The Intel Powermac / Powermac Conroe / Mac Pro thread - Page 12

You're a smart guy onlooker... I never understood why you were so intrigued with Alienware when you could build your own machines. Either way, I never was a fan of alienware... but now that Dell has acquired them... they are dust. On top of that, what dell has done with their technology is a disgrace. Have you seen the new dellienware computers? *throws up*


The functions and objects that are available through the coregraphics library are not direct to the gpu. In other words there is a ton of code that apple wrote to make coregraphics work. You create the object in place of an image. That object has the under the hood abilities to talk to the gpu... it's transparent to the dev really. But that object also adds some functions to manipulate the object. In other words... there isn't a clean way to say... use xx percent of the gpu vs. cpu when creating this image. It basically does all of that for you.

I suppose during the hardcore renderings... you could offload the creation of the image to the gpu... but honestly... i don't see that saving a lot of time. At least in cinema 4d (the only one i'm truly familiar with rendering)... it renders line by line. Dual processor it starts top and half way down and goes does.... line by line. Usually those renderings take some hardcore cpu TIME to get each line. So you offload a line to the gpu... it might take as much or close to as much time as to just have the cpu handle it. Then the final image is made... then what? Is it being manipulated afterwards? If so then yah CoreGraphics can help... but unless its being further manipulated once the rendering is done I fail to see how it can help. Maybe i'm missing something?

Either way, Have you used cinema on a pc with sli? If so how much did it help during modeling? Do you think alias and maxon would have to implement code for sli in the mac version if macs went sli?

I'm in a rush but I just wanted to say

I said that..

"Doesn't the lib determine what percentages can, or need to be offloaded in other similar situations already?"

Sorry; there's a little terminology confusion here. Usually "integrated" graphics are in the northbridge, while "discrete" graphics are a separate chip. But discrete graphics don't have to take up a slot; I predict Apple will put a discrete graphics chip on the Intel Xserve motherboard, leaving all the slots free.

Here are some quad Woodcrest vs. quad G5 numbers:

http://www.realworldtech.com/forums/...7567&roomid=11


Looks like Apple will be touting a 2X performance improvement.

Looks like I will be too.

Did you see the dicussion? Was that the real Linus Torvalds? And he likes it, he really likes it.

Will a 3 ghz Conroe then be basically about the same as a Quad g5 performance wise?

Oh shiii...I'd better get some ear plugs so I don't hear the quad-Woodcrest screaming.

IBwhat? Whatscale? P.What Semi? I can't hear nuthin'...I've got this quad-Woodcrest screaming here.

Make sure they aren't cheap ones.

http://arstechnica.com/news.ars/post/20060524-6898.html

Yep, that's him alright. First time I see him posting outside kernel mailing lists. Quite... interesting.

Woodcrest is shaping up to be pretty impressive indeed.

Not really all that necessary; it barely beats Opteron in some benchmarks, and it beats it by an OK maring in others. Considering that Opteron is using slower memory, is clocked lower, and is expected to move to a 65nm process soon, it's not that impressive.

What is impressive is seeing Intel admit their mistake with NetBurst and move on. To greener pastures.

Actually, according to the tests, and the description, that's not true.

first of All, there is this:
" there is still a lot of performance left on the table for Woodcrest. Current compilers, JVMs and applications have not been optimized for Woodcrest, and our system is using slower FBD-533 memory, rather than FBD-667."

Jon's conclusion, after much ado, is what matters in his article:

"In sum, when the more integer-intensive benchmarks start coming out, you should expect to see Woodcrest's lead over Opteron widen, AM2 or no AM2. Also, Woodcrest has much stronger SSE hardware, so its vector performance should be significantly higher than Opteron for properly optimized SSE code."

And, don't get into the MHz myth again. They are different designs. The actual clock speed doesn't matter. Power 5 is also clocked slower, so what?

From your own source:




The conclusion is only as important as the body itself.


Your own source uses the MHz "myth" (don't use Jobs' marketing BS please!) as a point of comparison.


They are both part of the same architecture.


Different architecture - different rules.

