Re: architectural goals, Byte Addressability And Beyond

Terje Mathisen <terje.mathisen@tmsw.no> schrieb:

Thomas Koenig wrote:

Anton Ertl <anton@mips.complang.tuwien.ac.at> schrieb:
 

It's still marketing.  I have listened to several talks about
converting S/360 programs to C code that can be run on arbitrary
hardware, and IBM's audience hears about such things, too, so IBM's
sales force has to provide reasons for not jumping ship.  And all
these new features that sound like they are useful are such reasons.
Things like decimal FP and CU14.
>
The fact that these feature provide no actual benefit is their best
property:

 
No actual benefit?
 
If you make such a strong statement, I assume that you have done a
thorough analysis of this feature for typical mainframe workloads
and can support your claims with benchmarks.
 
Care to show exactly what you did, and what the results were?
 

I am pretty sure Anton is correct, at least for data residing in RAM,
since any reasonably efficient sw algorithm to do the same thing should
be able to keep up with memory bandwidth, right?

I'm not sure that would be the case for text containing some
non-ASCII characters, where you cannot predict branches well
(consider Å, Ø and Æ, which together appear to make up around
a bit more than 2.5% according to a random statistic I just
grabbed off the Internet), or ä, ö and ü which have around 1.5%
occurrence together.

In Chinese or Japanese text, I assume the spaces and punctuation
are 7-bit ASCII (are they, actually?) so things would be even
worse for branch prediction.