- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
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?
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Yes, using "for" loops and some type of user hints (e.g., OpenMP simd construct) with an appropriate code generation option (e.g., for AVX, AVX2, AVX512) is a good starting point in my opinion.
![](/skins/images/B7BA37F9CE4B52FF7CAE1FB0388839C8/responsive_peak/images/icon_anonymous_message.png)
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page