Re:Intel i7 loop performance anomaly
by rayiner on Tuesday December 03, 2013 @10:56PM
(#6844952)
The 18-uop limit comes from how Sandy Bridge (and Haswell) handle the decoded instruction cache. A 32-byte line of the instruction cache can map up to 3 lines in the u-op cache, each of which can hold 6 instructions. Any 32-byte line of instructions that decodes to more than 3x6 = 18 u-ops cannot be stored in the u-op cache.
[ Parent
| on HN ]
There are no comments on this comment yet.