On Tue, Aug 28, 2012 at 11:39 AM, Kirk Wolf wrote, in part:
>assume that the CPACF Co-processor assists with UTF8-16 conversion
>nstructions, as well as compression instructions.   I guess that somehow
>IBM considers this "crypto" since its on the crypto co-processor.

Right. The EC12 Technical *Intro* (as oppposed to *Guide*) at 
http://www.redbooks.ibm.com/redbooks.nsf/RedpieceAbstracts/sg248050.html?Open 
says in part:
New hardware support for Unicode UTF8<>UTF16 bulk conversions (CU12/CU21)

So it appears that the point here is "offload some fiddly bit-twiddling to the 
cheaper MIPS". I'd guess that it has to be more than some number of bytes to 
make that worthwhile, with the overhead added by the CEX call!

My motto: "CEX is not always good" :)
--
...phsiii

Phil Smith III
[email protected]<mailto:[email protected]>
Voltage Security, Inc.
www.voltage.com<http://www.voltage.com/>
(703) 476-4511 (home office)
(703) 568-6662 (cell)


----------------------------------------------------------------------
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO IBM-MAIN

Reply via email to