[patch] Speculative prefetching

[Andreas Jaeger]

Paolo Carlini <pcarlini@suse.de> writes:

> Hi Zdenek!
>
>>   181.mcf           1800   357       505    *     1800   291       618    *
>>
>>
> Have you got a "theory" explaining this HUGE win?!? Without violating
> the non
> disclusure agreement for SPEC, can we say that the data structures /
> access patterns
> of this test are "obviously" amenable to prefetching?

AFAIK 181.mcf is memory bound.  

Public details about mcf are at:
http://www.spec.org/cpu2000/CINT2000/181.mcf/docs/181.mcf.html

Btw. I would be interested in SPECfp also,

Andreas
-- 
 Andreas Jaeger, aj@suse.de, http://www.suse.de/~aj
  SuSE Linux AG, Maxfeldstr. 5, 90409 Nürnberg, Germany
   GPG fingerprint = 93A3 365E CE47 B889 DF7F  FED1 389A 563C C272 A126
-------------- next part --------------
A non-text attachment was scrubbed...
Name: not available
Type: application/pgp-signature
Size: 188 bytes
Desc: not available
URL: <http://gcc.gnu.org/pipermail/gcc-patches/attachments/20040319/d8ca962c/attachment.sig>