Alan Coopersmith wrote:
> How do these interfaces compare with the sun_prefetch.h ones provided
> by Sun Studio? Is the difference just that these are compiler
> independent?
>
Yes, you hit the nail on the head. These are not dependent on the
compiler; they are implemented for gcc as well as s
Paul Durrant wrote:
>
> Hmm. That was integrated a long time after I did my implementations
> (that's how long I've been waiting to integrate!). It looks like it has
> the right semantics for x86 but the sparc implementation seems to be
> n_writes; I'm not sure what that will do.
> I'd be willi
Bart Smaalders wrote:
>
> What about prefetch64()?
>
Hmm. That was integrated a long time after I did my implementations
(that's how long I've been waiting to integrate!). It looks like it has
the right semantics for x86 but the sparc implementation seems to be
n_writes; I'm not sure what tha
Roland Mainz wrote:
>
> Why do both interfaces do not have a |length| operand ? Some
> CPUs/architecturs allow to define a memory range (rounded up to the CPUs
> block size) to be pre-fetched...
>
Roland,
The intention is to keep things simple. In case it was not apparent
from my submission
James Carlson wrote:
>
> Are there SPARC equivalents? Have you considered other CPUs?
>
Yes and, in fact, the names of the inlines correspond more to the SPARC
nomenclature. I have implementations for both SPARC and x86.
> On PPC, there are four related instructions that I know about:
>
>
Garrett D'Amore - sun microsystems wrote:
[snip]
> PROPOSAL
>
> Add inlines for i386/amd64 and sparcv9 for the following types of prefetch:
>
> void prefetch_read_many(void *)
>
> This requests data be loaded into a cache for repeated reading. (This
> equates to a 't0' prefetch on x86 CPUs).
>
Garrett D'Amore - sun microsystems writes:
> Add inlines for i386/amd64 and sparcv9 for the following types of prefetch:
>
> void prefetch_read_many(void *)
>
> This requests data be loaded into a cache for repeated reading. (This
> equates to a 't0' prefetch on x86 CPUs).
>
> void prefetch_read
Bart Smaalders wrote:
> Garrett D'Amore - sun microsystems wrote:
>> ON currently lacks interfaces for device
>> drivers to request prefetch in a platform agnostic way.
>
>
> What about prefetch64()?
>
> -= Bart
>
In light of the excellent questions asked (many of which I don't
personally have a
Garrett D'Amore - sun microsystems wrote:
> ON currently lacks interfaces for device
> drivers to request prefetch in a platform agnostic way.
What about prefetch64()?
-= Bart
--
Bart Smaalders Solaris Kernel Performance
barts at cyber.eng.sun.com http://blogs.su
How do these interfaces compare with the sun_prefetch.h ones provided
by Sun Studio? Is the difference just that these are compiler
independent?
--
-Alan Coopersmith- alan.coopersmith at sun.com
Sun Microsystems, Inc. - X Window System Engineering
Template Version: @(#)sac_nextcase %I% %G% SMI
This information is Copyright 2009 Sun Microsystems
1. Introduction
1.1. Project/Component Working Name:
prefetch interfaces
1.2. Name of Document Author/Supplier:
Author: Paul Durrant
1.3 Date of This Document:
11 matches
Mail list logo