Amiga.org
Amiga computer related discussion => Amiga Hardware Issues and discussion => Topic started by: Piru on February 03, 2012, 08:15:16 AM
-
(http://sintonen.fi/pics/blender_benchmark.png)
Benchmarks were run with:
blender_binary -b projects/bricks_and_water_plugin.blend -o ram:pool -F JPEG -f 0
PS. Blender does neither require nor utilize 3D HW for the rendering benchmark.
-
@piru: Now I know you don't own all those machines yourself so could we have a link to the data you used please.
.....and that SAM result just doesn't seem right. I would have expected a jump, but four times the Peg II result I just find hard to accept.
-
@piru: Now I know you don't own all those machines yourself so could we have a link to the data you used please.
X1000 PA6T 1.8GHz (http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35053&forum=33&start=200&viewmode=flat&order=0#650749)
Pegasos 2 G4 1131MHz (http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35053&forum=33&start=240&viewmode=flat&order=0#650805)
Sam440ep Flex AMCC 440EP 733Mhz (http://amigaworld.net/modules/news/article.php?storyid=6238#83985)
PowerBook G4 1.67GHz and Mac mini G4 1.5GHz are my own machines. Mac mini is running stock MorphOS 2.7.
-
What is it with your obsession for benchmark on X1000? All I needed to know is that its the fastest machine you can get AmigaOS4 on and if that is what i'm interested in and want to use then that is what I'm going to have to get. Plus hopefully drivers and support for the hardware should only get better over time.
Plus I'm really look forward to getting it, I haven't been this excited getting a computer since...well my last Amiga. i dont think any PC or Mac no matter how good they are and for the amount the x1000 cost me, I could of got some serious kit, could of given me the same feelings.
-
the problem is that mac mini g4 1.5 with OS4 beta could be faster that x1000 :)
-
What is it with your obsession for benchmark on X1000? All I needed to know is that its the fastest machine you can get AmigaOS4 on and if that is what i'm interested in and want to use then that is what I'm going to have to get. Plus hopefully drivers and support for the hardware should only get better over time.
Plus I'm really look forward to getting it, I haven't been this excited getting a computer since...well my last Amiga. i dont think any PC or Mac no matter how good they are and for the amount the x1000 cost me, I could of got some serious kit, could of given me the same feelings.
I think it is interesting to OS4 users. Pegasos II G4 is still good choice if you want performance. Pegasos II is not the fastest OS4 hardware anymore but close.
-
@AmigaNG
What's wrong with these kind of benchmarking? It's interesting for people...
-
I have no problem with benchmarks, I'm actually interested to know how fast my new Amiga will run. Its just I get the feeling some people are trying to prove a point with them. Sorry if I'm wrong.
Here the thing I have a PC, a bit old now, it has Intel Core 2 duo running at 3Ghz, AMD 5790HD 1gb graphics card, 4gb DDR3 1066mhz ram, creative titanium 7.1 sound card, 2x1tb hard drives and windows 7 64 bit, now this PC can do everything I need it too, and my guess it likely three or four times faster if not more than my x1000 will be or ever will be, my point is I didn't buy it for performance, I bought it for the best AmigaOS experiences I can have, to be more part of the great amiga community, to try and get back into my amiga roots, I think a few people cant or never will understand that and thats fine, it just some posts at the moment are coming across as try to spoil the fun, again I'm sorry if I'm wrong, text is never a good way of translating what people real motives are.
-
I have no problem with benchmarks, I'm actually interested to know how fast my new Amiga will run. Its just I get the feeling some people are trying to prove a point with them. Sorry if I'm wrong.
Here the thing I have a PC, a bit old now, it has Intel Core 2 duo running at 3Ghz, AMD 5790HD 1gb graphics card, 4gb DDR3 1066mhz ram, creative titanium 7.1 sound card, 2x1tb hard drives and windows 7 64 bit, now this PC can do everything I need it too, and my guess it likely three or four times faster if not more than my x1000 will be or ever will be, my point is I didn't buy it for performance, I bought it for the best AmigaOS experiences I can have, to be more part of the great amiga community, to try and get back into my amiga roots, I think a few people cant or never will understand that and thats fine, it just some posts at the moment are coming across as try to spoil the fun, again I'm sorry if I'm wrong, text is never a good way of translating what people real motives are.
