Archives Discussions

[kbentley57]

I'm trying to learn the OpenCL language with C++, and I'm having a little trouble getting started.  I've purchased a machine to start developing natively on, with an A10 5800K as the APU.  I've downloaded the latest AMDAPP sdk,  and have installed the drivers in Ubuntu's repos. (more on my software later down).  I first had issues compiling the samples, but I sorted that out with another post, adding #include <unist.h> in the samples/opencl/SDKUtil/include/SDKCommon.hpp file.  I'm now able to compile the samples, and I can run clinfo, as well as HelloCL.  The output are below:

clinfo

kyle@lal:/opt/AMDAPP/samples/opencl/bin/x86_64$ clinfo

Number of platforms:                 1

  Platform Profile:                 FULL_PROFILE

  Platform Version:                 OpenCL 1.2 AMD-APP (923.1)

  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

  Device ID:                     4098

  Board name:                     AMD Radeon HD 7660D

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

  Max compute units:                 6

  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:             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

  Native vector width char:             16

  Native vector width short:             8

  Native vector width int:             4

  Native vector width long:             2

  Native vector width float:             4

  Native vector width double:             0

  Max clock frequency:                 800Mhz

  Address bits:                     32

  Max memory allocation:             134217728

  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:             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:                     None

  Cache line size:                 0

  Cache size:                     0

  Global memory size:                 134217728

  Constant buffer size:                 65536

  Max number of constant args:             8

  Local memory type:                 Scratchpad

  Local memory size:                 32768

  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 properties:                

    Out-of-Order:                 No

    Profiling :                     Yes

  Platform ID:                     0x00007fab7abbc140

  Name:                         Devastator

  Vendor:                     Advanced Micro Devices, Inc.

  Device OpenCL C version:             OpenCL C 1.2

  Driver version:                 CAL 1.4.1741

  Profile:                     FULL_PROFILE

  Version:                     OpenCL 1.2 AMD-APP (923.1)

  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_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_popcnt

  Device Type:                     CL_DEVICE_TYPE_CPU

  Device ID:                     4098

  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:             4

  Preferred vector width double:         0

  Native vector width char:             16

  Native vector width short:             8

  Native vector width int:             4

  Native vector width long:             2

  Native vector width float:             4

  Native vector width double:             0

  Max clock frequency:                 3800Mhz

  Address bits:                     64

  Max memory allocation:             2147483648

  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:             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:                 3834286080

  Constant buffer size:                 65536

  Max number of constant args:             8

  Local memory type:                 Global

  Local memory size:                 32768

  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 properties:                

    Out-of-Order:                 No

    Profiling :                     Yes

  Platform ID:                     0x00007fab7abbc140

  Name:                         AMD A10-5800K APU with Radeon(tm) HD Graphics 

  Vendor:                     AuthenticAMD

  Device OpenCL C version:             OpenCL C 1.2

  Driver version:                 2.0 (sse2,avx,fma4)

  Profile:                     FULL_PROFILE

  Version:                     OpenCL 1.2 AMD-APP (923.1)

  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_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_popcnt

HelloCL

kyle@lal:/opt/AMDAPP/samples/opencl/bin/x86_64$ ./HelloCL

HelloCL!

Getting Platform Information

Creating a context AMD platform

Getting device info

Loading and compiling CL source

Running CL program

Done

Passed!

It appears that everything is installed correctly.  However, when I try to run any other sample, I get an error; here is some output of two of the compiled examples:

kyle@lal:/opt/AMDAPP/samples/opencl/bin/x86_64$ ./MersenneTwister

Platform 0 : Advanced Micro Devices, Inc.

Platform found : Advanced Micro Devices, Inc.

Selected Platform Vendor : Advanced Micro Devices, Inc.

Device 0 : Devastator Device ID is 0xb8d460

Error: clCreateCommandQueue failed. Error code : CL_OUT_OF_HOST_MEMORY

kyle@lal:/opt/AMDAPP/samples/opencl/bin/x86_64$ ./SimpleGL

Platform 0 : Advanced Micro Devices, Inc.

Platform found : Advanced Micro Devices, Inc.

Selected Platform Vendor : Advanced Micro Devices, Inc.

Device 0 : Devastator Device ID is 0x1d92660

Number of displays 1

glXCreateContextAttribsARB 0x7f164889a000

Number of interoperable devices 1

Interop Device ID is 0x1d92660

libGL error: failed to load driver: swrast

libGL error: Try again with LIBGL_DEBUG=verbose for more details.

