Slashdot Mirror
G5 vs Opteron, Finally
metfoo writes "It's been months since the G5 and Opterons have been available for purchase. When the G5 systems were first released, many Mac bashers and AMD nuts discredited the G5's performance. They always ended their comments with 'Wait until its compared to an Opteron, then we'll talk.' Well, it's finally time to talk. Barefeats has posted an article comparing the two systems. The G5 line was compared to a Dual 2GHz Opteron and the results are impressive. In gaming, the Opteron system proved to be superior, which is partly due to the superior 9800XT over the base Radeon 9800. The G5 spanks the Opteron in many of the non-gaming tests, except for the Photoshop tests."
That since they are running the Opteron in 32-bit mode, it's not taking advantage of it's full potential. Guess we'll wait until "round 2" like he says, but it still looks bad that he kind of dodges this. If it were me I'd be running the benchmarks on 64-bit linux versus 64-bit linux.(gentoo?)
If they would have used a linux platform instead of Windows...
Jason Faulkner
Old Os Administrator
jason@oldos.org
oldos.
One main issue with the UT 2003 tests. It doesn't say if they are running UT 2k3 2225.1 or 2225. 2225.1 brings MASSIVE performance increases. From the notes:
It's much, much faster. Several optimizations have been made, lots of Altivec code has been added, and the entire sound subsystem has been rewritten. Performance improvements of 25% or more over the original retail version are typical, with single CPU systems achieving a more noticible gain.
Am I just an exception?
"You know why you do not see me styling wit my homies? Because I have no homies!!" -Mojo Jojo
I'll get you started:
(a) Mac only has one mouse button
(b) PC is like a Dodge Neon, Mac is like a BMW
(c) Mac has no games
(d) Windows XP: DRM
(e) Linux has no games
(f) X windows sucks
(g) etc.
O.K., hopefully this will put to bed all those folks who cry about Apple computers being so damned expensive. Feature for feature, the G5 is about $600 cheaper than the Opteron. I certainly found this out when I was pricing workstations from Dell and other Wintel manufacturers and the G5's from Apple. I went with a fully loaded G5 and the price delta was $1200 cheaper going with the G5. Plus, OS X is soooooo nice.
Visit Jonesblog and say hello.
it's interesting that the G5 was bested in photoshop benchmarks... heh. (how long will it be until someone else publishes some benchmarks that utilize some other filters and show the G5 to be faster?)
Those two processors are not compared. The video graphics cards, the motherboard speed, and other things are compared. It should be labeled how Apple G5 Platform compares to Athlon Based Platform.
Unreal Tournament 2003 runs in Direct X mode on the Opteron and OpenGL mode on the G5. Some say this isn't a fair test but if you are choosing between the two systems, you need to know how it runs your favorite game.
If a G5 running in OGL gets such low scores something is wrong. D3D renders slower and requires more processing power than OGL.
-illumina+us "I put on my robe and wizard hat..."
The G5 was running in 32-bit mode as well. When dealing with 32-bit data, 32-bit mode and 64-bit mode on the G5 have the same performance. I had thought this was true of the Opteron as well.
if I recall, ut2k3 (And the original UT) had opengl renderer dlls as well.. Why not try these? I have found them to be much faster than the d3d renderer.
Personally, I would love to see the same tests performed under a standard install of Linux SuSE (SMP) for AMD, and Mac OS X standard install. There should be several cross-platform *nix benchmark utilities out there that will run on both. Anyone up to doing this and then posting on Slashdot?? :-P
The desktop iteration of the Opteron is the Athlon FX-51. Maximum PC has run multiple benchmarks on the two systems to compare them, and the athloh whoops up on the G5. As a matter of fact, the G5 lost in all but one or two tests to the two frontrunners, the Athlon FX and the P4 Extreme Edition. This was obviously in 32-bit mode. I don't hate macs, but in this race (the desktop race), it certainly comes out under the other two major chip manufacturers.
The thing that's true now is that the Mac systems are competitive. They're close to the fastest Intel/Athlon systems -- close enough that there's not an OBVIOUS performance reason to choose one or another.
They're close in price, too (if you go PC white box then the PC is still less than half the price, but for a Xeon system or something from Dell it's fairly close).
I don't think this benchmark is going to make up ANYBODY's mind one way or another, though -- it's an emotional debate rather than a logical one.
The good thing is the Mac's numbers are no longer embarrasingly crappy, as they were in the latter G4 days.
This post is weird (and a bit too formal).
Someone send this guy here...
http://www.slashcode.com/
"Things are more moderner than before- bigger, and yet smaller- it's computers-- San Dimas High School football RULES!"
Price comparisation:
- comparisation of artificially low memory systems as Apples prices are where Apple makes the most on. On the one hand claiming 'we don't want to build ourselves as Apples can't be build, and then going to another store to add memory, just isn't fair when comparing prices.
- Boot-testing the Mac for performance difference with other the HD is a good thing, but the test in the other direction (booting the PC with the other HD might reveal that the bottleneck is in the other direction).
- MacOS X is certainly better in 64bit environments than not wanting to run beta software on a system bought for performance.
- The problem with the Mac is also that the graphics subsystem is already dated. The release cycle of Macs is just too long. When they're first released they -arguably- beat most of the fastest PC's. But the next version is only released at quickest 6 months later, if you compare at that time with latest hardware. Macs just can cope up.
- I also assume that near the end of the cycle, Apple's profit margins are incredible high. It's a very good marketing tactic to keep hardware and software tied to each other, keeping it all under control.
- As I'm typing this on my top-equipped 12" PowerBook, I must admit that MacOS X is a good OS and the hardware is very good (this laptop was cheaper than any comparable hardware at the time I ordered it - not any more at the time when it got delivered)
- And as a rule of thumb, I always say it's better to buy a less expensive system and upgrade it quicker than to go for the fastest and be stuck with it for an extra year.
- Macs also have a better second hand value, and that shouldn't be forgotten when taking the price into account.
- But most performance comparisations clearly SUCK because they tend to be optimised for a certain system (because of lack of knowledge of the party), or highly dependent on release schedules of involved hardware or software.
had feature called "The Race Is On" by Jonathan Seef. The comparison was between G5 and PC's with opteron. The PCs seemed to fare better in most of the tests (photoshop, word, quake, premiere, mp3-encoding, mpeg-2 encoding). Mac seemed to be better only with the DVD creation. By the way, I use Powerbook G4. Anyone's got a link for the article ?
Science as a way of life.
They are not the 'only' 64-bit desktop's available. What's this guys jabbering about? The Opteron is not even a desktop CPU. Try the Athlon 64 variants my friend. Also, this really should have waited until 64-bit XP came out or for now, testing should have been performed under Linux. Also, if this is meant to be a CPU vs CPU comparison, I am sorry but you cannot do that. There are so many factors that account for the end peformance results. All the subsystems in each computer are so different (core logic chipset, harddisks!!, video, etc, etc) that you cannot put them on a level playing field. The only real way ou could do a CPU - CPU direct comparison is if both had the same interface and could be used in the same motherboard and were clocked the same. This way you could get an accurate per clock performance comparison. This is balonga.
Great test by a Macintosh advocacy site! Now it's settled, the G5 is the fastest processor on Earth, and Mac's are cheaper than PC's....
or something.
Yeah. Polite, spelled correctly, good grammar.
Hmmmm....
Maybe WE should ask him for the advice?
You should use AdiumX on your Mac.
First, lets examine the statement The G5 spanks the Opteron in many of the non-gaming tests, except for the Photoshop tests. I see five tests in this review, and there are two wins for G5, two wins for Opteron, and one tie. So I really don't see either chip spanking the other. On the second page Opteron wins two, G5 wins one.
Second, the configuration notes section was pathetic. It doesn't really give a very good description of the real configuration of the systems. Anyone that views benchmarks regularly knows that the devil is in the details. Still, this is equally a problem for Opteron and G5.
Third, I wonder what kind of comparison is really valid. Anyone familiar with the AMD/Intel world knows that you can't just grab two 2Ghz chips and run them head to head. The architectures are not the same, it wouldn't be a valid comparison. So with two entirely different ISAs, what chips should be run head to head? The only obvious comparison would be each manufacturer's fastest...in this case I believe the 2GHz G5 is Apple's current fastest, but AMD does have a 2.2Ghz part that is available (see pricewatch) and that wasn't tested.
Lastly, let me address the importance of compilation. I can't speak for G5, but you would get a substantial boost in performance on most applications just with a recompile for AMD64 chips. This is because Opterons have 32 GPRs instead of 16, which can make a big difference (especially in multimedia apps like photoshop). Obviously these products aren't commercially available, but people should be aware that a substantial performance boost for AMD64 could come just from optimized releases of software once it reaches a wide enough audience to make it worthwhile for software vendors.
I guess this has turned more into a "notes about AMD64 architecture" post than anything else. It looks to me like this review is interesting but doesn't really settle much. Both Opteron and G5 performed well.
The G5 was running in 32-bit mode as well.
They don't say, therein lies one of the many problems with the benchmark. They could have been using the 64-bit patches for photoshop, though one assumes not.
I know this isn't quite on topic, but I wonder how the latest Alpha design would fair. The alpha was the first mass produced 64 bit chip that had any commercial success. It was introduced in the early nineties. IN fact Linus had one. Basically the curret EV78 is a 6 or 7 year old design, but in most serious tests of processor power it has done quite good. It's amazing that such an "old" design still works so well. The last SPEC numbers I can find are here. Considering the platorm has been ignored and basically orphaned, it's suprising that this chip still powers many of the worlds top rated super computers.
How does all this relate to the G5 and Opteron? Well AMD gets it's bus design from the Alpha lineage. The G5 is built by IBM, who I believe is building the alpha cores as well (I could be wrong, I can't keep up). The irony? Every current intel pentium chip is quality control checked by machines with alpha processors. Funny world huh?
AngryPeopleRule
"Science is about ego as much as it is about discovery and truth " - I said it, so sue me.
Buy a fucking mouse for gods sake!!!
It costs 15 bucks and makes the whole system 500 times better.
A blog about stuff.
Here are some benchmarks that show comparitive performance under Maya and Mental Ray. The G5 does not due so well in this, atleast compared to Intels and AMDs offerings. An item of interest in both benchmarks are the stats from an SGI Tezro workstation with 4 procs. Mental Ray for Maya http://www.zoorender.com/html/benchmark_mental.htm
Standard Maya Renderer
http://www.zoorender.com/html/benchmark_maya.htm
Also there are alot better reviews already published that cover these cpus respective performance in more detail.