Sure, but Core Solo, Pentium M, Athlon XP and Pentium 4 are all part of the same architecture too. Yet a 1.6 GHz Core Solo is faster than a 1.6 GHz Pentium M, which is faster than a 1.6 GHz Athlon XP, which is faster than a 1.6 GHz Pentium 4. Same amount of cores (one). Same architecture (x86). Same clock speed (1.6 GHz). Yet, awfully large differences. Of course, front-side bus and cache size play a large role, but that's hardly all there is to it. If they all had a 100 MHz bus and 512 KB of L2 cache (and no L3 cache), the Core Solo would likely still be fastest.

The problem with Woodcrest (and what's going to delegate it to the workstation class machines) is the Front Side Bus. It took the Pentium 4 something like...400 clocks to fill the L2. The Opteron does it in under 10. HyperTransport is much more scaleable then the 50 year old FSB design and Intel needs to realize that, join the HT consortium, and throw it into Core 3. Woodcrest looks like a very viable Power Mac replacement chip though.

FSB isn't the issues. Woodcrest uses a DiB (Dual Independent Bus) the L2 cache is 4 or 8MB and ondie running at cpu speed. The FSB of Woodcrest has been cranked up to 1333Mhz.

Intel has CSI which is their Hypertransport like product. Frankly ondie memory controllers are wonderful if your applications are sensitive to memory latency but if you just need bandwidth a fast FSB is fine and allows for updating the controller a lot easier.

so far, even the DDR2 socket designs have shown no improvement from the increased memory speeds, so it doesn't matter. As the Woodcrests were using slower memory then they can, even though it was faster than that in the Opterons, it more than balances out.






You should have read the articles he linked to.



True, but, again read the other articles.



But not the same designs. What is the speed of the Zeons that the Opterons were beating? And what was their speed? Different designs, and not totally the same architecture either. Netburst was very different from the Opterons. The new Core design is closer to the way AMD has been doing things, but with several advantages, as was noted. As was also noted in the links, that Woodcrest has a way to go in performance improvement. It has much more "leg" than the K8, which is reaching its limits.

[/QUOTE]

With that much L2 on a server, you run the risk of cache thrashing, which will severely limit the life of the processor. Hypertransport is pretty much useless with one processor, but 2+ processors really shows its strength. Processor 1<->Processor 2 is much faster then Processor 1 <-> Northbridge <-> Processor 2.

That's a new one. Where did you read that a large cache gives problems with cache thashing? normally, it a cache that's too small that has that problem. Besides, if the look ahead which determines what will be in the cache is good, these problems won't occur. What does this have to do with the life of the CPU?

Agreed, cache thrashing is too little cache, hitting the cache before memory and never getting anything because nothing valuable is stored in cache. Only downfall of too much cache is it starts to take too long to go through the cache to make sure what the cpu is looking for isn't in there. Which of course beats the purpose of cache...... since it's supposed to be extremely quick.

The whole point to cache is that is is much faster than main memory. It also doesn't have the delays associated with having to go to main memory. The information in cache is known, so the cpu doesn't have to search through the cache to find what it wants. It just gets it. Very little delay involved.

But, what about the statement that it leads to a shortened cpu life?

Heh I wasn't the one that made that statement :-P .... asking the wrong person

Ah, yes, sorry.

It's late.

ok,

so I don't wanna hijack the thread or anything.

but my guess is we're only about a quarter (max) away from the PM's successor's (MP? ) release....

so what do y'all think the specs will roughly be?

low end
dual dual 2,5GHz conroe/woodcrest?

mid
dual dual 2,7GHz conroe/woodcrest?

top
dual dual 3Ghz conroe/woodcrest? (do they even clock that fast already?)

FSB, cache etc speculation aside, which chips are available now or w/i a month or so that would at least match the current PPC based models in terms of performance..... are there chips available today from Intel at a similar price range that will kick the quad G5 in the knackers ? ? ?

ufo

Mass rollout of Woodcrest comes in June. Apple has to deliver the nextgen Powermacs by late June or they'll get lost in the shuffle. Everyone...and I mean everyone with workstation/server products is gearing up for Woodcrest.

Woodcrests come in 1.86/2.0/2.33/2.66/3.0 GHz speeds. Based on the pricing, I'd bet on Quad-2.0, Quad-2.33, Quad-2.66, simply because 2 of the 2.33 chips aren't gonna fit in the budget for a $2000 computer. I could see the top of the line affording 2 X 3.00 GHz, just to do it, though.