Then dont read it.
If you say "i want a machine that gives me the best OS4 experience" and the machine that gives you that is already out and not the latest most expensive hardware, dont you want to know these kinds of things?
So please tell us how a lesser more expensive system gives you a better experience? Or do you hate your money that bad?
-
Seems to me like people are trying to point out that their PowerMacs using MorphOS are faster than the fastest AmigaOS 4 machine out there.
Which is probably true. It's also true that any modern x86 out there will blow either system out of the water. To outsiders we're all crazy for arguing over whose platform is faster, when they're both far slower than what everybody else uses.
It's also true that for myself I don't care, and I value my AOS 4 machines much more than any PC. Power is not important to me, it's how it uses it - and if the X1000 offers me a way to use it in a way that no other machine does, then that's reason enough to get excited.
@AmigaNG:
Nil illegitimi carborundum. In pragmatic terms, benchmarks mean nothing, except numbers. What matters is which you prefer, and no amount of figures and statistics can tell you that.
-
If you say "i want a machine that gives me the best OS4 experience" and the machine that gives you that is already out and not the latest most expensive hardware, dont you want to know these kinds of things?
Yes i would like to know how much faster it is, compared to Sam boards and Peg2, now ok so far certain test show that X1000 is only just beating the Peg2 which i am slightly surprise by but then performance is only half the issue, one of the other reason I made decision to get the x1000 over sam boards or peg2 was because of how stable both the hardware and software is on the system as reported by beta testers and it is the system that is set up for the future of the OS and hopefully only get better with time.
So please tell us how a lesser more expensive system gives you a better experience? Or do you hate your money that bad?
Yes i hate money. :) I'm off to buy an old lp record for £100, because i hate them ultra clear digital recording for 79p.
-
the problem is that mac mini g4 1.5 with OS4 beta could be faster that x1000 :)
Also might not be. You can't draw meaningful conclusions from a small number of selective benchmarks. For instance in the thread I started at http://www.amiga.org/forums/showthread.php?t=60612, the X1000 is over 300-400% faster than the Mac Mini. You'd have to run *lots* of benchmarks to draw more definite conclusions.
Also bear in mind that these benchmarking threads should be taken with an EU salt mountain since the system is nowhere near optimized yet.
Taken from http://blog.hyperion-entertainment.biz/
"Given the rushed nature of this AmigaOS 4.1 Update 5 release, there are still some bugs and a few rough edges. Remember, the X1000 was originally planned to be released only with AmigaOS 4.2 installed. Also please keep in mind most of the X1000 system is still unoptimized. This is truly the most powerful Amiga Operating System hardware platform ever released and we plan to utilize this hardware to its full potential in due course."
Wait till it has been optimized and then redo these benchmarks.
-
@Spirantho
AMEN! :)
-
and we plan to utilize this hardware to its full potential in due course.
Which means, using the second core aswell....
-
The whining about the benchmarks is hilarious. If I dumped over 3,000 bucks on this crap I probably wound't want to see it either.
-
Seems to me like people are trying to point out that their PowerMacs using MorphOS are faster than the fastest AmigaOS 4 machine out there.
Which is probably true. It's also true that any modern x86 out there will blow either system out of the water. To outsiders we're all crazy for arguing over whose platform is faster, when they're both far slower than what everybody else uses.
I think those benchmarks are perfectly demonstrating where PPC hardware is going today.
It's also true that for myself I don't care, and I value my AOS 4 machines much more than any PC. Power is not important to me, it's how it uses it - and if the X1000 offers me a way to use it in a way that no other machine does, then that's reason enough to get excited.
I am sure you wouldn't mind if X1K was winning by wide margin :-)
-
I think those benchmarks are perfectly demonstrating where PPC hardware is going today.
I disagree. These benchmarks are a small part of the full story. They're maths-heavy (which is arguably the X1000's weak point against the G4 Macs), whereas in bandwidth-heavy apps it's a completely different story. Then you have to account for the fact we're only use one core in the X1000 at the moment. PLUS it's unoptimised.
