Got a tip for us?
Let us know
Become a MacRumors Supporter for $50/year with no ads, ability to filter front page stories, and private forums.
PowerMac G5 1.6GHz PSBench 7 Results
- Thread starter MacRumors
- Start date
- Sort by reaction score
Do you guys only post to one thread?
Just a question - a popular sentiment on the most recent PB thread is that if Apple update their PowerBooks (uh, emphasis on Power?) with a speed bumped G4, people should still buy one, it will be a great laptop, etc.
Now on this thread, people are saying "wait til everything gets written in 64 bit code! Then that G5 will kick a**."
Ahem. So if a year or two from now, when everything's should be optimized to 64 bit code, what am I supposed to think about the $2500 people are saying I should drop on a new G4 rev PB? Could you people please tell those others in the PB thread to stop singing the praises of a speed-bumped G4 PB update?
Talk about FUD. I thought people on this board were supposed to "Think Different", not toe the Apple Corporate/Macolyte line.
Props to Neo. Skeptics, right or wrong, keep the rest of us honest. Those issues are legitimate. Let them be discussed.
Those of you talking about banning/censoring him for raising a voice of dissent should consider a job as White House Press Secretary. Wait a minute... Ari Fleischer, I know you've been retired for the past few months - is that you?
Just a question - a popular sentiment on the most recent PB thread is that if Apple update their PowerBooks (uh, emphasis on Power?) with a speed bumped G4, people should still buy one, it will be a great laptop, etc.
Now on this thread, people are saying "wait til everything gets written in 64 bit code! Then that G5 will kick a**."
Ahem. So if a year or two from now, when everything's should be optimized to 64 bit code, what am I supposed to think about the $2500 people are saying I should drop on a new G4 rev PB? Could you people please tell those others in the PB thread to stop singing the praises of a speed-bumped G4 PB update?
Talk about FUD. I thought people on this board were supposed to "Think Different", not toe the Apple Corporate/Macolyte line.
Props to Neo. Skeptics, right or wrong, keep the rest of us honest. Those issues are legitimate. Let them be discussed.
Those of you talking about banning/censoring him for raising a voice of dissent should consider a job as White House Press Secretary. Wait a minute... Ari Fleischer, I know you've been retired for the past few months - is that you?
Just to clear things up: the G5 is second worst, not second best in this test (the numbers mean "time in seconds"). So it takes the G5 1.6 about 3 minutes to do this test whereas a P4 3.06 system does the same thing in slightly more than 2 minutes.
Concerning the Opteron and its Photoshop performance, here's the link [this one's for the pro who thinks "a dual processor Opteron 246 ... will NEVER beat a Dual 2 Ghz G5 in Photoshop. NEVER]:
http://www.gamepc.com/labs/view_content.asp?id=opteron244&page=6
As you can see, an Opteron 244 system finishes the Photoshop test in only 71.2 secs, the fastest and most up-to date Xeon (3.06/1 MB) in 74.1.
So stop arguing about speed matters. It's pathetic.
Re: Do you guys only post to one thread?
You should think you're dropping $2500 on a good laptop. Or you can roll that $2500 into a good desktop. You can't expect parity between the two...
There's people who think Transmeta makes a good laptop because they like the benefits of the Crusoe. There's people who want a top end P4 in a little box they can carry and plug into the wall because they like the benefits of that.
Personally I think the G4 is an excellent laptop processor, and I think the G5 will be an excellent desktop processor. I'm not towing the Apple line, I just agree with the design tradeoff's they're making.
I'm not ignorant-- I'm a professional engineer who's spent his career on both Windows boxen and Unix workstations and eventually decided that Apple's current product lineup best matches the way I work and satisfies the factors most important to me.
If you prefer different design tradeoffs, there's a whole spectrum of other options out there.
Why do people act so surprised that posters on an Apple discussion forum, who have looked at the options out there and put their money into Apple products might agree with Apple's choices?
You should think you're dropping $2500 on a good laptop. Or you can roll that $2500 into a good desktop. You can't expect parity between the two...
There's people who think Transmeta makes a good laptop because they like the benefits of the Crusoe. There's people who want a top end P4 in a little box they can carry and plug into the wall because they like the benefits of that.
Personally I think the G4 is an excellent laptop processor, and I think the G5 will be an excellent desktop processor. I'm not towing the Apple line, I just agree with the design tradeoff's they're making.
