Sign in with
Sign up | Sign in
Your question

64-bit computing

Last response: in Home Audio
Share
Anonymous
June 24, 2005 4:06:54 PM

Archived from groups: rec.audio.pro (More info?)

I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
know about? Do I need a special configuration/software/etc..I will
mostly be running Reason and Cubase, and I think I will be getting an
m-audio fireware sound system.

More about : bit computing

June 24, 2005 6:11:38 PM

Archived from groups: rec.audio.pro (More info?)

On 6/24/2005 2:06 PM, donaldjcecil wrote:
> I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
> know about? Do I need a special configuration/software/etc..I will
> mostly be running Reason and Cubase, and I think I will be getting an
> m-audio fireware sound system.

Go AMD. Shown to be better performance for audio.video. But what OS
are you going to run? XP is still 32bit?
Anonymous
June 24, 2005 6:11:39 PM

Archived from groups: rec.audio.pro (More info?)

Dan wrote:
> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>
>> I am thinking on getting a 64-bit Intel chip. Any prerequisites I
>> should know about? Do I need a special configuration/software/etc..I
>> will mostly be running Reason and Cubase, and I think I will be
>> getting an m-audio fireware sound system.
>
>
> Go AMD. Shown to be better performance for audio.video. But what OS
> are you going to run? XP is still 32bit?
I have always heared AMD runs hot. Maybe that's not the case anymore. I
will look into it. And I think there is a 64-bit XP..but dont quote me.
I better just do some more research.
Related resources
June 24, 2005 6:53:09 PM

Archived from groups: rec.audio.pro (More info?)

On 6/24/2005 2:21 PM, donaldjcecil wrote:
> Dan wrote:
>
>> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>>
>>> I am thinking on getting a 64-bit Intel chip. Any prerequisites I
>>> should know about? Do I need a special configuration/software/etc..I
>>> will mostly be running Reason and Cubase, and I think I will be
>>> getting an m-audio fireware sound system.
>>
>>
>>
>> Go AMD. Shown to be better performance for audio.video. But what OS
>> are you going to run? XP is still 32bit?
>
> I have always heared AMD runs hot. Maybe that's not the case anymore. I
> will look into it. And I think there is a 64-bit XP..but dont quote me.
> I better just do some more research.

I think they have solved the Heat problems that were with one of the
chips around 2003. In fact, I think Intel runs hotter on average now.
Also, AMD64 processors can run 32bit software so they make migrating to
64 bit easier. But I don't know how much 64 bit software is out there
in the windows world. You may want to wait until Windows64 is common
place and the bugs have been worked out. I run a AMD64 server at home
using Linux64 and have had no problems.
Anonymous
June 24, 2005 7:44:48 PM

Archived from groups: rec.audio.pro (More info?)

donaldjcecil <djcecil@cox.net> wrote:
>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>know about? Do I need a special configuration/software/etc..I will
>mostly be running Reason and Cubase, and I think I will be getting an
>m-audio fireware sound system.

This seems like a bad idea. The Itanium runs like a slug in 32-bit mode,
and none of those applications will run in native 64-bit mode.
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 24, 2005 7:44:49 PM

Archived from groups: rec.audio.pro (More info?)

Scott Dorsey wrote:
> donaldjcecil <djcecil@cox.net> wrote:
>
>>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>>know about? Do I need a special configuration/software/etc..I will
>>mostly be running Reason and Cubase, and I think I will be getting an
>>m-audio fireware sound system.
>
>
> This seems like a bad idea. The Itanium runs like a slug in 32-bit mode,
> and none of those applications will run in native 64-bit mode.
> --scott
i have always heard its not best to be on the forefront of technology.
sounds like i should follow that advice.
Anonymous
June 24, 2005 8:31:59 PM

Archived from groups: rec.audio.pro (More info?)

donaldjcecil <djcecil@cox.net> wrote:
>Scott Dorsey wrote:
>> donaldjcecil <djcecil@cox.net> wrote:
>>
>>>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>>>know about? Do I need a special configuration/software/etc..I will
>>>mostly be running Reason and Cubase, and I think I will be getting an
>>>m-audio fireware sound system.
>>
>> This seems like a bad idea. The Itanium runs like a slug in 32-bit mode,
>> and none of those applications will run in native 64-bit mode.
>
>i have always heard its not best to be on the forefront of technology.
>sounds like i should follow that advice.

