| Many thanks to all those who replied to my question re Markov Chains.
Cheers
Arne
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa01599;
5 May 99 21:00 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10f7qA-0006si-00
for jpff@maths.bath.ac.uk; Wed, 5 May 1999 21:00:22 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (UAA14491); Wed, 5 May 1999 20:57:05 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Wed, 5 May 1999 20:56:54 +0100
Received: from root@smtp1.fas.harvard.edu [140.247.30.81] by hermes via ESMTP (UAA16264); Wed, 5 May 1999 20:56:51 +0100 (BST)
Received: from login6.fas.harvard.edu (IDENT:volpe@login6.fas.harvard.edu [140.247.30.76]) by smtp1.fas.harvard.edu with ESMTP id PAA02588; Wed, 5 May 1999 15:56:49 -0400 (EDT)
Received: by login6.fas.harvard.edu with ESMTP id PAA10234; Wed, 5 May 1999 15:56:48 -0400 (EDT)
Date: Wed, 5 May 1999 15:56:48 -0400 (EDT)
From: Dew Drops
cc: Csound List
Subject: tempo
In-Reply-To: <372E38B1.777F5760@bellsouth.net>
Message-ID:
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
Does anyone know of a program or something that's been written that can
take in a piece of music and determine it's tempo ?
Drew
_____________________________________________________________________________
One is not superior merely because one sees the world as odious.
-- Chateaubriand (1768-1848)
Drew Volpe volpe@fas.harvard.edu
_____________________________________________________________________________
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02075;
6 May 99 0:53 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fBU2-0006ye-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 00:53:46 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (AAA02691); Thu, 6 May 1999 00:51:38 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 00:51:27 +0100
Received: from howl.werewolf.net [12.23.152.10] by hermes via ESMTP (AAA17852); Thu, 6 May 1999 00:51:26 +0100 (BST)
Received: from default (dial307.werewolf.net [12.23.154.7])
by howl.werewolf.net (8.9.0/8.9.0) with SMTP id SAA04589
for ; Wed, 5 May 1999 18:42:12 -0500 (CDT)
Message-ID: <002701be9753$26653800$079a170c@default>
From: Hans Mikelson
To: Csound
Subject: Corrections to Csound Magazine Beginners Article
Date: Wed, 5 May 1999 18:58:17 -0500
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 4.72.3110.5
X-MimeOLE: Produced By Microsoft MimeOLE V4.72.3110.3
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
Hi,
I made some corrections to the spring 1999 issue beginners article in the
Csound Magazine. Seems I was confused over fundamental and first harmonic
in my discussion. I hope I did not cause too much confusion for others.
Thanks to Mark Milano for pointing out these errors.
Bye,
Hans Mikelson
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02212;
6 May 99 1:46 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fCIx-0006zN-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 01:46:23 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (BAA09331); Thu, 6 May 1999 01:44:13 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 01:44:02 +0100
Received: from root@[192.33.12.137] by hermes via ESMTP (BAA08043); Thu, 6 May 1999 01:44:00 +0100 (BST)
Received: from jsw98.hampshire.edu ([172.20.96.227]) by hamp.hampshire.edu (8.8.8/8.7.3) with SMTP id UAA19247 for ; Wed, 5 May 1999 20:50:51 -0400 (EDT)
Message-ID: <000d01bf0120$e105d3e0$e36014ac@jsw98.hampshire.edu>
From: Josh Whiting
To: csound@maths.ex.ac.uk
MMDF-Warning: Parse error in original version of preceding line at UK.AC.Bath.maths.omphalos
Subject: csound processor optimizations?
Date: Fri, 17 Sep 1999 11:25:30 -0400
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 4.72.2106.4
X-MimeOLE: Produced By Microsoft MimeOLE V4.72.2106.4
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
I am wondering if any versions of csound are available that are optimized
for certain processors, i.e. P2 or P3, or other processors. I am not really
technically knowledgeable enough to know what optimizations that might
include or how to implement them by modifying the source code, but i am at
least aware that the P3 has a new instruction set that provides a
significant increase in FPU operations per cycle, and software such as Seer
System's Reality is optimized to take advantage of it.