I'm not ignorant-- I'm a professional engineer who's spent his career on both Windows boxen and Unix workstations and eventually decided that Apple's current product lineup best matches the way I work and satisfies the factors most important to me.
If you prefer different design tradeoffs, there's a whole spectrum of other options out there.
Why do people act so surprised that posters on an Apple discussion forum, who have looked at the options out there and put their money into Apple products might agree with Apple's choices?
Re: Do you guys only post to one thread?
i hope you're seriously interested... otherwise this is a waste of time...
buying a mobile is something different than buying a table computer. in my opinion the most important factors are mobility and stability.
so what you should look at is:
- does the mobile fit in a bag i would usually use when i go to work/uni?
- will i be ready to carry this weight, if not -> check for a smaller model
- how long is the battery time? if the battery is too short, is there electricity at the place where i would use my mobile normally? if not -> check for another model.
- is the mobile stable?
- what material is is made off? (careful, there is PC laptop with a metal like painting)
- where are the plugs
- if there is fragile plugs, are they well enough covered when you have to stuff the mobile in a bag
if all these things are answered and your happy with those you'll have only little choice in mobile models left over. then you might think about speed, OS, beauty.
i have a tiBook 1st generation. i don't treat it very well, but it's still quite OK. if i had the money to buy a new one, i'd take a 12inch AluBook. that would be the personal device for me. i would maybe wait for the updates as there was rumors of a thinner 12inch model.
- kaos
i hope you're seriously interested... otherwise this is a waste of time...
buying a mobile is something different than buying a table computer. in my opinion the most important factors are mobility and stability.
so what you should look at is:
- does the mobile fit in a bag i would usually use when i go to work/uni?
- will i be ready to carry this weight, if not -> check for a smaller model
- how long is the battery time? if the battery is too short, is there electricity at the place where i would use my mobile normally? if not -> check for another model.
- is the mobile stable?
- what material is is made off? (careful, there is PC laptop with a metal like painting)
- where are the plugs
- if there is fragile plugs, are they well enough covered when you have to stuff the mobile in a bag
if all these things are answered and your happy with those you'll have only little choice in mobile models left over. then you might think about speed, OS, beauty.
i have a tiBook 1st generation. i don't treat it very well, but it's still quite OK. if i had the money to buy a new one, i'd take a 12inch AluBook. that would be the personal device for me. i would maybe wait for the updates as there was rumors of a thinner 12inch model.
- kaos
In the original article it said that the 1.6Ghz G5 is about the same as a Athlon XP2400. Well the Athlon XP 2400 is clocked at around 1.7Ghz with a 266Mhz bus, so this does not look so good for the G5.
Until Panther is released and the apps being tested are fully optimized the benchs will just all need to be repeated,and even then if the 2ghz is to fast Mac users will jump on it and PC users will say its all lies,and vice versa.
I dont care if my G5 on order is not the fastest personal computer in the world as I never believed that anyway,but I do care thats its going to be a hell of a lot faster then the previous models, if you want your G5 to be so fast to make PC users eat crow then be under no illusions noone is going to admit anything,and this argument {in general} will carry on until the next rev of the G5 is released and then it will start all over again.What good does it do to have a G5 which is say .5 of a sec faster then a dual xeon,or .5 slower,so if you are looking forward to bragging rights then youre buying for the wrong reason.
Just be happy we are not sitting on a G4 1.6 dual or something and "still" waiting for the G5.
I dont care if my G5 on order is not the fastest personal computer in the world as I never believed that anyway,but I do care thats its going to be a hell of a lot faster then the previous models, if you want your G5 to be so fast to make PC users eat crow then be under no illusions noone is going to admit anything,and this argument {in general} will carry on until the next rev of the G5 is released and then it will start all over again.What good does it do to have a G5 which is say .5 of a sec faster then a dual xeon,or .5 slower,so if you are looking forward to bragging rights then youre buying for the wrong reason.
Just be happy we are not sitting on a G4 1.6 dual or something and "still" waiting for the G5.
You people need to realize that no bench test is truly fair. ALL yes ALL tests are manipulated to show a particular manufacturers strong points. The most important thing about performance is: When I set it up does it peform to my needs? If you can answer yes to that question then taht is the only benchmark you need.
for all the people who asked Im going to do the full test on my 1.42 a little latter and get back with the results. Anyone else here have a 1.42 also? Because I seriously did not think the 1.6g5 was going to be this much faster then my 1.42g4 because I had seen some cpu tests online (not apple ones) that even showed the 1.42g4 dual as being faster then the 1.6 g5...
