Rockbox.org home
release
dev builds
extras
themes manual
wiki
device status forums
mailing lists
IRC bugs
patches
dev guide
translations



Rockbox mail archive

Subject: RE: Re: time to sleep?

RE: Re: time to sleep?

From: Scharke, Heiko <Heiko.Scharke_at_systemonic.com>
Date: Thu, 22 Aug 2002 20:11:01 +0200

Hi,

can you compile your code examples with the SH gcc and disassemble it
again???
Using tkdiff should show the differences ...

Heiko

-----Original Message-----
From: Linus Nielsen Feltzing [mailto:linus_at_haxx.se]
Sent: Donnerstag, 22. August 2002 17:42
To: rockbox_at_cool.haxx.se
Subject: RE: Re: time to sleep?


On Thu, 22 Aug 2002 17:36:05 +0200, Sven Karlsson wrote:
> Hi again,
>
> > and every instruction from the RAM anyway. We have no cache.
>
>
> I perfectly know that. In fact, caches have little to do with this.

Yes, they do. If you want fewer memory accesses you will have to use
either a cache or sleep between the memory accesses. This is a RISC
without a cache.

> So the net outcome is shorter code, better register usage, and
> fewer memory accesses. All contributing to the power usage.

Yes, the power usage will be lower _if_ the CPU can do something good
with the time it saves, i.e sleep or loop in a cache. Otherwise it
will still spend its time fetching NOP's from the same RAM that we
saved us some accesses from.

> Anyway, I'll keep my big mouth shut for a while now.

Please don't. These types of discussions are almost always fruitful.

/Linus

-- 
Linus Nielsen Feltzing, linus_at_haxx.se on 2002-08-22
Received on 2002-08-22

Page template was last modified "Tue Sep 7 00:00:02 2021" The Rockbox Crew -- Privacy Policy