2.3 & 2.5 Ghz Xserve Updates?

[MacRumors]

According to ThinkSecret (http://www.thinksecret.com/news/0412xsan.html), Apple's 1U server is set to receive a speed bump in January, likely at Macworld Expo San Francisco. Systems will be bumped to a 2.3GHz G5 processor, identical to what Virginia Tech received months ago for its System X cluster, although sources didn't dismiss the possibility that a 2.5GHz Xserve might emerge as well.

The update also relates to the upcoming release of Xsan - the new shared-storage solution due from Apple. The expected release is in the 'Fall of 2004', but new rumors place the possible release of the application possibly as late as January 2005. The current developer's Xsan Preview Build, 7N156, expires December 31, 2004.

[jackieonasses]

They need too. I wonder if they will just stick overly loud fans on the 2.5 or use liquid cooling...

[BornAgainMac]

Noise won't be as much of a factor in a computer room compared to an office.

[jackieonasses]

Noise won't be as much of a factor in a computer room compared to an office. That is what i meant. I would just put large amounts of fans, to save money without the liquid mechanism.

[andiwm2003]

does that mean the 2.0 G5's will then be available for my imacG5 20" that i will order next year? :D

[Mord]

whats with xsan i know it's a file system but whats the advantage of useing it?, as for xserves, fan noise is not much of an issue there loud as hell as it is so it cant get worse and frankly no one cares

[Trowaman]

I figured this was coming, just I expected it to happen at the end of November with new emacs. Oh well, updates are good.

[swissmann]

How big is the Xserve compared to a 17 inch powerbook?

[Mord]

giant

[MattG]

How big is the Xserve compared to a 17 inch powerbook?BIG

[maya]

They need too. I wonder if they will just stick overly loud fans on the 2.5 or use liquid cooling...

A 2.5GHz Xserver is great news IMO.

Apple is most likely going to use the new low powered G5 chips for the 2.5GHz model since no liquid cooling will be required and would most likly be less noisy and less power to drive it.

2.3GHz is already available however only to Virginia Tech.

This is also great news because it means that the PMG5 will either see a 2.8 - 3.0GHz models.

iMac G5 will be bumped to 2.0GHz in its rev B state.

And will we see a PowerBook G5, I wish MacRumors had some sort of bet on this one where we can wager money on. :)

[~Shard~]

2.3 GHz would be nice, but since they have the 2.5 GHz chip already at their disposal, it wouldn't surprise me to see that as an upgrade either. As for a MWSF release for this update, makes sense to me, I think it's a strong possibility.

And before this thread gets corrupted by all the G5 PowerBook whiners: no, just because the xServe is getting faster G5 chips and it is a relatively small enclosure, this does not mean we will be seeing G5 PowerBooks released at MWSF as well... :cool:

[~Shard~]

And will we see a PowerBook G5, I wish MacRumors had some sort of bet on this one where we can wager money on. :)

Oh, we will see one - just not at MWSF '05. If you think a G5 PowerBook will be released at MWSF then I'll be happy to take your money off your hands... :p :cool:

[mattroberts]

this storage solution, anybody have a bit more of an idea as to what is in it? (an educated guess is fine)

[varmit]

I would like to see both 2.3 and 2.5. Or 2.0 and 2.3. All dual processor accept the cluster node. Gives the ability to go cheaper or go for the gold with the highest.

[DPazdanISU]

I really want to buy an iMac but I can't stand the video card. Gimme a processor boost to 2ghz and even at least an optional upgrade to 128 video. Then an iMac will be in my room :rolleyes:

[maya]

Oh, we will see one - just not at MWSF '05. If you think a G5 PowerBook will be released at MWSF then I'll be happy to take your money off your hands... :p :cool:

The cheque is in the mail. ;) :)

[maya]

I really want to buy an iMac but I can't stand the video card. Gimme a processor boost to 2ghz and even at least an optional upgrade to 128 video. Then an iMac will be in my room :rolleyes:

What about the noise, for the love of think about the noise. ;) :)

[swissmann]

BIG

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?

[Mudbug]

And will we see a PowerBook G5, I wish MacRumors had some sort of bet on this one where we can wager money on. :)

www.flyonthemac.com

[outerspaceapple]

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?


My guess is Apple has already kinked out most of the bugs related to the PBG5, and is just waiting for an optimal time to release it. 2 weeks before christmas isn't exactly optimal.

Back to subject though, XServe G5s are closing in on those x86 servers in terms of GHz (although we all know they can already handle way more instructions-per-second), and this is great news for apple. Having a 10 XServe cluster running at 2.5GHz as opposed to 2.0 or 2.3 is a huge improvement.

Like another reader pointed out, this should also mean great things for the PMG5, iMac G5, and even possibly the PBG5.

[Rower_CPU]

Apple has a whole page devoted to it in their server info: http://www.apple.com/xsan/

Should answer people's questions.

[maya]

www.flyonthemac.com

Thank you. :)

[ThomasHobbes]

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?

When they're 1.7 Ghz G4's out now (Sonnet, confirmed that it is indeed a true 1.7, not overclocked like Giga Designs (1.6 to 1.73)) why go slower and way hotter with a G5?

Apple probably has 1.8 G4's and that's the next update.

[swissmann]

My guess is Apple has already kinked out most of the bugs related to the PBG5, and is just waiting for an optimal time to release it. 2 weeks before christmas isn't exactly optimal.

Back to subject though, XServe G5s are closing in on those x86 servers in terms of GHz (although we all know they can already handle way more instructions-per-second), and this is great news for apple. Having a 10 XServe cluster running at 2.5GHz as opposed to 2.0 or 2.3 is a huge improvement.

Like another reader pointed out, this should also mean great things for the PMG5, iMac G5, and even possibly the PBG5.

I agree with you. I hope you are right on the PBG5 - I'm much more in the market for one of those than an XServe. Maybe someday my comapany will be big enough to warrant a couple XServes though.

