[Beowulf] Stroustrup regarding multicore

[Ed Hill]

On Wed, 27 Aug 2008 10:00:19 -0400 "Perry E. Metzger" wrote:
> 
> Getting back to the original topic, a set of C++ classes that handled
> APL style array operations and automatically parallelized them on
> vector processors would be quite neat, and would actually be a
> legitimate use of C++ (unlike the very wide variety of illegitimate
> uses of the language.)


Hi Perry,

It seems that you have (some?) experience implementing compilers and I
have almost none.  So, I'm curious about what you consider "legitimate" 
and why.  And please understand -- I'm not trying to start arguments or 
change any opinions about language choices [ other than perhaps my own 
:-) ].

Just for perspective, I use C++ for more than half of my coding these days 
and the main reasons I tend to prefer it are:

  + I'm fond-ish of STL-style and "generic" coding approaches
  + the Boost libraries are very helpful (e.g., threads, 
    serialization, BGL, regexp, filesystem, ASIO, ...)
  + (re-)use of various computational geometry, signal/image 
    processing, and other libraries written in C and C++
  + its relatively easy to (re-)use Fortran routines written by 
    team members or 3rd parties
  + speed of execution and memory use
  + C++ compilers and libraries just keep improving (IMO)
  + have (over the years) grown accustomed to the syntax

If I had to sum it up in one line it would be: "I'm use C++ a lot because 
I just can't seem to find a superior replacement for it."

And I'm still (half-heart-edly) looking for replacements...

Ed

-- 
Edward H. Hill III, PhD  |  ed at eh3.com  |  http://eh3.com/
-------------- next part --------------
A non-text attachment was scrubbed...
Name: signature.asc
Type: application/pgp-signature
Size: 189 bytes
Desc: not available
URL: <http://www.beowulf.org/pipermail/beowulf/attachments/20080827/073db2ac/attachment.sig>