Woodcrest pricing: http://www.theinquirer.net/?article=29510

Conroe isn't multi-processor. They'll be relatively cheap, but they'll be standard for mid-range to high-end desktops, not workstations.

I assume that Apple will put Conroe into the low/mid range Power Macs. Woodcrest will be the high end though...most definetly. An Octomac.

Yes but remember, apple gets HUGE discounts from bulk. So it could still be possible to go 2.66.

I wouldn't count out 2x3ghz either... that'd really stick it to IBM for not delivering, switching to intel directly to 3ghz... steve's like that you know =)

Hmm...so I guess we won't see the PowerMac being released before August...you're right about Steve. I know he's itching to go up on stage and finally exclaim "We're at 3GHz! And only Intel could bring us there" just to stick it to IBM. Releasing the 3GHz machine without an announcement or with a delayed announcement just wouldn't do it for Steve.

I hope Steve proves me wrong. I want a new computer today*.

*today = June 19th.

Did i miss something? Why not before august? Cause it's steve?

The Powermacs are coming before August.

Granted this is HP but

HP announced Generation 5 servers using Xeon 5000 and 5100 dual-core procs


My emphasis added. Granted Apple "could" wait to the first week of Aug and WWDC to announce but by then workstation/server using Woodcrest will have been shipping for almost 6 weeks. I'd not expect too much fanfare with Apple joining the party over a month late.

You know Steve is going to rub that in their faces BIG time! My hats off to intel already, but that is the icing on the cake.


I don't think Apple is all that concerned about 6 weeks. Maybe they will announce Xserves before then to sweeten the pot, and get people anxious with an end note like: "See you all at WWDC", but I still think Apple will hold out on the PowerMac until then. I think It's the Principal of the 3GHz thing at WWDC that has all the appeal for Apple. Developers have not forgotten, and neither did Apple. I think developers want to hear it, and SJ is more than happy to oblige them.

Ok... so has anyone even determined if the mac pro will be sporting conroe or woodcrest? I mean from the sound of it... the mac pro's should have woodcrest. If they didn't only the xserve would have woodcrest, does that make sense?

I bank on this:

XServe: Woodcrest
Mac Pro: Woodcrest (or both)
iMac: Conroe
MacBook Pro: Merom
MacBook: Yonah
MacMini: Yonah

What do you guys think?

Why wouldn't they be concerned. They uses the same hardware that every PC manf is using. It's going to look a bit odd that they are joining the party 6 weeks late. Apple had leeway to delay products when they had their own platform. Now they just will look laggardly. I think Xserve would be fine for WWDC...Powermac replacements too late.

3Ghz is nothing at this level clients want more proof of performance that a simply mhz metric. Every Tier 1 vendor will have Woodcrest parts shipping late June. Apple not being there means they've missed the bus.

I absolutely agree with you. I believe Apple is intel's biggest client now with dell leaving. If anything apple could be EARLY with these announcements.... much like the macbook pro was with yonah. I believe they were the first yonah computers shipping.

I expect the same to happen with woodcrest.

I mean come'on folks. WWDC is a ways away Apple's STILL a company that has earnings to make. You don't hold off announcing a product that's ready to ship for half a quarter because you want to try and make an impact at a tradeshow for Developers nonetheless.

Apple will ship Powermac replacements in June or early July. They can save Xserve and Xserve RAID updates for WWDC.

Dell isnt leaving they're just giving the option of operons in their servers now.

I think you're dead on.

I doubt they'll get that much extra off, the article talked about the price cascade for buying in mass already. 2x3ghz is a possibility, but might look weird if you have 3 models with a .66 Ghz jump in there somewhere, because the lowend almost has to 2.0ghz if it sells for $2000. At $850/700/470/330 for 3.0/2.66/2.33/2.0, the 3.0 ghz line seems like a stretch if Apple wants a big margin.

I think MacPro gets 3 ghz Woodcrest. It's a psychological barrier that I think Apple would like to break. As far as price, up goes the price. Apple has done it already on MacBook and Mini so why not MacPro?