No, it's fine to be on the forefront of technology if you're trying to
do something that requires being there. Spending $8k on an Itanium
machine to run your applications slower than a 486-50 would, though,
seems like a bad match between application and system.
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 25, 2005 12:23:40 AM

Archived from groups: rec.audio.pro (More info?)

Bill Ruys wrote:

> (4) You will need to get a 64-bit DAW environment to enjoy the benefits of
> 64-bit computing:

And what might those be for audio? I understand that the
internal architecture of the 64 bit machines is better but
is that lost when running them in 32 bit mode?

> Cakewalk has a free public beta available here: http://www.cakewalk.com/x64/
> They will probably be one of the first to market with a true 64-bit DAW
> application
> (5) There are quantifiable benefits in running a 64-bit DAW on a 64-bit OS
> with 64-bit plug-ins

Due to what? All that extra data being passed over the bus
(which is almost certainly zero in an audio app), and the
probably longer instructions would only seem to me to incur
a bandwidth penalty.

I just can't see why going to 64 bits offers anything but
potential penalties for audio. All it gives inherently is
really big integers and addresses which are useful for
database transaction processing machines with the
requirement of _very_ large real memory, but how so for audio?


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 25, 2005 12:25:54 AM

Archived from groups: rec.audio.pro (More info?)

A thought occured to me after sending that last respone off.
Is it possible that there is an intentional, designed in
penalty for running 32 bit mode? You know, marketing
considerations and all that.


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 25, 2005 12:43:19 AM

Archived from groups: rec.audio.pro (More info?)

Dan <dan@nospam.com> wrote:
> On 6/24/2005 2:21 PM, donaldjcecil wrote:
>> Dan wrote:
>>
>>> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>>>
>>>> I am thinking on getting a 64-bit Intel chip. Any prerequisites I
>>>> should know about? Do I need a special configuration/software/etc..I
>>>> will mostly be running Reason and Cubase, and I think I will be
>>>> getting an m-audio fireware sound system.
>>>
>>>
>>>
>>> Go AMD. Shown to be better performance for audio.video. But what OS
>>> are you going to run? XP is still 32bit?
>>
>> I have always heared AMD runs hot. Maybe that's not the case anymore. I
>> will look into it. And I think there is a 64-bit XP..but dont quote me.
>> I better just do some more research.
>
> I think they have solved the Heat problems that were with one of the
> chips around 2003. In fact, I think Intel runs hotter on average now.
> Also, AMD64 processors can run 32bit software so they make migrating to
> 64 bit easier.

The AMD and Intel 64bit implementations are for all intents and purposes
identical to the outside world - I should know, I was a circuit designer on
Prescott (the Intel 64bit Pentium 4) for a couple years. They will both run
32bit or 64bit code. They will in fact run the exact same code, with the
exact same results. Performance differences will be dependent on a huge
number of different issues - mostly relating to the application in question.

--
Aaron
Anonymous
June 25, 2005 12:44:00 AM

Archived from groups: rec.audio.pro (More info?)

Scott Dorsey <kludge@panix.com> wrote:
> donaldjcecil <djcecil@cox.net> wrote:
>>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>>know about? Do I need a special configuration/software/etc..I will
>>mostly be running Reason and Cubase, and I think I will be getting an
>>m-audio fireware sound system.
>
> This seems like a bad idea. The Itanium runs like a slug in 32-bit mode,
> and none of those applications will run in native 64-bit mode.

I think you're forgetting the Intel 64 bit x86 part.

--
Aaron
Anonymous
June 25, 2005 8:34:59 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain wrote:

>
>
> Bill Ruys wrote:
>
>> (4) You will need to get a 64-bit DAW environment to enjoy the
>> benefits of 64-bit computing:
>
>
> And what might those be for audio? I understand that the internal
> architecture of the 64 bit machines is better but is that lost when
> running them in 32 bit mode?
>
>> Cakewalk has a free public beta available here:
>> http://www.cakewalk.com/x64/
>> They will probably be one of the first to market with a true 64-bit
>> DAW application
>> (5) There are quantifiable benefits in running a 64-bit DAW on a
>> 64-bit OS with 64-bit plug-ins
>
>
> Due to what? All that extra data being passed over the bus (which is
> almost certainly zero in an audio app), and the probably longer
> instructions would only seem to me to incur a bandwidth penalty.
>
> I just can't see why going to 64 bits offers anything but potential
> penalties for audio. All it gives inherently is really big integers and
> addresses which are useful for database transaction processing machines
> with the requirement of _very_ large real memory, but how so for audio?
>
>
> Bob

It might halve the number of bus cycles for transfers, but it's
probably still PCI, which (SFAIK) is inherently 32 bit. I know
of no 64 bit versions of PCI.

