RFR(XS): 8141624: Limit calculation of pre loop during super word optimization is wrong

[Vladimir Kozlov]

Done.

On 11/9/15 1:58 PM, Volker Simonis wrote:
> Vladimir & Vladimir,
>
> thanks for the reviews!
>
> I'd still need a sponsor to push it trough JPRT :)
>
> Thanks,
> Volker
>
> On Monday, November 9, 2015, Vladimir Kozlov <vladimir.kozlov at oracle.com <mailto:vladimir.kozlov at oracle.com>> wrote:
>
>     Good.
>
>     Thanks,
>     Vladimir K
>
>     On 11/6/15 5:53 AM, Volker Simonis wrote:
>
>         Hi,
>
>         can I please have a second review and a sponsor for this fix
>         contributed by gunter.haug at sap.com:
>
>         http://cr.openjdk.java.net/~simonis/webrevs/2015/8141624/
>         https://bugs.openjdk.java.net/browse/JDK-8141624
>
>         The variable "MemNode* best_align_to_mem_ref" is hidden by a second
>         declaration of a variable with the same name in an inner block of the
>         function "SuperWord::find_adjacent_refs()". This leads to unaligned
>         accesses in generated code. While many platforms handle these
>         correctly (slower, though), Itanium and potentially other platforms
>         which don't allow unaligned access will crash.
>
>         Thank you and best regards,
>         Volker
>