I'd agree that everyone tries to win SPEC benchmarks, but it's still
the best indicator out there, and in many cases things that are good
for SPEC benchmarks also benefit real applications. AMD has submitted
results using other compilers recently, gcc and Pathscale.
Your point about clock-rate against performance seems rather ironic on
a Mac forum. FWIW Itanium2 delivers the best floating point performance,
better than even the P4 at 3.4 GHz, yet runs at 1.5 GHz. Clock is a poor
indicator.
5% for a doubling of cache is about right, cache miss rates generally halve
with doublings, so if the rate was 90% with 1 MB you'd hope for 95%
with 2 MB, 97.5% with 4 MB, 98.75% with 8 MB, and so on. In simple
terms you get diminishing returns as you invest in more cache. 5% going
from 1 MB to 2 MB is quite good IMHO.
There's a difference between physical and architectural registers, the
Centrino may have 8 architectural registers, but the physical number
is greater. IIRC it was 32, might be higher.
To summarise: The G4 is long in the tooth, has a slow FSB, and the
performance is not as high as contemporary mobile x86 processors.
Worse still for Apple (at the moment) is that Dothan is competitive with
current PowerPC desktop processors. This will likely change though
as 970fx ramps up, 975 and 750vx are releases, and the new
e600 and so on arrive.
When the new processor for Apple laptops arrives, Mac 'group-think'
will change and people will admit that the G4 was past its prime. [/B]
Sorry but you didnt address any of the concearns I posted about.Spec scores are not valid real world performance indicators and intel "cooking the books" make it a joke.Your claim that these tricks they use to get high scores are useful in the real world is hollow.They use tags that allow the processor to make branch predictions that would be invalid in real software.Absolutely useless in the real world.Did you not read the cnet article snip? What exactly do you think "disproportionate" means.Let me help.It means it doesnt look like the real world.The industry is not fooled by this,so why are you? Why by the way did you change the discussion from the G5 to the G4? That was not the claim of yours I was addressing.I was pointing out how completely unreal intels spec scores are in the face of real architectural details.So I take it you believe the 1.6 centrino is faster than a duel 2 ghz G5 tower? You must because if those scores mean anything that conclusion is unescapeable.These score are rediculous and you know it.
Your bit about cache and performance is right but irrelevent.I dont know why you even posted that.My point was that in your first post you claim the level 2 cache and fsb were responsible for its insane performance on spec and I mearly pointed out that that claim doest stand up,especially compared to the ppc970.All you did was concede the point to me.Thanks.
You are being a bit catty about the registers as well.Yes the x86 has rename registers but so does ppc.That doesnt enter into the picture though.The drop in performance comes when you run out of architectural registers.X86 Compilers can pretend to have more but must generate a lot of extra code to move values around to keep up the "pretence".This gives a pretty fair performance hit.Why do you think amd has added registers to the amd64 (16 in 64 bit mode)?
Bottom line-many performance claims that come out of the x86 world and of course from its fanboys are nothing but fluff.
This has gotten way off track.So I want to ask one question.Intel claims a spec int score of 1206 for a 1.6 ghz centrino.Apple claims a score of 800 for the 2 ghz G5.Do you think these figures represent anywhere near to a fair and accurate indication of the relative performance of these two processors?
I know from experience with dealing with Intel development that they are switching over to dual core and amd64 bit designs. Here is the difference that you need to understand, we are dealing with the G4 and the Pentium M dothan, you brought in the powerpc 970 which in all cases beats the pentium m dothan in performance, speed and ability.
I seriously doubt this but won't say for sure until real hard data comes out. At this point it does appear that Dothan will beat the 970 in the variants now on the market.
Quote:
No doubt there and nothing you can say will change that
There is no disputing that the dothan is a good chip and i have already outlined where its advantages are in powermanangement and battery life, but not performance, bit by bit it is still based on the same series of cores that make up the current generation of 32 bit intel processors.
This is possibly the biggest mistake or bit of mis informaiton seen in a long time. Dothan and the other Centrino processor are not based on intels current P4 cores. Almost everybody in the world knows this. You could argue that they are somewhat derived from the P3 family, but certianly not intels current 32 bit cores.
Quote:
It is powerful and i have no doubt that the 2ghz dothan is probably faster than the g4 at 1.5 ghz, however the g4 processor 3 years ago had a 600 mhz equivalency factor with intel processors and now has a 100-200 mhz factor, this factor is basically the g4 runs at 800 mhz it is the equivalent of x mhz in pentium 4/m/III processors and amd as well, it has shrunk to almost non existence, but when i am reviewing a processor's performance do not forget that the 1.5 ghz g4 and the dothan m processor are both brand new and speed for speed running at equal clock, the g4(mpc7447a) will run faster and perform better, but burn more power and run hotter than the dothan, these are tradeoffs to me
You will have to rephrase the above into something I can parse.