[CTerry]

Looks like rumours are like buses. You don't see one for ages and then 3 come along at once.

[MacsRgr8]

Looks like rumours are like buses. You don't see one for ages and then 3 come along at once.

And I am happy to see rumors once again. Not just "news".
:)

Someone will start "The Official MWSF '05 Thread" shortly, so all rumors will be piled up in that one. :D

[coolfactor]

If they're only gonna be at 2.5Ghz for the Xserves, then the industry (aka IBM) must've really "hit the wall" with the 90nm process. This'll be 1.5 years after they were hoping for 3.0Ghz.

Hopefully IBM's restructuring (selling off PC business) will allow more resources to go into chip-making. Let's go IBM, let's go! :cool:

[Nicky G]

If they're only gonna be at 2.5Ghz for the Xserves, then the industry (aka IBM) must've really "hit the wall" with the 90nm process. This'll be 1.5 years after they were hoping for 3.0Ghz.

Hopefully IBM's restructuring (selling off PC business) will allow more resources to go into chip-making. Let's go IBM, let's go! :cool:

Just because they have "hit the wall" with the 90nm 970, doesn't mean future "G5s" won't clock considerably higher. Look at the roadmap for the next few 970-variant revisions. They all start at around 3GHz I believe.

[i_am_a_cow]

When they're 1.7 Ghz G4's out now (Sonnet, confirmed that it is indeed a true 1.7, not overclocked like Giga Designs (1.6 to 1.73)) why go slower and way hotter with a G5?

Apple probably has 1.8 G4's and that's the next update.

ummmm, PBs are only 1.5 top end...

I wish they would update soon because I want one soon, and I don't want to buy an outdated one.

[eSnow]

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?

If you ever visited a server room, you'd know the answer: Servers can be cooled aggressively, even if it means they produce noise like a starting jet-engine and blow lots of energy in the process.

The same is obviously not true for a laptop computer.

[MacBandit]

ummmm, PBs are only 1.5 top end...

I wish they would update soon because I want one soon, and I don't want to buy an outdated one.


He's referring to recent release of 1.7GHz G4 upgrades from Sonnet for the Cube and G4 PowerMacs. They are of a variant that is low enough power and low enough heat that they could be installed in a Powerbook.

[MacBandit]

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?


YES!! The XServe is huge as compared to any laptop. The 17" Powerbook has the following dimensions.

Size and weight (17-inch model)

* Height: 1.0 inch (2.6 cm)
* Width: 15.4 inches (39.2 cm)
* Depth: 10.2 inches (25.9 cm)

Total volume = 157.08 cubic inches.

The XServe has the following dimensions.

Size and weight (XService)

* Height: 1.73 inches (4.4 cm)
* Width: 17.6 inches (44.7 cm)
* Depth: 28 inches (71.1 cm)

Total volume = 852.54 cubic inches.

The XServe is 5.43 times larger then the 17" Powerbook.

A closer comparison would be the G5 iMac but there are serveral issues with that comparison for on the G5 iMac is also huge as compared with a 17" Powerbook. Also The G5 iMac doesn't have a keyboard built in and use the screen for one side of the housing thus not as much material is needed making it thinner yet. Finally the iMac isn't designed for the beating a Powerbook has to endure so it's not as strongly built and thus thinner yet.

I'm not saying a G5 Powerbook is not possible but it is an error to look at the iMac or XServe and ask why they can't build the Powerbook.

[Chomolungma]

[/QUOTE]I'm not saying a G5 Powerbook is not possible but it is an error to look at the iMac or XServe and ask why they can't build the Powerbook.[/QUOTE]

Just because Dell can do it i.e. making a 10 lbs 2 inch thick laptop, people will assume Apple can do it too.

I rather have a stylist computer over a computer that is 200 mhz higher!

-

[MacBandit]

Just because Dell can do it i.e. making a 10 lbs 2 inch thick laptop, people will assume Apple can do it too.

I rather have a stylist computer over a computer that is 200 mhz higher!

-


Exactly. Apple adheres to a certain level of quality and functionality that forces then to cut back on some technologies at times. They could sell a 17lb 2" G5 aptop right now if they wanted to. All they would have to do is put a lid that doubles as a fold down keyboard and a slim battery pack for the bottom of the case and tada you have the G5 lugable.

[maya]

YES!! The XServe is huge as compared to any laptop. The 17" Powerbook has the following dimensions.

Size and weight (17-inch model)

* Height: 1.0 inch (2.6 cm)
* Width: 15.4 inches (39.2 cm)
* Depth: 10.2 inches (25.9 cm)

Total volume = 157.08 cubic inches.

The XServe has the following dimensions.

Size and weight (XService)

* Height: 1.73 inches (4.4 cm)
* Width: 17.6 inches (44.7 cm)
* Depth: 28 inches (71.1 cm)

Total volume = 852.54 cubic inches.

The XServe is 5.43 times larger then the 17" Powerbook.

A closer comparison would be the G5 iMac but there are serveral issues with that comparison for on the G5 iMac is also huge as compared with a 17" Powerbook. Also The G5 iMac doesn't have a keyboard built in and use the screen for one side of the housing thus not as much material is needed making it thinner yet. Finally the iMac isn't designed for the beating a Powerbook has to endure so it's not as strongly built and thus thinner yet.

I'm not saying a G5 Powerbook is not possible but it is an error to look at the iMac or XServe and ask why they can't build the Powerbook.

I am sure we are forgetting that the iMac G5 also has its PSU in the case and a powerbook or iBook have they adapters outside.

Speakers on a notebook are always rubbish.

You also forget that the imac G5 has a thick layer of white plastic and clear acetate and the backing for the VESA mount and stand to sit stable. All those attribute to the overall size. Plus the iMac G5 is using the first GEN G5 chips that were included in the rev A PMG5.