The difference
1.6GHz PowerPC G5
Bus 800MHz
1.8GHz PowerPC G5
Bus 900MHz
Dual 2GHz PowerPC G5
Bus 1GHz per processor
I'm shure that the 2Ghz with 1ghz per processor BUS will make the difference. If the test reported above are true, wi wil see a stunning performance here for 2.0 G5.
1.6GHz PowerPC G5
Bus 800MHz
1.8GHz PowerPC G5
Bus 900MHz
Dual 2GHz PowerPC G5
Bus 1GHz per processor
I'm shure that the 2Ghz with 1ghz per processor BUS will make the difference. If the test reported above are true, wi wil see a stunning performance here for 2.0 G5.
Re: Re: Do you guys only post to one thread?
Hey, thanks for the tips.
As someone who's been lugging laptops around on transatlantic business trips for 6 years, I had no idea those kinds of things were important. I thought the only thing that really mattered was the stability of the cup holder that slides out of the side of laptops. The PBs don't have this and I guess that's why I haven't bought one yet.
Who do you guys think you are assuming that every person who posts a comment critical of Apple products is some naive computer newbie?
There have been fair points raised about how to assess the value of Apple products, and not just in benchmarks, yet when this happens, a lot of people on this board seem eager to dismiss them or make convenient excuses for one aspect of their claim but not the others.
That the 1.6 G5 is not clearly blowing away the other processors it is being compared against SHOULD at least draw some acknowledgement that maybe the G5 isn't the huge leap forward against x86 processors that it was made out to be. Yet I'm hearing "Well, benchmarks are so subjective", "Those Photoshop filters aren't really the ones that matter", "The code hasn't been optimised to take advantage of 64 bits", etc.
Which brings me to the fundamental question from my earlier post that neither you nor Analog Kid addressed substantively. That is, if, with the introduction of the G5, we can assume that the OS and apps will move to 64 bit code (and should assume, or else why develop a 64 bit processor?), will a G4 rev PB be a good value if and when they are released?
Jeez, and as much as I covet the case and the OS of the PB as I do not own a Jetta or a Bimmer and I need something to get chicks with, I'm sorry but the answer is "No, a minor speed-bump rev to a G4 PB is NOT a good value at $2500", especially if G5 PBs are due within 12 months time. Why can't you just admit that? Come on now, it will be good for you. Say it with me.... "Apple is phasing out 32 bit processors from its general architecture"
If they release increasingly faster G5 PBs after I get a 1st gen G5 PB, then fine, I'll still be happy with my purchase b/c I'll be able to run the latest 64 bit software 3 years from now somewhat effectively.
The same cannot be said about the G4. It's a lame-duck architecture by definition now. I'm not saying this, the G5 is. Note: architecture and product are not the same thing; lame-duck doesn't mean useless, just more predictably obsolescent.
** Historical note: In the beginning, Steve introduced the G4 PowerBook. And this was good. The G4 ran crucial applications like Photoshop a lot faster than wintel machines at the time. And this was good. The blindly faithful sang hosannahs (no, actually, taunts) about the superiority of their hardware. And this was... alright. But then the forces of wintel conspired to make their machines as fast and then faster than The Mac. And this was natural. And then the blindly faithful changed their tune; they began to sing that processor specs weren't really relevant. Megahertz was a false idol and that "The Experience" equalled performance. "Nay," said the skeptics, "performance equals performance." But these blasphemers were quickly stoned by all-too eager Macolytes armed with puck mice they publicly praised as "innovative design" but secretly reviled And this was predictable. And then Steve passed down from the heavens the miracle of a 64bit G5, and once again the blindly faithful dusted off those hymn books praising processor specs and raw computing speed - yet still stoning all those skeptics who had been asking questions about performance. And this was unfortunate. Then the same parishoners, conveniently leaving their hymn book of Processor Prominence behind, then traveled to and fro the Thread of the Undying Question of PowerBook Updates so they could continue to recite their songs of Processor Irrelevance (which they had practiced so long and hard to learn by wrote) and convince the unwitting to pay $2500 for G4 PB Pardons. And this was hypocritical. Yet one rose among them to ask if this were so and quickly did the Macolytes raise their puck mice in wrath to smite down the blasphemer in their Temple of Smugness but before they could strike, this blasphemer declared "Yea, I say unto thee: Let he who paid a premium to buy an Apple Lisa before Apple quickly moved on to the Mac cast the first puck mouse."