Quote:
3) DO not forget that the AMD64 and IA64 are totally different architectures, the AMD 64 is x-86-64, which gives native 32 bit as well as 64 bit processes, IA64 is strictly 64 bit and will never be seen in a consumer desktop because of price and cost difficulties
Or IA64 is a is a piece of junk that only meets the needs of a select few users. On the other hand some of those few users that can make use of the IA64 line have done so on the desktop.
Quote:
4) The Power5 is a significant jump in performance from the power4 core and has been completely redesigned, very much the way that the itanium 2 has been redesigned from the itanium 1, which has been around for a while
The evidence we have at the moment does not support that. It appears that Power5 was expanded enough to support SMT and its ability to pass data around. The processor is otherwise rahter similar to the Power4
Quote:
5) Do not forget that Intel does not have a large market for the Itanium because, whoa, Ibm is the market leader in Servers, Enterprise ready solutions and Business Servers and has named Linux and 64 Power5 processors as its next generation and primary processor that powers it. The powerpc 980 which is yet to be released is goign to be based on the power5 core, do not forget that the power4 and power5 are Dual Core processors that are significantly more expensive and more powerful than even the itanium 2,
6) Ibm is suffering losses at its fab in NY, because it is NEW and has yet been pumped to full volume, when you open a new fab it takes between 2-5 years for it to begin producing at full capacity with minimal failures/defects and this particular factory has only been open approx 2 years and is working at very diminished capacity.
Both processors are good, but clock vs clock the G5 crushes the dothan and the g4 beats it in some categories and loses in others, but the g5 loses in none to the dothan.
Ok I suppose you have all the details to support the idea that dothan never wins agianst the 970. Mind you I'm a big fan of the PPC family and I don't see how anybody could make such a statement at this time. At a given clock rate dothan will perform better than a P4 with some code bases plus it is going to scale clock rate wise. There is just ot much evidence to say without qualification that the 970 will beat Dothan in every matter.
I disagree that we are off topic!, the point of the thread is can the Powerbook remain competitive with PC notebooks with Centrino 1.7's and the now announced Dothan 2GHz without a G5?.
Or can Moto get the G4 beyond the current clock rate, whilst updating FSB, namely the rumoured 7460 out in time?.
I think ultimately the answer will come down to price/power dissapation. If Moto/freescale gets its 7460 out to 2GHz THIS year then we may only be 6 months behind. That said, a 970FX @ 2G would undoubtably be competitive with the Dothan.
My guess, Apple go G5 in the PB at MWSF 05, whilst the ibook/eMac remain G4.
PB, if you're going to use FFT to compare performance, do it right--compare every major implementation with different compilers on every platform.
Fortunately, this laborious task has been done. Although the G4 gets its ass handed to it, the G5 kicks everyone's ass. Altivec helps a lot, but even without it, the G5 beats P4s and Opterons on double precision tests.
So stupid i had to reply, The Dothan even close to the g5 are you kidding me, i dont need to have a brain cell to have known that to be bullshit and you know it. Not only is the g5 a DUal Processor system, you know what two processors are. The g5 powerpc 970 is signnificantly more powerful single processor than the dothan in any of its variants, as stated throughout this thread and all other logistics, benchmarks are useless, but then common sense strikes, desktop vs laptop, Server Procssor vs Intel laptop processor, even as a next generation processor, the dothan is not as powerful
Quote:
Originally posted by wizard69
This is so full of BS I just had to respond.
I seriously doubt this but won't say for sure until real hard data comes out. At this point it does appear that Dothan will beat the 970 in the variants now on the market.
This is possibly the biggest mistake or bit of mis informaiton seen in a long time. Dothan and the other Centrino processor are not based on intels current P4 cores. Almost everybody in the world knows this. You could argue that they are somewhat derived from the P3 family, but certianly not intels current 32 bit cores.
You will have to rephrase the above into something I can parse.
Or IA64 is a is a piece of junk that only meets the needs of a select few users. On the other hand some of those few users that can make use of the IA64 line have done so on the desktop.
