Slashdot Mirror
Comparative G5/G4 Tests
rocketjam writes "Barefeats.com has posted test results comparing a 2GHz G5 MP, 1.8GHz G5, 1.6GHz G5 and G4 MP's at 1.4GHz, 1.25GHz and 1GHz. They use Photoshop, Cinebench 2003 and a Bryce 5 render for tests. Bottom line is the G5 2GHz MP has the best bang for your buck, but you might think twice about trading in that dual processor G4 for a solo G5...the G4s hold their own quite well. They also say tests in Panther yielded significant increases in the G5 scores."
Seems more like promotional material for Apple. Consider their analysis of performance improvement when discussing OX X 10.3:
....CPU score increased 40%
....Thread score increased 44%
....Memory score increased 38%
We ran Xbench 1.1 on a G5 1.8GHz with 10.3 beta build 7B49. Compared to 10.2.7 "Jaguar"....
Hmm. I guess that Apple users aren't too discriminating when it comes to stats or methodological testing descriptions in a review! (Perhaps, though, with Anandtech and Tom's Hardware, we're just spoiled.) Surely, there must be better Mac-related reviews out there (and hopefully some that pit them against the latest Intel and AMD offerings, just to be interesting).
It's not a very difficult feat to get more performance per dollar than the G4 - it was already abyssmal in that regard. When the G4 was introduced the prices made sense, but they just kept on charging the moon while G4 improved only marginally compared to the P4 improving by leaps and bounds.
For great justice.
Why didn't they use a real 3d package and do render tests in Maya.
And I find it hard to believe that a 20 second render test will show much insight into a machines speed.
Why not go with a more realistic scene render that would take a couple hours??
-I just work here... how am I supposed to know?
BareFeats is meant to give a quick initial impression of what is going on. Some of his tests are supposedly done in a store with display model machines.
In general though, testing procedures for Macs is nothing like it is for PC's. Too bad Anandtech and others wouldn't put some focus on Mac's from time to time. *shrug*
The article says there are pretty hefty performance gains from upgrading to Panther on a G5, but unless we know how much Panther benefits a G4 as well, it is hard to say what plan of action is best. You can get a Powermac G4 Dual 1.25 GHz for $1599 (went to store.apple.com, clicked on single 1.25 model, and added a second processor), and it looks like it gives you performance that equals or rivals the single G5s (based on the benchmarks given, with all systems running Jaguar)... I think it may be best to wait until Panther arrives before making any purchasing decisions based on these kinds of benchmarks.
Slashdot's first reaction to VMware
A lot of programs are yet to be at all tweaked for the G5s. There are a couple of new processor functions (hardware square root for instance) that may bring big gains. Also, there are old functions from the G4 that slow down the G5. Check out Apple's G5 performance primer. I read that the changes are enough to make the guy who made the mac rc5 engine want to re-write it for the G5 (no simple tweaks). He was hoping to get by with just some minor tinkering, but the chip does require a lot more than that to take advantage of it's potential.
Let me take another example; regarding CineBench.
http://www.postforum.com/forums/read.php?f=6&i=87
In that post, a guy called Richard from the Maxon development labs says this:
This compares to a 1.8ghz G5 score that I've seen of 188. Which means they're aiming to get a fair bit out of optimisation for the chip. Just as a means of further comparison...
http://www.imashination.com/bench.
You'll see the top score these people have recorded is for a dual Xeon 2.4ghz - with a score of 502. If the G5s make it up to over 500, that says a lot about the chip.
Finally, you've also got to include a mention of the compilers. Whilst some optimisation has been made to GCC, the GCC guys rejected a whole heap of improvements for the G5 because they were too platform specific. There's a good thread over at Ars Technica that discusses some pretty big gains when using the IBM XLC compiler. Other Mac-specific compilers should yield some pretty awesome gains too.
So, in summary - take these scores with a grain of salt. They're just the beginning.
-- james
It looks like the Dual G5 2GHz has the best bang for the buck.
Yeah, it's a big bang but it's also a heck of a lot of bucks and I'm not yet convinced it's worth it. Of course, if (or more likely, when) Apple discontinues the G4-based Powermacs, we won't have a choice.
not a mac owner, but il bite. On the G5 I spent about 20 minutes trying to install Adobe Arcobat 6. 20 minutes even if you start "installing now", it would probably take you a lot longer that 20 minutes to install Acrobat Reader-days maybe, coz you would still have to wait for "your" _g5_ to arrive...