And then...
Hey, thanks for the tips.
As someone who's been lugging laptops around on transatlantic business trips for 6 years, I had no idea those kinds of things were important. I thought the only thing that really mattered was the stability of the cup holder that slides out of the side of laptops. The PBs don't have this and I guess that's why I haven't bought one yet.
Who do you guys think you are assuming that every person who posts a comment critical of Apple products is some naive computer newbie?
There have been fair points raised about how to assess the value of Apple products, and not just in benchmarks, yet when this happens, a lot of people on this board seem eager to dismiss them or make convenient excuses for one aspect of their claim but not the others.
That the 1.6 G5 is not clearly blowing away the other processors it is being compared against SHOULD at least draw some acknowledgement that maybe the G5 isn't the huge leap forward against x86 processors that it was made out to be. Yet I'm hearing "Well, benchmarks are so subjective", "Those Photoshop filters aren't really the ones that matter", "The code hasn't been optimised to take advantage of 64 bits", etc.
Which brings me to the fundamental question from my earlier post that neither you nor Analog Kid addressed substantively. That is, if, with the introduction of the G5, we can assume that the OS and apps will move to 64 bit code (and should assume, or else why develop a 64 bit processor?), will a G4 rev PB be a good value if and when they are released?
Jeez, and as much as I covet the case and the OS of the PB as I do not own a Jetta or a Bimmer and I need something to get chicks with, I'm sorry but the answer is "No, a minor speed-bump rev to a G4 PB is NOT a good value at $2500", especially if G5 PBs are due within 12 months time. Why can't you just admit that? Come on now, it will be good for you. Say it with me.... "Apple is phasing out 32 bit processors from its general architecture"
If they release increasingly faster G5 PBs after I get a 1st gen G5 PB, then fine, I'll still be happy with my purchase b/c I'll be able to run the latest 64 bit software 3 years from now somewhat effectively.
The same cannot be said about the G4. It's a lame-duck architecture by definition now. I'm not saying this, the G5 is. Note: architecture and product are not the same thing; lame-duck doesn't mean useless, just more predictably obsolescent.
** Historical note: In the beginning, Steve introduced the G4 PowerBook. And this was good. The G4 ran crucial applications like Photoshop a lot faster than wintel machines at the time. And this was good. The blindly faithful sang hosannahs (no, actually, taunts) about the superiority of their hardware. And this was... alright. But then the forces of wintel conspired to make their machines as fast and then faster than The Mac. And this was natural. And then the blindly faithful changed their tune; they began to sing that processor specs weren't really relevant. Megahertz was a false idol and that "The Experience" equalled performance. "Nay," said the skeptics, "performance equals performance." But these blasphemers were quickly stoned by all-too eager Macolytes armed with puck mice they publicly praised as "innovative design" but secretly reviled And this was predictable. And then Steve passed down from the heavens the miracle of a 64bit G5, and once again the blindly faithful dusted off those hymn books praising processor specs and raw computing speed - yet still stoning all those skeptics who had been asking questions about performance. And this was unfortunate. Then the same parishoners, conveniently leaving their hymn book of Processor Prominence behind, then traveled to and fro the Thread of the Undying Question of PowerBook Updates so they could continue to recite their songs of Processor Irrelevance (which they had practiced so long and hard to learn by wrote) and convince the unwitting to pay $2500 for G4 PB Pardons. And this was hypocritical. Yet one rose among them to ask if this were so and quickly did the Macolytes raise their puck mice in wrath to smite down the blasphemer in their Temple of Smugness but before they could strike, this blasphemer declared "Yea, I say unto thee: Let he who paid a premium to buy an Apple Lisa before Apple quickly moved on to the Mac cast the first puck mouse."
