Sidebar Sidebar
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.

Dual Core PowerPC 970s

fluidinclusion said:
I agree. the PowerMac 970 would be great. Remember the commercial a year or two ago that had a guy carring a box with a G5 or G6 on it? They were ripping on what Apples current and near future naming scheme is before it even happened. I'd support a new naming system. It's not like you can even figure out what other companies' names for their models even are (e.g. P720GX-421YK Inspirduroncrapon)

A PowerMac 970 seems so much more powerful because of the "970" >> "5" or "6". Marketing 101.
Click to expand...

the G-naming is much easier. also thing of a consumer who knows nothing about computers. he/she walks to an apple store/apple reseller and starts looking at the names. There's "PowerMac 980" and "PowerMac G6". Just think which one looks more cryptical -> the consumer will get the G6.

...and this is totally just my guess ;D anyway I think the G-naming is ok. I don't really see any reason for changing it.
 
Hector:

I spent too much time looking this stuff up. ;)

tests have shown that it shows very little benefit
Click to expand...
Two points: first I don't believe that, and second, that was the G4 they tested, not the G5.

Point one: Powerlogix did some SDR vs DDR L3 testing for their upgrades and that PDF is still available. It shows one test (Cinbench for what its worth) that goes 7% faster going from 1MB SDR L3 to 2MB DDR L3, and in those circumstances Photoshop was boosted 4%. If there were no L3 at all, the performance impact would be larger.

http://www.powerlogix.com/downloads/SDRDDR.pdf

Point two: Evidence that L3 matters can be found by examining P4 vs P4EE tests, clearly that 2MB L3 is making a difference in some benchmarks, sometimes a lot of difference, and sometimes none at all. In Civ3 the L3 apparently provides a 16% kick in the pants, on a 3D studio test it can add 12%.

http://www.aceshardware.com/read.jsp?id=60000253
http://www.anandtech.com/cpuchipsets/showdoc.aspx?i=1965

There are countless other tests of the P4EE out there which you can find if you'd like.

i was pointing out the general lack of need for such a cache because the ram is fast enough and so is the system bus.
Click to expand...
What do you mean "fast enough"? Perhaps you didn't pay any attention to what I said about latency, the silent enemy. I think you should mosey over to Apple's official PR page and ponder the performance scaling going from 2.0ghz to 2.5ghz:

http://www.apple.com/powermac/performance/

Take the "Bibble 3.1a" test for example: the 2.5 is 150% the speed of a P4, the 2.0 is 119% the speed, so (100+150)/(100+119) = 14.2% speedup. That's the best test Apple presented as far as I know, the Photoshop test of all things showed a (100+98)/(100+82) = 8.8% speedup, "Audio Plug-ins" showed a (100+180)/(100+159) = 8.1% speedup. Remember, those are all on a 25% clock speed boost. A hypothetical 3ghz 970fx would be less than 18% faster at Photoshop than a 2ghz G5, on Apple's own test.

(Aside: note that Apple's G5 prices are in line with observable performance differences rather than clockspeed.)

Intel provides us a point of comparison: their 2.0ghz P4 vs the 2.53ghz P4, both Northwood cores with 512k L2. The 2.0ghz chip has a 400mhz FSB and the 2.53ghz chip has a 533mhz FSB, similar FSB scaling to what Apple has done (33% vs 25%, so Intel has a bit of an edge). Like the G5, the RAM on the P4's does not change ("note that we ran all of our CPU tests with PC800 RDRAM", on pg 6).

http://www.anandtech.com/showdoc.aspx?i=1615&p=1

18.3% on "Content Creation" which includes Photoshop.
27.3% on MP3 encoding with Lame (the accuracy of measurement is suspect).
19.7% on MPEG-4 encoding with Xmpeg.
20.8% on Adobe After Effects 5.5
22.0% on 3D Studio Max
19.6% on Maya

Feel free to do more math if you'd like.

So based on the combination of Apple's own evidence and tests performed by Anandtech, I think most people will agree that the 1.25ghz FSB and dual DDR 400 isn't doing the trick. With only 512k of L2 the G5 gets a lot of cache misses (depending heavily on the application of course) and each of those misses will require the G5 to wait on the main RAM. That'll put an end to performance scaling real fast if the RAM is slow to respond, which is what we are seeing.