Whenever a new generation of Mac systems comes out, the faster of the oldest systems beats the slowest of the newer systems. The G4's don't need to be traded in for quite some time.
Harold
Barefeats is a "real world" benchmarking site. No benchmarking is TRULY scientific, and Rob at Barefeats hardly pretends to be. Still, the benchmarks that he posts give a good general indication of the performance you can expect.
The G5 is NOT going to excel at Altivec optimised code, the G4 will remain the Altivec champ until IBM puts the kind of Altivec resources onto the 970 that Moto put onto the 745x series. For most other stuff, the G5 will wipe the floor with the G3 and G4 chips.
That was classic intercourse!
I just want to know if the dual 2GHz is actually fast enough to play a decent sized city in SimCity 4 running at 1920x1200.
(Perhaps, though, with Anandtech and Tom's Hardware, we're just spoiled.)
Did you just imply that Anandtech and Tom's hardware are valid places to go to learn about PC hardware? LMAO. For the uninitiated, here's a quick rundown of every Tom's hardware and anandtech page.
Motherboard X just came in. It's Company X's newest board, poised to grab the speed crown from Company's Y. Can it do it? Read on! (click banner ad.)
Next Page: Here is a blue line that represents motherboard X. You can see that it barely outdistances Y in this key test, as shown by the shorter line. But what about this other test? (click through for more huge banner ads.)
(click through for more huge banner ads.)
(click through for more huge banner ads.)
(click through for more huge banner ads.)
(click through for more huge banner ads.)
Conclusion: Boy, Motherboard X sure is fast! I can't wait to get my hands on one again, and I'll surely pay a premium for such speed. There may be banner ad for a company selling this motherboard RIGHT ON THIS VERY PAGE! I know what I'd do, if I wanted to be l33t, and you want to be l33t, don't you?
(click through for more huge banner ads.)
Next week: Will the red line finally beat the blue line in our extensive test suite?
(-1, Raw and Uncut is the only way to read)
g{The G5 is NOT going to excel at Altivec optimised code, the G4 will remain the Altivec champ until IBM puts the kind of Altivec resources onto the 970 that Moto put onto the 745x series}g
That's not strictly true, the problem is that altivec that's optimal for the 745x chips is worst case for the 970, since best case on the 745x makes heavy use of the vec_dst (prefetch) instruction, which is handled serially on the 970 and hence stalls the Altivec hardware.
also the G5 is a lot less likely to run into bandwidth bottlenecks with altivec code on large datasets.
but will it make the Internet faster, like Intel's P4 does?
The vec-dst issue is one problem, but just review the G4e article at arstechnica and have a look at the G4e's Altivec execution unit design - it's a generation ahead of that in the PPC 970 (which is approximate in execution resources to the Altivec unit of the MPC 7400 - albeit running at 2-4 times the 7410's clock rate!)
That was classic intercourse!
You can grate cheese with the G5, but not the G4... :^)
(I suppose you could grate cheese with the fan on the back of the G4, but that would get messy real quick!)
Slashdot's first reaction to VMware
...for the G5. Adobe Photoshop has been specially coded to take every possible advantage of the G4's architecture. I wouldn't be surprised if the program held back information and bits of commands in order to keep the standard 133MHz bus clear and chugging along with data as fast as possible. Just imagine the sort of speeds we'll get when Adobe really unleashes the beast and allows the program to entirely saturate two 1GHz busses with information and optimizes the code for the G5.
Pile that all on top of the speed increases seen under Mac OS 10.3 and you'll get a box that absolutely screams for Photoshop work (let alone anything else). With the tests performed today at bare feats, we can see that the G5 can beat the G4 at it's own game, let's see what the G5's game looks like.
I mailed the barefeats guy but haven't heard back yet...
:-) The same seems to be the case for the G5 in general... it's only going to get faster.
The photoshop tests indicate version 7.0, while Adobe has posted some optimised libraries and plugins for 7.0.1 that supposedly speed up some functions considerably.
I haven't heard back as to whether the author actually used 7.0.[0] or the slightly optimised 7.0.1.
so far, I'm pretty happy with the reported G5 performance considering how different the architecture is to the G4.
Apple's in a very odd position for a Computer Company right now. Instead of releasing increasingly bloated software that runs ever slower, requiring ever faster hardware... their hardware is getting faster and the software is speeding up. i'm running Panther now and it is noticeably faster at many tasks.