I am sure most of the delays have to deal with power consumption and the NEW low powered G5 chips should help in this area. Heat is always a problem look no further than the PowerBook G4 and iBook G4.

I remember that the Ti G4 PB also had heat issues.

Fitting in a 1" enclosure was pushed buy the industry its not a rule. the older powerbooks even the new ones are thicker than 1" so why are people complaining.

Suddenly people cannot carry more than 4.9 lbs in they backpack or hand. :rolleyes: <-- and YES I also travel with my PowerBook, and its not a burden, the only burden is the more things I have to carry around or loose for that matter.

[maya]

Exactly. Apple adheres to a certain level of quality and functionality that forces then to cut back on some technologies at times. They could sell a 17lb 2" G5 aptop right now if they wanted to. All they would have to do is put a lid that doubles as a fold down keyboard and a slim battery pack for the bottom of the case and tada you have the G5 lugable.

Apple and Steve Jobs, also toots that they have the BEST engineers and invest in R&D big time. Might as well get what you pay for. :rolleyes:

Why do some of you have the need to stand up for Apple, are you on they payroll. If you were that is another story.

[sjl]

this storage solution, anybody have a bit more of an idea as to what is in it? (an educated guess is fine)
The easiest way to think of Xsan is to think about NFS, and other networked filesystems. You have multiple computers, all accessing the same filesystem at the same time. With NFS and similar, the server does the actual operations, preventing any corruption from occurring (due to two or more systems writing to the same file at the same time.)

Xsan, CXFS, and similar products (Sistina's GFS? -- now part of Redhat) take this to the logical next step. Instead of relying upon a TCP-IP network to allow multiple systems to access a single filesystem simultaneously, they take advantage of the SAN infrastructure to do the same job over the SAN. It's literally the case that you have one raw disk hooked up to several systems at the same time; in principle, you could do the same thing with Firewire and SCSI hard drives. (SCSI would be limited by the number of devices on the chain, so for most purposes wouldn't be practical, especially if you want to RAID the physical drives.)

In order to avoid filesystem corruption, CXFS (and almost certainly Xsan) use a "metadata server". Each system allocates storage through the metadata server, but actually accessing that storage is done directly. Things like updating directory entries and so forth are also done through the metadata server. Often, the metadata server is clustered, to cope with unexpected hardware failure and other such lossage.

All of this is most useful when dealing with large files, such as media editing. If you're dealing with smaller files, like Word documents, etc., standard networked filesystems are most likely to be far more cost effective.

If you need this sort of capability now, talk with SGI. CXFS is available for OS X right now. Xsan is still under testing. I actually might have been able to get a job working on the OS X port of CXFS; I didn't bother applying for various reasons.

[sjl]

ummmm, PBs are only 1.5 top end...

I wish they would update soon because I want one soon, and I don't want to buy an outdated one.
Face facts. If you can buy it, it's obsolete. The only question is how much so. Buying the bleeding edge will always be exorbitantly expensive. Me? I'm quite happy with my 1.25 GHz 15" PowerBook, thank you very much.

[MacBandit]

I am sure we are forgetting that the iMac G5 also has its PSU in the case and a powerbook or iBook have they adapters outside.

Speakers on a notebook are always rubbish.

You also forget that the imac G5 has a thick layer of white plastic and clear acetate and the backing for the VESA mount and stand to sit stable. All those attribute to the overall size. Plus the iMac G5 is using the first GEN G5 chips that were included in the rev A PMG5.

I am sure most of the delays have to deal with power consumption and the NEW low powered G5 chips should help in this area. Heat is always a problem look no further than the PowerBook G4 and iBook G4.

I remember that the Ti G4 PB also had heat issues.

Fitting in a 1" enclosure was pushed buy the industry its not a rule. the older powerbooks even the new ones are thicker than 1" so why are people complaining.

Suddenly people cannot carry more than 4.9 lbs in they backpack or hand. :rolleyes: <-- and YES I also travel with my PowerBook, and its not a burden, the only burden is the more things I have to carry around or loose for that matter.


No I thought of those things and yes it does have a thicker case then a Powerbook but if you factor in the fact that it only has a case on the back and not on the back and front like a Powerbook (because the screen is the front) then it's not as big a difference. Also all laptops have a built in Powersupply. The external powersupply is a converter to down conver AC to usually 12VDC. The internal Powersupply regulates battery power and distributes power to all the individual power consumers (i.e CD/DVD, PCMCIA, Wireless card, LCD, CPU, etc.).

I was just trying to say with my post that the engineering required to put a G5 in an iMac is no where near as difficult as that of a laptop. Also while the 1" standard is self adhered it would be a mistake to make a laptop too much thicker or heavier as it would look like a downgrade by consumers.

[MacBandit]

Apple and Steve Jobs, also toots that they have the BEST engineers and invest in R&D big time. Might as well get what you pay for. :rolleyes:

Why do some of you have the need to stand up for Apple, are you on they payroll. If you were that is another story.


You might also ask why some people have the need to tear Apple down. I don't worship Apple like some and I'm not one that thinks Apple can do no wrong but I do think that on the whole they make a very nice product expense aside.

[maya]

You might also ask why some people have the need to tear Apple down. I don't profit Apple like some and I'm not one that thinks Apple can do no wrong but I do think that on the whole they make a very nice product expense aside.

If you are stringing the cord that I am "tearing down" Apple, you are wrong. I am neutral in these matter as with any company, I do expect what I pay for, if I am paying 1000+ I expect that amount of quality and service. :)

[MacBandit]

If you are stringing the cord that I am "tearing down" Apple, you are wrong. I am neutral in these matter as with any company, I do expect what I pay for, if I am paying 1000+ I expect that amount of quality and service. :)


No, no, I was infering no such thing. I was simply stating a counter point to your question.

