<br><br>
<div><span class="gmail_quote">On 4/11/07, <b class="gmail_sendername">Geoff Jacobs</b> <<a href="mailto:gdjacobs@gmail.com">gdjacobs@gmail.com</a>> wrote:</span>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">Jon Forrest wrote:<br>> The examples you give are very good reasons why there is<br>> a clear need for more than 32-bits of address space for
<br>> data. Again, I agree completely. But, if you read my original<br>> posting, this is not what I'm talking about. I'm talking<br>> about the need for more than 32-bits of address space for<br>> instructions (
a.k.a "text"). Why don't you run the "size"<br>> command on any of your big programs and report back what<br>> you find. My guess is that they'll be in the order<br>> of 10s of megabytes. (I agree that this method doesn't
<br>> show the true run-time text-size requirements but<br>> it's a good first attempt).<br><br>Um, that would require distinct memory pools or some weird internal<br>mapping scheme. Not nice. Much better architecturally to have no
<br>difference between pointers to instructions and pointers to data.</blockquote>
<div> </div>
<div>Hear hear! For self-adapting softare you *can't* distinguish instructions from data. That may sound over-specialized but I invite you to consider DNA and what it does: instruct enzymes to modify DNA. An awful lot comes out of that process. So I don't think it's just von Neumann's whim.
</div>
<div> </div>
<div>Peter</div><br>
<blockquote class="gmail_quote" style="PADDING-LEFT: 1ex; MARGIN: 0px 0px 0px 0.8ex; BORDER-LEFT: #ccc 1px solid">--<br>Geoffrey D. Jacobs<br><br>_______________________________________________<br>Beowulf mailing list, <a href="mailto:Beowulf@beowulf.org">
Beowulf@beowulf.org</a><br>To change your subscription (digest mode or unsubscribe) visit <a href="http://www.beowulf.org/mailman/listinfo/beowulf">http://www.beowulf.org/mailman/listinfo/beowulf</a><br></blockquote></div>
<br>
!DSPAM:461d3e2f158643326710967!