And then...
take a dual 2ghz g5 with 6gb of ram
then take a intel p4 3.06 ghz at 800mhz bus with HT with 4 gigs of ram
open a 2 gig photoshop file
see which is the fastest computer!
apple is positioning the g5 as the fastest personal computer..
not the fastest workstation(even tho it may be priced like one)
im guessing that since the g5 can support more then 4 gigs of memory more can be done on it by those who need to do it.
especially big stuff
anyways..
remember when the first p4 came out.. at 1.4ghz.. people were cryling and complainging that the p3 at 1ghz was faster.. and in many respects it was.. the p4 was superscaler.. it can reach higher clock speeds. and cant do as much per clock speed.. but by being able to reach very high clock speeds it still ending up faster then the p3.. same thing is happening with the g5
if you were able to take a single g4 1.4 and a g5 1.4 the g4 would prob win.
but since the g5 is made to scale well mhz wise.. right now its
fast but soon it will be much faster.. you people just need some more patients.
remember sometimes your comparing a 3ghz processor to a 1.6 ghz processor.. the fact that the 1.6 can compete at all in some test is amazing
then take a intel p4 3.06 ghz at 800mhz bus with HT with 4 gigs of ram
open a 2 gig photoshop file
see which is the fastest computer!
apple is positioning the g5 as the fastest personal computer..
not the fastest workstation(even tho it may be priced like one)
im guessing that since the g5 can support more then 4 gigs of memory more can be done on it by those who need to do it.
especially big stuff
anyways..
remember when the first p4 came out.. at 1.4ghz.. people were cryling and complainging that the p3 at 1ghz was faster.. and in many respects it was.. the p4 was superscaler.. it can reach higher clock speeds. and cant do as much per clock speed.. but by being able to reach very high clock speeds it still ending up faster then the p3.. same thing is happening with the g5
if you were able to take a single g4 1.4 and a g5 1.4 the g4 would prob win.
but since the g5 is made to scale well mhz wise.. right now its
fast but soon it will be much faster.. you people just need some more patients.
remember sometimes your comparing a 3ghz processor to a 1.6 ghz processor.. the fact that the 1.6 can compete at all in some test is amazing
Fastest 100,000 orders!
Jobs statement about the G5 being the fastest PC in the world redefines his ability to both suck and blow (apologies to Bart) at the same time ... with the truth!
http://forum.cubase.net/forum/Forum5/HTML/009443.html
Still, he understands the bankability of hype...100,000 orders
Jobs statement about the G5 being the fastest PC in the world redefines his ability to both suck and blow (apologies to Bart) at the same time ... with the truth!
http://forum.cubase.net/forum/Forum5/HTML/009443.html
Still, he understands the bankability of hype...100,000 orders
Re: Re: Re: Do you guys only post to one thread?
hmm...
i'm not sure your post IS a reply to my post but anyway.
how should i know that you're a regular mobile user?
in the last three months three of my friend bought PC laptops. they never had mobiles before. i don't care what your OS is as long i don't have to do the support. for them these points i made here were helpful. and if you read my post again, did i say there is only stable apple mobiles? no. i said there is not many stable mobiles. and i still say that. but there is stable PC mobiles. you just have to know very well what you want and what to look for. that's the whole secret... no?
edit: i even wrote in my original post "then you might think about speed, OS, beauty." do you see the 2nd thing... it's "OS"...
hmm...
i'm not sure your post IS a reply to my post but anyway.
how should i know that you're a regular mobile user?
in the last three months three of my friend bought PC laptops. they never had mobiles before. i don't care what your OS is as long i don't have to do the support. for them these points i made here were helpful. and if you read my post again, did i say there is only stable apple mobiles? no. i said there is not many stable mobiles. and i still say that. but there is stable PC mobiles. you just have to know very well what you want and what to look for. that's the whole secret... no?
edit: i even wrote in my original post "then you might think about speed, OS, beauty." do you see the 2nd thing... it's "OS"...
1.42 results
Here are the results from my 1.42ghz dual g4 powermac (fw800), 2gb of ram, GeForce4 Ti 128mbs, running 10.2.6.
90 Degree Rotate-1.0
9 Degree Rotate-3.6
.9 Degree Rotate-7.4
1 Gaussian-5.5
3.7 Gaussian-6.7
85 Gaussian-8.1
Unsharp 50/1/0-5.3
Unsharp 50/3.7/0-10.1
Unsharp 50/10/5-7.9
Despeckle-5.5
RGB-CMYK-7.6
60% Reduction-2.3
LensFlare-9.9
Color Halftone-11.2
NTSC Color-10.8
Accent Edge-18.2
Pointilize-19.6
Watercolor-37.8
Polar Coordinates-8.4
Radial Blur-32.6
Lighting-7.6
Here are the results from my 1.42ghz dual g4 powermac (fw800), 2gb of ram, GeForce4 Ti 128mbs, running 10.2.6.
