>>> On 5/25/2018 at 05:18 PM, Alan Altmark <[email protected]> wrote: 
-snip-
> The performance benefit of "compactness" isn't worth (IMO) the breakage 
> that comes with it.  Under laboratory conditions you can create 32-bit 
> programs with AM64.  They just can't (generally) deal with 31-bit APIs, 
> something they must use to get the benefit of 32-bit registers.  If I have 
> to jump through hoops to break my 4 GiB address space in half so I can 
> call 31-bit APIs, all the value leaks away.

OK, that's pretty much what I thought.  I couldn't understand why this was such 
a "big deal" if that was the only reason it was being promoted.  Not to mention 
that starting with SLES15, we'll no longer be shipping the 31/32-bit 
compatibility libraries on any of the architectures we support.  Kind of 
renders the whole thing moot from what I can see.

Thanks, Alan,


Mark Post

----------------------------------------------------------------------
For LINUX-390 subscribe / signoff / archive access instructions,
send email to [email protected] with the message: INFO LINUX-390 or visit
http://www.marist.edu/htbin/wlvindex?LINUX-390
----------------------------------------------------------------------
For more information on Linux on System z, visit
http://wiki.linuxvm.org/

Reply via email to