From: Rutger Hofman <rutger@cs.vu.nl>
To: Jonathan Larmour <jifl@jifvik.org>
Cc: "Jürgen Lambrecht" <J.Lambrecht@televic.com>,
"Ross Younger" <wry@ecoscentric.com>,
"eCos developers" <ecos-devel@ecos.sourceware.org>,
"Deroo Stijn" <S.Deroo@televic.com>
Subject: Re: NAND technical review
Date: Tue, 13 Oct 2009 12:59:00 -0000 [thread overview]
Message-ID: <4AD47ADE.9010606@cs.vu.nl> (raw)
In-Reply-To: <4AD3E92E.5020301@jifvik.org>
Jonathan Larmour wrote:
[snip]
>> We also prefer R's model of course because we started with R's model
>> and use it now.
>
> You haven't done any profiling by any luck have you? Or code size
> analysis? Although I haven't got into the detail of R's version yet
> (since I was starting with dissecting E's), both the footprint and the
> cumulative function call and indirection time overhead are concerns of
> mine.
In a first step in mitigating the 'footprint pressure', I have added CDL
options to configure in/out support for the various chips types, to wit:
- ONFI chips;
- 'regular' large-page chips;
- 'regular' small-page chips.
It is in r678 on my download page
(http://www.cs.vu.nl/~rutger/software/ecos/nand-flash/). As I had
suggested before, this was a very small refactoring (although code has
moved about in io_nand_chip.c to save on the number of #ifdefs).
One more candidate for a reduce in code footprint: I can add a CDL
option to configure out support for heterogeneous controllers/chips. The
ANC layer will become paper-thin then. If this change will make any
difference, I will do it within, say, a week's time.
As regards the concerns for (indirect) function call overhead: my
intuition is that the NAND operations themselves (page read, page write,
block erase) will dominate. It takes 200..500us only to transfer a page
over the data bus to the NAND chip; one recent data sheet mentions
program time 200us, erase time 1.5ms. I think only a very slow CPU would
show the overhead of less than 10 indirect function calls.
Rutger
next prev parent reply other threads:[~2009-10-13 12:59 UTC|newest]
Thread overview: 58+ messages / expand[flat|nested] mbox.gz Atom feed top
2009-10-02 15:51 Jonathan Larmour
2009-10-06 13:51 ` Ross Younger
2009-10-07 3:12 ` Jonathan Larmour
2009-10-07 16:22 ` Rutger Hofman
2009-10-08 7:15 ` Jürgen Lambrecht
2009-10-15 3:53 ` Jonathan Larmour
2009-10-15 11:54 ` Jürgen Lambrecht
2009-10-15 3:49 ` Jonathan Larmour
2009-10-15 14:36 ` Rutger Hofman
2009-10-16 1:32 ` Jonathan Larmour
2009-10-19 9:56 ` Ross Younger
2009-10-19 14:21 ` Rutger Hofman
2009-10-20 3:21 ` Jonathan Larmour
2009-10-20 12:19 ` Rutger Hofman
2009-10-21 1:45 ` Jonathan Larmour
2009-10-21 12:15 ` Rutger Hofman
2009-10-23 14:06 ` Jonathan Larmour
2009-10-23 15:25 ` Rutger Hofman
2009-10-23 18:03 ` Rutger Hofman
2009-10-27 20:02 ` Rutger Hofman
2009-11-10 7:03 ` Jonathan Larmour
2010-12-11 19:18 ` John Dallaway
2010-12-22 14:54 ` Rutger Hofman
2009-10-15 15:43 ` Rutger Hofman
[not found] ` <4ACDF868.7050706@ecoscentric.com>
2009-10-09 8:27 ` Ross Younger
2009-10-13 2:21 ` Jonathan Larmour
2009-10-13 13:35 ` Rutger Hofman
2009-10-16 4:04 ` Jonathan Larmour
2009-10-19 14:51 ` Rutger Hofman
2009-10-20 4:28 ` Jonathan Larmour
2009-10-07 9:40 ` Jürgen Lambrecht
2009-10-07 16:27 ` Rutger Hofman
2009-10-13 2:44 ` Jonathan Larmour
2009-10-13 6:35 ` Jürgen Lambrecht
2009-10-15 3:55 ` Jonathan Larmour
2009-10-13 12:59 ` Rutger Hofman [this message]
2009-10-15 4:41 ` Jonathan Larmour
2009-10-15 14:55 ` Rutger Hofman
2009-10-16 1:45 ` Jonathan Larmour
2009-10-19 10:53 ` Ross Younger
2009-10-20 1:40 ` Jonathan Larmour
2009-10-20 10:17 ` Ross Younger
2009-10-21 2:06 ` Jonathan Larmour
2009-10-22 10:05 ` Ross Younger
2009-11-10 5:15 ` Jonathan Larmour
2009-11-10 10:38 ` Ross Younger
2009-11-10 11:28 ` Ethernet over SPI driver for ENC424J600 Ilija Stanislevik
2009-11-10 12:16 ` Chris Holgate
2009-11-12 18:32 ` NAND technical review Ross Younger
2009-10-13 14:19 ` Rutger Hofman
2009-10-13 19:58 ` Lambrecht Jürgen
2009-10-07 12:11 ` Rutger Hofman
2009-10-08 12:31 ` Ross Younger
2009-10-08 8:16 ` Jürgen Lambrecht
2009-10-12 1:13 ` Jonathan Larmour
2009-10-16 7:29 ` Simon Kallweit
2009-10-16 13:53 ` Jonathan Larmour
2009-10-19 15:02 ` Rutger Hofman
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=4AD47ADE.9010606@cs.vu.nl \
--to=rutger@cs.vu.nl \
--cc=J.Lambrecht@televic.com \
--cc=S.Deroo@televic.com \
--cc=ecos-devel@ecos.sourceware.org \
--cc=jifl@jifvik.org \
--cc=wry@ecoscentric.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 read-only IMAP folder(s) and NNTP newsgroup(s).