On Thu, Apr 26, 2001 at 10:09:32PM -0400, Sergey Babkin scribbled:
| "Michael C . Wu" wrote:
| >
| > With the branch prediction, cache tracing, and EPIC instructions,
| > you really want to use an ILP compiler. Without a compiler that
| > can decide on good ways to output binaries that run with all the IA-64
| > innovations^Wreinvention-of-the-wheels.
Correcting my unclear and grammatrical incorrect sentence:
"Without a compiler that can decide on better ways to output
binaries using all of the features of IA-64 CPU's, you really
miss the point of using IA-64."
| Anothing interesting point is that the optimisation for IA-64
| seems to be highly processor-specific: the code optimized for
| Itanium won't be optimal for McKinley and vice versa. I've heard
| an estimation of about 1.5 times speed increase due to the
| model-specific optimisation.
You are asking a *lot* from the computer architects. :)
If we can solve the issue of compatibility without
inhibiting performance, we'd be REALLY rich now.....
--
+-----------------------------------------------------------+
| [EMAIL PROTECTED] | [EMAIL PROTECTED] |
| http://iteration.net/~keichii | Yes, BSD is a conspiracy. |
+-----------------------------------------------------------+
To Unsubscribe: send mail to [EMAIL PROTECTED]
with "unsubscribe freebsd-hackers" in the body of the message
