Update 14.1 changes include:
- Support for OpenCL Standard Portable Intermediate Representation (SPIR) 1.2 consumption.
- Intel® Manycore Platform Software Stack (Intel® MPSS) 3.2 and 3.2.3 support.
NOTE: Using OpenCL Runtime 14.1 with MPSS 3.2.1 is not recommended, as this combination introduces stability issues.
- Performance improvements:
- Faster execution of code dominated by statically diverging dynamically uniform branches
- More efficient event traversing algorithm
- NO_DMA mode is default, which improves buffer creation speed (not a preview feature anymore)
- Improved device side memory pool control
- CPU only: Starting with this release, kernel binary is the very final machine code. This enables creating the kernel binary offline and distributing it with the application machine code binary. This also eliminates the compilation time at the end-use product (clCreateProgramWithBinary)
- Bug fixed (for Intel® Xeon Phi™ coprocessors only): Compilation crash when a struct is defined globally in the CL file.
- New performance-related environment variables on Intel Xeon Phi –see the user guide for details
CL_CONFIG_MIC_DEVICE_FORCE_BUFFERS_PINNING_ON_HOST
CL_CONFIG_MIC_DEVICE_2MB_POOL_FINI_SIZE_MB
CL_CONFIG_MIC_DEVICE_2MB_POOL_INIT_SIZE_MB
- Added 32-bit version of the runtime for Windows OS.
- Added OpenCL CPU device support on Intel Core™ processors.