[Chomolungma]

it is inevitable :D

[rdowns]

I really want to buy an iMac but I can't stand the video card. Gimme a processor boost to 2ghz and even at least an optional upgrade to 128 video. Then an iMac will be in my room :rolleyes:

Hope you're prepared to wait a while. The iMac has been shipping for only 10 weeks. Furthermore, the delay in the iMac was (reportedly) heat issues. What makes you think they'll be able to bump the processor and video card in a Rev B? Faster chip, faster FSB, better video card= way more heat. The iMac is awesome, you want it/need it, buy it!

[CTerry]

it is inevitable :D
I predict that the new iFlamingo is inevitable too. The iFlamingo will the first computer tower in the shape of a hilarious pink bird. IT'S INEVITABLE!

[~Shard~]

The cheque is in the mail. ;) :)

Thanks, didn't think it would be that easy! Wait a second, you don't have my address.... ;) :cool:

[~Shard~]

www.flyonthemac.com

I never knew that site even existed! Man, I'm going to be having some fun on there, methinks.... :cool:

[swissmann]

If you ever visited a server room, you'd know the answer: Servers can be cooled aggressively, even if it means they produce noise like a starting jet-engine and blow lots of energy in the process.

The same is obviously not true for a laptop computer.
That's a very good point. I'm wondering how much cooler a 1.6 is than a 2.5 though?

[swissmann]

When they're 1.7 Ghz G4's out now (Sonnet, confirmed that it is indeed a true 1.7, not overclocked like Giga Designs (1.6 to 1.73)) why go slower and way hotter with a G5?

Apple probably has 1.8 G4's and that's the next update.

Is this a MHz myth thing? Would a G5 at 1.6 outperform a G4 at 1.8?

[JFreak]

this storage solution, anybody have a bit more of an idea as to what is in it? (an educated guess is fine)

imagine having 100 macs in a network and being able to let your network server use for example half of every mac's hard drive as one combined giant storage space...

[JFreak]

Is this a MHz myth thing? Would a G5 at 1.6 outperform a G4 at 1.8?

it all depends. in pro audio work (protools) a 1.5GHz G4 powerbook pretty much equals to a single-cpu 1.6GHz G5 powermac.

[MacBandit]

Is this a MHz myth thing? Would a G5 at 1.6 outperform a G4 at 1.8?

For FPU and high bandwidth intensive tasks the G5 would eat the G4 alive. For regular use the G4 and current iteration of the G5 are pretty much equal clock to clock.

[ASP272]

I didn't have time to read the entire thread, but does anyone speculate a 3.0ghz Xserve? I thought I had heard a previous rumor somewhere about a possible jump straight to the 3ghz. That would be awesome!

[JFreak]

I didn't have time to read the entire thread, but does anyone speculate a 3.0ghz Xserve? I thought I had heard a previous rumor somewhere about a possible jump straight to the 3ghz. That would be awesome!

a 3GHz G5 powerbook would also be awesome, but that too will not happen too soon...

[morkintosh]

But so much size difference that a PowerBook couldn't fit a single 1.6 GHz processor in it and still have room to cool?

Yes, 1U != 1 inch ... nevermind that most kU form factor machines (considering that they are MUCH longer than a powerbook) have a series of fans that sit vertically in the center and push air around the box and out the back, you can't fit that in a laptop form factor.

I will reiterate what apple has already said: NO G5 POWERBOOKS FOR SOME TIME!! Give it up already!

[AidenShaw]

imagine having 100 macs in a network and being able to let your network server use for example half of every mac's hard drive as one combined giant storage space...

...and imagine having pieces of your file corrupted or inaccessible because someone turned his computer off for the weekend... :mad:

Xsan uses a central Fibre Channel disk system (Xserve RAID) that is shared by more-or-less diskless clients. You need a $500 FC card for each system on the Xsan, and a FC switch to interconnect them. (about $6000 for an 8-port switch (http://shopper.cnet.com/SANbox2_8_-_switch_-_8_ports/4014-6432_9-30626852.html))

http://www.apple.com/xsan/

[deputy_doofy]

...
I will reiterate what apple has already said: NO G5 POWERBOOKS FOR SOME TIME!! Give it up already!

So, by "NO," you mean maybe this January, right? ;)

[AidenShaw]

I wonder when XServe will get better I/O capabilities - the two 100 MHz PCI-X slots on the XServe are getting pretty long in the tooth...

The Xserve has a single theoretical 800 MBps I/O bus (or 1GBps if you only have one card), while Intel is now pushing PCI Express on the servers and workstations (the Dell 1850 1U dual 64-bit Xeon server has 6000 MBps PCI Express I/O (one 4GBps and one 2GBps) http://www1.us.dell.com/content/products/productdetails.aspx/pedge_1850?c=us&cs=555&l=en&s=biz&~page=1&~tab=specstab#tabtop, the HPaq DL360 1U dual 64-bit Xeon has 8000MBps (two 4GBps))

Some server I/O needs can no longer be met by PCI-X - a single InfiniBand or 10GbE card needs more bandwidth than 133 MHz PCI-X can deliver. Multiport 2 Gbps FC cards can also eat a PCI-X.

[MacBandit]

Yes, 1U != 1 inch ...


Umm, no it doesn't. The XServe is 1.73 inches thick. 1U = 1.75".

[AidenShaw]

...most kU form factor machines (considering that they are MUCH longer than a powerbook) have a series of fans that sit vertically in the center

Note the 7 high RPM fans next to the CPUs....

http://images.apple.com/xserve/images/xs_architechturetop_010604_.jpg

[MacBandit]

Note the 7 high RPM fans next to the CPUs....

http://images.apple.com/xserve/images/xs_architechturetop_010604_.jpg


Also the 2 large blower fan inates in the front.

http://images.apple.com/xserve/images/xs_indextop_010604_02.gif

[swissmann]

it all depends. in pro audio work (protools) a 1.5GHz G4 powerbook pretty much equals to a single-cpu 1.6GHz G5 powermac.

