On Mon, 27 Jul 1998, Eduardo E. Horvath wrote:

: Even in 32-bit land it makes sense to separate the architectures.  Much
: better to issue a nice fast multiply than use multiply-step instructions.
: More importantly, bcopy() can be re-coded to use block move instructions
: for a huge performance increase.  Without this sort of optimization, the
: machines run dog-slow.

Then sparc64 probably should become its own MACHINE_ARCH so that it can make
use of all of this.

:  Unfortunately, we don't have any mechanisms yet to
: link in architecture specific libraries dynamically yet.

This isn't as useful as it may seem for sparc V8 vs. sparc V9; you'd really
want to compile the whole of libc for V9.  And if you're going to do that,
and have other speedups to use (different argument passing conventions,
different stack structuring), it may as well be useful to split the
MACHINE_ARCH as part of that.

-- 
-- Todd Vierling (Personal tv@pobox.com; Bus. todd_vierling@xn.xerox.com)