sorry for having posted, re reading nou's post solved it, it works if:

* somebody logged me in Xsession

* i connect by ssh and export DISPLAY=:0

 

0 Likes
duanrb
Journeyman III

What do you mean that Xserver running and logged in under some user?

Do you mean to be logged in as root as to X session?

I still cannot see the devices. Device Count = 0

Thanks a lot for your time.

 

 

0 Likes

i mean logged into Xsession like normal desctop user witk keyboard and monitor. then you can log in as same user export DISPLAY and then you can execute OpenCL app remotely.

0 Likes
duanrb
Journeyman III

How to logged into Xsesssion like normal destop user with keyboard and monitor. what're the commands? thanks

0 Likes

Originally posted by: duanrb How to logged into Xsesssion like normal destop user with keyboard and monitor. what're the commands? thanks

 

Following document could help you

http://developer.amd.com/gpu_assets/App_Note-Running_ATI_Stream_Apps_Remotely.pdf

0 Likes