Dana Mitchell wrote:
>They probably already have a nice z emulator that runs on power hardware,  
>just not the software licensing in order to run z/OS on it.

zPDT used to support Power, but appears not to any more—none of the literature 
admits it exists.

As for it eating into z hardware sales—yes, this has been the traditional 
problem: IBM seems convinced that people on z will never leave, and 25 years of 
attrition hasn’t convinced them otherwise. Many of us in the community would 
like to see them encourage small systems, on the “from tiny acorns, mighty oaks 
do grow” theory. Instead, the 64-bit MP3000 follow-on was killed, and zPDT/zD&T 
are redheaded stepchildren. I despair for IBM.

John McKown wrote:
>​I knew that the IBMi software runs on Power, but I thought it was a
>"special for IBMi" version. That is, if you were only going to run AIX or
>Linux, you could get a Power system which would not run IBMi.​ But I
>probably misunderstood what the document was saying.

I’m sure this is not the case, because the IBM i OS and Linux can coexist on 
the same hardware.

A final note, for the record: the article is typical El Reg garbage in that it 
completely misrepresents Moore’s Law anyway. The law is not about performance, 
it’s an observation that “the number of transistors in a dense integrated 
circuit doubles approximately every two years.” That end was seen coming long 
ago, has been wide discussed for years. The fact that execution optimization 
techniques may be reaching (or have passed) another limit is a different point 
entirely.

It’s sort of like bemoaning the fact that automotive fuel economy hasn’t 
changed a lot in the last 20 years, while missing the point that cars are more 
reliable and much more powerful than they used were (ok, sort of the opposite 
point, but analogous): they’re *different* aspects—often intertwined, but far 
from the same.
--
...phsiii

Phil Smith III
Senior Architect & Product Manager, Mainframe & Enterprise
Distinguished Technologist
Micro Focus (Voltage)

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

Reply via email to