The reason I ask is because I need to use csound in real time. I don't
really need any of the advanced synthesis opcodes, just basics and the midi
features. I have been using a digital synthesizer (the roland jx-305, which
is sample-based) and a software sequencer to make my music but I am
frustrated by the synthesizer's limitations (especially because it isn't
expandable - i cannot use my own samples). I see csound as having strong
potential as a substitute (and its free!).
so, any help in finding an optimized csound or anything else that would help
me get it going in real time would be greatly appreciated.
thanks
josh whiting
jwhiting@hampshire.edu
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02265;
6 May 99 2:04 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fCap-0006zc-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 02:04:51 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (CAA04418); Thu, 6 May 1999 02:02:53 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 02:02:42 +0100
Received: from root@big.fishnet.net [204.89.144.3] by hermes via ESMTP (CAA08938); Thu, 6 May 1999 02:02:41 +0100 (BST)
Received: from rcsreg.com (x200.core.fishnet.net [204.89.144.200])
by big.fishnet.net (8.9.2/8.8.5) with ESMTP id RAA21871;
Wed, 5 May 1999 17:07:31 -0700 (PDT)
Message-ID: <3730EAF4.FF4EA4C0@rcsreg.com>
Date: Thu, 06 May 1999 01:05:56 +0000
From: Tobiah
X-Mailer: Mozilla 4.51 [en] (X11; I; Linux 2.2.5 i686)
X-Accept-Language: en
MIME-Version: 1.0
To: Dew Drops
CC: Csound List
Subject: Re: tempo
References:
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
I have never done this, but there is 'tempest' opcode. You may have to
couple it with 'downsamp' because it takes a k-rate input. I'll
bet it works well with rap music!
Dew Drops wrote:
>
> Does anyone know of a program or something that's been written that can
> take in a piece of music and determine it's tempo ?
Received: from shaun.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02333;
6 May 99 2:29 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by shaun.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fCyq-0004IS-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 02:29:40 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (CAA04298); Thu, 6 May 1999 02:27:19 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 02:27:07 +0100
Received: from mail2.lig.bellsouth.net [205.152.0.56] by hermes via ESMTP (CAA18264); Thu, 6 May 1999 02:27:06 +0100 (BST)
Received: from bellsouth.net (host-209-215-23-72.gnv.bellsouth.net [209.215.23.72])
by mail2.lig.bellsouth.net (8.8.8-spamdog/8.8.5) with ESMTP id VAA28735
for ; Wed, 5 May 1999 21:27:05 -0400 (EDT)
Message-ID: <3730F00D.2084B71D@bellsouth.net>
Date: Wed, 05 May 1999 21:27:41 -0400
From: Patrick Pagano
X-Mailer: Mozilla 4.5 [en] (Win95; I)
X-Accept-Language: en
MIME-Version: 1.0
To: Csound List
Subject: Delay
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
Hi Folks
I want to add delay to this simple instr
I am honestly at my wits end
can someone please help me add a long decaying reverb or delay so it
sounds
really psychedelic
I know you all are probably fed up with me but I am begging
sr = 44100
kr = 4410
ksmps = 10
nchnls = 2
instr 1;Begin: Untitled1
kenv1 expon 1000, p3/2, 1000
ksig4 lfo 1000, 5, 0
asig2 oscili ksig4, p4*2, 1
aharm1 harmon asig2, 440, .3, 272, 544, 1, 64, 0.04
asig3 oscili aharm1, p4, 1
asig1 pluck kenv1, p4, 448, 1, 1
amod1 delay asig1, p3*3
outs asig3,asig2 + amod1
endin ;Untitled1
f1 0 8192 10 1 ;GEN10 Sine Wave
; p1=Instr p2:Start p3:Duration p4:User
i1 0 10 128
i1 0 10 192
i1 0 10 224
i1 0 10 256
i1 0 10 272
i1 5 10 256
i1 5 10 384
i1 5 10 448
i1 5 10 512
i1 9 10 544
i1 9 10 608
i1 9 10 928
i1 9 10 992
i1 10 5 128
i1 10 5 192
i1 10 5 256
i1 10 5 448
i1 10 5 512
i1 10 5 544
i1 14 5 64
e
;thanks
;Pat-the pathetic guy who cannot get delay to work