90 Degree Rotate-1.0
9 Degree Rotate-3.6
.9 Degree Rotate-7.4
1 Gaussian-5.5
3.7 Gaussian-6.7
85 Gaussian-8.1
Unsharp 50/1/0-5.3
Unsharp 50/3.7/0-10.1
Unsharp 50/10/5-7.9
Despeckle-5.5
RGB-CMYK-7.6
60% Reduction-2.3
LensFlare-9.9
Color Halftone-11.2
NTSC Color-10.8
Accent Edge-18.2
Pointilize-19.6
Watercolor-37.8
Polar Coordinates-8.4
Radial Blur-32.6
Lighting-7.6
Overall times
Just a crude comparison of the overall time it took to finish the image for each processor:
1x1.6 GHz G5
Overall Time: 180.1 (sec)
1x3.06 GHz P4b
Overall Time: 124.6 (sec)
1xAthlon 3000+
Overall Time: 148 (sec)
1x2.0 GHz G5 (assuming linear scaling in overall time)
Overall Time: 144.08 (sec)
Just a crude comparison of the overall time it took to finish the image for each processor:
1x1.6 GHz G5
Overall Time: 180.1 (sec)
1x3.06 GHz P4b
Overall Time: 124.6 (sec)
1xAthlon 3000+
Overall Time: 148 (sec)
1x2.0 GHz G5 (assuming linear scaling in overall time)
Overall Time: 144.08 (sec)
Re: Re: One big note ...
I work on intel servers in real life. FYI - Xeon DP FSB will go to 800MHz in 1Q 2004
I work on intel servers in real life. FYI - Xeon DP FSB will go to 800MHz in 1Q 2004
Re: My Benchmarks
hahahhahahhaha, great, hehehhehhe!!!!
Originally posted by ultrafiel
Ok, I've decided to do my own benchmarks on a new Pentium 4. Processes:
Start windows: 20 secs
Launch Photoshop 7: 8 secs
Start PSBench: 2 secs
Get hit by Sobig.F: 0.5 secs
Swear at my computer: 1 min.
Spread virus to friends: continuous
Try to patch my computer: 2 days
Start over again after patch: 20 sec
Launch Photoshop: 8 secs
Start PSBench: 2 secs
Get hit by a variant of Sobig.F: 1.5 secs
Curse at my computer: 10 min
Spread new virus: continuous
Try to patch: 1 day
Take computer to shooting range: 30 min.
Fill computer full of lead: 1 hour.
Go home and relax: 3 hours...
Ya that about covers it. I know it isn't very scientific. But I'll stay with OS X. Besides any of you thinking that your G5 is too slow, feel free to donate it to me. My 450 AGP G4 could use a nice retirement.
hahahhahahhaha, great, hehehhehhe!!!!
Because the Opteron is quite similar to the Athlon but with four key advantages: better floating point performance, 64-bit instructions, better memory bandwidth, and SSE2 support. Of those four advantages, only the last two are even relevant for Photoshop, and they probably will not be enough to offset the Xeon's HT advantage.
Regarding the benchmarks you posted, I will admit that the Opteron performed better than I expected. Unfortunately, since they only give the aggregate score (of what appears to be a PSBench run, from comparing the Athlon MP 2200 times to Ace's Athlon MP 2200 times), we have no idea how the Opteron and the Xeon actually compare to each other - all we are doing is comparing four filters (accent edges, pointillaze, water color, and radial blur). For the record, I doubt that the GamePC website was being dishonest when they gave the aggregate PSBench score - they probably just do not understand that the aggregate score is not meaningful for PSBench (which is understandable since they area gaming site, not a graphic design site).
The strange thing is that the PSBench aggregate score seems to be heavily memory constrained - that is partially why the Opteron is doing much better than the Athlon and the Xeon/3.06 1 MB does much better than the Xeon/3.06. But the G5/1.6 actually has the fastest memory subsystem of all the system's in Ace's test, so why doesn't it *really* clean up? Possibly cache is more important than memory bandwidth in this test (the Xeon 1 MB and the Opteron both have big caches), or possibly some key PSBench filters have not yet been optimized for the G5. It would be very helpful if we could actually see some detailed, consistent G4 PSBench scores, but those have yet to appear.