Cheers
Silly goose. There are no 64-bit patches. Right now OS X *cannot* run 64-bit code so the test would have had to have been 32-bit. The G5 Plugin/patches are for altivec and the ilk. The G5 can run some G4 AltiVec very, very slowly. The G5 plugin changed this code to run faster on a G5.
...you can't afford it.
Your other points are incomprehensible...
Blar.
Here are some benchmarks that show comparitive performance under Maya and Mental Ray. The G5 does not due so well in this, atleast compared to Intels and AMDs offerings.
t al.htm
_ maya.htm
An item of interest in both benchmarks are
the stats from an SGI Tezro workstation with 4 procs.
Mental Ray for Maya
http://www.zoorender.com/html/benchmark_men
Standard Maya Renderer
http://www.zoorender.com/html/benchmark
Also there are alot better reviews already published that cover these cpus respective performance in more detail.
Cheers
Right now OS X *cannot* run 64-bit code so the test would have had to have been 32-bit.
OS X can run 64 bit code. I've compiled and run 64 bit apps just fine.
I'm going to refrain from comment until SuSe comes out with a kernel that is optimized for the 64 bit chipsets.
Load that mutha onto both systems that are matched as close as they can get, then run RAW benches, comparing how they can crunch the numbers.
After that, then run benches using the fancypants applets that have all the bells and whistles and see if they add up.
I seem to recall when the G4 hit the market, they had a raw benching comparison between it and the K7 (Thunderbird) chip.. The G4 got edged out in the numbers, barely! I sent the review to a fellow that is a well known mac fanatic, I heard later that he was mooing for quite some time afterwards.
First rule of holes; When in one, stop digging.
I would liek to say teh test is unfair and biased so i can sound like most of you. Tne tes should be more standard.
1) Why would you argue this and waste your valueable time.
2) Both systems have advanatges and disadvanatages, liek everything else in yoru life
3) Why don't you spend the hours you essentialy waste on this riddiculous debate by doing something constructive liek volunteering for community service or collecting stamps
4)Have A Good New Year be you RISC, CISC, MIPS or x86, ppc, x86-64 Itanuium, SPARC MIPS,
just have fun being constructuve; you people are smart
> In gaming, the Opteron system proved to be superior, which is partly due to the superior 9800XT over the base Radeon 9800. The G5 spanks the Opteron in many of the non-gaming tests, except for the Photoshop tests.
I wouldn't think benchmarks would matter as much when comparing the two in these arenas. If I was looking for a good gaming or a good Photoshop machine, I'd choose a platform over a processor speed.
What I would like to see is an in-depth comparison of operating systems. *Not* the programs that run on them- the operating systems themselves. Maybe now people will realize that it's just as important for a system to be easy to use as it is for a system to be fast.
Albuquerque PC
Carrying around an external mouse sucks ass on a notebook.
according to them:
Athlon 64 vs. Apple G5 Systems: Not Even Close
Now i can't say whether these tests are any less or more objective, but they do draw a completely different conclusion.
-Jon
this is my sig.
Only beta software? SuSE and Redhat both have official, supported releases for Opteron. Others probably do as well that can be considered better than beta quality, but even sticking strictly to supported platforms you don't need to go beta.
Other than that, I didn't really take time to comprehend most of that post. I think OSX is an excellent OS, but have found Apple hardware poor in both performance and reliability and customer service to be about as hostile as I've had experience dealing with. I've sworn off Apple, as much as I would like to applaud the software developers for OSX, the hardware and service has been unbearable. Even Compaq has historically provided me better support than Apple, and I'm not crazy about their support either. Apple was more interested in treating me like dirt for calling them on a warranty repair.
XML is like violence. If it doesn't solve the problem, use more.
...of those who confuse supercomputing and distributed computing.
hopefully this will put to bed all those folks who cry about Apple computers being so damned expensive.
In the midrange and the high end, it seems Apple's performance per dollar is competitive to Wintel PC vendors'. But in fact, the "Macs are expensive" conventional wisdom results from the fact that Apple has refrained, wisely or not, from targeting the $500-$700 "entry level" price range.
...is the ability to calmly discuss the merits of various processors and operating systems without the chance it might devolve into a flamewar. Sure, it might be a bit dry, with all the facts and figures strictly presented in cost-benefit format, but the lack of heated emotion when discussing Apple and PC pricing and available software really makes /. an invaluable resource. I know that when I read the intelligently-moderated posts on the subject there will be no rancor or hard feelings by the participants, who are truly only interested in shedding light on the wonderful variety of choices available to the reader.
It's running Windows XP, so we have a bunch of slow down right there. I had a 200ish mhz laptop with FreeBSD and a 400mhz WinNT machine running the same program, and the FreeBSD machine ran it about twice as fast. Moral of the Story: Operating systems can add a lot of overhead.
Of course, I don't know what the overhead of OSX is against XP, but I think it's something I had to point out.
Everyone can compare numbers until pigs fly but what about user perception? Yes it's great X component makes X application run faster. But as a whole who's out there using these applications on a daily basis? What about from power on to usability (of which many users just leave the pc running) or how long it takes from click until your email application fires up and starts accessing email?
It's really these things that users care about not the 1% that may be using specialized applications that were complied to take advantage of these processors.
The G5 will obviously have a advantage due to the OS being tweaked for it and the Opteron will have a advantage if the applications are compiled 64bit. Of which were any of these applications full 64bit or recompiles.
There is also a world of difference in the applications depending on which compiler you run. Intel compilers are vastly superior to many run of the mill compilers and will generally run better on Intel systems. AMD and Apple probably have their own compilers and more than likely encourage the use of them. Now since application developers will use what's cheapest and is most stable across platforms you'll probably see the differences you're seeing. Any native Apple application will obviously be done with a apple compiler. Photoshop may have been done with a generic thus better performance on x86/64 vs it compiled for a G5 processor which Apple may or may not release all specs for proper compilation with a generic.
Either way comparing them in this manner is nothing but a mess of varibles unless you're using everything the same across the board.
Better to compare bandwidth and other functions of the processors and not varible application performance where you're not sure of the breeding of code.
Opteron is for servers that beat crap out mighty [t]Itanic any time of a day, G5 is for fancy desktop. Show us G5 in server tests, until then let's move along, nothing to see here...
My other Beowulf cluster is... er...
This article strictly compares the 970 to the G5 using GAMING benchmarks.
The Opteron and the G5 (IBM PowerPC 970) are two disparately different chips meant to serve two different purposes. The Opteron is AMD's server chip designed to handle for the most part, 64 bit high performance database applications and applications which require large memory models in which the 64 bit memory addressing is needed-- NOT 64 bit desktop applications or games. That's reserved for the Athlon 64 which is clocked significantly higher and has a much smaller L2 cache than the Opteron. On Gaming and desktop content creation benchmarks the Athlon64 is a much better match for the 970.
If you want to compare apples to apples I would compare the IBM Power4 to the Itanium2 to the Opteron, hook them all up to an EMC storage array using fiberoptic SAN connections, and run a few million row length Oracle and DB2 databases and some SQL database benchmarks -- and for load up a few gigantic thermodynamic simulations up into main memory and see how quickly they can run through them. THAT would be an appropriate test for these server chips.
An x-86 processor and a G5...
I have here a bag of oranges, and a bag of apples.
Learn something new.
Because I don't use Photoshop and don't do much media processing, I'm not all that interested in how those application-level benchmarks play out. The things I care about are integer-based. Although I've done some crossplatform benchmarking of my typical workload before, it's time-consuming to get that all set up the right way. I may return to that at some point, but I've found that SPEC CPU2000 roughly corresponds, at least in the integer tests. The rate tests don't measure communication costs between processes on multiple processors, so they're a bit of a best case for multiprocessor systems. Still, they can be revealing.
Apple publishes a base 17.2 SPECint_rate for the dual 2GHz G5 (not submitted to SPEC? they point here. Among the published scores at spec.org is a dual Opteron 248 running Linux and using gcc.
It scores 27.4.
Xi Computing charges $200 more for the dual 248 over the 246 the parent article was writing about. So deduct ~10% of MHz from that 27 if you want both boxes to be dual 2GHz....
no you show your ignorance, because powerbooks/ibooks/ etc. have USB ports so you can hook up a real mouse to them. which is the only way I'd ever use a notebook.
I think there is confusion whether by "maintaining" one mouse button we mean "has" or "supports". My powerbook only has one mouse for the trackpad, but my external mouse has three (well, two and a clicker wheel, but you understood what I meant) and most apps (including the finder and apple apps) support them. I use them all the time (and can be done with control- and command- clicking with just the one button).
Regardless, I don't see any of this resulting in the salvation/downfall of apple (the mouse buttons I mean, the G5 is clearly important).
..unless you know enough about PCs to assemble from components.
Shop here if you know what you're doing. With components you'll spend about $1500 building an absolutely top-end Pentium 4 system that would be $3000 plus from Dell.
Apple have no business trying to sell to people who know what they're doing since you can't build an Apple G5 from scratch and avoid their exhorbitant markups.
Are you sure you meant nice and not niche?
The G5 may be a niche processor for now, but I really hope that it can give x86 a run for the money.
The Internet is full. Go Away!!!
I was told the same thing about OS X. Got a G3 to run it, see if I liked it, found the thing to be buggier than windows 95, incredibly bloated, with apps using far more deskspace and cpu than would seem sensible, and totally unflexible as far as look and feel go. Yes, there are $30 shareware apps that'll fix the appearance flaws, and yes, they are flaws, but why the should I spend $30 for something that should be built into the OS?
Marxism is the opiate of dumbasses
Admittedly, I don't keep up-to-date on any of the software in these tests other than the games, but... Has *any* of this software been ported to 64-bit? You can't just take any old 32-bit program, run it on a 64-bit processor, and say "hey, it's 64-bit!". The software has to be compiled for the 64-bit instruction set, and often requires source code changes as well. I'm pretty damned sure that none of those games have been ported to 64-bit, and I highly doubt any of the other software has been.
So, basically, all this test is doing is comparing the 32-bit speeds of these processors. 32-bit programs have nothing to gain from a 64-bit architecture (as far as I know). So, there's no reason to hype this as the battle of the 64-bit processors, because we haven't even seen their 64-bit speeds yet.