Error: clCreateCommandQueue failed. Error code : CL_OUT_OF_HOST_MEMORY

Location : SimpleGL.cpp:719

I'm guessing I'm running out of memory, or at least that is what the error code would lead me to believe.  I'm sure that I have enough free memory in the system to run these programs, so there must be something else software related causing the error.

My hardware specs:

kyle@lal:/opt/AMDAPP/samples/opencl/bin/x86_64$ sudo lshw -sanitize -short

H/W path      Device     Class       Description

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

                         system      To Be Filled By O.E.M. (To Be Filled By O.E.M.)

/0                       bus         FM2A75M-DGS

/0/0                     memory      64KiB BIOS

/0/8                     memory      4GiB System Memory

/0/8/0                   memory      2GiB DIMM DDR3 Synchronous 933 MHz (1.5 ns)

/0/8/1                   memory      2GiB DIMM DDR3 Synchronous 933 MHz (1.5 ns)

/0/f                     memory      192KiB L1 cache

/0/10                    memory      4MiB L2 cache

/0/16                    processor   AMD A10-5800K APU with Radeon(tm) HD Graphics

/0/100                   bridge      Family 15h (Models 10h-1fh) Processor Root Complex

/0/100/1                 display     Trinity [Radeon HD 7660D]

/0/100/1.1               multimedia  Advanced Micro Devices [AMD] nee ATI

/0/100/5                 bridge      Family 15h (Models 10h-1fh) Processor Root Port

/0/100/5/0    eth0       network     RTL8111/8168B PCI Express Gigabit Ethernet controller

/0/100/10                bus         Hudson USB XHCI Controller

/0/100/10.1              bus         Hudson USB XHCI Controller

/0/100/11                storage     Hudson SATA Controller [AHCI mode]

/0/100/12                bus         Hudson USB OHCI Controller

/0/100/12.2              bus         Hudson USB EHCI Controller

/0/100/13                bus         Hudson USB OHCI Controller

/0/100/13.2              bus         Hudson USB EHCI Controller

/0/100/14                bus         Hudson SMBus Controller

/0/100/14.1              storage     Hudson IDE Controller

/0/100/14.2              multimedia  Hudson Azalia Controller

/0/100/14.3              bridge      Hudson LPC Bridge

/0/100/14.4              bridge      Hudson PCI Bridge

/0/100/14.5              bus         Hudson USB OHCI Controller

/0/101                   bridge      Family 15h (Models 10h-1fh) Processor Function 0

/0/102                   bridge      Family 15h (Models 10h-1fh) Processor Function 1

/0/103                   bridge      Family 15h (Models 10h-1fh) Processor Function 2

/0/104                   bridge      Family 15h (Models 10h-1fh) Processor Function 3

/0/105                   bridge      Family 15h (Models 10h-1fh) Processor Function 4

/0/106                   bridge      Family 15h (Models 10h-1fh) Processor Function 5

/0/1          scsi0      storage    

/0/1/0.0.0    /dev/sda   disk        64GB OCZ-VERTEX4

My Software:

Ubuntu 12.10 x86_64

gcc (Ubuntu/Linaro 4.7.2-2ubuntu1) 4.7.2

GNU Make 3.81

AMD APP SDK 2.7

AMD Linux Catalyst

Driver Packaging     9.00.11-120920a-147436C-ATI

2D Driver Version     9.0.2

Catalyst Control Center Version     2.17

RandR Version     1.3

     OpenGL Version 4.2.11903 Compatability Profile Context

I apologize for the lengthy post, but I wanted to include as much as info as possible up front.  If more software info is needed I'll be happy to post back.  Stated clearly, my question is why am I receiving the CL_OUT_OF_HOST_MEMORY errors on the compiled examples, and what action do I need to take to correct the errors?

Thanks in advance

Kyle Bentley

[kbentley57]

I think I may have found the solution to my problem.  In the BIOS, the amount of shared video memory was set to auto, and I had assumed it could be allocated on demand.  I'm still not sure if this is the case.  I changed the amount of shared memory to 512 MB, the max setting, and I was able to run all of the sample programs successfully.  That leads me to another question though; how much system ram can an APU allocate to the GPU?  I was under the assumption it could let it have all the RAM it wanted, but perhaps my motherboard is limiting me to 512 MB?

EDIT:  It turns out that I was running an early BIOS.  There was an updated BIOS released by AsRock just a few days ago that sets the correct limit to 2 GB.  Everything seems to be running fine now.  Marking as solved.

Message was edited by: Kyle Bentley