This will be the final post in my planned short vectorization series. Although I reserve the right to post more on vectorization in the future!
In my last blog, I introduced the concept of vectorization, which is parallelism across data ele
One of my performance focus areas for this year is vectorization.
Any parent knows the simple rule: "Never help a child with a task he can succeed at himself. Otherwise you don't make any good for the kid, for you and for the whole planet".
In the previous blog, I explained two mini-kernels, the scatter and gather, which can be written up quickly and still have the benefits of compiler vectorization with Array Notations.
Intel® Software Development Emulator (released Jun 8, 2017)