I certainly don't think this is a fair comparison. They're running Windows XP 32 bit on an Athlon 64. Yet, the version of MacOS 10 that runs on the G5 is partially optimized for the G5. Some libraries that run in MacOS 10 are indeed 64 bit. This benchmark will not stand up to public scrutiny until two entirely 64 bit operating systems were available for these two entirely 64 bit computers.
Now, I realize that you're just an annoying troll, but what exactly would make you think that Unreal Tournament would even be using 100% of a 2 GHz CPU?
The thing that's true now is that the Mac systems are competitive.
The good thing is the Mac's numbers are no longer embarrasingly crappy, as they were in the latter G4 days.
Why does it always take a G(x+1) in order to finally get people to honestly assess the G(x) ?
On the latest Top500 list Virginia Tech's Mac cluster is number 3 with 2200 2GHz G5 processors, and Los Alamos National Laboratorys machine, with 2816 2 GHz Opteron processors is number 5.. I didn't look at the topology, or connection medium, but I am certain that the Mac cluster was cheaper, and is faster running the SAME benchmarks...
You gonna fly over, and install replacement parts if they go bad? Gonna fully warantee it, and give me tech support when I need it? Gonna provide me with software patches, firmware upgrades, and online technical references?
Probably not.
Ok this is crazy. Since when does this count as a benchmark? Correct me if I'm wrong but the point is to minimize the differences. Not only are they running different OSes, they're running different video cards. This is the biggest example of grab ass benchmarking.
Whats so hard about running these machines with a 64bit distro of linux with both running the same vid card and the same amount of ram. Its like each time these people do benchmarks they purposely sabotage themselves.
[Just Shut Up and Do What I say]
It's not going to.
While I do think that any competition is good, even if it's coming from the "other side of the world" (aka macs) it's not going to seriously compete. It is a good thing to keep Mac users Mac users, but it's probably not going to switch PC users into them.
It's the same as the Linux Dilemma. If I'm running a Windows PC, and I have all these apps... I'm not going to be able to run them on a mac. Sure, with a mac there's a lot of equivilents and mac versions, but who wants to re-purchase everything they have?
In the end, it's good for the mac users. If you're one of them, then you're fortunate to have some new processors for your platform.
Switching your statement:
The Opteron/Athlon64 may be a nitch processor for now, but I really hope that it can give Intel a run for the money.
- It's not the Macs I hate. It's Digg users. -
>Am I just an exception?
No. Your the rule but to a very small degree.
Most people don't care about how a car preforms.. Do you care how quickly your car will go from 0 to 60? If you get up to speed quickly it so matters not if it takes 2 micro seconds or 1 full second to reach the 25 MPH spead limit enforced becouse of the naborhood kids playing in the street.
But some people live on those nasty busy streets where if you don't reach 60 MPH near instantly you'll never get out of the driveway.
That's it for the car anolog.
Your running a web browser, e-mail, simple stuff. Once your computer is fast enough those things work instantly and you never notice a slowdown.
But the computer dosen't always produce results inside a number of seconds. Some tasks take minuts, hours, days.
Try recompiling your Linux kernel. It takes time (after you've downloaded the latest source) you have to wait and wait and wait and for those of us still doing things that make us wait and wait and wait speed becomes an issue.
Speed of disk, speed or network, speed of ram, speed of processor. What ever it is that is making us wait and wait and wait is what we will look at.
Ever notice that website that seams to run slow?
Must be populare. Why is it slow?
Maybe they don't have enough bandwith...
Or maybe the computer is slow only able to handle 4,000 people at once quickly and your not lucky 4,001... Ohh no... your user 8,000
Untill computers can outthink us humans they'll be to slow. Even then the computers themselfs will want to be faster if just to out think the Jones bots.
I don't actually exist.
to Mac people??? The same people who thought that the "G3 was faster than the fastest Pentium II" for years!
Let me try to make this simple: neither Windows XP nor OS X are 64-bit OSs, and neither was running 64-bit programs. This is a much better situation for the G5 than the Opteron. 64-bit mode on the G5 really only allows for 64-bit instruction execution, and 64-bit pointers. On the Opteron, 64-bit mode enables a host of non-64-bit-related improvements, notably a doubling of the visible register set.
The bottom line is this:
The G5 will run 32-bit code just as fast (or faster, because of better cache utilization) than 64-bit code. The Opteron will run 32-bit bit code about 20% slower than 64-bit code, because of the architectural improvements in X86-64 long mode.
Note that none of the apps here would really benifet from 64-bit processing. Floating point is already 64-bit (actually, 80-bit) in both processors, and the only program that could concievably use 64-bit integer math would be Photoshop. Neither machine had more than 4GB of RAM, so 64-bit memory addressing was a non-factor.
That said, the G5 beat the Opteron by more than 20% in most of the benchmarks. I fully expect that with both CPUs running optimized 64-bit code, the G5 would still be faster, though the performance delta will be less.
A deep unwavering belief is a sure sign you're missing something...
Read the chart again, G5 lost on all tests.
this is my sig.
and all Macs, regarding the second/right click issue...I agree that carrying an external mouse is not always convenient -- that is why 'ctrl' clicking *is* the equivelant to second/right clicking. I know it is not the same, in that it requires the use of both hands, but I don't think that is a negative thing. It is very similar to using 'shift' and 'command" with modifier keys...
We apologise for the fault in this post. Those responsible have been sacked. -- Signed RICHARD M. NIXON
This is not true of the Opteron. 64-bit mode is about 20% faster than 32-bit mode.
A deep unwavering belief is a sure sign you're missing something...
Please tell me why this matters. Maybe 4, 3, or 2 years ago, this would have been news. Today? Not really.
First off: there is very, very little that is currently constrained by raw processor speed nowadays. The main hardware limitations are elsewhere: memory and bus speeds, mainly.
Second off: There are precious few tasks that can actually use a full 3GHz of processing power optimally. Games don't need that kind of speed now. Video, audio, or photo editing benefit only marginally more so, and for at least 90% of that small demographic, the need simply isn't there. Some high-end servers will certainly benefit from this kind of hardware; however, I doubt that many such purchase decisions are based on value-per-MHz benchmarks, but on purchase viability and what software they need to do the job.
We "nerds" realize that "faster, more powerful, higher numbers" isn't where it's at anymore in terms of processors. We realize that the future is in low-power, high-efficiency processors, since easily 95% of all computer use needs less than a GHz of power (and we can assume this will be the case for a long time, unless basic UI design and use practices change drastically, or we see an obscene amount of general OS bloat; the second is a possibility, knowing MS, but not likely to catch on where it matters, I feel).
~/ssh slashdot.org ssh: connect to host slashdot.org port 22: too many beers
How much harder is it to hold down the CTRL button with the mouse button (or trackpad's button) to get the right-click functionality? Seriously? I don't mind the one button mouse. I thought I'd hate when I got my first Mac two or three years ago (I used Windows for a decade, and Amiga/C64's before that)... and you know what, it's not really that bad. CTRL+mouse click works just fine for me. You only need one hand for the mouse, so the other hand will almost always still be on the keyboard, and subsequently right by the CTRL button, making the CTRL+mouse click not really hard or awkward.
And as the other poster said, if you don't like it, buy a third-party USB mouse. I've seen ones with like five or six buttons, and you can program them to work with Macs just like you can with Windows. The right button and scroll wheel work out of the box with Macs. It's not that hard, people.
why don't you use a mac running their new OS, fucktard. it has built in support for scroll wheels, 3 buttons, and it's all setup to work by default with most mice.
plug just about any multi-button scroll mouse and it works fine.
right click on the desktop (or jsut about anything) and you get a contextual menu. and it's not just emulating a ctrl click. it's real multi mouse button support.
don't spew your ASM coding garbage trying to sound smart. the support is there, it's been there since it was called NeXT.
My manual inline 4 has smoked some assholes in, i'm assuming 6 auto, Cameros not to mention many a rice boi. It may not be a BMW, but the (pre '99, dunno about the later models) SOHC version has 150 or so HP stock, not bad for a very light compact car. 0-60 in 4 seconds and i'm still in 3rd gear, still wish i had an SRT-4 as an above poster mentioned. Mmm, factory turbo...
"Sic Semper Tyrannosaurus Rex."
Mac sites were bitching about Motorola's lack of progress with the G4 years before the G5 showed up. And the arrival of the G4 didn't cause everyone to say that the G3 was crap, because it wasn't. It's only been a few months since Apple stopped using the G3 in any of their products, but I expect them to drop the G4 as soon as humanly possible.
How to solve most of our problems: 1.Lots of nuclear plants. 2.Cure aging.
The science community will always suck up FLOPs. A handy rule of thumb is that a single simulation or data reduction should take less than one working day. Any more and the develop-test-debug cycle becomes too painful. You can bet that today's grad students are running 10-hour processes just as I was 10 years ago, but they can do things in that time that would have required access to Big Iron (and the attendant big budgets) back in the 90s.
Companies like WETA Digital (warning: FLASH heavy) and Google do some pretty neat things with that power, too.
eMac: $800.
Lindows PC and an LCD panel: $500.
Giving a word processing and web machine to both grandmas: Priceless.
One important consideration in the G5 versus Opteron comparison is who is standing behind the product. The only tier 1 vendor who has announced Opteron systems is Sun, and those are currently vaporware.
Tier 1 designation (which is done by market analysts, and includes companies like Dell, IBM, HP, Sun, Apple) is especially important for governmental purchases, as national law dictates that unless you stipulate the purchase comes from a tier 1 vendor, in order to prevent fraud the purchase order must be put out for bid, in which case the purchase order will go to the lowest bidder, which is often undesirable as the lowest bidder will typically be disreputable and a terrible pain to deal with.
In the past at my job we have always purchased systems from tier 1 vendors, first IBM and then Sun. Recently we experimented in cost savings by purchaseing a HPC cluster from a vendor found through the bids system, and it has been nothing but a nightmare. We've decided in the future to purchase only from tier 1 vendors because of this experience, and will probably end up building our next cluster from G5s (we are an educational institution and thus receive a very generous educational discount from Apple), especially with the recent release of IBM's XL Fortran compiler for OS X.
Well, it's finally time to talk BULLSHIT.