I am sure you wouldn't mind if X1K was winning by wide margin :-)
Well, yes, I would get some satisfaction from that. :) But only because I'm a bit tired of people trying to spoil the enjoyment of people who do want the latest AmigaOS 4 hardware.
I make no pretence about the fact that I prefer AmigaOS 4 - I do (and I do have MOS and AROS too). And I want Trevor's work to be rewarded, not rubbished. But even if the X1000 slaughtered every PowerMac out there I still wouldn't be going out of my way to point it out to MOS users.
-
I also prefer AmigaOS4.x versus MOS or AORS, but I also want to use my favourite Operating System for almost everything I need...
So, I need raw power and not only disk transfer or simlar power(that I need really poor...)...
Unfortunately ppc hw today wasnt so nice for home computing, and that was the point imho...
Theorically speaking I think we need a dual-3GHz A1X1000 to get some "modern" results...
X1000 was nice no dubt on that, but with a powefull cpu was much more nice I think...
Just for joke...any chance to get PA-Semi working at 2/2.2GHz overclocking it?
-
Agreed - if you want to compete with x86 you'd need the same investment into the PPC architecture, which just isn't going to happen. Your best bet on that front is AROS, which is x86, of course.
But I think it's important that people remember that nobody ever claimed the X1000 to be more than the most powerful AmigaOS 4 machine out there - it's never been pretended that it can compete with 8-core i7s, because it can't.
-
Which means, using the second core aswell....
Have they worked out how to do SMP reliably with AOS's lack of memory protection, then? I thought that was the limiting factor on why there's no multicore support...
Also, I'm not sure I understand the idea that older PPC hardware is inadequate. The 1.67GHz PowerBook G4 I had was at least as responsive as my Eee,* which I use with no trouble as my main daily-driver computer, and the MDD G4 that currently serves as my Mac machine is pretty well ahead of either of them. Even the Pismo PowerBook G3 I got in a trade handles things pretty well in OS9, and serviceably in OSX. I'm sure the same can be said for similarly-clocked non-Mac PPC boards.
* (Disk I/O and raw memory bandwidth were limiting factors, but then my Eee has its own different limitations, so it about evens out in the wash.)
-
@ Tuxedo
A 3 ghx OS4 machine will run our non existant, not yet coded programs that ship on $20 smartphones by default, OS4 software that we need at rapid speeds in 3 ghz ranges, which does not exist....
I'm a big fan of OS4. But I bet Blender crashes just as nice on a X1000 as it does on my SAM 440.
-
@ Tuxedo
I'm a big fan of OS4. But I bet Blender crashes just as nice on a X1000 as it does on my SAM 440.
I would imagine it crashes about 4 times as quickly. That's progress for you. :)
-
What is it with your obsession for benchmark on X1000? All I needed to know is that its the fastest machine you can get AmigaOS4 on and if that is what i'm interested in and want to use then that is what I'm going to have to get. Plus hopefully drivers and support for the hardware should only get better over time.
Well... it's been predicted by many that it would be the fastest Amiga compatible system when it's released.. so it's interesting to see if it is and by what margin. And of course every new hardware is benchmarked everywhere in every platform. Usually people would like to know what they get for the money and not just go on blindly by rumours or marketing speech.
-
Well... it's been predicted by many that it would be the fastest Amiga compatible system when it's released.. so it's interesting to see if it is and by what margin. And of course every new hardware is benchmarked everywhere in every platform. Usually people would like to know what they get for the money and not just go on blindly by rumours or marketing speech.
I'll bite, what is (hardware wise) Amiga compatible about the A1X1K?
-
I disagree. These benchmarks are a small part of the full story. They're maths-heavy (which is arguably the X1000's weak point against the G4 Macs), whereas in bandwidth-heavy apps it's a completely different story.
Or in other words -- when data no longer fits in L2 cache in G4 then 1682M is winner?
Then you have to account for the fact we're only use one core in the X1000 at the moment.
Using 2nd core wouldn't improve Lame benchmarks much.
PLUS it's unoptimised.