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02490;
6 May 99 3:51 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fEGL-00070S-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 03:51:49 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (DAA16968); Thu, 6 May 1999 03:49:22 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 03:49:11 +0100
Received: from root@big.fishnet.net [204.89.144.3] by hermes via ESMTP (DAA02279); Thu, 6 May 1999 03:49:09 +0100 (BST)
Received: from rcsreg.com (x234.core.fishnet.net [204.89.144.234] (may be forged))
by big.fishnet.net (8.9.2/8.8.5) with ESMTP id SAA25334;
Wed, 5 May 1999 18:52:20 -0700 (PDT)
Message-ID: <37310386.353132B4@rcsreg.com>
Date: Thu, 06 May 1999 02:50:46 +0000
From: Tobiah
X-Mailer: Mozilla 4.51 [en] (X11; I; Linux 2.2.5 i686)
X-Accept-Language: en
MIME-Version: 1.0
To: Patrick Pagano
CC: Csound List
Subject: Re: Delay
References: <3730F00D.2084B71D@bellsouth.net>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
> I know you all are probably fed up with me but I am begging
> Pat-the pathetic guy who cannot get delay to work
I think that what is happening here, is that your note is
ending before the delay gets a chance to come around. You
see that the first note duration is 10, yet the delay signal
would not happen until 30, when the note is already shut off!
I also gather that what you really want is a 'delay' in the
guitar effect sense, which feeds its output back into it's
input, usually at a slightly lower volume so that the sound
fades out as it repeats. For this you need the 'delayw/delayr'
pair.
I would make an instr 99 with a global delay:
>>> ORC <<<
sr = 44100
kr = 4410
ksmps = 10
nchnls = 1
gaSig init 0
instr 1
iFront init p3 * .1
iBack init p3 * .2
iMid init p3 - (iFront + iBack)
aEnv linseg 0, iFront, 1, iMid, 1, iBack, 0
aSig oscil p4 * aEnv, p5, 1
gaSig = gaSig + aSig
endin
;***** GLOBAL DELAY INSTRUMENT *****
instr 99
kDelaydecay init .8
iDelaytime init 1.3
aSig delayr iDelaytime
delayw kDelaydecay * (gaSig + aSig)
out aSig + gaSig
gaSig = 0
endin
>>> SCO <<<
f1 0 65536 10 1 .6 .3 .1
i1 0 .5 10000 220
i1 .2 .2 10000 404
i1 .6 .4 10000 344
i99 0 30
>>> END <<<
Toby
- There otta be a law -
Received: from shaun.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02498;
6 May 99 3:54 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by shaun.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fEIt-0004JV-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 03:54:27 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (DAA17564); Thu, 6 May 1999 03:52:01 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 03:51:50 +0100
Received: from smtp0.mindspring.com [207.69.200.30] by hermes via ESMTP (DAA10244); Thu, 6 May 1999 03:51:49 +0100 (BST)
Received: from Realizer (user-2ive2oe.dialup.mindspring.com [165.247.11.14])
by smtp0.mindspring.com (8.8.5/8.8.5) with SMTP id WAA06668;
Wed, 5 May 1999 22:51:43 -0400 (EDT)
Message-ID: <001601be976b$3c27f8e0$79d496c0@Realizer.ngt.sungard.com>
From: Michael Gogins
To: Josh Whiting , csound@maths.ex.ac.uk
MMDF-Warning: Parse error in original version of preceding line at UK.AC.Bath.maths.omphalos
Subject: Re: csound processor optimizations?
Date: Wed, 5 May 1999 22:47:13 -0400
MIME-Version: 1.0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: 7bit
X-Priority: 3
X-MSMail-Priority: Normal
X-Mailer: Microsoft Outlook Express 4.72.3110.1
X-MimeOLE: Produced By Microsoft MimeOLE V4.72.3110.3
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
Since we have access to the source code, it is easy to recompile it with
optimizations for our own particular platform. I find that, with Visual C++
5 and 6, "blend" code generation optimized for "fastest code" with inlining
"any suitable" functions produces the fastest code for Pentium or Pentium
II. The inlining of everything possible produces a modest but real
performance gain.