You call those tests? This dude is an amateur, not a benchmarker. That pricing thing is bullshit - the Opteron build was farmed out to someone who overpriced it by over 1000 bucks.
Do you know anyone who wouldn't build their own dual Opteron?
The machine benchmarked was not the same as the machine configured... or as the review itself says, "as long as you don't buy it [the RAM] from The Apple Store". Considering that this came after he just got done explaining why he didn't assemble the PC piecemeal, I consider it to be quite deceptive.
pb Reply or e-mail; don't vaguely moderate.
to me the Mac is good enough. The latest batch of machines are all plenty fast for what most folks do.
Now it comes down to OS preferences, applications used and such. One can run pretty much anything under win32 these days, most things on OS X and most *other* things under Linux.
Price is still a consideration for me. I now have my eye on a Mac, but still need to live within my means for now. That means build it or white box Intel hardware for about one more cycle. I like the Mac because of the nice synergy between the hardware and the OS and standard apps --always have. (SGI started doing a fine job of this back in the early 90's as well.)
I totally believe Intel / AMD systems will, in general, be able to run faster simply because the release cycle is shorter and because of market demands for speed. There is always somebody willing to pay for peak performance. Sadly, this means hot-running Intel chips.
The good enough factor is growing interesting these days however. Most folks don't need a third of the CPU being sold today. With hardware prices being what they are, selling slower machines for less money really does not make any sense. Given the basic truth that all the machines today are fast enough, maybe we will finally see some creative differentiators again on the PC side of things --an area where Apple has the clear lead.
Tangent mode on:
Why doesn't somebody start making nice intergrated Linux machines? There is enough of a market to really ask the question: Does every PC need to run win32 anymore?
Apple clearly keeps its market based on a lot of different factors besides performance. Seems their model could be emulated today at a very reasonable price point using Linux as the core OS and building out from there.
How many here would buy a nice machine made to run Linux? Imagine a cool form factor, many intergrated features (video i/o, DVD, audio, USB, Card Readers, graphics and such all in the box, nicely supported configured and ready to go?)
It's almost as if the Desktop Linux project needs a hardware partner. The two together could give application developers a solid target to focus on... Just a coupla thoughts.
Blogging because I can...
Didn't AMD get their ev6 bus for their Athlons from the Alpha? If I recall right, the original Athlons could be run on a motherboard designed for DEC ALPHA's.
So it continues to live on, in a way.
Everything you said is true, Cat. However, let's dig a little deeper. Despite the fact that some people are just unreasonable Mac (or Win or *NIX) bashers, Steve Jobs did his damndest to make this debate emotional rather than logical. At a time when the Windows OS was at it's lowest, most vulnerable (pre 2000), Steve Jobs offered us pretty colors. That and the very unlogical notion that G4s were somehow faster than Intel offerings.
Add to that the fact (OK...maybe it's just my opinion.) that Apple is really known as more of a "lifestyle" company than a computer manufacturer. What's embarrasingly and maddeningly crappy about the Mac now is the disposable hardware mentality that Jobs has brought to the table. My sister is going through her own personal iBook hell right now. While we were at the Genius Bar, 2 other patrons with similar iBook problems came in. At least with PCs you can go to Staples and buy replacement parts.
As a worker ant in the multimedia field, I appreciate Apple's new found speed, however, my company has already begun the move towards PCs for design. It's just a damn shame that computer choices in the 21st Century come down to either unscrupulous (Gates), unreal (Jobs) or unsupported (Linux).
hmm...you could use virtual PC until you need to upgrade the the latest version and then just get the mac version.
VPC gives you DnD, so what is the problem?
I am the Alpha and the Omega-3
Mod this man up, he speaks the gospel!
-bZj
.sig
32bit software usually means better use of the processor cache (and memory in general - unless you have many 64bit quantities. Floating point numbers perhaps...)
Answer this question: will final cut pro run on an x86 based machine?
To me, and most Mac users, gaming is irrelvant. Most people that use Macs are in a profession such as desktop publishing, video production, or graphic arts. Sure they may play a game or two, but their machine is used for work.
I do a little bit of everything with my G3 700Mhz 14.1" iBook, but mostly its MS Office, Mail, Safari, and Quark that I use. Along with Final Cut Pro and Photoshop when need be.
Our office is 95% Mac and 5% FreeBSD, which we run on Althon white boxes, and we have beat out competition because of productivty. We are not spending loads of time with viruses and patching security issues on a weekly basis. Our machines rarely lock up, none have crashed (knock on wood), and that helps with the bottom line.
Does it help in video rendering to have the extra speed and power of the 64-bit G5? Yeah, the faster a project is rendered, the quicker we move on to the next. But for everyday business use, our older G4 500's, 867's, and Dual 1.25gz will serve us for years to come and even though Apples cost more up front, we know we have saved time and money by using macs for our desktops.
"The problem with socialism is eventually you run out of other people's money" - Thatcher.
This is probably flamebait. However: IBM, working with Apple, did provide Apple with an awfully nice chip. However, there's a lot more to a computer than a chip - your premise is a bit naive (even though you used that nice and pretentious "Apple are" anti-colloquial phrasing), so I'll explain this in proper tone. You see, Jonny, a chip depends on the rest of the computer just like the computer depends on it. Apple's exorbitant R&D department made the chip a computer. Besides, have you looked inside the thing? It's purty.
No you haven't because OS X doesn't support 64-bit in any meaningful manner. Apple like's to claim that it's a 64-bit system because they can handle 64-bit integers through their math libraries, but that does not make it a 64-bit operating system (or 64-bit applications).
OS X provides you and your applications with a 32-bit address space. Until that is changed, it will never be a 64-bit operating system. Right now it's more like running WinNT/2K/XP in PAE mode on a 32-bit x86 processor.
Because the world is full of stupid shoppers.
Scratch Dan Heatly from the list of people looking forward to the 1000 horsepower car. Did anyone else see his face on ESPN today?
I guess tjstork is too busy oozing to know what's going on around him.
But it just annoys me, because I happen to be a person who does not run that one particular app, and I start rolling my eyes where the article mentions they're talking about some old app compiled for i386 (which has so few registers) instead of x86-64, and on some legacy OS.
It doesn't seem like a "real world" test to me. Ok, sure, for some people, running 386 code and Windows XP is their "real world," as sad as that seems to me. But it's not my world. I live in a world where I have the source to most of the stuff I run, and compiling it to run natively is perfectly viable and easy. We are not waiting for "64-bit software"; we have had the software for years, and cheap hardware is what we were waiting for.
Running Adobe Photoshop compiled with Pentium optimizations vs Photoshop (optimized for the 604 or whatever) just seems silly, from this perspective. Crippled code vs crippled code is not realistic, to me. I wish someone would show me Gimp vs Gimp, emerge(gcc) vs emerge(gcc), mencoder vs mencoder -- with each system running appropriately-compiled code. Because that is the real world (my real world), that is what I'll actually be running when/if I get a new machine.
Now .. it's not like I have any right to demand these guys do some benchmarking of my real world apps, for free. :-) But at the same time, when they publish an article called "Dual G5 versus Dual Opteron" that is actually something far more narrow and specialized than the title suggests, then I think some deception has occurred, and people will draw ridiculous conclusions from it. Misinformation should be attacked. Appending "when running legacy binaries" to the title, would have made it a much better article.
"Believe me!" -- Donald Trump
The normal price will probably drop to around 3k in Jan. when Jobs announces a new speed bump for the G5 Which should max out around 2.4-2.6GHz.
In new edition of MacAddict they did a similar test with the G5 but tested against the 3.2 P4 from Intel. The P4 also whooped the G5 in Photoshop filter test, BUT when they imported a 25 mb and 50 mb imported file and followed it up with a Photoshop action that mimics real world usage the G5 killed the P4.
Photoshop action included the following steps: Gaussion blur, 50 pixel radius; Revert; Gaussion blur, 1-pixel radius; Unsharp Mask, amount of 150 percent, 2-pixel radius, threshold of 0; Despeckle; Dust & Scratches, 8-pixel radius, threshold of 0; Sharpen Edges; Rotate, 90 degrees clockwise, Mode Change, RGB and CMYK; Resize, 150 percent, proportions constrained, bicubic interpolation; Save As, TIFF, no compression.
In the tests the G5 ran 4-8 sec. faster then the P4. Both machines had 1GB of ram.
No you haven't because OS X doesn't support 64-bit in any meaningful manner. Apple like's to claim that it's a 64-bit system because they can handle 64-bit integers through their math libraries, but that does not make it a 64-bit operating system (or 64-bit application)
The instructions in the app itself, and the math libraries are 64 bit. So it's a 64 bit application, but many of the calls (for my purposes, the ones I don't care about) are 32 bit. If I cared I'd run Linux on it.
Oh wow and if it comes from a PC mag or a windows site it also must be from a FUCKING PRO-PC SITE. Notice barefeats have actually posted bad parts that go against the Mac. If it was just for the Mac it would've never even showed the PC winning anything. So I don't consider this a one sided event.
Well, to be honest, yes. Apples' hardware usability dept claim that this is "easier" for users. Um, correct me if I'm wrong here... and I'm not...
but "Ctrl-click is 2 steps.
Right-click is only one.
Usability at its' finest... hehe...
Yeah, sucky comeback, but I had to try something.. hehe.
The Opteron is exactly the same cpu core as the Athlon 64. Depending on which model Opteron is in question, it then adds some number of additional hypertransport links (to support 2-, 4- or 8-way multiprocessing), memory controllers and onboard cache memory.
Translated into english: The Opterons are, at worst, exactly as fast as the Athlon64, and in most cases are faster. Using an Athlon64 in the same test will not produce faster results.
News for Nerds. Stuff that Matters? Like hell.
The article seems to imply that computer graphics is pretty much everything that a computer ever needs to do. Therefore, if the G5 beats the Opterons at most of those CG related benchmarks, then it must be faster than the Opteron at almost everything...
Maybe it's not an intentional bias. The site seems catered towards the Mac crowd and those might be things that Mac users care more about. PCs are often used for games and that might be an issue PC users would care more about.
So, maybe as far as Mac users are concerned, the G5 is faster than the Opteron, but I doubt they really needed the convincing to start with. However, I must state that those benchmarks are nowhere near being definitive. It doesn't convince me, the PC-user, and that's the audience it should be targetting. I'm not trying to be stubborn about it (in fact, I'm saving up money for the Powerbook because it and OSX outclass any PC laptop out there) but I use none of those applications he tested on except for PS7, which the Opteron did better on.