*Shrug*?

--
Les Cargill
Anonymous
June 25, 2005 8:35:00 AM

Archived from groups: rec.audio.pro (More info?)

Les Cargill wrote:

> It might halve the number of bus cycles for transfers, but it's
> probably still PCI, which (SFAIK) is inherently 32 bit. I know
> of no 64 bit versions of PCI.
>
> *Shrug*?

The memory/processor bus isn't PCI. It's much faster and
much wider. I can't remember what it's called, though. My
point is that no matter how wide or fast it is, shuffling
more data (the upper word of long integers which will be
zero for audio apps if used at all) through it can only be a
penalty.


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 25, 2005 11:35:02 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>Bill Ruys wrote:
>
>> (4) You will need to get a 64-bit DAW environment to enjoy the benefits of
>> 64-bit computing:
>
>And what might those be for audio? I understand that the
>internal architecture of the 64 bit machines is better but
>is that lost when running them in 32 bit mode?

The Opteron is pretty fast when running in 32-bit mode. The Itanium is
a total pig in 32-bit mode and you'd be happier with a 486-50.

>> Cakewalk has a free public beta available here: http://www.cakewalk.com/x64/
>> They will probably be one of the first to market with a true 64-bit DAW
>> application
>> (5) There are quantifiable benefits in running a 64-bit DAW on a 64-bit OS
>> with 64-bit plug-ins
>
>Due to what? All that extra data being passed over the bus
>(which is almost certainly zero in an audio app), and the
>probably longer instructions would only seem to me to incur
>a bandwidth penalty.
>
>I just can't see why going to 64 bits offers anything but
>potential penalties for audio. All it gives inherently is
>really big integers and addresses which are useful for
>database transaction processing machines with the
>requirement of _very_ large real memory, but how so for audio?

First of all, 64-bit floating point operations are a lot faster. That can
be a big deal for some kinds of processing. (Double int operations are
also faster but for audio stuff nobody cares.)

Secondly, your address space is much larger, so now you can have an individual
process greater than 4 Gb. (I don't know if this is true in Windows, but it
is in a regular operating system and for most people it's the whole point
of going 64-bits.)
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 25, 2005 11:37:17 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>
>A thought occured to me after sending that last respone off.
> Is it possible that there is an intentional, designed in
>penalty for running 32 bit mode? You know, marketing
>considerations and all that.

Probably less the case than the fact that the 32-bit mode is usually just
an afterthought.

Remember when the vax came out? It had a 16-bit compatibility mode so you
could run all your RSX-11 applications on it. An abacus would have been
faster, but nobody was really expected to use 16-bit mode. It was only
there to help you port your applications, and it disappeared from the
architecture in a couple years.
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 25, 2005 11:47:00 AM

Archived from groups: rec.audio.pro (More info?)

On 2005-06-24, donaldjcecil <djcecil@cox.net> wrote:
> Dan wrote:
>> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>>
>>> I am thinking on getting a 64-bit Intel chip. Any prerequisites I
>>> should know about? Do I need a special configuration/software/etc..I
>>> will mostly be running Reason and Cubase, and I think I will be
>>> getting an m-audio fireware sound system.
>>
>> Go AMD. Shown to be better performance for audio.video. But what OS
>> are you going to run? XP is still 32bit?
>
> I have always heared AMD runs hot. Maybe that's not the case anymore.
> I will look into it. And I think there is a 64-bit XP..but dont quote
> me. I better just do some more research.

With AMD's 90nm process, it's Intel that runs hot. 120W vs.
70W, IIRC.

--
André Majorel <URL:http://www.teaser.fr/~amajorel/&gt;
(Counterfeit: hur@gravid.com hikifiv@docile.com)
"J'baiserai la France jusqu'à ce qu'elle m'aime." -- Un rappeur
Anonymous
June 25, 2005 12:25:38 PM

Archived from groups: rec.audio.pro (More info?)