Further optimization would involve resorting to something like the Intel
performance library, which replaces select parts of the Microsoft runtime
library, not to mention monkeying with the Csound algorithms.
-----Original Message-----
From: Josh Whiting
To: csound@maths.ex.ac.uk
Date: Wednesday, May 05, 1999 8:45 PM
Subject: csound processor optimizations?
>I am wondering if any versions of csound are available that are optimized
>for certain processors, i.e. P2 or P3, or other processors. I am not
really
>technically knowledgeable enough to know what optimizations that might
>include or how to implement them by modifying the source code, but i am at
>least aware that the P3 has a new instruction set that provides a
>significant increase in FPU operations per cycle, and software such as Seer
>System's Reality is optimized to take advantage of it.
>
>The reason I ask is because I need to use csound in real time. I don't
>really need any of the advanced synthesis opcodes, just basics and the midi
>features. I have been using a digital synthesizer (the roland jx-305,
which
>is sample-based) and a software sequencer to make my music but I am
>frustrated by the synthesizer's limitations (especially because it isn't
>expandable - i cannot use my own samples). I see csound as having strong
>potential as a substitute (and its free!).
>
>so, any help in finding an optimized csound or anything else that would
help
>me get it going in real time would be greatly appreciated.
>
>thanks
>josh whiting
>jwhiting@hampshire.edu
>
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02550;
6 May 99 4:44 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fF5U-00071q-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 04:44:40 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (EAA03121); Thu, 6 May 1999 04:42:00 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 04:41:49 +0100
Received: from root@renoir.op.net [209.152.193.4] by hermes via ESMTP (EAA12043); Thu, 6 May 1999 04:41:47 +0100 (BST)
Received: from someip.ppp.op.net (d-bm2-11.ppp.op.net [209.152.194.49]) by renoir.op.net (o1/$Revision: 1.18 $) with ESMTP id XAA09051; Wed, 5 May 1999 23:41:40 -0400 (EDT)
Message-Id: <199905060341.XAA09051@renoir.op.net>
To: csound@maths.ex.ac.uk
Cc: Josh Whiting
Subject: Re: csound processor optimizations?
In-reply-to: Your message of "Fri, 17 Sep 1999 11:25:30 EDT."
<000d01bf0120$e105d3e0$e36014ac@jsw98.hampshire.edu>
Date: Wed, 05 May 1999 23:39:21 -0400
From: Paul Barton-Davis
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
In message <000d01bf0120$e105d3e0$e36014ac@jsw98.hampshire.edu>you write:
>I am wondering if any versions of csound are available that are optimized
>for certain processors, i.e. P2 or P3, or other processors. I am not really
>technically knowledgeable enough to know what optimizations that might
>include or how to implement them by modifying the source code, but i am at
>least aware that the P3 has a new instruction set that provides a
>significant increase in FPU operations per cycle, and software such as Seer
>System's Reality is optimized to take advantage of it.
Unless you code in assembler, you are unlikely to find any compilers
for C or C++ out there just yet which do justice to the new FPU SIMD
features on the P3 (Xeon).
However, if you run on a Unix platform (and perhaps Windows, I don't
know), then using pgcc to compile Csound will give you a substantial
performance benefit. You can also (as mentioned on the Csound
FrontPage's documentation on benchmarks) replace the regular math
library with a much faster one (freely available).
--p
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02616;
6 May 99 5:30 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fFnu-00074h-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 05:30:34 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (FAA18226); Thu, 6 May 1999 05:27:13 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 05:27:00 +0100
Received: from out4.ibm.net [165.87.194.239] by hermes via ESMTP (FAA08369); Thu, 6 May 1999 05:26:59 +0100 (BST)
Received: from ibm.net (slip-32-101-77-83.dc.us.ibm.net [32.101.77.83]) by out4.ibm.net (8.8.5/8.6.9) with ESMTP id EAA133900 for ; Thu, 6 May 1999 04:26:57 GMT
Message-ID: <37311B29.CF645A31@ibm.net>
Date: Thu, 06 May 1999 00:31:37 -0400
From: "Job M. van Zuijlen"
Reply-To: zuijlen@ibm.net
Organization: electona
X-Mailer: Mozilla 4.5 [en] (Win98; U)
X-Accept-Language: en
MIME-Version: 1.0
To: Csound List
Subject: Re: csound processor optimizations?