In the future, I suggest testers to use a more balanced set of test and research their audience. If all they want to do is rubber-stamp a prevailing opinion, then keep this up. Otherwise, try targetting those who don't normally agree with you. It's tough but at least it would be something more useful than rubber-stamping.
EvilCON - Made Famous by
I don't know if the author of the article was just trying to make the mac look cheaper, or if they just weren't looking very hard (I suspect the latter), but they could have EASILY shaved $82 off the cost of the Opteron system and got 1394b support for free too boot!
For some reason they configured the Opteron with an add-in Serial ATA RAID controller, supposedly in order to better match the configuration of the Mac (which doesn't support RAID, but I digress). This added $117 to the price. However they completely ignored the motherboard upgrade option that added SATA support (no RAID) and 1394b support together for only $35.
They could also have shaved another $37 off the price by using a software modem instead of a hardware modem (though the HW modem might be a good idea for Linux users that need dial-up) or $72 off the price by not including a modem at all for those of us with broadband connections.
In the end though, the Mac is still a bit cheaper. Macs are not expensive for what you get, the problem is that you don't have much choice but to get top-end. To price out a dual-processor Opteron with similar specs to a dual-processor Mac, you'll be easily over $3000 and possibly up closer to the $3938 of the Xi computer system. However, if you don't need all those features you can easily configure yourself an Athlon64 system for SIGNIFICANTLY less.
I have absolutely no need for a modem (got an old external kicking around in case of emergancies) and have never owned any 1394b devices. Therefore, if I were configuring a PC for myself I would never bother adding either of those two options. I might also configure a cheaper video card and I probably wouldn't bother with a DVD-RW drive, though I would prefer to have two optical drives (one CD-RW and one DVD). These are all easy options on most PC configurations, but often they aren't on Mac configurations. Simply put, you have more choices on PC configurations than on Macs. If you desired setup matches that of a Mac closely, then they often offer good value for your money. If not, then they can be quite expensive for what you want.
for it to matter.
Whether the sun is up or down my job isn't affected by it. Most people's jobs don't depend on the time of day. But if you ask a farmer, it matters quite a bit.
For you it's just a pissing contest. For people who run massivly computationally intensive programs, this kind of thing matters a great deal. Time is money. You have to consider the cost of the hardware and the cost of the time for it to complete the project. A 500Mhz system could render LotR. But it wouldn't be released in our lifetime and that time would cost more than the movie could possibly bring in.
You're not a troll. You're just shortsighted. One, maybe 2 inches depending on the length of your nose.
"It doesn't matter to me so how can it matter to anybody?"
I think you need a new pair of shoes.
Ben
Work Safe Porn
Huh?
For the 3 games you can play on a G5?
Why not compare more relevant things? Okay, you say, let's do some applications tests. Okay, photoshop filters. A couple rendering jobs. Yawn. Who the hell does this on their machines all the time? Okay, now the five of you, leave the room.
Why not give me some more information about the guts of the machine, like how fast memory access is or how each bus design handles contention issues, explain why they're relevant in various facets of operating system or application execution, and provide some anecdotal evidence by way of application benchmarks. Hell, run them in a debugger so we can see if our assumptions about system behavior are correct in real-world situations.
These people get a dual G5 and a dual Opteron and all they do is run Photoshop and Quake 3 on it and call it a night. What the hell? Where's the investigation, the effort? How much more boring could that article have been? (Okay, maybe they could've lost the graphs and numbers and just told us, "Trust us, this one's faster", but that would've seemed like they were phoning it in.)
In summary, I was a little disappointed.
- A.P.
"Remember when the U.S. had a drug problem, and then we declared a War On Drugs, and now you can't buy drugs anymore?"
As far as the pricing on the Apple machines, it may seem a bit steep at first but when you look at the total package (sexy aluminum case, sweet fan setup, SATA hard drives, Firewire 800, 64bit PCI (even as far back as the old B&W G3 I recently picked up) and especially the resale value you really aren't doing to poorly. I love the comparisons where people say "I can build an x86 box for half the price". Well, the problem is that the x86 box is worth crap 3 months after you build it while the Apple boxen seem to hold their values long after your half priced x86 box becomes a machine you cannot even give away except maybe to a buddy who wants an old machine to use as an IPCop firewall box.
The G5 definitely isn't a slow machine, you will be able to resell your G5 without taking a bath on your investment, and OSX is damned slick....I mean...REALLY slick.
All in all I would have to say that the G5 machines are holding their own. Slower on some things, faster on other things, but nevertheless holding their own. The price/performance thing really depends on what you want the machine to do for you. I personally play games on a Playstation 2, listen to music on a real live stereo system and use a computer for browsing the web and checking email. So for me, OSX is a really nice environment to work in and the price of admission for OSX dictates Apple hardware. For others that play games I guess x86 and Windows is the way to go, and for those that like a total lack of intergration of their various UI components and appreciate a plethora of different "widgets" and toolkits all crammed together in a hodgepodge of a UI with no unified look or feel from application to application (wanrning, run-on sentence) and an almost unrelenting requirement to be tweaked and fiddled with then I guess a Linux x86 desktop is the way to go.
I guess where my rant is going is that the hardware playing field seems to be fairly level these days and therefore your choices in systems would have almost entirely to do with how you plan on using your machine and/or which particular environment you prefer to work or play in.
"The strong will do what they want, the weak will do what they must."
-Thucydides
Register renaming helps alieviate the problem, but it does not eliminate it in any way. You still end up loading, storing and decoding all the extra instructions used to shuffle the data to/from memory, even if in reality you are just hiding the data away in your renamed registers. This results in more bus contention, less available cache space and a higher load on your instruction decoders. The end result is that you're still taking a performance hit even if the data is just being hidden.
IA-32 is especially bad for registers. Not only does it have WAY fewer real registers than basically anything else out there these days, but it also has a bunch of restrictions on how those registers can be used. The end result is that you often only have 4 GPRs that you can actually use for data, resulting in a LOT of shuffling. With the AMD64 instruction set, AMD did a smart thing by not only doubling the number of GPRs, but they also removed essentially all of the restrictions of which register can be used for what. This gives you the full 16 registers to use all of the time.
This is why AMD64 code will often (usually?) be faster than IA-32 code on Opterons and Athlon64 processors even though it's 64-bit code. Despite common belief, 64-bit code is usually SLOWER than 32-bit code when all else is equal (ie with the G5) unless you're using more than ~2.0GB of memory or lots of 64-bit integers (the latter being quite rare).
We've had benchmarks for months, actually meaningful benchmarks. They show that the G5 is a nice, competitive chip, but it's merely keeping up with AMD performance-wise. And G5 systems are behind Opteron systems in terms of bang-for-the-buck and features.
If you check the published SPEC benchmarks for the Opteron 148 against Apple's claimed SPEC results for the G5, you'll see that a dual G5 is not faster than the Opteron. It is pretty telling, incidentally, that Apple still has not actually submitted official SPEC results for the G5's--they really don't seem comfortable with the comparison on a real benchmark.
Of course, a dual Opteron will have other advantages for many users: you can get it in 1U rack mounts, it runs a lot more application software, and it's cheaper.
Running five application programs does not constitute a meaningful benchmark of the CPU. We don't know how those applications are written, what CPUs they are compiled for, what compilers they used, etc. Most likely, none of those applications have been tuned for Opteron, wherease they have received extensive tuning for PPC and AltiVec over the years. The differences may be something as trivial as cache conflicts. All those "benchmarks" tell you is that if you must run the current version of Bryce and AfterEffects, you may get more bang (but not necessarily more bang-for-the-buck) out of a G5 for the time being.
Wooooooooo!!!
Seriously, I've been saying for a while now (a coule months, anyway) that the G5 was a superior chip and I've had to listen to the "Wait until its compared to an Opteron, then we'll talk" retorts, even having people use that exact phrase a few times. Don't get me wrong, I like AMD. If (god forbid) I ever have to use a PC, I much prefer to use ones running AMDs and some type of Linux, but damn does it feel good to be right. And now all of the Op supporters only logical explanation as to how their processor lost is that the bear feats guys is being paid off by Apple/IBM/The Illuminati, somebody. Yeah, that has to be it.
I don't care if this gets modded Flamey, or Trolly (since, you know, you never learned how to accept a defeat), or Insightfully, or Funnyy, or even at all. I don't care what you have to say in reply to it. Both OSes were less than 64 Bits, and if anything the AMD had an edge over the G5 with a better graphics card. In fact, looking at the stats, it would have been almost impossible to build a more equal, fair test. And I was really surprised to see the G5 system actually cost nearly $700 less. Wow. Seriously, I didn't see that coming, even if the Op system was a "purchased" system. All I have to say is:
Wooooooo!!!
Request: ECM unit, 1000 km fullerene cable, 1 tactical nuclear weapon. Reason: Birthday party for foreign dignitary.
If they really wanted to get my attention, they would benchmark a few things which they didn't: Time to encode MP3's Time to build a makefile
Who moved my sig?
They claim that thay are the:
"ONLY web site in the world that has begged for months, driven for miles, and worked for hours to test both the Opteron and G5 as carefully and as fairly as possible."
well, 'their' report dates 12-15-03,
yet this following report as dated 3+ MONTHS before theirs:
http://www.unixgods.org/~tilo/Opteron_vs_G5.html
Just fyi:)
If I could get all the hardware and software I needed at a decent price I might try one. I am not willing to pay the Mac premium and not have access to my favorite PC games.
a) The hardware doesn't match. Geez guys - you could have at least used the same goddamn type of video card.
..... eh nevermind ... judging by the stupid mistakes these imbeciles made - math beyond counting Mhz, Gigabytes, framerates and Fahrenheits might be a tad beyond them.
b) The software doesn't match. Why on EARTH didn't you use Linux on both machines? The software isn't matched at all. Windows XP (WinNT) kernel is a VMS derivative with some mach code stuffed it. OS X kernel is a mach + BSD server + Iokit system. Next time you do an "analysis" why don't you boot the opteron with MS-DOG 6.22 and the G5 in Mac OS 4... ok? Stupid...
c) UT2003 amd Q3A aren't CPU benchmarks. They'r GPU benchmarks and the 9800XT won - good work guys...
d) Math is pretty CPU intensive. Maybe you shoud
And you've just proven you have no idea what Final Cut Pro does
I looked at every link you've provided, and I can indeed see that the industry is standardizing on Linux for their 3d animation and rendering needs. The render clusters are cheap, powerful, and produce high quality results that are equal to a more expensive Mac solution, making them the choice for 3d animation and effects.
