Intel® Cilk™ Plus – an extension to the C and C++ languages to support data and task parallelism – is being deprecated in the 2018 release of Intel® Software Development Tools. It will remain in deprecation mode in the Intel® C++ Compiler for an extended period of two years. It is highly recommended that you start migrating to standard parallelization models such as OpenMP* and Threading Building Blocks (TBB). For more information see Migrate Your Application to use OpenMP* or TBB Instead of Intel® Cilk™ Plus. Research into Cilk technology continues at MIT's Cilk Hub.
Intel® Cilk™ Plus is the easiest, quickest way to harness the power of both multicore and vector processing.
Intel Cilk Plus is an extension to the C and C++ languages to support data and task parallelism.
High Performance:
Easy to Learn:
Easy to Use:
Build 4501 of the Intel Cilk Plus SDK was released on Monday, 01-23-2017. This version includes 64-bit Cilk screen/view binaries for Linux* and OS X* operating systems.
A new version of open-source Intel Cilk Plus runtime library (build 4467) is available for download now. This version contains build fix for Cygwin* and SPARC* support submitted by the community.
Build 4421 of the Intel Cilk Plus SDK was released on Wednesday, 11-11-2015. This version supports the latest versions of Linux*, OS X*, and Windows* operating systems.
Hello~I have a problem, and i need some help.
I encountered this problem while compiling WRF. The error log is as follows:
../main/module_wrf_top.f90(768): error #5082: Syntax error, found 'DO' when expecting one of: PRIVATE FIRSTPRIVATE REDUCTION COLLAPSE LASTPRIVATE SHARED DEFAULT LINEAR COPYIN ...
DO ij = 1, head_grid%num_tiles
---^
../main/module_wrf_top.f90(768): error #5082: Syntax error, found ',' when expecting one of: <END-OF-STATEMENT> ;
DO ij = 1, head_grid%num_tiles
------------^
../main/module_wrf_top.f90(766): error #7644: The statement or directive following this OpenMP* directive is incorrect.
!$OMP PARALLEL DO &
Can someone help me?
I saw the article/guide to translate code from cilk plus to TBB or openMP. That's all fine, but the article ignores the concept of Array Notations.
Now, with the deprecation of Cilk Plus, I am wondering was is Intel's take on how we should translate code using array notations to code that doesn't use it. And of course, to keep the same performance as before.
Does simple 'for' loops around the data, coupled with some #pragmas, the preferred solution? Or should be try to go for AVX intrinsics?
