[Gllug] arch & cpu number confusion

[Nix]

On Fri, 6 Jan 2006, Richard Jones yowled:
> On Fri, Jan 06, 2006 at 10:52:28AM +0000, Nix wrote:
>> speedups under some circumstances because we can use CMOV, and of course
>> -march=sparcv8 and above has huge advantages for some loads on SPARCs
>> because SPARCv7 didn't have integer multiply or divide
>> operations. (There is an enormous speedup to SSH negotiation when
>> OpenSSL is compiled for SPARCv8, for instance.)
> 
> I thought that SPARCv7 was forward compatible - ie. it would trap the
> unknown instruction and emulate it?  Assumes your OS knows about the
> new instructions of course ...

Well, yes, your OS *could* do that. Maybe Solaris does. Linux certainly
doesn't; it'd be astonishingly slow for starters. (Like the cmpxchg
emulation on i386s, only far, far worse: multiplies are much more common
than lock acquisitions.)

-- 
`I must caution that dipping fingers into molten lead
 presents several serious dangers.' --- Jearl Walker
-- 
Gllug mailing list  -  Gllug at gllug.org.uk
http://lists.gllug.org.uk/mailman/listinfo/gllug