All of lore.kernel.org
 help / color / mirror / Atom feed
From: Brad Midgley <bmidgley@xmission.com>
To: bluez-devel@lists.sourceforge.net
Subject: Re: [Bluez-devel] sbc and fixed-point progress
Date: Fri, 26 Aug 2005 21:01:30 -0600	[thread overview]
Message-ID: <430FD78A.6070507@xmission.com> (raw)
In-Reply-To: <C70061B183DE09419568AB2060C52A95B73437@arion.intra.local>

Victor

> The _anamatrix8[] and _sbc_proto_8[] are  extracted from anamatrix8[][]
> and sbc_proto_8_80[]. 
> Basically what I did is, made loop unrolling, then the rearanged
> resulting code minimizing the number of multiplies

wow. you the man as they say.

FYI I stubbed in the fixed-point 4 subband stuff for now but I'd 
eventually like to see it in there. Curently it may not behave right 
when you build with USE_FIXED and then encode with 4 subbands (it tries 
to use floating point)

I don't know if you've used 4 subbands much, but it sounds quite 
respectable and it would allow us to scale down to some of the 
smallest/slowest embedded processors out there (memory permitting).

> P.S. There is a bug in general code of SUB64 (not much  influencing the
> final result). I'll check in fix this weeken and also I did some
> cleaning up of my code and added arm assembly for ADD64, SUB64. I still
> plan to modify joint stereo code in sbc_pack_frame()  (as there are some
> floating point ops still remain there) sbc_init() (and a2play) to accept
> encoder parameters like nr. of subbands, bit pool and so on.

you probably saw that a2play has some rough options for encoder params, 
jut the -t (thrifty) flag.

> P.P.S. I'm also thinking to merge floating point and fixed point filter
> code, so USE_FIXED will decide which macro to use floating or fixed
> (general|arm). Btw, I also think it is quite easy to implement 32 bit
> version this way.

nice

Brad


-------------------------------------------------------
SF.Net email is Sponsored by the Better Software Conference & EXPO
September 19-22, 2005 * San Francisco, CA * Development Lifecycle Practices
Agile & Plan-Driven Development * Managing Projects & Teams * Testing & QA
Security * Process Improvement & Measurement * http://www.sqe.com/bsce5sf
_______________________________________________
Bluez-devel mailing list
Bluez-devel@lists.sourceforge.net
https://lists.sourceforge.net/lists/listinfo/bluez-devel

  reply	other threads:[~2005-08-27  3:01 UTC|newest]

Thread overview: 36+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2005-08-26  8:02 [Bluez-devel] sbc and fixed-point progress Victor Shcherbatyuk
2005-08-27  3:01 ` Brad Midgley [this message]
  -- strict thread matches above, loose matches on Subject: below --
2005-09-07  7:14 Victor Shcherbatyuk
2005-09-07 21:18 ` Victor Shcherbatyuk
2005-08-26  8:07 Victor Shcherbatyuk
2005-08-24 12:18 Victor Shcherbatyuk
2005-08-24 16:40 ` Brad Midgley
2005-08-24 21:06   ` Victor Shcherbatyuk
2005-08-26  5:10 ` Brad Midgley
2005-08-27 22:54   ` Victor Shcherbatyuk
2005-08-28  5:44     ` Brad Midgley
2005-08-28 22:26       ` Victor Shcherbatyuk
2005-08-23 20:42         ` Roberto
2005-08-29 17:08           ` Brad Midgley
2005-08-23 21:10             ` Roberto
2005-08-29 20:18               ` Brad Midgley
2005-08-29 21:04                 ` Roberto
2005-08-23 15:00 Victor Shcherbatyuk
2005-08-01  8:20 Victor Shcherbatyuk
2005-08-01  8:41 ` Brad Midgley
2005-07-28 13:14 Victor Shcherbatyuk
2005-07-28 14:59 ` Brad Midgley
2005-07-28 18:41   ` Victor Shcherbatyuk
2005-07-28 19:21     ` Victor Shcherbatyuk
2005-07-28 21:09       ` Brad Midgley
2005-08-21 18:47   ` Victor Shcherbatyuk
2005-08-21 21:56     ` Roberto
2005-08-21 22:24       ` Victor Shcherbatyuk
2005-08-22  6:15     ` Brad Midgley
2005-08-22  7:22       ` Brad Midgley
2005-09-03 15:33 ` Victor Shcherbatyuk
2005-09-03 16:05   ` Brad Midgley
2005-09-06 21:53     ` Victor Shcherbatyuk
2005-09-07  3:24       ` Brad Midgley
2005-07-04  4:03 Brad Midgley
2005-07-04 11:11 ` Marcel Holtmann

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=430FD78A.6070507@xmission.com \
    --to=bmidgley@xmission.com \
    --cc=bluez-devel@lists.sourceforge.net \
    /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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.