Bill Ruys wrote:

< snip >

> (2) AMD64 Winchester and Venice cores run cool (less than 25 degrees Celcius
> on a 3200+)

Which must mean they've reduced power consumption to something sensible.

Any idea how many watts they consume ?

Surely you don't *actually* mean 25C though. Ambient temp itself can easily be
more than that !

< snip >

> (5) There are quantifiable benefits in running a 64-bit DAW on a 64-bit OS
> with 64-bit plug-ins

Which means that until such a date that happens there's no clear benefit worth
having of any note. Possibly other than the new CPUs having a 'cleaner' internal
design that may give them a little extra efficiency processing some ( 32 bit )
instructions.

Graham
Anonymous
June 25, 2005 12:33:18 PM

Archived from groups: rec.audio.pro (More info?)

On 2005-06-25, Bob Cain <arcane@arcanemethods.com> wrote:
> Bill Ruys wrote:
>
>> (4) You will need to get a 64-bit DAW environment to enjoy
>> the benefits of 64-bit computing:
>
> And what might those be for audio? I understand that the
> internal architecture of the 64 bit machines is better but
> is that lost when running them in 32 bit mode?
>
>> Cakewalk has a free public beta available here:
>> http://www.cakewalk.com/x64/ They will probably be one of the
>> first to market with a true 64-bit DAW application (5) There
>> are quantifiable benefits in running a 64-bit DAW on a 64-bit
>> OS with 64-bit plug-ins
>
> Due to what? All that extra data being passed over the bus
> (which is almost certainly zero in an audio app), and the
> probably longer instructions would only seem to me to incur
> a bandwidth penalty.
>
> I just can't see why going to 64 bits offers anything but
> potential penalties for audio. All it gives inherently is
> really big integers and addresses which are useful for
> database transaction processing machines with the
> requirement of _very_ large real memory, but how so for audio?

I think that, going from 32 bits to 64 bits on an x64-64 (not
ia64, which is different), two things happen: (1) because
addresses and certain integers double in size, you lose and (2)
because you have more registers, you win.

I'd like to see a benchmark.

--
André Majorel <URL:http://www.teaser.fr/~amajorel/&gt;
(Counterfeit: xiv@misogyny.com enipew@squirmed5boris.com)
"J'baiserai la France jusqu'à ce qu'elle m'aime." -- Un rappeur
Anonymous
June 25, 2005 1:38:40 PM

Archived from groups: rec.audio.pro (More info?)

Andre Majorel wrote:

> I think that, going from 32 bits to 64 bits on an x64-64 (not
> ia64, which is different), two things happen: (1) because
> addresses and certain integers double in size, you lose and (2)
> because you have more registers, you win.

Ah, yes. I'd forgotten about the register increase. Hard
to see that offseting the increased bandwidth requirement,
however.

> I'd like to see a benchmark.

Me too.


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 25, 2005 1:44:38 PM

Archived from groups: rec.audio.pro (More info?)

Scott Dorsey wrote:

> First of all, 64-bit floating point operations are a lot faster. That can
> be a big deal for some kinds of processing. (Double int operations are
> also faster but for audio stuff nobody cares.)

That's almost got to be a 32 bit mode detuning. Hard to see
why the operating mode should affect FP operations unless it
was purposeful.

>
> Secondly, your address space is much larger, so now you can have an individual
> process greater than 4 Gb. (I don't know if this is true in Windows, but it
> is in a regular operating system and for most people it's the whole point
> of going 64-bits.)

I just can't see, other than for large sample cache's, why
an audio app would outgrow 32 bit addresses and require such
massive real memory.


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 25, 2005 2:16:15 PM

Archived from groups: rec.audio.pro (More info?)

"donaldjcecil" <djcecil@cox.net> wrote in message
news:bRYue.773$ro.360@fed1read02...
>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>know about? Do I need a special configuration/software/etc..I will mostly
>be running Reason and Cubase, and I think I will be getting an m-audio
>fireware sound system.

I'd suggest hanging off a bit until mobos, operating systems , drivers, and
applications are all working happily (with an advantage) on these CPUs. And
they become affordable.

geoff
June 25, 2005 2:26:23 PM

Archived from groups: rec.audio.pro (More info?)