However, Final Cut Pro isn't a 3d animation program, and has absolutely nothing to do with this. It's a nonlinear editor, something which really can't be clustered effectively, especially not with dirt cheap boxes. And before you accuse me of not knowing what I'm talking about, I used to build and maintain clusters professionally. Final Cut Pro is an app that doesn't benefit from openMosix, probably not even if you put in some vastly expensive interconnect like Myrinet.
In other words, you don't know what you're talking about.
- Free tabletop fantasy gaming! Grey Lotus
Last time I checked, OS X came out well over a year prior to XP.
It was Pepsi (the opposite of Coke), and that was Sculley (pretty much the opposite of Jobs).
So, what was your point again?
Final Cut Pro ... [is] a nonlinear editor, something which really can't be clustered effectively, especially not with dirt cheap boxes.
:)
Take a looksie at Cinelerra. It's still under development, but it's cluster support is working fine already. I've used it with a renderfarm of 20 low end PII boxes (and if they're not dirt cheap boxes, I don't know what is), and it worked perfectly.
And before you accuse me of not knowing what I'm talking about, I used to build and maintain clusters professionally.
Given the above counter example, can I accuse you of not knowing what you're talking about?
yes but the functionality available via the right-click cmd+click is SEVERELY limited in comparison with other operating systems. Perhaps it's flushed out a bit since OS 9.5 but as of then and all MacOS prior to that right click was great and all but it really wasn't as helpful as on linux and windows. On windows everything and it's dog is available via rightclick.
On linux everything and it's dog is available if it's actually easier when it's there (except on the desktop in kde or gnome, neither of them have all the fundementals in the menu you get when you right click the desktop, notably the ability to create a new file of a basic type and have it open in the default editor for that type). Other than that you simply never look for something in the right click menu's that isn't there when you right-click.
On a mac it's SOMETIMES there. ctrl-clicking isn't so bad on a mac, but really that's because you probably won't find what your looking for if you do. The things most lacking in this regard were web browsers (netscape and IE when I last used a mac), netscape of course has always opened into an html editor (which is a royal pain in the arse if your a web designer who *gasp* actually knows html and writes it himself).
But IE didn't even have a view source if I remember correctly in the rightclick menu. This is an issue when your trying to view the source of multiple frames in a webpage your running directly off your drive to make on the fly changes and refresh the visible display. This one simple feature has the ability to magically turn the browser into a fairly slick html/javascript/whateverscript IDE.
This is just one example but I found similar small issues (no individual other thing was so big that it stands out in my mind) but added up, even after 2yrs it was still something that frustrated me each and every day.
Next year it will be 128-, 256-, 512-, 1024-bits.... see a trend? Where does it end? And, do people always believe more expensive and bigger numbers (faster clock) is necessarily better?
Is the migration to 64-bit part of the scheme of planned obselecence? Or merely an excuse to fix the 2038 32-bit Unix Y2K problem by a hardware hack? Haven't we learned from the wintel platform that making hardware/software purposely incompatible? M$ft/intel ostensibly maintains backward compatibly, but in truth, Falcon AT is not going to run on native DOS on Athlon64 FX or Pentium EE. Either do code-morphing transmeta style, build an emulator, or break compatibility and design a usable, general-purpose, stable system to last for the foreseeable future and stop changing things!
1) 64-bit chips are vastly more complex, requiring 1 more gate delay for mux/dmux's.
2) Clock skew becomes an even bigger issue, as most of the cpus (excluding ROMs/RAMs/cache/CAM) is dedicated to clock synchronization by area.
3) What does one need w/ 64-bit buses? A 32-bit bus is sufficient, word size can be increased by multiples of 32-bits regardless. A 64-bit signed add/sub can be done in two 32-bit add/subs, it can even be done in parallel using carry prediction and double the hardware, save the carry-out choice. All this extra precision is unnecessary in most cases... it would be better to have an uber-efficient 4 x 8-bit operand parallel CPU that could execute code as if it were microcode. That way, you could do variable precision operations, possibly saving cycles. Otherwise, you'll have that honkin' 64-bit UINT calculated every time you want to increment by one. Let's see.... increment overflow will only take 585000 years at 1 MPS. Darn that off-by-one bug!
4,5,...) Pipeline stall cycle length (deeper pipelines), more complex functional units, larger footprint, cycle efficiency, etc/etc.
Serial busses are potentially faster than any parallel bus, since a serial bus can have embedded clock (manchester, diff manchester, etc.). And the differential serial bus is always nice in the noise-immunitity department.
Change isn't always progress, but an excuse to push product out the door.
"Marketing is the art of trickery and deceit to convince people to buy your product, much like dating and job interviewing."
The biggest trick the devil pulled was letting lawyers become politicians so they can write the laws.
It's what is available in the contextual menu's that suck. If you find yourself doing it more than twice an hour when in the application, it should be in the menu when right-click/ctrl-click/whatever you want to do.
The OS was designed around a one button mouse concept. you don't miss right-click as much as a mac user because most of the functions that would normally be there are elsewhere instead. The problem is that they are commonly used functions that make ALOT easier.
I find myself right clicking an average of once per minute on windows. About once every 5mins on linux (generally because things are laid out better or the keystrokes are more useful than right click would be.) The mac is laid out better, but isn't even caught up to windows in terms of the usefulness of keystrokes, let alone linux. So that rates to looking for something in a right click menu about once every 2mins, finding every 3rd time if your used to it being there. If your used to the mac you look about once every 15mins.
Umm, the recent powerbooks all have a PgUp, PgDn and Del key. Take a look. Also, I believe OS 10.3 now has the ability to let the user assign/reassign key commands. That means that you could assign one key to function as the second mouse button. I would confirm this but I'm logged in to 10.2 currently.
I have to agree. Even if *Macs/Apples/Whatever they call themselves this day of the week) completely outrun PC's, they simply are not an option for me (unless, perhaps, if someone had a Linux distro running on it). It's not a condition of brand loyalty, it's simply practicality. Every computer I'll ever use in the workplace will either have a MS or *nix OS (or both) because of the nature of my line of work. I also believe that PC's are just plain more customizable in hardware and software.
Another way to look at it is the big picture. PC and Apple are competing standards. By market share and prevalence, PC won. If all the efforts at the continued Apple project were instead used on PC's, we'd have: another competitor to windows, another processor company to compete against, another company making graphics cards, another company making LCD screens: They are good at these things, but as they stand sitting in another standard, they aren't competing on their own right, but the standard itself, so they don't leave the impact they should.
Shouldn't the right-thinking person feel a little silly testing a 64 bit OS with a word processor?
That depends. I could write you a heavy number-crunching simulation app (eg a realistic gas, n-body gravitational system, laser-plasma interaction, etc), complete with 3D GUI to represent the current state of the system, which would put any realistic system through its paces. Measure fps of the GUI, steps/second of the simulation, maximum precision, runtime for given starting conditions, whatever.
But if the end user is going to use the system primarily for word processing, the test would be useless.
It's official. Most of you are morons.
Ok, first a nitpick: There is no os 9.5. You've got 9.2 and then skips up to 10.
But really, try OS X. Complaining about the awkwardness of OS 9 (and hell yeah, contextual menus were useless). kind of like complaining about Windows 98 or KDE 1.0.
They've all gotten a lot better since then.
Mod point free since 2001
While rendering USED TO take up a lot of your NLE time (the only aspect of editing that can utilize a cluster), these days most of NLE is just tedious interactive work with the system. What matters most about an NLE system is the UI, something people in the free software world know jack crap about.
Also, it's not just coincidence that the G5 is less "penalized" for 32 bit code than the Opteron. When AIM (Apple, IBM, and Motorola) sat down to design an ISA, they designed a series of chips that would logically and effectively span the gap. When Intel sat down to design an ISA... well, I guess no one brought the donuts. In any case, yes, the performances of the G5 in 32 bit mode and the performance of the G5 in 64 bit mode are much, much more similar than the performances of the Opteron in 32/64 bit modes. This is the result of conscious design and, while it suggests that in 64 bit mode the Opteron will seem significantly faster than the G5 (well, noticeable. Okay, measureably?), un under current usage, which really is mostly 32 bit on both platforms, the G5 seems to put up a more than fair fight... and I'm not sure I really get the people who are complaining "rigged test" just because AIM can design an ISA and Intel can't.
I've had this sig for three days.
Strangely enough I found using a one-button trackpad way easier than the single-button mouse on a Mac desktop.
The trick is that the Ctrl, Alt and the Apple button are just next to the trackpad. You can either use your left hand that is on the keyboard anyway to hold either of those buttons and the right hand to click (and control the trackpad), or you just use one hand in order to click and push one of the meta-keys (thumb on button, index on meta-key).
It sounds complicated, but it really isn't. I too was scared of the one button mouse whan I bought my iBook two years ago. I even bought a nice Logitec Optical with it in case I couldn't handle the one-button trackpad. I gave the one button trackpad a try though, and guess what still is in it's original box? The Logitec mouse... (Not really, I gave it to my sister, but you get the point)
Ahhh...the great dumpster continuum. Many a free computer will be found there. -- sowth (748135)
Its not so much a rigged test, but a useless one, if you are going to be running optimized 64-bit code. If you're going to be running off the shelf Windows and Mac apps, its probably a fair comparison, but if you'll be running your own custom programs, or using a fully 64-bit OS like Linux, than its not.
A deep unwavering belief is a sure sign you're missing something...
Moreover, I don't know of a good optimizing AMD64 compiler that fully exploits the architecture. PGC might be okay, Metrowerks has a long history of building shitty compilers (my professional opionion) any compilers that anyone has experience with?
I think that you can probably get a lot more out of both chips. Most of those mac apps are compiled with GCC, which is great but xlC is a ton better on POWER and PowerPC.
They look about even in my book.
unless, perhaps, if someone had a Linux distro running on it
I don't follow the PPC world much, but I know of two PPC Linux distros -- Debian and Yellow Dog. I'm sure there are others.
Note to ACs: I usually delete AC replies without reading them. If you want to talk to me, log in.
