[GHC] #8279: bad alignment in code gen yields substantial perf issue

[GHC]

#8279: bad alignment in code gen  yields substantial perf issue
--------------------------------------------+------------------------------
        Reporter:  carter                   |            Owner:
            Type:  bug                      |           Status:  new
        Priority:  highest                  |        Milestone:
       Component:  Compiler                 |          Version:  7.7
      Resolution:                           |         Keywords:
Operating System:  Unknown/Multiple         |     Architecture:
 Type of failure:  Runtime performance bug  |  Unknown/Multiple
       Test Case:                           |       Difficulty:  Unknown
        Blocking:                           |       Blocked By:
                                            |  Related Tickets:
--------------------------------------------+------------------------------

Comment (by simonmar):

 I've noticed things like this in the past.  One hypothesis is that when
 the code is tightly packed together the branch predictor doesn't work so
 well, but that's just a guess.

 The way forward is to do systematic measurements with all of nofib,
 measuring performance counters and code size with various alignment
 strategies.  Also someone could thoroughly read the latest Intel
 optimization guides and see if we're doing the right things.

-- 
Ticket URL: <http://ghc.haskell.org/trac/ghc/ticket/8279#comment:6>
GHC <http://www.haskell.org/ghc/>
The Glasgow Haskell Compiler