Geoff Wood <geoff@nospam-paf.co.nz> wrote in message
news:42bc85b9$1@clear.net.nz...
>
> "donaldjcecil" <djcecil@cox.net> wrote in message
> news:bRYue.773$ro.360@fed1read02...
> >I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
> >know about? Do I need a special configuration/software/etc..I will mostly
> >be running Reason and Cubase, and I think I will be getting an m-audio
> >fireware sound system.
>
> I'd suggest hanging off a bit until mobos, operating systems , drivers,
and
> applications are all working happily (with an advantage) on these CPUs.
And
> they become affordable.
>
> geoff
>
>

LOL.......you'll be waiting a life time for that.....this is the reason I
picked up my G5.I am not a mac freak either as I use PCs as much as Mac.
Anonymous
June 25, 2005 2:46:21 PM

Archived from groups: rec.audio.pro (More info?)

the apps aren't ported to 64 bit in any meaningful way yet. the only
"advantage" right now is you can get massive amounts of ram, like 8 gig
or 20 gig or something crazy.

but regular 32 bit computers can run 1 gig or 2 gig of ram just fine,
which is plenty.

AMD Athlons do run hot, can't comment on the other lines.

Spend your money on extra hard drives and a raid-0 setup, much more
relevant to your needs.
Anonymous
June 25, 2005 10:31:57 PM

Archived from groups: rec.audio.pro (More info?)

donaldjcecil wrote:
> Dan wrote:
>> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>>
>>> I am thinking on getting a 64-bit Intel chip. Any
prerequisites I
>>> should know about? Do I need a special
configuration/software/etc..I
>>> will mostly be running Reason and Cubase, and I think I
will be
>>> getting an m-audio fireware sound system.
>>
>>
>> Go AMD. Shown to be better performance for audio.video.
But what OS
>> are you going to run? XP is still 32bit?

There's a beta version of XP64 on MS's site, last time I
looked.

http://www.microsoft.com/windowsxp/64bit/evaluation/tri...

> I have always heared AMD runs hot.

Not so with XP64s. They are some of the coolest chips I've
ever seen since the days of P3s and K6s.
Anonymous
June 26, 2005 12:14:29 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain wrote:
> Scott Dorsey wrote:

>> Secondly, your address space is much larger, so now you can have an
>> individual
>> process greater than 4 Gb.

> I just can't see, other than for large sample cache's, why an audio app
> would outgrow 32 bit addresses and require such massive real memory.

On many operating systems it is sometimes more convenient or efficient
to memory map files and deal with them as addressable memory instead
of as files that require system calls every time you want to read or
write anything. A 64-bit system would give you much more flexibility
to memory map files. In other words, you needn't have gigabytes of
RAM for a 64-bit address space to be useful.

Also, even if you aren't memory mapping them, files larger than 2 GB
typically require some kind of special API for large files. Yes, you
can accomplish this easily enough on a 32-bit machine, but it's a tad
cleaner to just use 64-bit integers on a 64-bit machine. True, it's
virtually impossible to imagine that computing file offsets would be
the bottleneck in an audio application even on a machine where 64-bit
integer computations require extra steps, but the fact remains that a
64-bit machine is able to deal with large files more easily and dealing
with large files is a task that is necessary for audio applications.
(A single-track 24-bit, 192 kHz audio sample that lasts 60 minutes
will require about 2GB of storage.)

There probably is not any compelling reason why 64-bit is necessary for
audio. On the other hand, it seems clear that the computer industry
will eventually move to 64-bit processors, and there are certainly some
audio tasks which could benefit from a 64-bit processor. The combination
of those two facts means to me that it's probably not a bad idea to
shoot for 64-bit if you're setting up a new audio machine. I certainly
wouldn't see it as a sufficient reason by itself to upgrade, but 64-bit
might be a nice thing to have to maintain "compatibility with the future".

- Logan
Anonymous
June 26, 2005 12:14:30 AM

Archived from groups: rec.audio.pro (More info?)

Logan Shaw <lshaw-usenet@austin.rr.com> wrote:
>
>There probably is not any compelling reason why 64-bit is necessary for
>audio. On the other hand, it seems clear that the computer industry
>will eventually move to 64-bit processors, and there are certainly some
>audio tasks which could benefit from a 64-bit processor. The combination
>of those two facts means to me that it's probably not a bad idea to
>shoot for 64-bit if you're setting up a new audio machine. I certainly
>wouldn't see it as a sufficient reason by itself to upgrade, but 64-bit
>might be a nice thing to have to maintain "compatibility with the future".