Why they choose to ship a one-button mouse even now is beyond me, but they aren't locking you into that mouse forever, and have obviously anticipated more functional aftermarket pointers.
To get this back on topic, if you are looking for a reason to get the Opteron over the G5, the stock mouse is only about a $19 reason.
Still no Half Life though (about the only PC game I still play. BZFlag works on my Mac though :). I hope that when they release HL2 then they will do an id and release the source for HL1 for porting. I wouldn't mind putting some time into that effort. Somehow, though, I doubt it will happen.
I am TheRaven on Soylent News
Macs tends to come with Nvidia chipsets now. If you want hardware 3D under Linux on Macs, you're SOL. The opensource nv driver won't do it and the wrapped Windows drivers availiable on x86 are a no-go.
How is it a competitive test between Athlons and G5s to talk about Xeons which are not even made by either company
Yeah, this news is two weeks old, and these benchmarks are meaningless when someone not qualified to do benchmarks is at the helm. They have already completely redone their gaming benchmarks, and had them pulled for a time. Here is what I posted about this two weeks ago when it was news. Thanks to Slashdot someone who is not qualified to comment on computer performance is now getting an audience as if they are when Ace's Hardware or Tech Report should be the ones doing it.
Pointless G5 vs Opteron Benchmarks Tue Dec 16, 08:21:40 AM
Author: Chris Tom
Barefeats is at it again. This time they compare a dual XI Opteron 246 against a dual 2GHZ G5 PowerMac. They do not get performance equal to my 246 tests. They do not acknowledge the Opteron 248. They do not give out full system specs. They do not realize beta Windows XP 64 for AMD64 has been out for months. They continue to have no idea how going from 128mb of video memory to 256mb changes gaming performance, and can not fathom that the integrated memory controller is the real reason that the games and other 3D marks are much higher. I mean come on, more video memory is going to make Quake 3 Arena faster? They also does not run SMP Quake 3 Arena. Barefeats is in no way qualified to run or comment on any benchmarks as they have demonstrated almost no knowledge of CPU or video card hardware. Do not take any of their numbers seriously. Their Cinebench marks are not as high as mine, and I worry that will also be the case with the other marks. Scott at Tech Report had told me he was trying to get a dual 2GHz G5 box to test, but of course Apple does not have the guts to let a real hardware site test one of their boxes.
ignorance is bliss. googlefiberatx.com
At the least, they should give UP benchmarks. I've got a pretty good gut feeling that OSX scales to 2+ processors far better than WinXP.
First off, the Photoshop tests have traditionally been what the Mac people cling to on benchmarks - "Well, the G5 did better on Photoshop so it's better at processing graphics." Well, the operton is 15% faster on MP and 10% faster on non-MP operations.
Second, how can you use the word "MANY" when you're talking about two tests? From reading the slashdot writeup I assumed there were 10+ tests and the G5 cleaned house on most of them. The Cinebench test was very close, the dual Opeteron system was about 2% slower than the dual G5 (51 score versus 50). The "Bryce 5" test doesn't appear to be optimized for multiple processors, meaning it's probably not even multi-threaded. If it was, why would the single processor G5 1.8ghz score the same (25) as the dual processor G5 1.8ghz? Adobe AfterEffects has a plugin to improve performance on multi-processor Mac based systems, but not for multi-processor Intel/AMD systems.
I think the surprising thing that should have been highlighted in the slashdot writeup is that the G5 finally got spanked on the Photoshop tests. Has anyone seen SPECINT tests with the Opteron?
I could have sworn that non of those applications currently run on 64-bit linux. And 64-bit windows is in betaland. I am not understanding this test.
Oh! I see it.. at the bottom:
"The Dual Opteron was running Windows XP Professional, not Windows XP 64 bit edition..."
Well wtf is that? Fucking moron. He's running all this shit in 32 bit emulation mode. Got damn Mac idiots.
It has everything to do with brakes. Most of today's sports sedans can now brake from 60 to 0 in around 100-120 feet in good conditions.
Good brakes deliver better cooling so they grip longer, mitigating the effects of heating. Good tires grip the road better, enabling more friction and thus quicker stopping.
This is my sig.
OS X is based on UNIX, so I don't really get your point ;-)
Pretty much anything that runs on Linux, runs on OS X. Including KDE and Gnome, if you're so inclined, as well as Perl, Python, Ruby, MySQL, JBoss, Oracle 10g, etc.
And there's a debian-style package manager (check out "fink" on Sourceforge).
I have always called mine a Bummer or BumW since the mid 80's.
and use a computer for browsing the web and checking email. Well, you don't need dual-proc G5 for web browsing and e-mail! An acient PII with 32MB ram and WindowsMe would be more than enough!
MySQL Error 1040: Can't return sig, Too many connections!
Heh... I was unaware of that, but the fact is, you can't compare an in development system to one that's being used NOW. And take a look at the front end system requirements... THAT is where your nonlinear editing is done, not on the cluster. Cinelerra does more than nonlinear editing, so it makes sense to use cluster support, and such a product is quite a good idea... but it isn't the same as saying Final Cut Pro could be clustered. So what I said still goes. For the mixing and cutting and splicing, a cluster does little good. It simply requires too much disk access with large files, which just doesn't work over an interconnect. I suppose it's theoretically possible, given a low latency high bandwidth interconnect, but then you're talking big bucks and a specialty system anyway.
So yes, I'm still right ;) Though thank you for the link to Cinelerra. All it does is farm out the rendering and other computations that CAN be farmed out... though I suppose it could give a boost to compression and such. In two years, it might be a competitor to Final Cut Pro, assuming Apple doesn't add cluster support(which is doubtful, as their compiler, for example, already supports distributed systems compilation)
What really would help Linux video editing is the development of a nonlinear editor that's easier to use than Final Cut Pro, and does what Cinelerra seems to do... farms out computations that can be done on other nodes. Final Cut is nice, but it isn't the easiest to use program, unlike most Apple products.
- Free tabletop fantasy gaming! Grey Lotus
This test is not scientific. It doesn't compare the same hardware running the same software.
...) have been polluting the Internet for some time now.
Duh.
The test is not fair. OS X is better optimized for 64bits.
So what.
The test is not "real world" enough, it only talks about graphical performance, 2D, 3D programs and games.
OK, acknowledged.
At the same time this is exactly the type of test *some* people have been waiting for. The other type of tests ("scientific" cough cough, "fair", "real world",
And now there's this little ditty of a test that is totally insignificant and at the same time totally pleasing for both camps (gaming crowd versus serious graphical apps).
What's wrong about that?
Incidentally, the problem with trying to cook up a good comparison is partly because there is not much of an equal offering in the PC camp. By this I mean a mass produced dual 64bit desktop machine. Instead of praising this innovative move and talking about the advantages and disadvantages, there was a lot of whining in the vine of "compare this with that server or that custom processor".
Which is of course just a bit ridiculous. Now you have about every comparison possible (Gooooogle for more) and still there's whining...
I think, therefore I am...I think.
I guess you haven't checked since 'well over a year prior to XP," but OS X has had three major updates, each introducing over 150 new features.
10.0 was first release before XP, 10.1 came around a year later (and 10.2 a year after this). 10.3 was released a few months ago and adds significant features. I may be wrong, but I believe XP was released in between the release of 10.1 and 10.2.
Thus, Windows XP has not undergone a feature update since the release of OS X 10.1, and Apple has released two feature updates since XP's release.
So, in effect, by your logic (and your language), "PC sucks" simply because, "Last time I checked, XP came out well over a year prior to Mac OS X 10.3 "Panther."
I'm really puzzled about the (Surprise) remark in the article.
The "(surprise)" remark is about Photoshop. I think the author of the article means that, since Photoshop is a very important app for Macs (they being the platform of choice for artists, at least traditionally), it is often expected that it should run better there than on Windows.
I don't know how true it is today that graphics professionnals prefer Macs overs Windows boxes, or whether Adobe et al put more effort in optimizing their products for either system, but it certainly seems odd that the G5, which the article finds to be faster than the Opteron in many cases, performs badly (relatively speaking) on an application as crucial as Photoshop.
Two words, click & hold. At first the ctrl-click bugged the hell out of me too, I had used PCs for years, i just figured out the click & hold like a week ago and its way simple.
A blog about stuff.
Athlon G5 vs Athlon 64 FX 51 - the Athlon64 FX 51 wins big, based on Overall performance in 15 test calculations on Mathematica 5.0.
AMD Athlon 64 FX-51 3200+, 512 MB, Windows: 3.02386
Athlon 2800+, 512 KB cache, 333 MHz FSB, Win. XP Pro: 2.50588
P4-B, 3Ghz, 4GB, W2K3: 2.1325
PowerMac G5, 2 GHz, 2.5 GB, MacOS 10.2.8: 2.04471
Alpha 21264C, 1250MHz, Unix: 1.96207
Dell P IV 2.4 GHz, 512MB, Win2000: 1.89181
Pentium 4, 2.4GHz, 512MB, Linux: 1.81
Pentium Xeon, 2.4GHz, 1GB, Linux: 1.79268
Athlon XP 1800+, 512MB, Linux: 1.65654
Gateway 700XL Pentium 4, 2.2GHz, 1GB RAM, WinXP Pro: 1.5303
Athlon 1.3 GHz, 768 MB, Windows XP home: 1.39993
Pentium P4, 2.0 Ghz, 1.5 GB RAM, 512kB cache, XP SP1: 1.2771
PowerMac 1GHz, 768MB, MacOS 10.2.8: 1.0
The number at the end of each row is an index, with the 1GHz PowerMac as the reference point. The 2.2 GHz Athlon64 FX 51 is therefore more than three times faster than that, whereas the 2GHz G5 is only two times faster.
Well, not since we have hardware T&L and Vertex Shaders...
HI O WISE PRINCE. WHT TOOK U SO DAM LONG?
Take a look at MMA 5.x timings.
The G5 loses 14 out of 15 tests to the Opteron. Moreover, the G5 loses to the Athlon 2800+ and the Pentium 3 GHz.
Console games are for the equivalent of Britney Spears loving female adolescents and for those who like to eat a McDonalds as their primary food source. Any serious gamers will stay with PCs because that is where the true elements of a game machine/environment all come together. Just like any serious gambler will end up in Vegas eventually. Since consoles were made for the masses, what you end up getting is a dumbed down game environment. All serious musicians eventually move away from $129 dollar guitars and 4 track recorders. Serious gamers don't like to work within the confines of a can'ned environment. I will never own a console for those reasons and others. I've been FPS gaming for over 10 years and find consoles cute and POP but lame.
