Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
1) optimize scom with no rc and directly inline asm(saved for 2K :D) 2) initialize all variables(doesnt really save size, just good guideline) 3) loop both cores when block is big and redundant(saved only 50B -_-) (50b for 3 blocks, each block saves 17b, or 4 instructions) 4) improvement on history update(saved 500B more :)) 5) functionalize the exit catchup routine which is identical twice (this back fired and cost us 100B :() 6) functionalize the eval eimr override macro which is identical twice (saved 130B :|) 7) finally the saving is about 2728B on CME 8) apply history update tech to sgpe, found bug in the tech, fixed (but our saving is back to ~2500B) 9) clean up sgpe redundent ex branching code (same as cme saved only about ~60B) 10) rebase Change-Id: Id94e5d8b0e51868bc058723c279b590f01e7fc71 Original-Change-Id: I3664d6a2dcab85f896a583852afde948e635bd02 Reviewed-on: http://ralgit01.raleigh.ibm.com/gerrit1/34777 Tested-by: Jenkins Server <pfd-jenkins+hostboot@us.ibm.com> Tested-by: PPE CI <ppe-ci+hostboot@us.ibm.com> Reviewed-by: AMIT KUMAR <akumar3@us.ibm.com> Reviewed-by: Gregory S. Still <stillgs@us.ibm.com> Reviewed-by: Jennifer A. Stofer <stofer@us.ibm.com>
- Loading branch information