The evidence we have at the moment does not support that. It appears that Power5 was expanded enough to support SMT and its ability to pass data around. The processor is otherwise rahter similar to the Power4
Ok I suppose you have all the details to support the idea that dothan never wins agianst the 970. Mind you I'm a big fan of the PPC family and I don't see how anybody could make such a statement at this time. At a given clock rate dothan will perform better than a P4 with some code bases plus it is going to scale clock rate wise. There is just ot much evidence to say without qualification that the 970 will beat Dothan in every matter.
Comparing dothan to the G5 is really rather pointless, as long as XP is the only available OS now, and for the next 3 years.
XP is falling so far behind X it really makes no difference what processor is behind it.
Way to poke at the G5 ... the P4 performed horribly when it first came out, and although it's performance is still quite underwhelming, it has improved by quite a bit.
I use both wintel and Apple Laptops and let me tell you one thing, my new PB 1.5 ghz is the fastest laptop i have ever had and use a pentium m at 1.6 ghz and it is not even close in performance or speed.
mpopkin, im interested in the apps you are using on both machines. IMO, real computer use is far more important than some cpu benchmarks, although, im a little suprised by the "not even close" comment.
This should put to rest some of the unguided attempts to label the Dothan series as a poor processor. While I'm not abotu to compare this to a G5, as it seems to be pretty useles on this board, I will say that this type of hardware would make an excellent laptop. It would be fair to say that the majority of the people using portables would be very pleased with Dothan in their machine.
AltiVec is why G4/G5 is better than the P3 derived centrino in real world tasks. Who cares if it takes an extra .5 seconds for me to open Word? or the system takes 40 seconds to boot on my 1GHz G4 powerbook vs. 20 on the centrino or dothan(I don't remember the last time i had to restart my system). When you do stuff that actually takes a lot of processor power like video encoding or photoshop filters or basically anything related to multimedia, a properly coded mac application will leave the windows equivalent in the dust.
Battery life of the pentium m is slightly overstated also. It may be better than the G4, but when they claim 8 hours, it really gets like 5 doing word proccessing/web browsing, and 3 when watching a dvd or playing a FPS game. A lot of that power savings comes from the fact that the chip scales down when running off batteries, and also the integrated wireless saves some power.
That said, we wont see a G5(in its current form) in a powerbook. Architectural revisions await 'fore 97X sees' portables
hi, im thinking of getting a PowerBook but i have a couple of questions that i would like to ask first, and if you guys could help me that would be great
Really how good are the G4? I mean like should i wait for the G5 to come out on PowerBook (ive got a PC in the meantime) or is it not worth the wait? I do network admin for a living and am very interested in the macs for audio prduction as a hobby, wat sorta pc is comparable?
the second question is will the price rise when they come out? i know its a hard question but they are pretty cheap atm is all...
I use both wintel and Apple Laptops and let me tell you one thing, my new PB 1.5 ghz is the fastest laptop i have ever had and use a pentium m at 1.6 ghz and it is not even close in performance or speed.
This really shouldn?t be happening with APPLE?S latest and greatest laptop hardware.
Hell, I?m running competitive with this stuff on cheap two year old hardware.
BTW, I?ve read a lot of your posts and you are well read and opinionated, but don?t sound as technical as the guys over at Ace Hardware or ARS Technica. Me thinks you?re winging it.
AltiVec is why G4/G5 is better than the P3 derived centrino in real world tasks.
AltiVec is only of use if the application you are interested in can be coded for it. It is otherwise wasted transistors.
Quote:
When you do stuff that actually takes a lot of processor power like video encoding or photoshop filters or basically anything related to multimedia, a properly coded mac application will leave the windows equivalent in the dust.
There are whole ranges of applications that "takes a lot of processor power" and will never make use of AltiVec. Then there is the issue of how many PowerMac applications are properly coded to take advantage of this power in the first place. I'm not denying that Apples vector unit works well but it certainly can be out performed when runned up agianst better hardware. No matter how you look at it the current G4's are looking a little poor in the portable segment. Apple and Motorola may have something up their sleeves for the next rev of the G4 and Powerbook, but by the time it comes out Dothan will have likely moved ahead several hundred MHz.
There is more to performance than just Photoshop. For some of us Linux users these applications neve come into play.
Quote:
Battery life of the pentium m is slightly overstated also.
Well maybe maybe not, this parameter is very much impacted by the user just as it is on the Apple hardware. Apple does very well here but the competition has made significant strides.