Really? This surprises me. Are we all just loving the G5 because it is already to 2.5 GHz and has potential to grow that way then. Or is it because it comes with a faster bus, 64 bit, and more RAM capabilities.

[swissmann]

For FPU and high bandwidth intensive tasks the G5 would eat the G4 alive. For regular use the G4 and current iteration of the G5 are pretty much equal clock to clock.

So you are saying if I type letters I am OK with a G4 or even an Mac Plus for that matter. But if I am doing video work and 3D design I probably could use a G5. I guess it is hard to define regular use. I have a Dual 1 GHz G4 Powermac and a Dual G5 Powermac 2 GHz and I even appreciate the difference in small things like navigating the finder. When working with multiple tracks in Final Cut Pro I appreciate it that much more.

[swissmann]

Yes, 1U != 1 inch ... nevermind that most kU form factor machines (considering that they are MUCH longer than a powerbook) have a series of fans that sit vertically in the center and push air around the box and out the back, you can't fit that in a laptop form factor.

I will reiterate what apple has already said: NO G5 POWERBOOKS FOR SOME TIME!! Give it up already!

I guess that the space for it to fit is isn't so much the problem as it is space for air to travel around is. However it seems to me that the 17 inch powerbook probably has a lot of potential dead air space. Of course Apple says not for some time or else they would kill current PowerBook sales.

[swissmann]

YES!! The XServe is huge as compared to any laptop. The 17" Powerbook has the following dimensions.

Size and weight (17-inch model)

* Height: 1.0 inch (2.6 cm)
* Width: 15.4 inches (39.2 cm)
* Depth: 10.2 inches (25.9 cm)

Total volume = 157.08 cubic inches.

The XServe has the following dimensions.

Size and weight (XService)

* Height: 1.73 inches (4.4 cm)
* Width: 17.6 inches (44.7 cm)
* Depth: 28 inches (71.1 cm)

Total volume = 852.54 cubic inches.

The XServe is 5.43 times larger then the 17" Powerbook.

A closer comparison would be the G5 iMac but there are serveral issues with that comparison for on the G5 iMac is also huge as compared with a 17" Powerbook. Also The G5 iMac doesn't have a keyboard built in and use the screen for one side of the housing thus not as much material is needed making it thinner yet. Finally the iMac isn't designed for the beating a Powerbook has to endure so it's not as strongly built and thus thinner yet.

I'm not saying a G5 Powerbook is not possible but it is an error to look at the iMac or XServe and ask why they can't build the Powerbook.


Awesome answer. Thanks! That does make for a huge difference in size. I didn't realize it was so deep.

[kenaustus]

What the rumor tells me is that IBM is getting good yields on the 2.3 gig G5. This, for me, opens up the chance that the PM range will also get a speed bump, with the 2.0 at the bottom, then the 2.3 and then 2.?, leaving the 1.6 and 1.8 for the iMac range - for now. It might also open up the eMac for a 1.6 before too long.

As for the G5 PB, it will be released when it is ready - meaning when Apple is satisfied with the various bits that will be critical, like cooling and battery life. I assume that there are a lot of prototypes that have been tested over the last 2 years and Apple just hasn't been satisfied. I also assume that they are working very hard with IBM to get a G5 PB on the market as soon as possible. I decided in April, when the new G4 PBs were announced, to update my old 667 PB. I wanted the power improvement for business trips and felt that I could get a good price for it when the G5 PB was announced and the initial dust settled.

[steveh]

Umm, no it doesn't. The XServe is 1.73 inches thick. 1U = 1.75".

That's exactly what he said:


Yes, 1U != 1 inch ...

"!=" does not equal "=", after all.

[MacBandit]

So you are saying if I type letters I am OK with a G4 or even an Mac Plus for that matter. But if I am doing video work and 3D design I probably could use a G5. I guess it is hard to define regular use. I have a Dual 1 GHz G4 Powermac and a Dual G5 Powermac 2 GHz and I even appreciate the difference in small things like navigating the finder. When working with multiple tracks in Final Cut Pro I appreciate it that much more.

Well yeah a Mac plus would be fine for text. I'm not surprized that a 1GHz increase in clock cycles shows a speed increase in every day use. I did say comparable clock to clock afterall.

[wdlove]

I didn't have time to read the entire thread, but does anyone speculate a 3.0ghz Xserve? I thought I had heard a previous rumor somewhere about a possible jump straight to the 3ghz. That would be awesome!

I was also thinking about the same issue as I read through the thread. Just hope that this isn't any indication for the Power Mac. Like others looking forward to seeing a 3 GHz.

[deputy_doofy]

Umm, no it doesn't. The XServe is 1.73 inches thick. 1U = 1.75".
Yes it does.
!= means NOT EQUAL in C, C++, Java, Javascript....
He could have also used:
<> (basic, VB, VBScript, etc...)

I just wanted to be a sm@rt@$$.

[AidenShaw]

"!=" does not equal "=", after all.

you mean "!=" does not equal "==", don't you?

[MacBandit]

Yes it does.
!= means NOT EQUAL in C, C++, Java, Javascript....
He could have also used:
<> (basic, VB, VBScript, etc...)

I just wanted to be a sm@rt@$$.

Okay thanks I always new I would forget C++ if I didn't use it long enough. :rolleyes:

[MikeBike]

For FPU and high bandwidth intensive tasks the G5 would eat the G4 alive. For regular use the G4 and current iteration of the G5 are pretty much equal clock to clock.

- Won't the Dual-Core G4 fix that FSB problem?
- Any new info on the FreeScale Dual-Core G4?

[alfismoney]

I wonder when XServe will get better I/O capabilities - the two 100 MHz PCI-X slots on the XServe are getting pretty long in the tooth...

