Jeez, I'm glad someone straightened that out - I believe the Grateful Dead would have prior art ;-) Jan On Wed, 2004-06-30 at 14:18, Them wrote:

Unless I am mistaken, most of the Creative Labs stuff is pretty substandard since they don't allow genuine controls over the word clock for the audio playback/sampling rates. I remember seeing a website test report on the Audigy cards and it revealed tell-tale noise at anything but 48KHz playback/recording. If you're willing to spend that kind of money on an Audigy Platinum, may I suggest you consider the Audiophile 2496 made by M-Audio. Or the Revolution 7.1. They are clean cards, and offer genuine multi-rate controls with good quality. You can find independent audio evaluations online. =MB= -- A focus on Quality.

On Thu, Jul 01, 2004 at 07:34:19PM +1200, thing wrote: I though the consensus was: M-Audio USB stuff : useless, forget it. Most other M-Audio kit is excellent. Better than Creative Labs anyway! It's taken me a while to get my DIO2448 (which has S/PDIF input only) doing the right thing, but that's a bit non-standard as sound cards go. -- Anahata anahata(a)treewind.co.uk Tel: 01638 720444 http://www.treewind.co.uk Mob: 07976 263827

M-Audio's PCI cards are probably the best supported cards in Linux (along with the Hammerfall cards). Jan On Thu, 2004-07-01 at 02:34, thing wrote:

Them wrote: Thanks, this now looks a good possibility, I can get one for little more than the creative. regards Thing

On 30-Jun-2004 Hartmut Noack wrote: } > http://www.google.com/search?q=patent+live+cd+recording } } utter stupidity :: so this is the "free market" ? No. That is capitalism. ---------------------------------- E-Mail: RickTaylor(a)Speakeasy.Net Date: 30-Jun-2004 Time: 18:40:30 This message was sent by XFMail ----------------------------------

Well, if you can build your modules yourself or get Pentium-4 builds of your software, the Pentium4 offers a ferocious DSP bang for the buck, even older versions like the Rev-A Northwoods (400-533 FSB). They offer SSE + SSE2 which if used to build your effects modules, can really boost the DSP performance a significant amount. AthlonXPs only offer SSE (SSE1). Modern GCC's (>= 3.3) offer fairly good Pentium4 code generation quality, but for real OOMPH! in your binaries, the Intel C compiler is the way to performance nirvana. gcc options as a starting point: CFLAGS='-O2 -mfpmath=sse -msse2 -march=pentium4 -mcpu=pentium4 \ -fomit-frame-pointer -s' CXXFLAGS='-O2 -mfpmath=sse -msse2 \ -march=pentium4 -mcpu=pentium4 -fomit-frame-pointer -s' ./configure blah.. =MB= -- A focus on Quality.

Good to know! I've always been paranoid about those two, so I covered them twice in my builds. One cost to mmx which doesn't exist for XMM (SSE) is that there is an expensive "FP mode switch" which comes into play. There is apparently an option to have GCC generate both x87 and sse code, but the documentation doesn't inspire confidence. Yeah, it's definitely a risker option. I've seen bloated binaries which don't execute as quickly as well. With some code, I've seen -O1 be faster than -O2 [like Dan Bernstein's FFT library to name just one]. The Intel compiler is alot better in this regard. In fact, I've yet to find code where the Intel compiler doesn't humiliate the GCC compiler's generated binaries. And yes, even if you have AMD hardware, the code's faster. The table below isn't technically 100% accurate, as the pipelining and instruction scheduling of the Pentium III is a bit of an oddball compared to both its successor and predecessor. I've found the code to generally run at its best on these AMD processors when tuned for these matching Intel CPUs regardless. AMD Athlon XP (Stepping 6 and later) ~== Pentium III (SSE) AMD Athlon (Stepping 4 and earlier) ~== Pentium II (MMX) AMD Duron Applebred (Stepping 8+) ~== Pentium III (SSE) AMD Duron Morgan or older (Step <= 6)~== Pentium II (MMX) Only Opterons have SSE2. No AMD CPUs support SSE3 currently, but those are petty improvements by comparison. SSE2 is a big deal, offering both FP and INT vector operations. I've used SSE2 to dramatically speed up things from cryptographic code, to pattern-matching stuff for fuzzy-spamsign detection. In 19 times out of 20, whenever someone gives me a binary which shows the Athlon XP to run it faster than an equivalently rated Pentium 4, when I recompile them both for optimal tune (for both Intel and AMD), the Pentium 4 blows it away. No questions asked, go make me a sammich, bitch. Hard data? How does 20-30% performance improvement in the OpenSSL crypto cores sound, and that's WITHOUT any SSE2 hand-rolled assembler. The Athlon XP seems to handle really bad code, like stuff compiled for a 386/486 with lots of unaligned accesses, etc much more gracefully than the Pentium 4. I've seen a commercial game server published by Interplay whose code was so bad, running it on a 3.2GHz P4 was slower than an XP2400+ [running the same exact OS + configuration]. As always, YMMV; I could be a Dark Agent of Sauron trying to lure you away from more expensive CPUs. =MB= -- A focus on Quality.