Quote:
That said, we wont see a G5(in its current form) in a powerbook. Architectural revisions await 'fore 97X sees' portables
That is why I think that we are very likely to see something from Motorola and Apple to deal with this issue. If Motorola can deliver to Apple a SOC processor that has an improved G4 core running at 2 to 2.5 GHz then we are talking competitive Powerbooks again. Assuming of course that the SOC takes care of the I/O bus issues. To have this work out well Motorola would have to invest in either Hypertransport or PCI-Express, niether of which seem to be on Motorolas road map. A 2.5GHz SOC running a PCI-Express interface to a GPU in a laptop would really rock. If they can get there in the next revision that would be world shaking.
To have this work out well Motorola would have to invest in either Hypertransport or PCI-Express, niether of which seem to be on Motorolas road map.
Motorola will probably go with RapidIO as the replacement for the MPX bus on the G4. Which brings up the question: will Apple be willing to go with a G4 with RapidIO when they're already using the Elastic Bus with the G5? It would mean that they would have two different chipsets for laptops & desktops, which is something Apple has been trying to avoid since they went to the G3. I think Apple may just decide to wait until they can get a real low power 970 derivative for the Powerbooks, instead of supporting two different interconnect architectures for desktops & laptops.
That may be the way the Motorola goes but to be honest I don't see enough industry up take to justify it.
On the otherhand if they are really serious about mix and matching components to fabricate SOC's seems to me that they would have to offer options. On of those options would be Hypertransport.
Currently I don't see e-bus making it to any laptop. Ideally you would have a SOC with memory and HT support built in possibly with a lot more. That would be a nice approach for the next revs.
Thanks
Dave
Quote:
Originally posted by Gamblor
Motorola will probably go with RapidIO as the replacement for the MPX bus on the G4. Which brings up the question: will Apple be willing to go with a G4 with RapidIO when they're already using the Elastic Bus with the G5? It would mean that they would have two different chipsets for laptops & desktops, which is something Apple has been trying to avoid since they went to the G3. I think Apple may just decide to wait until they can get a real low power 970 derivative for the Powerbooks, instead of supporting two different interconnect architectures for desktops & laptops.
On the otherhand if they are really serious about mix and matching components to fabricate SOC's seems to me that they would have to offer options. On of those options would be Hypertransport.
Right, but remember one of the rumors about why Apple went with IBM for the G5 was because they wanted Motorola to adopt HT, and Moto scoffed at the idea. Now, it could be that Freescale's management is more open to the idea, but who knows what will happen.
Quote:
Currently I don't see e-bus making it to any laptop. Ideally you would have a SOC with memory and HT support built in possibly with a lot more. That would be a nice approach for the next revs.
Yeah, it would. The next 12 months or so will be interesting-- who knows when a Powerbook will show up with a new processor?
Every chip maker will leap frog each other from time to time. B ut as long as Apple has a game plan for it's laptops to remain relatively competitive (performance and pricing) with PC notebooks, I'm cool.
I really hope they do have one though.
As someone earlier pointed out, a few seconds here and there don't matter a whole lot to me either. What does is functionality. Meaning a robust hardware system that can handle the software and a display that matches it (xbrite?)
However, I am curious about all these PC comparisons. I'd be interested to know if those here making them, have actually spent real world experience on them. Although this is a pro-Apple forum, it would be great to know that comments are not just hearsay and spec based...but hands on user based.
Comments
Originally posted by catbat
cuneglasus:
I'd agree that everyone tries to win SPEC benchmarks, but it's still
the best indicator out there, and in many cases things that are good
for SPEC benchmarks also benefit real applications. AMD has submitted
results using other compilers recently, gcc and Pathscale.
Your point about clock-rate against performance seems rather ironic on
a Mac forum.
better than even the P4 at 3.4 GHz, yet runs at 1.5 GHz. Clock is a poor
indicator.
5% for a doubling of cache is about right, cache miss rates generally halve
with doublings, so if the rate was 90% with 1 MB you'd hope for 95%
with 2 MB, 97.5% with 4 MB, 98.75% with 8 MB, and so on. In simple
terms you get diminishing returns as you invest in more cache. 5% going
from 1 MB to 2 MB is quite good IMHO.
There's a difference between physical and architectural registers, the
Centrino may have 8 architectural registers, but the physical number
is greater. IIRC it was 32, might be higher.
To summarise: The G4 is long in the tooth, has a slow FSB, and the
performance is not as high as contemporary mobile x86 processors.
Worse still for Apple (at the moment) is that Dothan is competitive with
current PowerPC desktop processors. This will likely change though
as 970fx ramps up, 975 and 750vx are releases, and the new
e600 and so on arrive.
When the new processor for Apple laptops arrives, Mac 'group-think'
will change and people will admit that the G4 was past its prime.