Of course these are just my opinions. But you also may want to also ask those who attend Quake Con every year.
+2
The problem is that it's a hack, a workaround. And it's not going to run everything- especially if you run any games.
VirtualPC is okay, but it's certianly not the answer and it too costs a bundle of money since you gotta buy a Windows license too.
Like I said, the G5 is a mighty fine peice of equipment. I just don't think it's going to bring any PC users over to Mac's - especially not when there's these AMD 64-bit chips hitting the market, if you're into the numbers.
- It's not the Macs I hate. It's Digg users. -
if you have software investments that you need to maintain, I assume you are not talking about your games...besides...who the hell said you have to dump Windows? I have a Mac and a PC and run what ever software I want. then when I upgrade software from the PC, I just get the Mac version instead...unless I like the windows version better or something.
why only have one computer? if PCs are so cheap, then having one should still no be to much.
I am the Alpha and the Omega-3
Okay, smartass. The comments previous to mine were not made by me, and if you're so fucking smart, name what features Apple has stolen from Microsoft!
On my end, I have many PC's.. 13 to be exact. Some new tech, some old tech. But they're all x86 PC's. Most run Linux.
I wouldn't mind having a Mac in the mix too, but they are too expensive for me. As I build all my own machines, I can put together a high end x86 box for a few hundred bucks. With a Mac, I have to buy a whole pre-assembled machine. While you can get a decent mac for pretty cheap, I wouldn't want just a run-of-the-mill, I'd want a high end Mac to match my high-end x86's.
Since there's really no software for the Mac that doesn't have a version for Windows or something, I see little reason to invest in the Mac.
Besides, we'll all be running Linux at some point anyways so who cares right? =)
- It's not the Macs I hate. It's Digg users. -
Good one! Touche' :)
..never new it did that... Thanks!
(climbs out from under rock)
Yes, to "test" the systems.
The page to which you pointed examined and talked about the published specs of both cpus, but I didn't see any benchmarks there.
Those are both valuable and important processes, but they're not interchangeable.
Stay away from Motherboards that have the Silicon Image 3X52 SATA driver. IT DOES NOT HAVE AN OPEN-SOURCE DRIVER.
Silicon Image has been kind enough to release a binary only driver for RedHat 7.3 and 8.0, Suse 8.0 and 8.1 and United version 1.0.
Linux - Because Mommy taught me to Share.
personal Video editing on a Mac is much better than on a PC.
that is why I like my Mac as opposed to what I do with the PCs I have.
I am the Alpha and the Omega-3
NOBODY!
"It's the height of ridiculousness to say for those 9 lines you get hundreds of millions."
Example: LAME isn't Altivec-enhanced yet, and shows no signs of getting that way. Ripping MP3s on my 733 MHz G4 takes roughly twice as long as on my 900 MHz Pentium-M laptop.
Breakfast served all day!
I am running older PC hardware. Interestingly enough, the features that made the long cycle possible are those that put the cost of said PC directly in line with an Apple machine. Go figure...
Anyway, you are finding what many folks are finding; namely, that your hardware today really will continue to do the job longer than they want you to believe it will.
OS X is a well crafted OS from what I see. Getting faster with new releases is a rare trend these days. After the design is well tweaked, I suspect this part of things will slow a bit, but will not likely regress into the mess that currently is win32 and a lot of Linux.
Sort of confirmes my idea regarding intergrated Linux machines. Well constructed hardware running Linux would exhibit many of the same value traits you currently see in OS X. The message to the market would be good for both camps...
Blogging because I can...
I had thought this was true of the Opteron as well.
It's not true. Opteron has twice the number of registers compared to old chips and those can't be used in 32 bit mode (due to backward compatible x86 instruction set)
"But really, try OS X"
As I said in my post, they could have improved them since then.
Didn't Apple steal the GUI off Xerox?
Aren't flat panels prohibitively expensive, even now?
Isn't QuickTime the most overused (i.e. it's used at all) format available?
Karma: It's all a bunch of tree-huggin' hippy crap!
Just to let you know the G5's are made by Intel. You probably should have said x86 vs. ppc not intel/amd vs g5. Not trying to be a dick, just informative.
> If all the efforts at the continued Apple project were instead used on PC's, we'd have: [...]
...no alternative to the Wintel lowest-common-demominator trash hardware.
Don't forget the most importing thing we would have:
-fred
Sign #11 of Slashdot overdose: You see the phrase 'moderate Republican' and you wonder if that would be a +1 or a -1.
> Just to let you know the G5's are made by Intel.
Wow... can I have some of what YOU'RE smoking?
The G5 is made by IBM. But I see your confusion: they both start with the same letter.
-fred
Sign #11 of Slashdot overdose: You see the phrase 'moderate Republican' and you wonder if that would be a +1 or a -1.
Haha. Can I change that to post as Anonymous Coward? Thanks for the correction, I'm one sleepy bastard. Me = Confused Jackass. ;-)
Neither chip was run with 64-bit code in this test because neither operating system supports it. OS X has a few little hacks that allow for some 64-bit integer operations, but that is of little use for the vast majority of applications. Real 64-bit systems have a 64-bit address space.
That being said, 64-bit code is generally SLOWER than 32-bit code. With 64-bit code your pointers are twice as large, so you use more memory bandwidth and more cache space. The performance hit isn't huge, but it does exist, probably about 5% slower on average.
The same is kind of true for the Opteron, except that the Opteron has a bit of an ace up it's sleave. In 64-bit mode the Opteron has twice as many registers as in 32-bit mode. Since a lack of registers is one of the major performance stumbling blocks of x86, doubling the registers boost performance by a fair bit. The end result is that 64-bit code on the Opteron is often FASTER than 32-bit code. Of course, this depends on the application. Apps that don't use many registers but lots of pointers will still be slower on the Opteron (perhaps up to 10% slower). Apps that use lots of registers can be significantly faster (30-50% faster in fairly extreme cases). Overall though it's usually about 0-5% faster on average.
Of course, as soon as you need more than ~2GB of memory per application, 64-bit code becomes rather critical. Apple will likely work on a split 32-bit/64-bit system for OS X. This way most apps can run in 32-bit mode for the higher performance, but apps that need lots of memory can run in 64-bit mode for the large address space. Linux for AMD64 already does this, though WinXP for AMD64 will be a pure 64-bit system making use of thunking to translate 32-bit system calls into 64-bit calls.
If you haven't seen any documentation it's only because you haven't looked hard enough!
There have been a number of tests comparing Opteron and Athlon64 processors in 32-bit and 64-bit mode under Linux and even a few that use Windows (beta version of WinXP). Here are a few links:
First off, some SPEC CINT2000 numbers: 32-bit OS + 32-bit apps, 64-bit OS + 32-bit apps and 64-bit OS + 64-bit apps. Unfortunately there are no similar CFP2000 numbers since GCC Fortran isn't up to the task, so you end up with lots of different variables making it nearly impossible to compare.
There is also this areticle at Ace's Hardware, and this little bit on Anandtech. Other tests exist.
Long story short, 64-bit support on the Opteron can and often does improve performance, even on apps that don't require lots of memory or use 64-bit integers. The extra registers help.
As for compilers, Microsoft plans on supporting AMD64 in their Visual.net 2003 compiler (beta versions are available now) and GCC supports the instruction set now. That makes up the compilers used for the vast majority of applications. As you mention, PGC is also doing a compiler, and it seems that Sun will support AMD64 with their compiler as well. Here is the AMD64 Developer Resource Kit page which lists all sorts of software with support for the AMD64 instruction set.
The Opteron was intended to be used in multiprocessor configurations with a NUMA design, and functions optimally with processor-local memory and a NUMA-aware OS. This benchmark was done with a degenerate motherboard on which all of the system memory is attached to one of the processors. The other processor must access all system memory indirectly through its peer, and its integrated dual-channel DRAM controller is not utilized at all, halving the maximum memory bandwidth of the system.
Few mass-market dual Opteron boards available now support processor-local memory on both CPUs. Sadly, most vendors seem reluctant to discuss this rather important detail in their whitepapers and marketing material. I think Tyan's boards, specifically their K8W desktop board, does this correctly and is a good choice from this point of view, but costs upwards of $450.
Even with a better designed motherboard, this benchmarker used Windows XP, which is not NUMA-aware. More recent Server 2003 and Linux releases are NUMA-aware, and would have to have been used to take advantage. Such details have been shown to boost performance by 20% in different but more reputable benchmarks.
The Opteron's new memory architecture is arguably a larger advantage over previous generations than its 64-bit arithmetic and addressing modes. This is a feature that it does not share with the G5.
You've got to be kidding, or else you don't own a console. I'll give you the other two; an FPS on a console is just a bad idea. But consoles have the entire Final Fantasy series, including Tactics, and they've also got amazing games like Disgaea. Breath of Fire, Shining Force, Dragon Force...I could go on. I don't see anything out for a PC in the RPG arena that would make me want to even try to get WINE to work, except for maybe FFXI, but that will be out for the PS2 in the spring (and it's an MMORPG anyway).
I'm sure that there are some nice RPGs out for the computer (other than old classics like Zork), but I already have more than enough console games to fill up my spare time in between all the other stuff I do. Heck, Disgaea is going to last me at least a few months on its own. And you only need to buy a new $150-$300 console every few years as opposed to upgrading your RAM, video card, CPU, etc., dealing with driver issues...aagh!
WMBC freeform/independent online radio.
Fast User Switching and the Alt+Tab feedback window, in 10.3 alone. I think this pales in comparison to what Microsoft has taken from Apple, however.
Boot speed across basically any system capable of running OS X has also been improved markedly. This is one of Steve Jobs' "things"; as far back as the original Macs, one of the "insanely great" things he insisted on was a boot speed within a certain amount of time.
This person's friend is reacting to a genuine effort by Apple to improve their users' experience.
"Fundamentalism" isn't about divine morality. It's about human authority.
"Here's another way to look at Panther's performance. For over three years now, Mac OS X has gotten faster with every release -- and not just "faster in the experience of most end users", but faster on the same hardware. This trend is unheard of among contemporary desktop operating systems."
"Fundamentalism" isn't about divine morality. It's about human authority.