References: <000d01bf0120$e105d3e0$e36014ac@jsw98.hampshire.edu>
Content-Type: text/plain; charset=us-ascii
Content-Transfer-Encoding: 7bit
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
As far as I know (others will correct me!), the compiler would have to
take care of any special characteristics/opcodes of the processor you
are using. Version 5 of the MS C++ compiler has a Pentium setting that
makes use of extensions introduced with this processor. I suspect that
at some point newer versions of compilers would make use of the advances
of P2 and P3 processors. I don't think there is a need to change the
source code, recompiling with the right compiler (when available) would
be enough. However, there may be changes possible in the source code
that would give further speed improvements. There are few versions of
Csound aimed at real time, such as Gabriel Maldonado's DirectCsound.
Gabriel may be able to tell you more about the benefits of the new
pentiums and/or whether he did something special to the code.
Job van Zuijlen
Josh Whiting wrote:
>
> I am wondering if any versions of csound are available that are optimized
> for certain processors, i.e. P2 or P3, or other processors. I am not really
> technically knowledgeable enough to know what optimizations that might
> include or how to implement them by modifying the source code, but i am at
> least aware that the P3 has a new instruction set that provides a
> significant increase in FPU operations per cycle, and software such as Seer
> System's Reality is optimized to take advantage of it.
>
> The reason I ask is because I need to use csound in real time. I don't
> really need any of the advanced synthesis opcodes, just basics and the midi
> features. I have been using a digital synthesizer (the roland jx-305, which
> is sample-based) and a software sequencer to make my music but I am
> frustrated by the synthesizer's limitations (especially because it isn't
> expandable - i cannot use my own samples). I see csound as having strong
> potential as a substitute (and its free!).
>
> so, any help in finding an optimized csound or anything else that would help
> me get it going in real time would be greatly appreciated.
>
> thanks
> josh whiting
> jwhiting@hampshire.edu
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02662;
6 May 99 6:07 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fGNH-000759-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 06:07:07 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (GAA01661); Thu, 6 May 1999 06:04:28 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 06:04:15 +0100
Received: from vcn.bc.ca [207.102.64.2] by hermes via ESMTP (GAA10951); Thu, 6 May 1999 06:04:14 +0100 (BST)
Received: from localhost (wfreno@localhost)
by vcn.bc.ca (8.9.2/8.9.2) with ESMTP id WAA26049;
Wed, 5 May 1999 22:03:05 -0700 (PDT)
Date: Wed, 5 May 1999 22:03:05 -0700 (PDT)
From: Wayne Freno
To: Patrick Pagano
cc: Csound List
Subject: Re: Delay
In-Reply-To: <3730F00D.2084B71D@bellsouth.net>
Message-ID:
MIME-Version: 1.0
Content-Type: TEXT/PLAIN; charset=US-ASCII
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
On Wed, 5 May 1999, Patrick Pagano wrote:
> Hi Folks
> I know you all are probably fed up with me but I am begging
No need to beg! I am a perpetual beginner too with Csound and
I have found that most people on the list are willing to help
with example code or advice.
> ;Pat-the pathetic guy who cannot get delay to work
There are no stupid questions! Keep hacking away and
eventually you will have learned a lot!
Wayne Freno
(The guy who also asks a lot of obvious questions.)
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa02685;
6 May 99 6:27 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fGgh-00075G-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 06:27:11 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (GAA18212); Thu, 6 May 1999 06:24:46 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 06:24:33 +0100
Received: from adsl-209-78-185-158.dsl.lsan03.pacbell.net [209.78.185.158] by hermes via ESMTP (GAA15797); Thu, 6 May 1999 06:24:31 +0100 (BST)
Received: from screech.weirdnoise.com (localhost [127.0.0.1])
by screech.weirdnoise.com (8.8.7/8.8.7) with ESMTP id WAA08072
for ; Wed, 5 May 1999 22:26:26 -0700
Message-Id: <199905060526.WAA08072@screech.weirdnoise.com>
X-Mailer: exmh version 2.0.2
To: csound@maths.ex.ac.uk
Subject: Re: csound processor optimizations?
