- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello,
I've got strange behavior of Intel C++ Compiler on linux. The problem is reproduce in online compiler godbolt on a small part. Inv value should be inverse of work, but with Intel it is not the case.
Problem solves if I add "-fp-model except".
I seems that lines 64-67 confuse compiler. There are no such lines there in work code, but the problem is the same.
Thanks
Aleksey
- Tags:
- CC++
- Development Tools
- Intel® C++ Compiler
- Intel® Parallel Studio XE
- Intel® System Studio
- Optimization
- Parallel Computing
- Vectorization
Link Copied
2 Replies
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
I've reported this bug ( internal #CMPLRIL0-31929) to the Developer. In the mean time, can you use -fp-model except for a workaround?
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Thanks for report, I hope it will be fixed in near updates.
Yes, but it's hard to say if it will be any faster than gcc. Requires some investigations.

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