More information about the Intel implicit vectorization module for OpenCL applications is available below.
What to know more? follow us at@IntelOpenCL
The Intel OpenCL SDK features an implicit vectorization module which boosts the performance of applications. The Implicit CPU vectorization module seamlessly compiles the users 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. Read Nadav Rotem blog here
Intels OpenCL implicit vectorization module is based on the LLVM compiler toolkit. We contributed major changes to the open source community for better support of Intel architecture:http://blog.llvm.org/2011/12/llvm-31-vector-changes.html
Check the OpenCL implicit vectorization module talk from the latest LLVM developers conference:http://youtu.be/QsoLyvvhRuc