The OS or benchmarks? I could buy that it was using conservative memory settings but according to memory benchmarks it is not case.
-
Theorically speaking I think we need a dual-3GHz A1X1000 to get some "modern" results...
Practically we call such device "Power Mac G5 Quad" or "Power Mac G5 Dual", which come with up to 2.7Ghz. Not 3 Ghz, but regarding the results we already have, ...
Geit
-
Or in other words -- when data no longer fits in L2 cache in G4 then 1682M is winner?
That's a good point, actually - neither the Mini nor the 1.67GHz PowerBook have an L3 cache. Wonder how a machine with an L3 cache would stack up?
-
"Given the rushed nature of this AmigaOS 4.1 Update 5 release, there are still some bugs and a few rough edges. Remember, the X1000 was originally planned to be released only with AmigaOS 4.2 installed. Also please keep in mind most of the X1000 system is still unoptimized."
They ask for sorry because it was so rushed??? Wasn't the X1000 with OS4.x not initially scheduled for "before summer"(note: summer 2010 was meant!!). It's more than 1.5 yeasr delayed and still they claim it a "rushed release". Funny guys.
-
Or in other words -- when data no longer fits in L2 cache in G4 then 1682M is winner?
This is why i'd be rather curious to see the result of the benchmark i suggested:
http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35053&forum=33&start=240&viewmode=flat&order=0#650877
But this thread suddenly got very silent.
-
I'll bite, what is (hardware wise) Amiga compatible about the A1X1K?
Exactly the same as with Mac with MorphOS. Nothing in hardware wise, but AmigaOS compatible operating system running on it. Nobody should look into hardware naming these days, only operating system compatibilities and quality of the hardware matter.
-
I think those benchmarks are perfectly demonstrating where PPC hardware is going today.
Well, PA6T is not a cpu of today, but a few years old. Was intended to replace G4 processors in energy efficebt systems. So it fits. Similar speed with invcreased I/O performance. A good competitor to teh 864x processor range. Anyway, it is a processor of yesteryear.
Generally PowerPC stil has some nice chips in the pipeline, Freescale's rediscovering of Altivec is pretty nice. The downside: it's expensive and there are no mainbaods available using these quite interesting and competetive chips. Also one of their strengthes is being multicore, which again requires according support by the OS which come at a cost - be it SMP (compability) or AMP (rather low benefit for non AMP apps).
All in all you are of course right: ppc on the desktop is currently "difficult" to say the least. Hence my hopes you'll follow an approch similar like I outlined/dreamed about on http://via.i-networx.de/q86.htm .
-
But this thread suddenly got very silent.
no wonder, as i was going to post pirus blender comparison chart over there i had discover that i had been restricted for a week. not that i didnt expect that after kas1e and me responded to the unbelievable moderation rants here:
http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35009&forum=33&start=160&viewmode=flat&order=0
-
This is why i'd be rather curious to see the result of the benchmark i suggested:
http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35053&forum=33&start=240&viewmode=flat&order=0#650877
But this thread suddenly got very silent.
Yes, very strange...?
Would be one of the most interesting benchmarks IMHO!
-
@fab:
btw heres your result, just seen it posted over at awnet:
Here the result from the X1000.
BENCHMARKs: VC: 82.849s VO: 0.006s A: 0.000s Sys: 6.697s = 89.552s
BENCHMARK%: VC: 92.5151% VO: 0.0062% A: 0.0000% Sys: 7.4787% = 100.0000%
so its again confirming the previous tests.
sigh, i hoped the ban will keep me off there, but it doesnt seem to work that way..
-
Generally PowerPC stil has some nice chips in the pipeline, Freescale's rediscovering of Altivec is pretty nice.
Nobody is building desktop/laptop motherboards using these CPU's, so they are completely irrelevant. For all purposes interesting to us, the PPC is dead. It's deader than dead. On its grave stone, it has the year 2005 cut in, and this is when Apple announced its migration to x86...
-
Nobody is building desktop/laptop motherboards using these CPU's, so they are completely irrelevant. For all purposes interesting to us, the PPC is dead. It's deader than dead. On its grave stone, it has the year 2005 cut in, and this is when Apple announced its migration to x86...