I liked 36-bit computers a lot better.
--scott

....remember if it doesn't have 36 bits, you're not playing with a full DEC...
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 26, 2005 3:12:24 AM

Archived from groups: rec.audio.pro (More info?)

"Arny Krueger" <arnyk@hotpop.com> wrote in message
news:o _OdnXbK5KzDRiDfRVn-hA@comcast.com...
> donaldjcecil wrote:
>> Dan wrote:
>>> On 6/24/2005 2:06 PM, donaldjcecil wrote:
>>>
>>>> I am thinking on getting a 64-bit Intel chip. Any
> prerequisites I
>>>> should know about? Do I need a special
> configuration/software/etc..I
>>>> will mostly be running Reason and Cubase, and I think I
> will be
>>>> getting an m-audio fireware sound system.
>>>
>>>
>>> Go AMD. Shown to be better performance for audio.video.
> But what OS
>>> are you going to run? XP is still 32bit?
>
> There's a beta version of XP64 on MS's site, last time I
> looked.
>
> http://www.microsoft.com/windowsxp/64bit/evaluation/tri...

It's been released for a month or more now.
Anonymous
June 27, 2005 12:52:30 PM

Archived from groups: rec.audio.pro (More info?)

On Fri, 24 Jun 2005 12:06:54 -0700, donaldjcecil <djcecil@cox.net>
wrote:

>I am thinking on getting a 64-bit Intel chip. Any prerequisites I should
>know about? Do I need a special configuration/software/etc..I will
>mostly be running Reason and Cubase, and I think I will be getting an
>m-audio fireware sound system.

32-bit, coming 64-bit... its just fine but _the_ bottleneck in audio
and video processing are still hard disks. Here, I'd opt for an U320
SCSI RAID0 set with at least 2, if not 4, fastest disks as of today,
Seagate Cheetah 15K.4, Maxtor Atlas, Fujitsu{IBM} MAM series... this
would give a real world 70-90 MB/s constant across platters throughput
of large files and it would be really the time-saver.

Edi Zubovic, Crikvenica, Croatia
Anonymous
June 27, 2005 2:08:06 PM

Archived from groups: rec.audio.pro (More info?)

On 27/06/05 08:52, in article j18vb1lf7iu5jtakmm3v4glolmvvp3jt2d@4ax.com,
"Edi Zubovic" <edi.zubovic[rem this]@ri.htnet.hr> wrote:

(...)
> 32-bit, coming 64-bit... its just fine but _the_ bottleneck in audio
> and video processing are still hard disks. Here, I'd opt for an U320
> SCSI RAID0 set with at least 2, if not 4, fastest disks as of today,
> Seagate Cheetah 15K.4, Maxtor Atlas, Fujitsu{IBM} MAM series... this
> would give a real world 70-90 MB/s constant across platters throughput
> of large files and it would be really the time-saver.

And then there's solid state disks... No moving parts as well.
Anonymous
June 27, 2005 9:40:47 PM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>
>
> Les Cargill wrote:
>
>> It might halve the number of bus cycles for transfers, but it's
>> probably still PCI, which (SFAIK) is inherently 32 bit. I know
>> of no 64 bit versions of PCI.
>>
>> *Shrug*?
>
> The memory/processor bus isn't PCI. It's much faster and
> much wider. I can't remember what it's called, though. My
> point is that no matter how wide or fast it is, shuffling
> more data (the upper word of long integers which will be
> zero for audio apps if used at all) through it can only be a
> penalty.

There are performance benefits especially when doing 64bit computations on a
64bit processor.

--
Aaron
Anonymous
June 27, 2005 9:40:48 PM

Archived from groups: rec.audio.pro (More info?)

aborgman@redshark.goodshow.net wrote:

> There are performance benefits especially when doing 64bit computations on a
> 64bit processor.

Most certainly, but what's in question is the relevance of
that to a DAW.


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 28, 2005 1:01:58 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>aborgman@redshark.goodshow.net wrote:
>
>> There are performance benefits especially when doing 64bit computations on a
>> 64bit processor.
>
>Most certainly, but what's in question is the relevance of
>that to a DAW.

