[Bug binutils/7005] New: Wrongly interpretation of branch hint codes for powerpc

[hellwolf dot misty at gmail dot com]

The binutils 2.18 for powerpc generate/output these codes:

  10:   40 82 00 00     bne-    10 <atomic_modify+0x10>
or
  10:   40 a2 00 00     bne+    10 <atomic_modify+0x10>


On IBM's website :
http://publib.boulder.ibm.com/infocenter/systems/index.jsp?topic=/com.ibm.aix.aixassem/doc/alangref/about.htm&tocNode=int_378

I got these information:

40 a2 -> (0100 00)(00 1_01_)0 .... (in binutils, it's interpreated as bne+)
40 82 -> (0100 00)(00 1_00_)0 .... (in binutils, it's interpreated as bne-)

Of which, the second group field is BO code, which means:

001at   Branch if the condition is False.

at field is(from IBM site, which apparently has an errata):
at      Hint
00      No hint is given.
01      Reserved
01      The branch is very likely not to be taken.
11      The branch is very likely to be taken.

So, who's right?

-- 
           Summary: Wrongly interpretation of branch hint codes for powerpc
           Product: binutils
           Version: 2.18
            Status: NEW
          Severity: normal
          Priority: P2
         Component: binutils
        AssignedTo: unassigned at sources dot redhat dot com
        ReportedBy: hellwolf dot misty at gmail dot com
                CC: bug-binutils at gnu dot org


http://sourceware.org/bugzilla/show_bug.cgi?id=7005

------- You are receiving this mail because: -------
You are on the CC list for the bug, or are watching someone who is.