Sorry but you didnt address any of the concearns I posted about.Spec scores are not valid real world performance indicators and intel "cooking the books" make it a joke.Your claim that these tricks they use to get high scores are useful in the real world is hollow.They use tags that allow the processor to make branch predictions that would be invalid in real software.Absolutely useless in the real world.Did you not read the cnet article snip? What exactly do you think "disproportionate" means.Let me help.It means it doesnt look like the real world.The industry is not fooled by this,so why are you? Why by the way did you change the discussion from the G5 to the G4? That was not the claim of yours I was addressing.I was pointing out how completely unreal intels spec scores are in the face of real architectural details.So I take it you believe the 1.6 centrino is faster than a duel 2 ghz G5 tower? You must because if those scores mean anything that conclusion is unescapeable.These score are rediculous and you know it.
Your bit about cache and performance is right but irrelevent.I dont know why you even posted that.My point was that in your first post you claim the level 2 cache and fsb were responsible for its insane performance on spec and I mearly pointed out that that claim doest stand up,especially compared to the ppc970.All you did was concede the point to me.Thanks.
You are being a bit catty about the registers as well.Yes the x86 has rename registers but so does ppc.That doesnt enter into the picture though.The drop in performance comes when you run out of architectural registers.X86 Compilers can pretend to have more but must generate a lot of extra code to move values around to keep up the "pretence".This gives a pretty fair performance hit.Why do you think amd has added registers to the amd64 (16 in 64 bit mode)?
Bottom line-many performance claims that come out of the x86 world and of course from its fanboys are nothing but fluff.
This has gotten way off track.So I want to ask one question.Intel claims a spec int score of 1206 for a 1.6 ghz centrino.Apple claims a score of 800 for the 2 ghz G5.Do you think these figures represent anywhere near to a fair and accurate indication of the relative performance of these two processors?
Originally posted by mpopkin
Totally agree that this post could go on forever
but last details are important
I know from experience with dealing with Intel development that they are switching over to dual core and amd64 bit designs. Here is the difference that you need to understand, we are dealing with the G4 and the Pentium M dothan, you brought in the powerpc 970 which in all cases beats the pentium m dothan in performance, speed and ability.
I seriously doubt this but won't say for sure until real hard data comes out. At this point it does appear that Dothan will beat the 970 in the variants now on the market.
Quote:
No doubt there and nothing you can say will change that
There is no disputing that the dothan is a good chip and i have already outlined where its advantages are in powermanangement and battery life, but not performance, bit by bit it is still based on the same series of cores that make up the current generation of 32 bit intel processors.
This is possibly the biggest mistake or bit of mis informaiton seen in a long time. Dothan and the other Centrino processor are not based on intels current P4 cores. Almost everybody in the world knows this. You could argue that they are somewhat derived from the P3 family, but certianly not intels current 32 bit cores.
Quote:
It is powerful and i have no doubt that the 2ghz dothan is probably faster than the g4 at 1.5 ghz, however the g4 processor 3 years ago had a 600 mhz equivalency factor with intel processors and now has a 100-200 mhz factor, this factor is basically the g4 runs at 800 mhz it is the equivalent of x mhz in pentium 4/m/III processors and amd as well, it has shrunk to almost non existence, but when i am reviewing a processor's performance do not forget that the 1.5 ghz g4 and the dothan m processor are both brand new and speed for speed running at equal clock, the g4(mpc7447a) will run faster and perform better, but burn more power and run hotter than the dothan, these are tradeoffs to me
You will have to rephrase the above into something I can parse.
Quote:
3) DO not forget that the AMD64 and IA64 are totally different architectures, the AMD 64 is x-86-64, which gives native 32 bit as well as 64 bit processes, IA64 is strictly 64 bit and will never be seen in a consumer desktop because of price and cost difficulties
Or IA64 is a is a piece of junk that only meets the needs of a select few users. On the other hand some of those few users that can make use of the IA64 line have done so on the desktop.
Quote:
4) The Power5 is a significant jump in performance from the power4 core and has been completely redesigned, very much the way that the itanium 2 has been redesigned from the itanium 1, which has been around for a while
The evidence we have at the moment does not support that. It appears that Power5 was expanded enough to support SMT and its ability to pass data around. The processor is otherwise rahter similar to the Power4
Quote:
5) Do not forget that Intel does not have a large market for the Itanium because, whoa, Ibm is the market leader in Servers, Enterprise ready solutions and Business Servers and has named Linux and 64 Power5 processors as its next generation and primary processor that powers it. The powerpc 980 which is yet to be released is goign to be based on the power5 core, do not forget that the power4 and power5 are Dual Core processors that are significantly more expensive and more powerful than even the itanium 2,
6) Ibm is suffering losses at its fab in NY, because it is NEW and has yet been pumped to full volume, when you open a new fab it takes between 2-5 years for it to begin producing at full capacity with minimal failures/defects and this particular factory has only been open approx 2 years and is working at very diminished capacity.