The Xserve has a single theoretical 800 MBps I/O bus (or 1GBps if you only have one card), while Intel is now pushing PCI Express on the servers and workstations (the Dell 1850 1U dual 64-bit Xeon server has 6000 MBps PCI Express I/O (one 4GBps and one 2GBps) http://www1.us.dell.com/content/products/productdetails.aspx/pedge_1850?c=us&cs=555&l=en&s=biz&~page=1&~tab=specstab#tabtop, the HPaq DL360 1U dual 64-bit Xeon has 8000MBps (two 4GBps))

Some server I/O needs can no longer be met by PCI-X - a single InfiniBand or 10GbE card needs more bandwidth than 133 MHz PCI-X can deliver. Multiport 2 Gbps FC cards can also eat a PCI-X.

First of all, the XSAN system is set up to run off of XRAID, which apple (and all other raid makers) ship with redundant power supplies, controller cards, and disks to prevent drive crashes from bringing down a system and also feature cell phone/email/pager/big flashing network alert systems that are automated at the hint of any problem. While none of these are foolproof, they do add up to a system that, when properly set up and administered, is infinitely more reliable than any hard disk the average consumer has ever used. There's data security built in that works fairly well along with a lot of software administration.

More importantly the XSAN is designed to relay everything across a fibre channel hub that moves MUCH faster than Gbit ethernet and is only meant to serve high end systems where, when you drop 2x$13,000 for two raid arrays plus $4000 for an xserve plus $4000 for a switch plus $5000 in backup parts and another $14,000 for a tape backup system you don't really need to worry about the tiny expense of buying a $500 card for each G5 you hook up to it. Not to mention the fact that you have a standards-compliant technology as opposed to 10Gbit, which still hasn't been finalized and won't be for a few years yet.

As for the PCIExtreme addition, realize that you've got a million other drive limitations, such as ATA only running at 150MBps, plus the channel limitations of fibre and ethernet, that are much more limiting than your PCI bus, so while I'd like to see apple make the change I think it's a little bit less pressing than simple processing power and room for 16 gigs of RAM...

[MacBandit]

- Won't the Dual-Core G4 fix that FSB problem?
- Any new info on the FreeScale Dual-Core G4?


It should if it ever makes it into Apples lineup but it will not fix the FPU.

[broken_keyboard]

SAN = Storage Area Network. Heh. What kind of self-important weenie made that name up?

[AidenShaw]

First of all, the XSAN system is set up to run off of XRAID, which apple (and all other raid makers) ship with redundant power supplies, controller cards, and disks to prevent drive crashes from bringing down a system and also feature cell phone/email/pager/big flashing network alert systems that are automated at the hint of any problem. While none of these are foolproof, they do add up to a system that, when properly set up and administered, is infinitely more reliable than any hard disk the average consumer has ever used. There's data security built in that works fairly well along with a lot of software administration.

No argument at all, but what does that have to do with my comments about the XServe falling seriously behind the curve for I/O capabilities - even considering the limitations of entry-level 1U servers?


More importantly the XSAN is designed to relay everything across a fibre channel hub that moves MUCH faster than Gbit ethernet and is only meant to serve high end systems where, when you drop 2x$13,000 for two raid arrays plus $4000 for an xserve plus $4000 for a switch plus $5000 in backup parts and another $14,000 for a tape backup system you don't really need to worry about the tiny expense of buying a $500 card for each G5 you hook up to it.

Look again, I was replying (in my other post, not the one that you quoted) to someone who seemed to think that Xsan would pool all the free space on all your Macs into one uber-filesystem.

I quoted some prices to point out to him that Xsan is not low-end freeware - I agree that you'll have very serious amounts of money invested in order to use it. I ordered two 16-port Brocade 2Gbps Fibre Channel switches today, and 20 more dual port 2 Gbps HBAs. And more than $5000 worth of fibres to connect them. Fibre Channel is serious money....


Not to mention the fact that you have a standards-compliant technology as opposed to 10Gbit, which still hasn't been finalized and won't be for a few years yet.


Sorry, but you are wrong here. 10GbE is IEEE 802.3ae, adopted in 2002. 10GbE is real, and is available from many manufacturers today. (e.g. http://www.foundrynet.com/products/l23wiringcloset/edgeiron/24GS_48GS_8x10G.html or http://news.com.com/HP+signs+on+high-speed+networking+start-up/2100-1010_3-5477022.html)

If you were paying attention to 10GbE, you'd see that the hot buzz is that it's moving from a network backbone role (your gigabit ethernet switches link to each other with 10GbE) to a server to switch role.


As for the PCIExtreme addition, realize that you've got a million other drive limitations, such as ATA only running at 150MBps, plus the channel limitations of fibre and ethernet, that are much more limiting than your PCI bus, so while I'd like to see apple make the change I think it's a little bit less pressing than simple processing power and room for 16 gigs of RAM...

It's PCI Express.... Was that a mistake, or an attempt to be cute?

Plus, SATA is 150 MBps per disk, so a 7 disk array theoretically exceeds the bandwidth of PCI-X. Only 7 disks.... In practice, a 6 disk array would be bandwidth-limited. (Even though the media transfer rate wouldn't be a problem, the transfers to and from those big caches on the disk would be affected. That means more latency.)

This is very application dependent. A 1U NFS server probably won't be PCI-X limited - unless you put a quad port 2Gbps FC HBA or a 10GbE or IB card into it. Even then, it would probably run out of CPU power before hitting hard PCI-X limits.

But think about the Xserve poster child - the VA Tech super-cluster. PCI Express is 3 times faster than PCI-X for InfiniBand, with 20% less latency. Instead of 7th on the supercomputer list, it might have been in the top 5 if the Xserve had current technology for I/O.

And please DO NOT underestimate the importance of lower latency.... Too often people focus on sustained bandwidth without realizing that latency is the real problem. Some applications need MB/sec, but many others need IOs per second.

"Latency" usually means that you're waiting for something. It doesn't matter how fast your CPU or memory bus happen to be - everyone waits at the same speed!

