OpenCL* for CPU
Ask questions and share information on Intel® SDK for OpenCL™ Applications and OpenCL™ implementations for Intel® CPU
Announcements
This forum covers OpenCL* for CPU only. OpenCL* for GPU questions can be asked in the GPU Compute Software forum. Intel® FPGA SDK for OpenCL™ questions can be ask in the FPGA Intel® High Level Design forum.
1663 Discussions

Dependency of Intel OpenCL runtime for Linux Ubuntu ( CPU device only ) on lsb-core package

SergeyKostrov
Valued Contributor II
551 Views
*** Dependency of Intel OpenCL runtime for Linux Ubuntu ( CPU device only ) on lsb-core package ***
0 Kudos
11 Replies
SergeyKostrov
Valued Contributor II
551 Views
During installation of Intel OpenCL runtime ( opencl_runtime_16.1.1_x64_ubuntu_6.4.0.025.tgz ) on Linux Ubuntu 16.04 LTS 64-bit in a virtualized environment of VMware Workstation 12 Player I was notified that there is a missing dependency on lsb-core package. I've terminated installation, installed lsb-core package, rebooted Linux Ubuntu, resumed installation, but the notification about missing lsb-core package was displayed again. I've continued installation and Intel OpenCL runtime was successfully installed. There are a couple of questions: - Could you explain why that dependency on lsb-core package is needed? - It looks like there is a bug in a script of the installer when packages consistency is verified since the message about missing lsb-core package did not disappear even if it was installed before. Could you check it? - Are there any plans to release an updated Intel OpenCL runtime for Linux Ubuntu 16.04 LTS 64-bit? Right now the installer informs that only 14.04 version of Linux Ubuntu is supported. Note: opencl_runtime_16.1.1_x64_ubuntu_6.4.0.025.tgz ( CPU devices only ) was used.
SergeyKostrov
Valued Contributor II
551 Views
I've finally completed OpenCL environment setups on Linux Ubuntu and two platforms, Intel OpenCL and AMD APP SDK, currently displayed by clinfo utility...
SergeyKostrov
Valued Contributor II
551 Views
[ clinfo - Part 1 ] ubuntu@ubuntu-vm:~$ clinfo Number of platforms: 2 Platform Profile: FULL_PROFILE Platform Version: OpenCL 1.2 LINUX Platform Name: Intel(R) OpenCL Platform Vendor: Intel(R) Corporation Platform Extensions: cl_khr_icd 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_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_fp64 Platform Profile: FULL_PROFILE Platform Version: OpenCL 1.2 AMD-APP (1214.3) 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
SergeyKostrov
Valued Contributor II
551 Views
[ clinfo - Part 2 ] Platform Name: Intel(R) OpenCL Number of devices: 1 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 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: 2800Mhz Address bits: 64 Max memory allocation: 6316211200 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: 25264844800 Constant buffer size: 131072 Max number of constant args: 480 Local memory type: Global Local memory size: 32768 Kernel Preferred work group size multiple: 128 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: Yes Profiling : Yes Platform ID: 0x0000000000cf1b60 Name: Intel(R) Core(TM) i7-3840QM CPU @ 2.80GHz Vendor: Intel(R) Corporation Device OpenCL C version: OpenCL C 1.2 Driver version: 1.2.0.25 Profile: FULL_PROFILE Version: OpenCL 1.2 (Build 25) Extensions: cl_khr_icd 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_byte_addressable_store cl_khr_depth_images cl_khr_3d_image_writes cl_intel_exec_by_local_thread cl_khr_spir cl_khr_fp64
SergeyKostrov
Valued Contributor II
551 Views
[ clinfo - Part 3 ] Platform Name: AMD Accelerated Parallel Processing Number of devices: 1 Device Type: CL_DEVICE_TYPE_CPU Device ID: 4098 Board name: Max compute units: 8 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: 2790Mhz Address bits: 64 Max memory allocation: 6316211200 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: 25264844800 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: 0x00007fe6f0de0fc0 Name: Intel(R) Core(TM) i7-3840QM CPU @ 2.80GHz Vendor: GenuineIntel Device OpenCL C version: OpenCL C 1.2 Driver version: 1214.3 (sse2,avx) Profile: FULL_PROFILE Version: OpenCL 1.2 AMD-APP (1214.3) 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
Jeffrey_M_Intel1
Employee
551 Views

Thanks for this info.  Very interesting to see this comparison!

At this time Ubuntu 14.04 is the only validated Ubuntu for this package.  I have not seen any plans or timelines for Ubuntu 16.04 support across the OpenCL SDK, cpu-only runtime, standalone Gen graphics, or Media Server Studio.  Let me check for more info.  I'll post here if there are any updates.   