Both processors are good, but clock vs clock the G5 crushes the dothan and the g4 beats it in some categories and loses in others, but the g5 loses in none to the dothan.
Ok I suppose you have all the details to support the idea that dothan never wins agianst the 970. Mind you I'm a big fan of the PPC family and I don't see how anybody could make such a statement at this time. At a given clock rate dothan will perform better than a P4 with some code bases plus it is going to scale clock rate wise. There is just ot much evidence to say without qualification that the 970 will beat Dothan in every matter.
Dave
Quote:
Or can Moto get the G4 beyond the current clock rate, whilst updating FSB, namely the rumoured 7460 out in time?.
I think ultimately the answer will come down to price/power dissapation. If Moto/freescale gets its 7460 out to 2GHz THIS year then we may only be 6 months behind. That said, a 970FX @ 2G would undoubtably be competitive with the Dothan.
My guess, Apple go G5 in the PB at MWSF 05, whilst the ibook/eMac remain G4.
Fortunately, this laborious task has been done. Although the G4 gets its ass handed to it, the G5 kicks everyone's ass. Altivec helps a lot, but even without it, the G5 beats P4s and Opterons on double precision tests.
For example, G5 versus 2.8GHz P4 Xeon versus G4 733MHz
Someone should start a new thread about this as the G5 results are relatively new.
Originally posted by wizard69
This is so full of BS I just had to respond.
I seriously doubt this but won't say for sure until real hard data comes out. At this point it does appear that Dothan will beat the 970 in the variants now on the market.
This is possibly the biggest mistake or bit of mis informaiton seen in a long time. Dothan and the other Centrino processor are not based on intels current P4 cores. Almost everybody in the world knows this. You could argue that they are somewhat derived from the P3 family, but certianly not intels current 32 bit cores.
You will have to rephrase the above into something I can parse.
Or IA64 is a is a piece of junk that only meets the needs of a select few users. On the other hand some of those few users that can make use of the IA64 line have done so on the desktop.
The evidence we have at the moment does not support that. It appears that Power5 was expanded enough to support SMT and its ability to pass data around. The processor is otherwise rahter similar to the Power4
Ok I suppose you have all the details to support the idea that dothan never wins agianst the 970. Mind you I'm a big fan of the PPC family and I don't see how anybody could make such a statement at this time. At a given clock rate dothan will perform better than a P4 with some code bases plus it is going to scale clock rate wise. There is just ot much evidence to say without qualification that the 970 will beat Dothan in every matter.
Dave
Originally posted by hasapi
My guess, Apple go G5 in the PB at MWSF 05, whilst the ibook/eMac remain G4.
Well we can only hope! Better yet would be that oe of Apples suppliers comes up with a high performance laptop specific chip.
[/B]
Dothan Pentium4 Athlon64
2GHz 3GHz 1,8GHz
SPEC
Int_base2000 1380 1276 1169
fp_Base2000 901 1382 1138
PovRay 3.5
optics.pov 372 447 397
CineBench 2003
Rendering 249 352 252
Dothan 2GHz
i855GME
FIC MD02
Pentium4 3Ghz
i865PE
Asus L5800GM
Mobile Athlon64 3000+
VIA K8T800
Yakumo Q8D
When it comes to synthetic benchmarks HINT would be my choice.
One bench fits all
XP is falling so far behind X it really makes no difference what processor is behind it.
Way to poke at the G5 ... the P4 performed horribly when it first came out, and although it's performance is still quite underwhelming, it has improved by quite a bit.
Originally posted by mpopkin
I use both wintel and Apple Laptops and let me tell you one thing, my new PB 1.5 ghz is the fastest laptop i have ever had and use a pentium m at 1.6 ghz and it is not even close in performance or speed.
mpopkin, im interested in the apps you are using on both machines. IMO, real computer use is far more important than some cpu benchmarks, although, im a little suprised by the "not even close" comment.
Thanks
dave
Dothan Pentium4 Athlon64
2GHz 3GHz 1,8GHz
SPEC
Int_base2000 1380 1276 1169
fp_Base2000 901 1382 1138
PovRay 3.5
optics.pov 372 447 397
CineBench 2003
Rendering 249 352 252
Battery life of the pentium m is slightly overstated also. It may be better than the G4, but when they claim 8 hours, it really gets like 5 doing word proccessing/web browsing, and 3 when watching a dvd or playing a FPS game. A lot of that power savings comes from the fact that the chip scales down when running off batteries, and also the integrated wireless saves some power.