[alfismoney]

sorry i replied to another posting at the start of my quoted response to you, i wasn't paying much attention when i was writing (PCIExtreme and all)

good point on the latency issue, i hadn't considered that in my numbers and you're completely right there. it will make a big speed difference. of course, that doesn't change my thought that flat out bus speed isn't the real issue here, only latency is. allow me to explain.

if you hand build your own lvd scsi cables out of gold (i've seen it done in labs) for maximum efficiency and use 15,000rpm drives you're not going to come close to 100MBps in regular usage. yes, you can get burst rates that are faster, but in regular usage it just doesn't happen. over serial ata, written across seven drives, you start to get higher throughput but you're not going to move enough data through the raid system controller to max it out, nor are you going to max out your fibre channel connection. sure, it will happen on occasion, but not regularly. this is why you need a full 7 disk setup to handle uncompressed high resolution video signals. the latency will improve drive response time but not improve the terrible throughput you end up getting from each drive. In the end, my argument is that you're never going to be moving more than 800MBps over this particularl pci bus until there's more data moving over your raid array, which apple's current fibre implementation just doesn't do. nor do most people need it. the upgrade is currently worthwhile only for the latency, not the megabyte speed.

[swissmann]

Well yeah a Mac plus would be fine for text. I'm not surprized that a 1GHz increase in clock cycles shows a speed increase in every day use. I did say comparable clock to clock afterall.

I guess my question I still have for myself is - are there advantages the G5 has over the G4 at the same clock cycle? It just seems like such a radically different chip there must be more to it than MHz.

[gekko513]

But think about the Xserve poster child - the VA Tech super-cluster. PCI Express is 3 times faster than PCI-X for InfiniBand, with 20% less latency. Instead of 7th on the supercomputer list, it might have been in the top 5 if the Xserve had current technology for I/O.
Your other points are quite valid but I doubt that the VA Tech cluster would be much higher even with PCI Express. The reason why I doubt this is that the VA Tech cluster and the Spanish cluster also based on the PowerPC 970 has the highest performance per processor of all top 20 systems except the Earth Simulator. If the VA Tech was held back by PCI-X then the G5 processors would have to be even more superior than the list currently suggests. I know the G5 is a good processor but it isn't THAT good.

[gekko513]

But AidenShaw ... where did you find the numbers on the latency for PCI Express vs PCI-X. I think I've read that PCI Express was faster than AGP in throughput but had a higher latency, so I also assumed that PCI Express would have a higher latency than PCI, but it seems I was wrong.

[AidenShaw]

But AidenShaw ... where did you find the numbers on the latency for PCI Express vs PCI-X. I think I've read that PCI Express was faster than AGP in throughput but had a higher latency, so I also assumed that PCI Express would have a higher latency than PCI, but it seems I was wrong.

http://www.mellanox.com/products/shared/InfiniHost_III_Ex_HCA_PO_050.pdf

"PCI Express offers a dramatic jump in I/O bandwidth capabilities with two to four times the peak bandwidth of PCI-X.

The latest performance results demonstrate that InfiniHost Express is delivering almost 3 times the bandwidth of PCI-X and 25 times the bandwidth of gigabit Ethernet.

Additionally, this bandwidth is delivered with a 20% reduction in latency.

This performance will enable faster as well as more powerful clustering and storage solutions for the summer of 2004 as the new PCI Express Servers arrive in the market."


Assuming that results for one architecture (AGP vs. PCI-Express) translate to another (PCI-X vs PCI-Express) is risky, and in this case false.

[AidenShaw]

Your other points are quite valid but I doubt that the VA Tech cluster would be much higher even with PCI Express.

I think that you're right - the VAtech cluster might have moved to 6th from 7th, but the Itanium cluster at #5 is much faster than VA Tech. A boost from the communications wouldn't have been enough to jump that gap and beat the Itanium cluster.

Note, however, that real performance in super-cluster performance is heavily dependent on the bandwidth and latency of the interconnects. The LINPACKD test used for the Top500 ranking is less dependent on bandwidth and latency than many useful applications. So on real cluster applications, the benefits of PCI-Express might be more more dramatic.

InfiniBand's big advantage is that for its relatively low cost ($1500 to $2000 or so per connection) it's more or less in the same league as the expensive special-purpose cluster interconnects.

Intel systems with PCI-Express have an advantage in bandwidth and latency right now. In this spring's Top500 listing, don't be surprised if Xeon 64-bit clusters take over several of the spots in the top 5 or top 10. (Not because of InfiniBand on LINPACKD, but because it will help real applications scale to larger clusters - and coincidentally do well on LINPACKD.)


I know the G5 is a good processor but it isn't THAT good.

Right - it isn't THAT good on real applications, but on LINPACKD it IS that good. ;)

Even IBM says that the PPC970 performs unrealistically well on LINPACKD (http://www-03.ibm.com/chips/products/powerpc/newsletter/jun2004/ppc_process_at_work.html)....

"In practice, only a small portion of peak capacity is achieved because a processor is rarely scheduled to do simultaneous “multiply and adds” in double precision.

However, the LINPACK benchmark, which is often used to rank supercomputers (the Top500 Supercomuter list), makes extensive use of simultaneous multiply and add."

[The Red Wolf]

...In order to avoid filesystem corruption, CXFS (and almost certainly Xsan) use a "metadata server". Each system allocates storage through the metadata server, but actually accessing that storage is done directly...

Wonderful post. I was going to do a write up, but I've come in to this thread a little late and your post was wonderful.

[The Red Wolf]

What the X-Serve needs is Dual Power supplies like the X-RAID, hard to fit in a 1U enclosure. Perhaps 2U or some very creative engineering. Backup power supplies in box are mandatory for enterprise data systems where I work. We could get allot of X-Serves if they just had that second power supply. Xsan running on X-Serves and X-RAIDs would be perfect for or server migration.

[AidenShaw]

What the X-Serve needs is Dual Power supplies like the X-RAID, hard to fit in a 1U enclosure.

