Intel i7 loop performance anomaly

Re:Intel i7 loop performance anomaly by stingraycharles on Tuesday December 03, 2013 @03:10PM (#6842830)

That's is already being discussed in the comments, and the author claims NOOP-aligning the code has no effect.

[ Parent | on HN ]

Re:Intel i7 loop performance anomaly by rayiner on Tuesday December 03, 2013 @03:12PM (#6842840)

You wouldn't NOOP-align the loop header, but instead replace the CALL instruction in the middle of the loop with an equivalent sequence of NOOPs. This would increase the distance between the loop header and the backward jump.

[ Parent | on HN ]