Those programs are too "simple" and one has a cache-spill footprint which ends up limiting its performance more than actual instruction scheduling and data access reordering. BZIP2 (Block sorting compressor) for example will spill the cache of ANY modern CPU, given the fact that its working memory set is at least 4-5MB (up to 20MB or so, depending on the compression level selected). For BZIP2, memory speed is everything. If you benchmarked an 800FSB 3.0GHz processor against a 400FSB 3.0Ghz processor, the 800FSB processor would blow its doors off. For gzip, the performance would be pretty close to identical. GZIP has some assembler helpers in the core guts (alas, written against the Pentium as the newest CPU)... so there's little ability to distinguish itself there. If you disable all of the ASM stuff in GZIP builds, you might see small deltas between the compilers in your comparison, but there's little room for code-gen area improvements in performance there. Try out LAME (mp3 encoding), OpenSSL's "speed" benchmark, etc. That link isn't from Intel. It's from MySQL, AB, the developers of MySQL. MySQL, AB has been touting this advantage for a while now, just less publicly. In fact, I think up until very recently, you could only get ICC builds of MySQL from them if you PAID for MySQL - it was probably one of the little "perks" of purchasing it. It was certainly never available for (public) download, again, up until very recently. In less formal settings, developers from within MySQL, AB have acknowledged the solid gains in speed from using the Intel compiler. You can find them with google. Well, it *IS* a marketing document after all, but it's mostly MySQL's marketing document, insofar as they are touting their speed advantage over their competitors. Yes, Intel is taking some limelight as well... but it's MySQL's marketing document. MySQL, AB includes a very comprehensive set of SQL torture tests for performance evaluation, which comes with their source code. The document includes all compiler settings used for both compilers' builds, so the claims are easily verified. In any event, I have seen the difference in my own code - it manages to discover vectorising code generation possibilities in surprising places. If you don't see any differences, maybe it's not for you. If you're earnest about investigating it, then try it out with at least the following settings: Assuming a P4: CFLAGS='-xW -tpp7 -march=pentium4 -mcpu=pentium4 -O3 -ipo' Assuming a P3/AthlonXP: CFLAGS='-xK -tpp6 -march=pentium3 -mcpu=pentium3 -O3 -ipo' Some very large projects create intermediate libraries - you may find you need to build those with -ip instead of -ipo I'm neither an Intel employee, nor an employee of MySQL, AB. I poo-poo'ed Intel until about a year or two ago when I gave their compiler an honest try on a modest 400FSB P4-1.6GHz CPU and was very pleasantly surprised. If you don't discover the same results, I'm sorry. I didn't design the CPU or the compiler, so THAT'S not MY fault. :) =MB= -- A focus on Quality.

It seems to me, then, that it would be worth recompiling and building the kernel up with the intel compiler, assuming I get a pentium4 system, hence you previous comment -- Veronica Merryfield, somewhere in Cambridgeshire, UK ----- Original Message ----- From: "Malcolm Baldridge" &lt;linux-audio(a)paypc.com&gt; To: "A list for linux audio users" &lt;linux-audio-user(a)music.columbia.edu&gt; Sent: Friday, July 02, 2004 6:54 AM Subject: Re: [linux-audio-user] moterhboard and sound card advise <http://dev.mysql.com/tech-resources/articles/intel-compiler-casestudy-mysql .pdf>

I am pleased... It's no surprise. The economies on the other hand are not false. How does the performance compare to an Athlon 64 running 64 bit linux? On 02-Jul-2004 Christophe Vescovi wrote: } Malcolm Baldridge a �crit : } } > If you're tired of CPUs which give nuclear reactors a run for the thermal } > dissipation money and false economies of "cheaper" CPUs, I think you'll be } > very pleasantly surprised by 800FSB P4 performance. } } Sorry, but it's no more true : } http://www.silentpcreview.com/article169-page2.html } Christophe ---------------------------------- E-Mail: RickTaylor(a)Speakeasy.Net Date: 02-Jul-2004 Time: 15:56:16 This message was sent by XFMail ----------------------------------