Right now, it's totally irrelevant. But I bet it turns out to make it
easier to design good fast reverbs. Double-precision floats can be a
good thing for reverb simulation.
--scott
--
"C'est un Nagra. C'est suisse, et tres, tres precis."
Anonymous
June 28, 2005 1:01:59 AM

Archived from groups: rec.audio.pro (More info?)

Scott Dorsey wrote:
> Bob Cain <arcane@arcanemethods.com> wrote:
>
>>aborgman@redshark.goodshow.net wrote:
>>
>>
>>>There are performance benefits especially when doing 64bit computations on a
>>>64bit processor.
>>
>>Most certainly, but what's in question is the relevance of
>>that to a DAW.
>
>
> Right now, it's totally irrelevant. But I bet it turns out to make it
> easier to design good fast reverbs. Double-precision floats can be a
> good thing for reverb simulation.

I may be wrong but I think that FP units have 64 bit wide
data paths even in 32 bit machines. In and of itself, 64
bit is really about integers and addresses. That there is a
larger register set in 64 bit mode, which I think is pretty
meager in 32 bit x86 architecture, is a definite plus.

Anybody know what the number of addressable registers is in
each?

Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 28, 2005 4:23:54 AM

Archived from groups: rec.audio.pro (More info?)

Well, it *is* winter here right now, but yup, my Athlon64 *really* does run
at about 25 degrees with an ambient room temp of about 18 degrees C. My
Athlon XP 3200 by comparison runs about 20 degrees hotter! So there must
have been some real advances in core technology between the two types of
chip. Not sure what the power comsumption is, but I do remember reading
that the AMDs are currently consuming far less than the P4s.

Bill.

"Pooh Bear" <rabbitsfriendsandrelations@hotmail.com> wrote in message
news:42BD06F2.7B35EC5B@hotmail.com...
>
> Bill Ruys wrote:
>
> < snip >
>
>> (2) AMD64 Winchester and Venice cores run cool (less than 25 degrees
>> Celcius
>> on a 3200+)
>
> Which must mean they've reduced power consumption to something sensible.
>
> Any idea how many watts they consume ?
>
> Surely you don't *actually* mean 25C though. Ambient temp itself can
> easily be
> more than that !
>
> < snip >
>
>> (5) There are quantifiable benefits in running a 64-bit DAW on a 64-bit
>> OS
>> with 64-bit plug-ins
>
> Which means that until such a date that happens there's no clear benefit
> worth
> having of any note. Possibly other than the new CPUs having a 'cleaner'
> internal
> design that may give them a little extra efficiency processing some ( 32
> bit )
> instructions.
>
> Graham
>
Anonymous
June 28, 2005 11:08:00 AM

Archived from groups: rec.audio.pro (More info?)

Bob Cain wrote:
> Scott Dorsey wrote:
>> Bob Cain <arcane@arcanemethods.com> wrote:
>>
>>> aborgman@redshark.goodshow.net wrote:
>>>
>>>
>>>> There are performance benefits especially when doing
64bit
>>>> computations on a 64bit processor.
>>>
>>> Most certainly, but what's in question is the relevance
of
>>> that to a DAW.
>>
>>
>> Right now, it's totally irrelevant. But I bet it turns
out to make
>> it easier to design good fast reverbs. Double-precision
floats can
>> be a good thing for reverb simulation.

> I may be wrong but I think that FP units have 64 bit wide
> data paths even in 32 bit machines.

I believe you're right.

> In and of itself, 64 bit is really about integers and
addresses.

Surprisingly, we're getting to the point where 32 bit
addressing is starting to look a little tight. The largest
32 bit integer is about 8 billion, which corresponds to the
ever-so-common 8 gigabyte addressing.

Right now I'm building customer machines with 0.5 and 1
gigabyte of RAM, so 8 gigabytes of RAM is quite easy to see
on the horizon. In fact I'm contemplating building a 2 GB
machine today.

Building machines with very large amounts of real memory is
stimulated by the fact that CPU speed has long been
outpacing hard drive speed. If you really want a 3+ GHz
machine to exploit its potential processing power, you don't
run much directly off the hard drive.

Since large amounts of RAM are being used to cache hard
drives that keep getting larger and larger, computer real
memory size has to in some sense, keep up with increases in
the size of the hard drive.