That said, we wont see a G5(in its current form) in a powerbook. Architectural revisions await 'fore 97X sees' portables
Really how good are the G4? I mean like should i wait for the G5 to come out on PowerBook (ive got a PC in the meantime) or is it not worth the wait? I do network admin for a living and am very interested in the macs for audio prduction as a hobby, wat sorta pc is comparable?
the second question is will the price rise when they come out? i know its a hard question but they are pretty cheap atm is all...
thank heaps, VHproject
Originally posted by mpopkin
I use both wintel and Apple Laptops and let me tell you one thing, my new PB 1.5 ghz is the fastest laptop i have ever had and use a pentium m at 1.6 ghz and it is not even close in performance or speed.
This really shouldn?t be happening with APPLE?S latest and greatest laptop hardware.
Hell, I?m running competitive with this stuff on cheap two year old hardware.
BTW, I?ve read a lot of your posts and you are well read and opinionated, but don?t sound as technical as the guys over at Ace Hardware or ARS Technica. Me thinks you?re winging it.
__________________________________________________ _______________________________________
Posted taken from:
http://www.macaddict.com/phpBB2/view...50560&start=50
CINEBENCH 2003 v1
************************************************** **
Tester : Ron
Processor : 17" PB G4
MHz : 1500
Number of CPUs : 1
Operating System : 10.3.3
Graphics Card : 128 Radeon 9700
Resolution : 1440x900
Color Depth : millions
************************************************** **
Rendering (Single CPU): 138 CB-CPU
Rendering (Multiple CPU): --- CB-CPU
Shading (CINEMA 4D) : 164 CB-GFX
Shading (OpenGL Software Lighting) : 428 CB-GFX
Shading (OpenGL Hardware Lighting) : 748 CB-GFX
OpenGL Speedup: 4.56
************************************************** **
I blame the crappy bus speed (166).
__________________________________________________ _
Two year old, $534.00 cheap, plastic laptop, out performing the 1.5GHz MIGHTY POWERBOOK . So much for the great G4 Architectural Superiority.
CINEBENCH 2003 v1
************************************************** **
Tester : JPD
Processor : HP ze4101 Laptop Athlon XP
MHz : 1.33 (XP 1500+)
Number of CPUs : 1
Operating System : XP Home
Graphics Card : ATI 320m (Onboard Graphics)
Resolution : 1024 x 768
Color Depth : 32 bit
************************************************** **
Rendering (Single CPU): 161 CB-CPU
Rendering (Multiple CPU): --- CB-CPU
Shading (CINEMA 4D) : 171 CB-GFX
Shading (OpenGL Software Lighting) : 426 CB-GFX
Shading (OpenGL Hardware Lighting) : 250 CB-GFX
OpenGL Speedup: 2.51
************************************************** **
Mercy, mercy look-a-here
http://www.barefeats.com/al15b.html
Originally posted by Imergingenious
AltiVec is why G4/G5 is better than the P3 derived centrino in real world tasks.
AltiVec is only of use if the application you are interested in can be coded for it. It is otherwise wasted transistors.
When you do stuff that actually takes a lot of processor power like video encoding or photoshop filters or basically anything related to multimedia, a properly coded mac application will leave the windows equivalent in the dust.
There are whole ranges of applications that "takes a lot of processor power" and will never make use of AltiVec. Then there is the issue of how many PowerMac applications are properly coded to take advantage of this power in the first place. I'm not denying that Apples vector unit works well but it certainly can be out performed when runned up agianst better hardware. No matter how you look at it the current G4's are looking a little poor in the portable segment. Apple and Motorola may have something up their sleeves for the next rev of the G4 and Powerbook, but by the time it comes out Dothan will have likely moved ahead several hundred MHz.
There is more to performance than just Photoshop. For some of us Linux users these applications neve come into play.
Battery life of the pentium m is slightly overstated also.
Well maybe maybe not, this parameter is very much impacted by the user just as it is on the Apple hardware. Apple does very well here but the competition has made significant strides.