} I will admit a lack of experience with these Athlon64 CPUs, however. I } don't have any of them. } } Identically clocked Athlons run 15-20C hotter than my P4-Northwoods in } identical rackmount profiles and cooling strategies. I have a feeling {after several arguments {search on soundonsound.com} and much shopping} that will very soon be the standard against which things will be measured. It's a very popular {Opterons as well} processor in Winworld {despite the fact that there's no software that takes advantage of it.} Windows64 will be out of beta soon enough and I'm sure that the platform will go. :} Seeing as there's already a large base of folk with the hardware already set up and ready to install the upgrade on. ...And because the hardware's really cheap and easy to put together. {Once it goes... Intel's going to have to come up with an alternative {and this time they won't be defining the platform} etc.} Perhaps it's something to consider. {Both when choosing a compiler and when evaluating hardware.} ---------------------------------- E-Mail: RickTaylor(a)Speakeasy.Net Date: 02-Jul-2004 Time: 21:24:17 This message was sent by XFMail ----------------------------------

} > It's a very popular {Opterons as well} processor in Winworld } > {despite the fact that there's no software that takes advantage } > of it.} } } Opterons are so expensive for their performance, alas. Not in contrast to Intels processors. http://www.pricewatch.com/ } > Windows64 will be out of beta soon enough and I'm sure that the } > platform will go. :} } } I'm not sure 64-bit computing for the masses is that much of an issue. It's } certainly not possessed of compelling advantages in the way Windows 95 } offered to DOS/Windows 3.1 users. Take a look at soundonsound. Take a look at many of the sales catalogs... it's the only thing they're selling. {straight commercial pages} } I don't know anyone outside of the hardcore who even have more than 1GB of } RAM in their machines. It still costs a non-trivial amount of money to put } more than 2GB into most systems. } } > Perhaps it's something to consider. {Both when choosing a compiler and } > when evaluating hardware.} } } Admitted. You speak some wisdom here. } } I am still scorched at AMD a bit for their thermal dissipation crimes of the } Athlons. But I'm also still simmering over how Intel dropped the ball (and } the entire match) with their Itanium. How many years have they been } shipping it? And how expensive, and relatively "useless" is it still? I wouldn't call it useless... just targeted. {and expensive} Once Athlon has opened things up... They'll either have to drop prices or come up with something compatible. {They'll have to come up with something compatible anyway...} :} You know how it goes with "buzzwords". AMD has done a lot to improve the operating temperature of their processors. } Maybe the PowerPC G5 is looking more and more attractive, but it's alas only } shipping in (surrounding) hardware I don't like with flawed Linux support. } Bleh. I just can't win. You mean the 64 bit model? :} ---------------------------------- E-Mail: RickTaylor(a)Speakeasy.Net Date: 02-Jul-2004 Time: 22:56:17 This message was sent by XFMail ----------------------------------

And if I were running transaction processing on a database I'd all over that like a cheap suit. But I'm not, so I won't ;-) Jan On Fri, 2004-07-02 at 00:54, Malcolm Baldridge wrote:

This will be my only Linux machine, although I am sure more will follow. I could prototype it, but I was hoping to get a good steer from current users. Thanks for the steer on soundcards. I want 1/4" in and posssibly stereo out. Input from a wireless link from a bass guitar. Could be balanced in, but would llike unbal as well, same for output. You are right about USB - not really. I want to use a pedal board to control it, possibly midi, or with a digital/analogue IO card. I also have thoughts of using as a synth. Raises another question - anyone writen a good pitch tracker (thinking driving synth from audio input). -- Veronica Merryfield, somewhere in Cambridgeshire, UK ----- Original Message ----- From: "Daniel James" &lt;daniel(a)mondodesigno.com&gt; To: "A list for linux audio users" &lt;linux-audio-user(a)music.columbia.edu&gt; Sent: Thursday, July 01, 2004 9:52 AM Subject: Re: [linux-audio-user] moterhboard and sound card advise

I am thinking of going with the Audiophile 2496. Can anyone confirm it will do duplex operation? And MIDI? I have seen the plugins available and will write some of my own. I plan on putting a system in a rack, not necesarily 1U. I can get rack enclosures, all steel. The lower plate has a matrix of holes for mounting board standoffs. This way I can have a pedal board with a rack above and behind along with my rack mount wireless receiver and then do all the power routing under the racks along with surge protection etc. Thanks

Hi Daniel My basses are passive but I use a wireless link. The receiver output is low impeadance, balanced and unbalanced are available. I am thinking of doubling it up as a polysynth - I do the keyboad thing as well. I did have some recording use in mind. If that becomes important, I might change the soundcard for more channels. Yes. One of the big things for me is to have a rich or thick chorus but without the depth or speed. This can only be accomplished by using a number of delay paths in parallel all running at slightly different rates. Years ago I made my own box with 5 bucket brigades and it was sooo lush - fantastic for my fretless. It died and nothing else matches it. I also want to play with various longer delay effects and phrase recording. One of the other things I would like to do is have pitch following synths, either by doing the work in code, which is not likely to yeild good results, or by using a pickup and convertor box - giving one of the requirements for MIDI, the other being the pedal board. Thanks - I'll go look.