linux-mm.kvack.org archive mirror
 help / color / mirror / Atom feed
From: Henrik Kjellberg <et05hk6@gmail.com>
To: mel@csn.ul.ie
Cc: linux-mm@kvack.org, linux-kernel@vger.kernel.org,
	akpm@linux-foundation.org, linus.walleij@stericsson.com,
	"Per Andersson" <Per.Andersson@cs.lth.se>,
	"Per Fridén" <per.friden@stericsson.com>,
	"Rickard Andersson" <rickard.andersson@stericsson.com>
Subject: Partial Array Self-Refresh on linux embedded systems
Date: Sat, 8 May 2010 13:15:05 +0200	[thread overview]
Message-ID: <m2ze31aef501005080415t3b43f92exc1abda4b34d92992@mail.gmail.com> (raw)

[-- Attachment #1: Type: text/plain, Size: 2033 bytes --]

Hello,
I have done my master thesis on the subject of Partial Array Self-refresh in
an embedded Linux environment at STEricsson. I have now finished my thesis,
started working and has verry little time (read: no time) to spend on Linux
hacking. There fore I would like to pass my work on, in hope that someone
else will find it interesting and worth puting som effort in.

One of the greatest challenges in mobile systems, like cell-phones, is
battery time. All unnecessary power consumers of a mobile system have to be
minimized. One such consumer is the dynamic memory. Dynamic Random Access
Memory (DRAM), is a volatile memory, where every bit of memory consists of a
capacitor and a transistor. When the capacitor is charged, the bit is set to
one, and when it is uncharged, the bit is set to zero.
 The main advantage with the construction is that only two components are
needed, which leads to a high memory density on the chip.
The disadvantage is the physical properties of a capacitor as a component.
The physical capacitor has leak currents, which drains the capacitor. The
leakage itself does not lead to noticeable losses, but the data will get
corrupted unless it is constantly refreshed by recharging the capacitor. The
recharging is done by reading out and writing back all the data of the
memory.
 During normal operation, the refresh is handled by the operating system.
When in idle mode, on the other hand, the refresh is done by the memory
itself, in a so called self-refresh mode, since the processor is powered
down. To refresh the whole memory if only a part of it is in use is a super
uous waste of power. That is why Partial Array Self-refresh (PASR) was
introduced.
There is no software implementation making use of PASR in the Linux kernel
as of today. The article is based on my master thesis, which aims to present
a possible implementation of PASR and evaluate its e ciency.

An article summarizing what I have done is found below:
http://sam.cs.lth.se/ExjobGetFile?id=240

Best regards
Henrik Kjellberg

[-- Attachment #2: Type: text/html, Size: 2152 bytes --]

                 reply	other threads:[~2010-05-08 11:15 UTC|newest]

Thread overview: [no followups] expand[flat|nested]  mbox.gz  Atom feed

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=m2ze31aef501005080415t3b43f92exc1abda4b34d92992@mail.gmail.com \
    --to=et05hk6@gmail.com \
    --cc=Per.Andersson@cs.lth.se \
    --cc=akpm@linux-foundation.org \
    --cc=linus.walleij@stericsson.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=linux-mm@kvack.org \
    --cc=mel@csn.ul.ie \
    --cc=per.friden@stericsson.com \
    --cc=rickard.andersson@stericsson.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).