10 Replies Latest reply on Apr 23, 2015 2:19 PM by maestrodan Branched to a new discussion.

    OpenCL on 14.12 Omega driver crack's OpenCL on linux

    maestrodan

      Hi, I have a amd kabini laptop, it's on AMD A6-5200, there is Radeon HD8400 and Radeon HD8570,

      Some time ago I can use opencl on my laptop for rendering in blender or using handbrake, libroffice, it can be done for all cpu and gpu together (4 Jaguar cores+Radeon HD8400+Radeon HD8570), but now there is Catalyst 14.12 omega driver and there is some problem.

      maestrodan@monstermash:~$ clinfo

      Number of platforms:                 1

        Platform Profile:                 FULL_PROFILE

        Platform Version:                 OpenCL 2.0 AMD-APP (1642.5)

        Platform Name:                 AMD Accelerated Parallel Processing

        Platform Vendor:                 Advanced Micro Devices, Inc.

        Platform Extensions:                 cl_khr_icd cl_amd_event_callback cl_amd_offline_devices

       

       

        Platform Name:                 AMD Accelerated Parallel Processing

      Number of devices:                 2

        Device Type:                     CL_DEVICE_TYPE_GPU

        Vendor ID:                     1002h

        Board name:                     AMD Radeon HD 8400 / R3 Series

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

        Max compute units:                 2

        Max work items dimensions:             3

          Max work items[0]:                 256

          Max work items[1]:                 256

          Max work items[2]:                 256

        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:                 600Mhz

        Address bits:                     64

        Max memory allocation:             134217728

        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:                 536870912

        Constant buffer size:                 65536

        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:                 134217728

        Max global variable size:             120795904

        Max global variable preferred total size:     536870912

        Max read/write image args:             64

        Max on device events:                 1024

        Queue on device max size:             524288

        Max on device queues:                 1

        Queue on device preferred size:         16384

        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:         1

        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:                     0x7f999827cfd0

        Name:                         Kalindi

        Vendor:                     Advanced Micro Devices, Inc.

        Device OpenCL C version:             OpenCL C 2.0

        Driver version:                 1642.5 (VM)

        Profile:                     FULL_PROFILE

        Version:                     OpenCL 2.0 AMD-APP (1642.5)

        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_atomic_counters_32 cl_amd_device_attribute_query cl_amd_vec3 cl_amd_printf cl_amd_media_ops cl_amd_media_ops2 cl_amd_popcnt cl_khr_image2d_from_buffer cl_khr_spir cl_khr_subgroups cl_khr_gl_event cl_khr_depth_images

       

       

        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:                 800Mhz

        Address bits:                     64

        Max memory allocation:             2147483648

        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:                 7720505344

        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:                 2147483648

        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:             Yes

          Fine grain buffer:                 Yes

          Fine grain system:                 Yes

          Atomics:                     Yes

        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:                     0x7f999827cfd0

        Name:                         AMD A6-5200 APU with Radeon(TM) HD Graphics

        Vendor:                     AuthenticAMD

        Device OpenCL C version:             OpenCL C 1.2

        Driver version:                 1642.5 (sse2,avx)

        Profile:                     FULL_PROFILE

        Version:                     OpenCL 1.2 AMD-APP (1642.5)

        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

       

      So, CPU can use only OpenCL 1.2, and Radeon HD8400 can use OpenCL 2.0 with new driver. HD8570 is not active now(UMA graphics in bios), but it can use only OpenCL 1.2 too. So, now with this driver all applications that can use OpenCL can't use it, Blender, Libroffice does'nt show anyone OpenCL combute device in settings, same for handbrake in init logs from it.

        • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
          ravkum

          Hi,

           

          Let us take it one application at a time. Libreofiice calc is tested to work with Omega driver. So I am not sure what is happening at your end.

           

          Which version of LibreOffice do you have?

           

          Regards,

          Ravi

          • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
            dipak

            As you mentioned, at some earlier time, you were able to use opencl for those applications. What was the catalyst driver version? Is that driver still working fine for your system?

              • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                maestrodan

                I' don't remember from which driver version opencl become avaiable for software like handbreake and blender, but previos version, catalyst 14.9 really has working opencl. UPD: It become working exactly in 14.9, and I can run blender of all platforms together(igpu+dgpu+cpu) with opencl.

                It was on ubuntu 14.04, but now some libs which needed for installing catalyst 14.9 are not avaiable, so I can't install it again. I can't build .deb files, and if I install it manualy, the Xorg will not start

                New version, fglrx 15.20(from ubuntu 14.04 repos) still can't use opencl.

                • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                  maestrodan

                  It's something strange, after I install 14.9, opencl works(on 14.04 with 1.15.1 Xorg before upgrading), then Ubuntu updates some packages of fglrx, and give an error during installation, then i run sudo apt-get purge fglrx*, and run system with mesa, after it I try to install xserver-xorg-lts-utopic and kernel from utopic, and install 14.9 catalyst from .deb packages, system can't load X-server, then I purge 14.9 and install 15.200 fglrx, and it can run OpenCL in blender now!  With OpenCL 2.0 on Radeon HD8400(Radeon R3), and the same in my main Ubuntu OS 14.04.2(all previos was on testing OS 14.04) and fglrx15.200, so now, I don't know how, but OpenCL works for Blender everywhere, but... when I try to run OpenCL by CPU in blender it's crushes with "Copying BVH to device".

                  And when I run OpenCL test in libreoffice it's gives an errors for all tests.

                  About blender:   is the OpenCL device list depends on Blender or on OpenCL drivers? There are entries: "AMD A6-5200" "Kalindi" "Hainan" and "AMD A6-5200+Kalindi+Hainan" and I cannot use only one of GPU with CPU or two GPU's without CPU.

                    • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                      dipak

                      Good to hear that fglrx 15.200 is working for you now. As you mentioned, you're able to access the OpenCL from blender (and other apps) but crashes when using it. Did you try any other OpenCL program (say any APP SDK OpenCL sample) to see whether OpenCL is properly working or not?  If samples run fine, then OpenCL setup is okay. Then there may be some other issues for the crashing. Please check and be sure.

                      I'm not sure about your blender question. I guess, blender forum may be more appropriate for this type of queries or someone more knowledgeable about blender may comment about it.

                       

                      Regards,

                        • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                          maestrodan

                          OpenCL is working for me in blender now, with ubuntu 14.04.2(kernel and xorg form 14.10), and I can use it in blender for rendering, and in handbrake. But when I choose in blender opencl on cpu(choose AMD A6-5200 OpenCL device or together with other opencl devices) it's crushes. With 14.30 all was good.

                          If I try to test OpenCL in LibreOffice, it's gives errors in all colums.

                          Strange, that now I have install a new 14.04.2 ubuntu from 0 to my laptop, with fglrx15.200, and In this OS OpenCL doesn't works(blender doesn't show opencl devices, and handbrake too). But in my main OS, it's still works.

                          About fglrx-why there is 15.200 on ubuntu repositories now, but only 14.12 on amd website?

                          Abut opencl-I can give you a clinfo information.

                            • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                              dipak

                              Regarding the catalyst, I really don't know why the mismatch is. I've asked the concerned team for more information. Once I get any reply, I'll share with you.

                              However, as I've been told, catalysts from AMD site are preferred one, if available. Did you ever try this package Desktop ?

                              Another fact which I came to know that Ubuntu 14.04.2 comes with an open source driver also known as Radeon driver. That open source driver does not have OpenCL.

                               

                              Regards,

                                • Re: OpenCL on 14.12 Omega driver crack's OpenCL on linux
                                  maestrodan

                                  On that page latest version is 14.12, and in ubuntu repos, latest fglrx package is 15.200.

                                  It's not stock opensource driver, installed in ubuntu by default, it's fglrx package from stock repos, and OpenCL is working for it(in Blender and Handbrake, at least)

                                  I don't know, will it work on ubuntu 14.04.2 with fglrx 14.501 from AMD website(catalyst 14.12), but some games like The Witcher 2 had some bugs on that driver, and I can't use OpenCL on it before.