In-Reply-To: Your message of "Fri, 17 Sep 1999 11:25:30 EDT."
<000d01bf0120$e105d3e0$e36014ac@jsw98.hampshire.edu>
Mime-Version: 1.0
Content-Type: text/plain; charset=us-ascii
Date: Wed, 05 May 1999 22:26:26 -0700
From: Ed Hall
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
I once spent an afternoon using various hand optimizations in an
attempt to speed up Csound's inner loop and a few of its opcodes
for Linux on Alpha. The techniques included pre-fetching (loading
a value into a variable significantly before use) and loop unrolling,
usually in combination. I was able to improve the performance on the
Csound "Xanadu" benchmark by over 12% on Alpha; the same code yielded
only a few percent improvement for a Pentium II. Profiling showed that
one of the opcodes (oscili, IIRC) was sped up over 35% on Alpha, and
negligibly on P-II; the change to the inner opcode-call loop alone
was worth almost 5% of the Alpha improvement, but less than half that
on a P-II.
My experiences on other programs have shown that such optimizations
can yield improvements on Alpha and yet slow down code on Pentia.
The reason: Alphas have more than four times the general-purpose
registers as do chips based on the x86; the imbalance for floating-point
is even greater. So adding temporary variables for pre-fetching is
likely to only slow a Pentium down with register spills and reloads.
And recent P-II systems have better main memory performance than
the 2-1/2 year-old design used for my Alpha's 164LX motherboard,
such that pre-fetching is less of a win even in those cases where
it is possible.
Other RISC's might show similar levels of improvement as Alpha.
I'm afraid this isn't likely to be helpful to the original requester,
but I did want to let the list know that, if performance is the
absolute priority, there are gains to be made--at the price of making
the C code almost entirely unreadable, and more compiler-specific. The
tiny gains on the more common systems out there just don't make it
worthwhile. If someone is really, really interested, I could send
them some patches, but they aren't in distributable form at the moment,
and are for an old (3.485) version.
(BTW, the Xanadu benchmark is linked from the Csound page. The Alpha
numbers I supplied did *not* use my optimizations--I used the publically
available source code. With the mods, I can actually run the longer
benchmark in less than a minute.)
-Ed
Received: from wallace.maths.bath.ac.uk by omphalos.maths.Bath.AC.UK id aa03238;
6 May 99 12:03 BST
Received: from [144.173.6.14] (helo=exeter.ac.uk)
by wallace.maths.bath.ac.uk with esmtp (Exim 2.12 #1)
id 10fLvu-0008C1-00
for jpff@maths.bath.ac.uk; Thu, 6 May 1999 12:03:14 +0100
Received: from noether [144.173.8.10] by hermes via SMTP (LAA02742); Thu, 6 May 1999 11:56:40 +0100 (BST)
Received: from exeter.ac.uk by maths.ex.ac.uk; Thu, 6 May 1999 11:55:57 +0100
Received: from eos.arc.nasa.gov [128.102.118.20] by hermes via ESMTP (LAA09981); Thu, 6 May 1999 11:55:36 +0100 (BST)
Received: (from jim-ra@localhost)
by eos.arc.nasa.gov (8.8.4/8.8.4)
id DAA29556; Thu, 6 May 1999 03:54:54 -0700
Date: Thu, 6 May 1999 03:54:54 -0700
From: "Dr J.Stevenson's research assistant"
Message-Id: <199905061054.DAA29556@eos.arc.nasa.gov>
To: ppagano@bellsouth.net, wfreno@vcn.bc.ca
Subject: Re: Delay
Cc: csound@maths.ex.ac.uk
Sender: owner-csound-outgoing@maths.ex.ac.uk
Precedence: bulk
Hey there are no stupid questions... there are just stupid people
whom ask the questions ;^)
> ;Pat-the pathetic guy who cannot get delay to work
There are no stupid questions! Keep hacking away and
eventually you will have learned a lot!
[ just kidding fire away w/ all questions else how woul;d one learn] |