That said, we wont see a G5(in its current form) in a powerbook. Architectural revisions await 'fore 97X sees' portables
That is why I think that we are very likely to see something from Motorola and Apple to deal with this issue. If Motorola can deliver to Apple a SOC processor that has an improved G4 core running at 2 to 2.5 GHz then we are talking competitive Powerbooks again. Assuming of course that the SOC takes care of the I/O bus issues. To have this work out well Motorola would have to invest in either Hypertransport or PCI-Express, niether of which seem to be on Motorolas road map. A 2.5GHz SOC running a PCI-Express interface to a GPU in a laptop would really rock. If they can get there in the next revision that would be world shaking.
Dave
To have this work out well Motorola would have to invest in either Hypertransport or PCI-Express, niether of which seem to be on Motorolas road map.
Motorola will probably go with RapidIO as the replacement for the MPX bus on the G4. Which brings up the question: will Apple be willing to go with a G4 with RapidIO when they're already using the Elastic Bus with the G5? It would mean that they would have two different chipsets for laptops & desktops, which is something Apple has been trying to avoid since they went to the G3. I think Apple may just decide to wait until they can get a real low power 970 derivative for the Powerbooks, instead of supporting two different interconnect architectures for desktops & laptops.
On the otherhand if they are really serious about mix and matching components to fabricate SOC's seems to me that they would have to offer options. On of those options would be Hypertransport.
Currently I don't see e-bus making it to any laptop. Ideally you would have a SOC with memory and HT support built in possibly with a lot more. That would be a nice approach for the next revs.
Thanks
Dave
Originally posted by Gamblor
Motorola will probably go with RapidIO as the replacement for the MPX bus on the G4. Which brings up the question: will Apple be willing to go with a G4 with RapidIO when they're already using the Elastic Bus with the G5? It would mean that they would have two different chipsets for laptops & desktops, which is something Apple has been trying to avoid since they went to the G3. I think Apple may just decide to wait until they can get a real low power 970 derivative for the Powerbooks, instead of supporting two different interconnect architectures for desktops & laptops.
On the otherhand if they are really serious about mix and matching components to fabricate SOC's seems to me that they would have to offer options. On of those options would be Hypertransport.
Right, but remember one of the rumors about why Apple went with IBM for the G5 was because they wanted Motorola to adopt HT, and Moto scoffed at the idea. Now, it could be that Freescale's management is more open to the idea, but who knows what will happen.
Currently I don't see e-bus making it to any laptop. Ideally you would have a SOC with memory and HT support built in possibly with a lot more. That would be a nice approach for the next revs.
Yeah, it would. The next 12 months or so will be interesting-- who knows when a Powerbook will show up with a new processor?
I really hope they do have one though.
As someone earlier pointed out, a few seconds here and there don't matter a whole lot to me either. What does is functionality. Meaning a robust hardware system that can handle the software and a display that matches it (xbrite?)
However, I am curious about all these PC comparisons. I'd be interested to know if those here making them, have actually spent real world experience on them. Although this is a pro-Apple forum, it would be great to know that comments are not just hearsay and spec based...but hands on user based.
There will be no PowerBook, there will however, be an XBook.
-15 and 17 only.
-Aluminum enclosure, all of which resembles the speaker grill on the current PBs.
-1 and 2 iPod hard drives, totalling 160 GBs, for pro apps where multiple drives come in handy.
-2.2 and 3.0 GHz G5 processor with 1.2 GHz and 1.8 GHz system bus.
-2 and 4 GB PC4000 RAM
-16X AGP Pro GPU with 512 MB VRAM
-3 USB, 2 FW400, 2 FW800, ADC (XBook must be plugged in) and DVI (full size)
-Swap Bay- A second optical drive, or a second battery.
-Built in mini WiFi
-Longer lived battery, yielding a claimed 8 hrs.
This will be sold alongside the existing portable options. Prices rumored to start at $3,499 and $4,099
This is real people!
Originally posted by fresco
This was just posted at macrumors
There will be no PowerBook, there will however, be an XBook.
-15 and 17 only.
-Aluminum enclosure, all of which resembles the speaker grill on the current PBs.
-1 and 2 iPod hard drives, totalling 160 GBs, for pro apps where multiple drives come in handy.
-2.2 and 3.0 GHz G5 processor with 1.2 GHz and 1.8 GHz system bus.
-2 and 4 GB PC4000 RAM
-16X AGP Pro GPU with 512 MB VRAM
-3 USB, 2 FW400, 2 FW800, ADC (XBook must be plugged in) and DVI (full size)
-Swap Bay- A second optical drive, or a second battery.
-Built in mini WiFi
-Longer lived battery, yielding a claimed 8 hrs.
This will be sold alongside the existing portable options. Prices rumored to start at $3,499 and $4,099
This is real people!
Could you post a link? And how is this real and not wild fantasy?