Incidentally, I did not say I was "so sure" the Xeon would beat the Opteron. I said that I would be quite surprised if the Opteron won in Photoshop. And I will still be surprised if the Opteron wins in Photoshop. What I am SURE of is that the Opteron will not beat the Dual G5 in Photoshop. You can bet money on that. (and in case it was unclear, getting a high aggregate score in PSBench does not constitute "winning", anymore than winning in an Apple run benchmark at WWDC constitutes "winning" - at a very minimum you need to win a clear majority of the subtests).
Re: Overall times
Ya thats probably close to what it would actually be.. but apple never said a single 2ghz g5 would be the fastest they said the dual 2ghz is the fastest. Where did I read that the g5 with dual processors gives a 90% increase in performance compared to it only having 1 processor of the same speed? Now obviously when you test it in the real world (photoshop its gonna gonna be 90% better then 144.08 seconds but it will definitely be better because photoshop does take advantage of dual processors.
Ya thats probably close to what it would actually be.. but apple never said a single 2ghz g5 would be the fastest they said the dual 2ghz is the fastest. Where did I read that the g5 with dual processors gives a 90% increase in performance compared to it only having 1 processor of the same speed? Now obviously when you test it in the real world (photoshop its gonna gonna be 90% better then 144.08 seconds but it will definitely be better because photoshop does take advantage of dual processors.
Re: Re: Re: One big note ...
I'm sure it will. FYI, the G5 FSB will go to 1.2 Ghz in 1Q 2004 (or half of whatever they clockspeed is increased to). =) Question is whether faster memory will be available by then to support it. I don't know.
I'm sure it will. FYI, the G5 FSB will go to 1.2 Ghz in 1Q 2004 (or half of whatever they clockspeed is increased to). =) Question is whether faster memory will be available by then to support it. I don't know.
not necessarily
Multiples other than 2:1 are possible for the PPC970 FSB.
If the CPU speeds go up more quickly than memory speeds, they'll be able to keep the bus at 1GHz with faster CPUs - memory speeds won't limit the CPU speed.
Multiples other than 2:1 are possible for the PPC970 FSB.
If the CPU speeds go up more quickly than memory speeds, they'll be able to keep the bus at 1GHz with faster CPUs - memory speeds won't limit the CPU speed.
Re: Re: Re: Re: One big note ...
The beauty of good chipset design doesn't necessarily need faster memory chips, just more slower ones. On a server we released we took PC100 memory and used it on a 400MHz FSB by quad-pumping to and from 4 memory chips at once.
At the time, DDR memory had a 30% premium over PC100 so it made the system less expensive.
Now I don't know if doing this in the desktop world is a good idea, because adding 256MB of RAM get's pointless whe you have to buy 4 64MB DIMMs to do it. But in a server it's different.
The beauty of good chipset design doesn't necessarily need faster memory chips, just more slower ones. On a server we released we took PC100 memory and used it on a 400MHz FSB by quad-pumping to and from 4 memory chips at once.
At the time, DDR memory had a 30% premium over PC100 so it made the system less expensive.
Now I don't know if doing this in the desktop world is a good idea, because adding 256MB of RAM get's pointless whe you have to buy 4 64MB DIMMs to do it. But in a server it's different.
Re: Overall times
Please do not quote aggregate PSBench scores as a performance indicator. As I explained earlier, the aggregate scores are VERY heavily weighted towards just four filters, so they are not at all indicative of overall performance. It is like quoting RC5 scores to show how "fast" the G4 is compared to the P4 - it's just a single benchmark, so it's not meaningful.
If you want to scale, you should reduce the time of each benchmark by 20% and compare the two machines. I calculate that a SINGLE G5/2.0 would win in 9 or 10 of the 21 benchmarks then versus the P4/3.06 HT, so it would just fall short in PSBench. But don't worry, it will do even better in more comprehensive PS benchmarks.
Please do not quote aggregate PSBench scores as a performance indicator. As I explained earlier, the aggregate scores are VERY heavily weighted towards just four filters, so they are not at all indicative of overall performance. It is like quoting RC5 scores to show how "fast" the G4 is compared to the P4 - it's just a single benchmark, so it's not meaningful.
If you want to scale, you should reduce the time of each benchmark by 20% and compare the two machines. I calculate that a SINGLE G5/2.0 would win in 9 or 10 of the 21 benchmarks then versus the P4/3.06 HT, so it would just fall short in PSBench. But don't worry, it will do even better in more comprehensive PS benchmarks.