Computers have to work with virtual address spaces, and even
8 GB addressing is too small when the address space is being
used to work with an entire database. Again, very large
databases are facilitated by large hard drives as well being
demanded by increased use of graphics and imaging.
Anonymous
June 28, 2005 7:37:27 PM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>
>
> aborgman@redshark.goodshow.net wrote:
>
>> There are performance benefits especially when doing 64bit computations on a
>> 64bit processor.
>
> Most certainly, but what's in question is the relevance of
> that to a DAW.

I'm certain there are some plugins that can benefit from it.

--
Aaron
Anonymous
June 28, 2005 7:39:38 PM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>
>
> Scott Dorsey wrote:
>> Bob Cain <arcane@arcanemethods.com> wrote:
>>
>>>aborgman@redshark.goodshow.net wrote:
>>>
>>>
>>>>There are performance benefits especially when doing 64bit computations on a
>>>>64bit processor.
>>>
>>>Most certainly, but what's in question is the relevance of
>>>that to a DAW.
>>
>>
>> Right now, it's totally irrelevant. But I bet it turns out to make it
>> easier to design good fast reverbs. Double-precision floats can be a
>> good thing for reverb simulation.
>
> I may be wrong but I think that FP units have 64 bit wide
> data paths even in 32 bit machines. In and of itself, 64
> bit is really about integers and addresses. That there is a
> larger register set in 64 bit mode, which I think is pretty
> meager in 32 bit x86 architecture, is a definite plus.

....and 64bit machines have 128bit FP datapaths (or more) in some cases.

> Anybody know what the number of addressable registers is in
> each?

Pretty irrelevant on the Intel parts considering replay and register
renaming.

--
Aaron
Anonymous
June 29, 2005 4:18:09 AM

Archived from groups: rec.audio.pro (More info?)

aborgman@redshark.goodshow.net wrote:

> ...and 64bit machines have 128bit FP datapaths (or more) in some cases.

Does that drop back to 64 in 32 bit mode? The question I'm
addressing is not whether the new 64 bit machines have a
more advanced architecture, that's to be expected, but
whether or not an audio app should have any sensitivity to
the mode it is compiled for so as to gain performance going
to 64 bit mode.

>
>
>>Anybody know what the number of addressable registers is in
>>each?
>
>
> Pretty irrelevant on the Intel parts considering replay and register
> renaming.

Doesn't the compiler still map variables to registers for
purposes of enhancing performance? The assumption is that
the addressable set is faster to use than main memory. Thus
the more that are are addressable for the compiler to
allocate variables to, the better the performance
independant of the factors you name. Wrong?


Bob
--

"Things should be described as simply as possible, but no
simpler."

A. Einstein
Anonymous
June 29, 2005 7:01:33 PM

Archived from groups: rec.audio.pro (More info?)

Bob Cain <arcane@arcanemethods.com> wrote:
>
>
> aborgman@redshark.goodshow.net wrote:
>
>> ...and 64bit machines have 128bit FP datapaths (or more) in some cases.
>
> Does that drop back to 64 in 32 bit mode?

That is going to depend on the individual instruction in question - for SIMD
type operations (SSE/SSE2/SSE2/Altivec etc) odds are it does not drop down
to using only the lower 64bits when running in 32b mode.

> The question I'm
> addressing is not whether the new 64 bit machines have a
> more advanced architecture, that's to be expected, but
> whether or not an audio app should have any sensitivity to
> the mode it is compiled for so as to gain performance going
> to 64 bit mode.

Re-compiling will always be the biggest gain, even going between different
steppings of the same processor - but even different pieces of silicon sold
as the same aren't necessarily the same.


>>>Anybody know what the number of addressable registers is in
>>>each?
>>
>>
>> Pretty irrelevant on the Intel parts considering replay and register
>> renaming.
>
> Doesn't the compiler still map variables to registers for
> purposes of enhancing performance? The assumption is that
> the addressable set is faster to use than main memory. Thus
> the more that are are addressable for the compiler to
> allocate variables to, the better the performance
> independant of the factors you name. Wrong?

With renaming you can map numerous things to the same register though, and
things like renaming and replay allow you to hide the latency of trips to
main memory by doing other computations in their stead while you wait for
memory.

--
Aaron
!