Showing results for 
Search instead for 
Did you mean: 

Archives Discussions

Adept I

Beginning with Parallel Programming

Hello everyone, I am new to parallel programming. But till now I have discovered that

we can use GPUs to enhance performance of computing as GPUs can have 100s of cores.

As in market there are two major vendors and developers of GPUs i.e NIVIDIA and AMD

.NIVIDIA makes use of CUDA whereas AMD uses streams. OpenCl(Open Computing Language) can be used on both. As I have HP laptop having GPU of AMD (Radeon HD 6470). I am using AMD APP SDK. But I am not sure about GPU I am using will support or not.It is not in the list of supported GPUs on AMD website.

Can I start parallel programming without GPU? I am using Fedora Linux for same purpose. Can anyone help in this regard?

7 Replies

Re: Beginning with Parallel Programming

AMD Supports OpenCL for your GPU . Additionally, you can use our OpenCL CPU implementation.

To discover available devices call from the command shell: clinfo .

Adept I

Re: Beginning with Parallel Programming

thx for your reply . I am using Fedora (3.3.2-6-fc16.x86_64). On this operating system

I am unable to install ATI Catalyst driver provided on this site which is prerequisite for installing AMD APP SDK.

Adept I

Re: Beginning with Parallel Programming

Thx Thx Thx.

I have installed AMD APP SDK and after running clinfo command got this o/p:

[root@localhost preetgill]# clinfo

Number of platforms:                 1

  Platform Profile:                 FULL_PROFILE

  Platform Version:                 OpenCL 1.1 AMD-APP (831.4)

  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:                 1

  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:                 800Mhz

  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:                     32768

  Global memory size:                 4092624896

  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:                     0x7f3f21715120

  Name:                         Intel(R) Core(TM) i3-2330M CPU @ 2.20GHz

  Vendor:                     GenuineIntel

  Device OpenCL C version:             OpenCL C 1.1

  Driver version:                 2.0

  Profile:                     FULL_PROFILE

  Version:                     OpenCL 1.1 AMD-APP (831.4)

  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

But I think It has not detected GPU.

Can you plz help me again.

Adept II

Re: Beginning with Parallel Programming

Do you have the drivers installed for your GPU? Also, are you doing this locally or over ssh? You have to do some magic for the latter.


Re: Beginning with Parallel Programming

AMD OpenCL SDK is officially supported on Ubuntu 11.04 ,Red Hat 6.* and OpenSuse 11.* .

However, you can look up: for Fedora related installation steps and notes.


Re: Beginning with Parallel Programming

AMD Catalyst 12.4 Linux driver (which includes the OpenCL runtime) now comes with Ubuntu 12.04 early look support and openSuse 12.1 production support.  Since the SDK is a couple months old it would be best to first install the SDK and then install the newest driver to get the most up-to-date OpenCL runtime.

Adept I

Re: Beginning with Parallel Programming

Yep I have followed the instruction give over here:

and have installed akmod-catalyst, xorg-x11-drv-catalyst and xorg-x11-drv-catalyst-libs

on my system. But after reboot system doesn't load GUI back. It is showing black screen with msgs:

Started Avahi ,DNS/DS-SDL  --------------------------  [ok]

------------------------------------------------------------- [ok]




Failed to start LSB: Build and install new kmods from akmod packages\See

Systemctl status akmods Service" for detail                      [failed]

Send mail....................................................................... [OK]