SergeyKostrov
Valued Contributor II
551 Views

I've verified a couple of tests already and results for a MemoryOptimization test, when Intel OpenCL platform is selected, don't look right. That is, bandwidth numbers are too high:

OclTest.MemoryOptimizations.png

 

SergeyKostrov
Valued Contributor II
551 Views

Here is the same test on Windows 7 for NVIDIA platform:

C:\...AMD\AMD APP SDK\2.9\Samples\OpenCL\Bin\x86_64>MemoryOptimizations.exe
Platform 0 : Intel(R) Corporation
Platform 1 : NVIDIA Corporation
Platform found : NVIDIA Corporation

Selected Platform Vendor : NVIDIA Corporation
Device 0 : Quadro K1000M Device ID is 00000000003F6A60
-----------------------------------------
Copy 1D FastPath        : 17.4474 GB/s
-----------------------------------------
Copy 1D CompletePath    : 16.6784 GB/s
-----------------------------------------
Copy 2D 32-bit (64x2)   : 16.7215 GB/s
Copy 2D 128-bit (64x2)  : 26.2851 GB/s
-----------------------------------------
Copy 2D 32-bit (64x4)   : 16.441 GB/s
Copy 2D 128-bit (64x4)  : 26.0899 GB/s
-----------------------------------------
Copy 2D 32-bit (8x8)    : 7.69187 GB/s
Copy 2D 128-bit (8x8)   : 22.6039 GB/s
-----------------------------------------
Copy 2D 32-bit (256x1)  : 16.5217 GB/s
Copy 2D 128-bit (256x1) : 26.3462 GB/s
-----------------------------------------
Copy 2D 32-bit (32x2)   : 9.48022 GB/s
Copy 2D 128-bit (32x2)  : 23.4351 GB/s
-----------------------------------------
Copy 2D 32-bit (64x1)   : 9.52661 GB/s
Copy 2D 128-bit (64x1)  : 22.8418 GB/s
-----------------------------------------
Copy 2D 32-bit (16x16)  : 14.9595 GB/s
Copy 2D 128-bit (16x16) : 26.0934 GB/s
-----------------------------------------
Copy 2D 32-bit (16x4)   : 8.69297 GB/s
Copy 2D 128-bit (16x4)  : 24.4265 GB/s
-----------------------------------------
Copy 2D 32-bit (1x64)   : 1.95445 GB/s
Copy 2D 128-bit (1x64)  : 7.63334 GB/s
-----------------------------------------
Copy 1D 128-bit         : 22.8878 GB/s
-----------------------------------------
NoCoal Copy 1D 32-bit   : 9.81886 GB/s
-----------------------------------------
Split Copy 1D 32-bit    : 8.7023 GB/s
-----------------------------------------
HasLocalBankConflicts 32-bit    : 8.80025 GB/s
-----------------------------------------
NoLocalBankConflicts 32-bit     : 84.4067 GB/s

As you see peak performance numbers are around 25 GB/s.

 

SergeyKostrov
Valued Contributor II
551 Views
Unfortunately, MemoryOptimizations test on Windows 7 for Intel OpenCL platforms failed: ... C:\...AMD\AMD APP SDK\2.9\Samples\OpenCL\Bin\x86_64>MemoryOptimizations.exe -p 0 Platform 0 : Intel(R) Corporation Platform 1 : NVIDIA Corporation Selected Platform Vendor : Intel(R) Corporation Device 0 : Intel(R) HD Graphics 4000 Device ID is 000007FEF5310300 Error: clGetDeviceIDs(CL_DEVICE_DOUBLE_FP_CONFIG) failed Error code : CL_INVALID_VALUE Location : ../../../../include/SDKUtil\CLUtil.hpp:1904 Error: SDKDeviceInfo::setDeviceInfo() failed Location : MemoryOptimizations.cpp:187 ...
SergeyKostrov
Valued Contributor II
551 Views
>>...Let me check for more info. I'll post here if there are any updates... Thank you. Please review a dependency on lsb-core package as well.
SergeyKostrov
Valued Contributor II
551 Views
>>- Could you explain why that dependency on lsb-core package is needed? On another Linux Ubuntu 16.04 LTS computer I didn't do any 'apt' updates / installs related to lsb-core package and Intel OpenCL runtime ( opencl_runtime_16.1.1_x64_ubuntu_6.4.0.025.tgz ) was successfully installed. So far I don't see any runtime problems with OpenCL test applications that use Intel OpenCL CPU-only platform.
Reply