OpenCL* for CPU
Ask questions and share information on Intel® SDK for OpenCL™ Applications and OpenCL™ implementations for Intel® CPU.
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.
1698 Discussions

New release: Intel® SDK for OpenCL* Applications XE 2013 R3


Happy New Year!

Intel has announced that Release 3 (R3) of the Intel® SDK for OpenCL* Applications 2013 XE now adds GOLD support for Microsoft Windows* Operating Systems on Intel® Xeon Phi™ coprocessors.  The SDK continues to support Red Hat Linux* and SUSE Linux*. Available as a free download, the XE version provides a comprehensive application development environment that supports the full OpenCL 1.2 standard on platforms with Intel® Xeon® processors and Intel Xeon Phi coprocessors. The XE version targets at developers of highly parallel applications including High Performance Compute (HPC), workstations, and data analytics. 

XE version page:

Please note that installation of MPSS ver 3.1.1 is needed (when using Xeon Phi):

The main improvements in this release are:

  • Gold support for OpenCL 1.2 using Intel Xeon Phi coprocessor on Windows* OS.
  • Performance improvements:
    • High performance implementation of clEnqueueFillBuffer() is included in this release
    • Execution overhead has been improved. Tiny workgroups now execute significantly faster.
    • Better vectorization of 8-bit and 16-bit data types (BYTE, WORD)
    • Improved the performance of out-of-order queues
  • Fixed kernel compilation crashes under debug and profiling modes
  • Two new Xeon Phi performance related environment variables. Recommended settings below (details in the user guide):​
    • CL_CONFIG_MIC_DEVICE_2MB_POOL_INIT_SIZE_MB = [Your total required buffers memory (peak)]


     Arik Narkis

0 Kudos
0 Replies