HP, IBM, Dell and even SuperMicro (http://www.supermicro.com/products/system/1U/6014/SYS-6014P-8R.cfm) have 1U systems with dual power.


But you're right - Apple needs a 2U or 3U system with more expansion slots and more redundancy. A 2U with 6 disks and 3 PCI-X slots and dual power would give the Xserve better traction in many IT departments. (Not as much traction as a quad-CPU 4U unit with 6 slots, but better than an entry 1U.)

[MacBandit]

I guess my question I still have for myself is - are there advantages the G5 has over the G4 at the same clock cycle? It just seems like such a radically different chip there must be more to it than MHz.

Well yes it does. The two most obvious is that the PPC970 has a real FPU and a FSB that's about a minimum of 5 times faster.

[AidenShaw]

Well yes it does. The two most obvious is that the PPC970 has a real FPU and a FSB that's about a minimum of 5 times faster.


Funny that most of the charts at http://www.barefeats.com/imacg5.html show the difference in performance between the G4 and the G5 is more or less the frequency difference between the two.

For example, on one iMovie4 test:

- 83 sec - Dual 1.42 PM G4
- 62 sec - Dual 2.00 PM G5

Just on clock rate, you'd expect 59 sec for the G5 - but it scaled worse than the clock rate.

So much for "real FPU" and a 5x bus....

As always, the only benchmark that is really useful is the one that runs the programs that you run. LINPACKD on VAtech's supercluster doesn't tell you how fast your Imac will rip your CDs! Random architectural features like "real FPU" and "double-pumped hyper-transformer" don't tell you much either.

[MacBandit]

Funny that most of the charts at http://www.barefeats.com/imacg5.html show the difference in performance between the G4 and the G5 is more or less the frequency difference between the two.

For example, on one iMovie4 test:

- 83 sec - Dual 1.42 PM G4
- 62 sec - Dual 2.00 PM G5

Just on clock rate, you'd expect 59 sec for the G5 - but it scaled worse than the clock rate.

So much for "real FPU" and a 5x bus....

As always, the only benchmark that is really useful is the one that runs the programs that you run. LINPACKD on VAtech's supercluster doesn't tell you how fast your Imac will rip your CDs! Random architectural features like "real FPU" and "double-pumped hyper-transformer" don't tell you much either.

Yet in a number of results the G5 showed a larger then clock cycle increase in over-all performance.

1.42GHz to a 2GHz = 141% increase

Itunes 4 Convert 34Minutes
G5/2.0 = 61 secs
G4/1.42 = 112 secs
184% increase

FileMaker 7 - 12 Actions
G5/2.0 = 170 secs
G4/1.42 = 253 secs
149% increase

Also in gaming performance the FSB really shows a benefit.

In any case results are only as good as your original hardware comparison. You have to have similar HDD and video cards. In most cases BareFeats fails to do this and is notorious for showing the results it wants to. I would take any result they publish with a grain of salt equal to the size a G5 itself.

[AidenShaw]

In any case results are only as good as your original hardware comparison.


I didn't cite the iTunes - because that's often a test of the CD reader as well as the CPU. iMovie, however, is brute CPU.

If something like "FileMaker" is using files, then the faster SATA drives on the G5 could be a major reason for the better than clock result.

Anyway, BareFeats is pretty good at the "how does this generation Mac compare to the last generation". Maybe they don't isolate all the variables - but neither will the end user. With Apple's limited configuration choices, it's very hard to do strict comparisons with only one variable.

The end user just wants to know how one system compares to another, and it doesn't really matter to the end user if the improvement is due to the new disk or the double-pumped hyper-transformer. Is "this new Mac significantly faster than the last Mac" is the question.

[MacBandit]

I didn't cite the iTunes - because that's often a test of the CD reader as well as the CPU. iMovie, however, is brute CPU.

If something like "FileMaker" is using files, then the faster SATA drives on the G5 could be a major reason for the better than clock result.

Anyway, BareFeats is pretty good at the "how does this generation Mac compare to the last generation". Maybe they don't isolate all the variables - but neither will the end user. With Apple's limited configuration choices, it's very hard to do strict comparisons with only one variable.

The end user just wants to know how one system compares to another, and it doesn't really matter to the end user if the improvement is due to the new disk or the double-pumped hyper-transformer. Is "this new Mac significantly faster than the last Mac" is the question.


The original question was based on a CPU to CPU comparison not on the end user computer to computer.

[AidenShaw]

The original question was based on a CPU to CPU comparison....


Exactly why I picked iMovie and not an I/O-heavy test... :)


Anyway, to the original question:

are there advantages the G5 has over the G4 at the same clock cycle?

I'd make two additional comments....

1) swissman - you have a 1GHz G4 and a 2 GHz G5. Run your own timings, is the 2GHz more than twice as fast as the 1 GHz?

2) I think that many tests have concluded that for most applications the primary benefit of the G5 is clock speed - the CPI for the 2 chips is more or less the same, with perhaps a small advantage to the G4.

It will be very interesting when Moto^H^H^H^H Freescale comes out with new "G4" chips with fast busses, especially when they are dual core and have low power consumption!!

[MacBandit]

Exactly why I picked iMovie and not an I/O-heavy test... :)




That defeats showing off one of the benefits of the G5 which is in/out data throughput due to a vastly superior FSB.

[AidenShaw]

That defeats showing off one of the benefits of the G5 which is in/out data throughput due to a vastly superior FSB.


Not at all, the FSB is what moves data between memory and the CPU -- therefore helping CPU-intensive jobs get to memory.

The FSB isn't involved in I/O at all - the I/O goes from memory to the I/O busses (HyperTransport <-> PCI-X). DMA transfers the data to/from memory without the CPU (FSB) being in the path.

Only after the I/O system has moved the data into memory can it go over the FSB to the CPU. (and vice-versa for output)