-----------------------<snip>--------------------:
I understand that LA can cause an "address generation interrupt" in
the pipeline on some "z" models and as a rule of thumb, LHI is better
to use when you can. Similar nasties occur with things like BCTR Rx,0
(typically used to decrement a register), such that AHI Rx,-1 tends to
work better. (In the early look-ahead processing that occurs in the
pipeline, the never-branch nature of the BCTR isn't (yet) recognized,
only that there is a branch. This stalls the pipeline's pre-processing
and parallel execution capabilities until the full nature of the branch
is interpreted.
----------------------<unsnip>-------------------
I should think thqat this form of LA shouldn't cause the
address-generation interrupt, since there
are no actual register references. Oh, well.....
Can anyone help me find more details on the "z" architecture so I can
read up on this sort of thing?
----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html