I'm not feeling witty so bite me
Might it be too soon to really determine how fast the G5 is? I imagine there's a lot of room for optimizing the code of a lot of applications for the PPC 970. Also, IBMs newest XL compilers are said to make a big difference in a lot of cases. Maybe the true speed of the new PowerMac isn't quite apparent yet?
Having listened in to a few programmers discussing that, it seems that it's pretty much only RC5 that actually manages to make full use of the Altivec unit in the 745x series chips anyway, and the benches I've seen that _haven't_ been littered with vec_dst show that the 970 scales in a fairly linear fashion over the G4 as far as altivec code codes (except it also maintains that scaling on larger datasets, since its got a fast memory subsystem, rather than a slow memory subsystem with a fast L3)
". The code is optimized for the mac. My friends P4 2.8ghz is only a little faster than my G4 733. Apple took advantage of this for years and had test results based on photoshop."
/somewhat/ different than those for prior PowerPC processors and the optimizations that took place for the G4 (such as using vec_dst in the AltiVec optimized portions of the code) actually work against the G5.
:-)
Your working with outdated information--by about 7 years.
The code is optimized for both platforms very heavily. A large portion of Photoshop's userbase is on Wintel machines and they were also paid (by Intel) awhile back to optimize their filters for Intel processors. Presumably they care about performance and keep both versions highly optimized. Saying that it is "more highly" optimized for the Mac is a fallacy--it hasn't even had more time to become optimized for the Mac, due to processor changes. The optimizations for the G3 and G4 are
I also heard a rumor, though I am not sure that it is true, that Photoshop would offload its interface to the graphics card for display on its own and that, with the introduction of QE, Photoshop was effectively rendering its display elements twice. This may be completely unsubstantiated though
While in general your point is good--that apps which are highly optimized for one platform are not necessarily highly optimized for another--Photoshop is a bad example.
Integrate Keynote and LaTeX
Yes, if we want to compare a Pentium4 Xeon or a Opteron, and even in comparisons such as this, we have to take the results with a (largish) grain of salt and realize that the PowerMac G5 *will* perform better in these tests given time for further optimizations--using xlc/xlf (which /preliminary/ reports show for the Jet3D benchmark will raise the score for a single 2 GHz G5 to around three times that of 2.66 GHz P4), recompiling in 64-bit, a system which is better optimized to take advantage of the processor, etc.
/now/ from a dual-processor G4 to either a single or a dual processor G5 the current benchmarks are more relevant. Otherwise, you are absolutely right, when it comes to benchmarks we still are premature.
:-)
This goes for everything.
OTOH, if you are thinking of upgrading
That being said, it is fun to look for the results
Integrate Keynote and LaTeX
"The G5 is NOT going to excel at Altivec optimised code, the G4 will remain the Altivec champ until IBM puts the kind of Altivec resources onto the 970 that Moto put onto the 745x series. "
/bandwidth limited/. The architecture that the G5 is based on is radically faster when it comes to things like loading from main memory or making optimal use of both processors.
Another poster has already mentioned the execution sterilization that occurs thanks to optimizations that worked quite well in the G4 (vec_dst et al), but there is another point on this issue that needs to be mentioned.
Even if the G5 performs slightly slower than the G4e with AltiVec enhanced code on an individual, it has the potential to be much much faster overall simply due to the architecture. One of the main problems with AltiVec on the G4e currently is that many of the apps that take advantage of it are
Integrate Keynote and LaTeX
The G5 supports PCI-X.
Integrate Keynote and LaTeX
How many more benchmarks are going to be necessary for people to start believing that this _is_ a great, viable, and priceworthy computer?
1Ghz FSU, dual 2Ghz 64-bit CPUs, 8GB RAM, serial-ata drives
All that for less than a UltraSPARC server, and you _still_ (!) need "proof" or validation???
This is getting ridiculous
Error 407 - No creative sig found
If you read Hannibal's appendium to his 970 articles he points out that the Altivec looks better than he initially thought. This isn't to say there isn't room for improvement. But to say that the G4 is the Altivec champ seems somewhat incorrect.
Hannibal's Followup
It is true that with G4 altivec code the G5 won't be as efficient as it could. Perhaps for some code the G4 might do better. But this is a simple matter to fix with a grep through your code. But initially altivec code won't show off the G5 until programmers do a simple recompile.