Auto vectorization of OpenCL code with the Intel OpenCL SDK

Started by Stefan, January 31, 2012, 12:58:53 AM

Previous topic - Next topic

0 Members and 1 Guest are viewing this topic.


QuoteThe IntelĀ® OpenCL* SDK features an implicit vectorization module which boosts the performance of applications. The implicit CPU vectorization module seamlessly compiles the user's OpenCL* kernels to fully utilize the full 8 wide floating point SIMD processing, boosting the performance of user code without user intervention. The implicit vectorization module uses state-of-the-art vectorization algorithms based on up-to-date compiler research to ensure that the code performs.
The IntelĀ® OpenCL* SDK implicit vectorization module is based on the LLVM compiler toolkit.


Wow... everyone is now using LLVM for OpenCL (and CUDA).