I claim that despite the massive bandwith, the G5 is bottlenecked on RAM worse than the G4 ever was. Quite a claim, eh?

So repeat after me, pleaseIBMgiveusondiememorycontrollers!. :) Larger caches, be they L2 or L3, would help as well.
 
ddtlm

pleaseIBMgiveusondiememorycontrollers


Me and my AMD64 second that!!


Max.

Anyone waiting for the next great system/drive/machine will wait forever, since after every release of any product, speculation starts on what will be included on the next version.

Max.
 
iNetwork said:
A HT Pentium 4 is a dual core chip.
Click to expand...

No, it's not. It's a single core model, with some extended logic to act as it were dual core. An "advanced" OS see it as two different processor instead just one. I mean XP/W2k is more advanced than W95/98/Me.

As far as I know the IBM implementation of SMT will be more efficient than Intel's HT. IBM's solution will have more "spare" registers to dispose.
 
hassanpr said:
I did order it through my job its the Board Of Education In my city so whats there excuse.
Click to expand...

I can only hope you are not a teacher.
 
Some points about being SMT-aware

maxvamp said:
We know that the OSX.4 kernel is smp/smt aware making any threaded app ( multiple apps ) perform better on this ( rumored ) machine.
Click to expand...

Are you sure that it's SMT aware? Since there aren't any SMT CPUs around, I doubt that the current version is SMT aware.

(Or is OSX.4 your shorthand for Tiger? By the time 10.4 ships, it could be extended to handle SMT of course.)

The important thing about being SMT aware is that the system needs to schedule intelligently for better performance.

For example, my dual Xeons with HT show up as four processor systems - CPU0, CPU1, CPU2 and CPU3.

In reality, CPU0 and CPU2 are the same - they are two logical processors in a single physical processor. CPU1 and CPU3 are the other chip.

Being SMT-aware means:

o if a thread is running on CPU0, it is better to schedule a second thread on CPU1 or CPU3. If it's put on CPU2, then the two threads share one physical processor (the ~25% boost) and the second physical CPU is idle. If this happens, the SMT system can be much slower than the non-SMT system.

o If you have enough threads to keep all logical CPUs busy, then it is better to schedule threads from the same process on the same physical CPU. Most of the time, this will give better cache behaviour, although depending on the code it might be better to be on different physical CPUs. (E.g. two pure floating point number crunching code threads might find that being able to use the floating point units in both CPUs offsets the less efficient cache usage.)

In addition, Windows XP and later gives an API so that a programmer can distinguish logical and physical CPUs, and either give the OS hints about how to schedule - or even to force a particular scheduling.

Windows 2000 didn't know about logical CPUs, so it sees them all as physical and isn't SMT-aware. It uses all the logical CPUs, but not in the most efficient manner.

XP and W2k3 are SMT-aware, and makes smarter choices on its own, and gives the programmer tools to be even better. (W2k3 has more SMT features than XP, as well as being NUMA-aware.)
 
Abstract said:
Okay, Apple would probably replace the two chips they are using with this one, dual core chip, but I hope they just use 2 dual core chips. Will software even be able to recognize that many microprocessors? Will you need to get new software to take advantage of two dual core chips?
Click to expand...

I'd guess that Apple would initially go back to the single processor for low and mid-range, and dual for high end due to low initial quantities of the new processor. As far as needing new software to recognize a dual core, dual processor system, I doubt it'd be much more than an OS revision bump, ie 10.4.4 or such.

Now if we could only get the new machines to move the AGP slot further away from the PCI slots, that would be great (or even to space all the slots out a bit more, since certain companies are bad about double width cards) :(
 
Hector said:
tests have shown that it shows very little benefit, i was pointing out the general lack of need for such a cache because the ram is fast enough and so is the system bus.
Click to expand...
Note also that this is using the wave pipelining on the bus, so some of the traditional benefits of an L3 cache don't apply anyway.
 
MacinDoc said:
"If this news is correct" would be the proper way to say this in English.
Edit: Sorry, didn't realize CarltonMusic and Fender beat me to it.
Click to expand...
Actually, all of you are a bit off. It should be, "If this news be correct." You're using the present subjunctive in English, which is the same form as the infinitive.
 
Don't you mean "remove the AGP slot" ?

relimw said:
Now if we could only get the new machines to move the AGP slot further away from the PCI slots...
Click to expand...


The next machines will have PCI Express (PCIe) graphics, no doubt.
 
manu chao said:
I would guess they would only call a Power 5 derived PPC a G6. If these news are correct (or, 'this news is correct'? might a native speaker please tell me what is the correct version), than this rumored Power 5 derived PPC might not see the light before the end of 2005 or even 2006.
Click to expand...

If you want to refer to news in the plural, the correct way to do so would be to say "If these news items are correct..." This would suggest you are referring specficially to multiple news items independant of each other (that is, drawn from seperate sources). However technically correct this may be, the average native speaker probably wouldn't talk like that, rather simply saying "If the news is correct..."

Just my 2 cents. (Not "My .02 cents" as that would be 2 tenths of a cent)
 
hitchhiker said:
The G-Series naming sytem is definitely getting too old. Sure, it makes some sense. But I think after the G6, apple should look for some other way to name their subsequent chip and powermac designs. Perhaps changing the first letter would help- "PowerMac X7" sounds much more advanced and interesting than staying with the G system for years to come.
Click to expand...

Well, if you look at military classifications, X usually means "experimental". I realize that most people probably would overlook that, but I think the G is cool. I don't know what it actually means, but I kind of think of it as "generation", since one could make the argument that the PPC 601/603/603E was a kind of G1, and the 604/604e was a sort-of G2.
 
Question: With a dual core, what will be the clock speed?

For example, let's say one of these new 970MPs have a clock speed at 3 GHz. Is each core 3 GHz or is each core 1.5 GHz and adds up to 3 GHz.

Also, would two cores also be able to act as one core? Let's say it is a 3 GHz clock speed for each core, could it also act as one 6 GHz core?
 
MikeTheC said:
guifa said:
Actually, all of you are a bit off. It should be, "If this news be correct." You're using the present subjunctive in English, which is the same form as the infinitive.
Click to expand...
'Scuse me? What version of English do you use?
Click to expand...
If it was good enough for Shakespeare, it's good enough for you :p
 
applekid said:
Question: With a dual core, what will be the clock speed?

For example, let's say one of these new 970MPs have a clock speed at 3 GHz. Is each core 3 GHz or is each core 1.5 GHz and adds up to 3 GHz.
Click to expand...
Each would be at 3.
Also, would two cores also be able to act as one core? Let's say it is a 3 GHz clock speed for each core, could it also act as one 6 GHz core?
Click to expand...
No. You really have two separate CPUs on one chip. The nice thing about have two on one chip is that the logic required to couple them is also on that chip, so it's faster, less comlicated to build, potentially cheaper.
 
First its a dual core G5

with an elastice bus meaning its defaulted to 1GHz bus to 3GHz speed per core.

remember its elastice so the default is 1GHz bus meaning Apple can crank up the bus to 1.5GHz per core at 3GHz speeds. This is neither good or bad thing if Apple choses to crank up the speed great for us if not they will stick it in low portables and iMac.

Its also has PowerTune Enhanced so its going to control the processor speed equally amoung both cores. At top speed you are looking at 3GHz when you are surfing the net or typing a document it will drop the speed down, so all this means is that even though you are buying a 3GHz G5 makes good uses of it otherwise you are wasting your money. Or donate it to me
;) :D
 
more power! Great! Wait! so few really have that serious a need for that kind of power, software just isn't keeping up. More than that, c'mon! Apple's alreaedy got the graphics crowd, etc.

The only thing that will seriously get me oohing and aaahhing is something that majorly reduces heat and power consumption. Those are the biggest limiting factors now. Do those, and we've got the ability to do G5's in less than powermac, and not be pushing it, spending extra money on cooling, etc. If you do them really well, apple could actually makes some seriously awesome laptops, that don't make your palms sweat when browsing the web and that have awesome batterylife. B/c now, again, an ibook can handle most everybody's needs, but who wants a computer that, like my PB, I sometimes can hardly keep my hands on long enough to put in it's case, and runs out of power in a little more time than watching a DVD on it? What I want to hear is a G5 that can directly compete with a pentium M, and beat it.
 
You must log in or register to reply here.
Register on MacRumors! This sidebar will go away, and you'll see fewer ads.
Top Bottom
Back