Nobody's building desktop/laptop motherboards with them at the moment. That's unlikely to change in the immediate future, but the industry can take surprising turns some times. In any case, the CPUs do exist.
Anyway, this from a guy with a MOS avatar?
-
no wonder, as i was going to post pirus blender comparison chart over there i had discover that i had been restricted for a week. not that i didnt expect that after kas1e and me responded to the unbelievable moderation rants here:
http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=35009&forum=33&start=160&viewmode=flat&order=0
LOL, appointing that ChrisH dude a moderator was probably the dumbest thing I have seen over there in a long time! But they have only themselves to blame, they brought this onto themselves! :lol:
(And for the record, true SMP on Amiga is *not* possible without breaking Amiga compatibility. If you are prepared to break the Amiga compatibility, it could be done tomorrow. If not, it can't happen. And this is not "controversial", "fantasy", or "inflamatory", it's cold heart facts! Oh, ChrisH...:lol:!)
-
@fab:
btw heres your result, just seen it posted over at awnet:
so its again confirming the previous tests.
sigh, i hoped the ban will keep me off there, but it doesnt seem to work that way..
Yes. Though the time spent in I/O seems a bit too high (probably some other factor). But in the end, the X1000 is just marginally faster than the Mac mini to decode the stream (82.8s against 84.6s). I actually expected better there. I'll just wait a bit to be sure this test was also done with AltiVec (even if it wouldn't be drastically different with or without it, unlike LAME).
-
if the X1000 offers me a way to use it in a way that no other machine does, then that's reason enough to get excited.
What way(s) would that be?
Please cite specific examples.
-
@fab:
btw heres your result, just seen it posted over at awnet:
so its again confirming the previous tests.
X1000: BENCHMARKs: VC: 82.849s (+a strangely high 6.697s for I/O, bringing it to 89.552s in total)
MacMini: BENCHMARKs: VC: 84.626s
This to decode a 69 seconds long clip.
Are my following conclusions about this test correct?
Conclusion 1: The X1000 is about on par(!) with a Mac Mini G4 when decoding x264 HD video.
Conclusion 2: The X1000 seems *unable*(!) to decode and play 1080p H264 clips. (This I didn't expect!)
-
Nobody's building desktop/laptop motherboards with them at the moment. That's unlikely to change in the immediate future, but the industry can take surprising turns some times.
It will never happen. Never EVER *EVER* **EVER!**
If the industry will want something else than x86, it will be ARM. In fact, that process has already begun, and you will start seeing results of this during the current or upcoming few years...
Anyway, this from a guy with a MOS avatar?
Most people today (including the MorphOS developers) understands the situation with PPC. Some MorphOS developer said on morphzone: "If we had know back then, what we know today about PPC, we would have choosen differently". That's why the plan is:
1) Short term: MorphOS 3.0 for PPC
2) Mid term: MorphOS 3.1, 3.2, 3.3, etc, ..., ..., for PPC
3) Long term: Re-evaluation about the CPU/HW situation, which may include a migration (to x86, ARM or both?)
We are using PPC only because this is where MorphOS currently is, not because PPC is the best, or even good enough (anything that can't play 1080p movies in 2012 isn't good enough).
-
It will never happen. Never EVER *EVER* **EVER!**
And you know that...how?
If the industry will want something else than x86, it will be ARM. In fact, that process has already begun, and you will start seeing results of this during the current or upcoming few years...
Sure. And what happens when they get tired of ARM? Or is that going to be as indisputably eternal as x86 seemed five years ago?
-
X1000: BENCHMARKs: VC: 82.849s (+a strangely high 6.697s for I/O, bringing it to 89.552s in total)
MacMini: BENCHMARKs: VC: 84.626s
This to decode a 69 seconds long clip.
Are my following conclusions about this test correct?
Conclusion 1: The X1000 is about on par(!) with a Mac Mini G4 when decoding x264 HD video.
Conclusion 2: The X1000 seems *unable*(!) to decode and play 1080p H264 clips. (This I didn't expect!)
Apparently he wasn't using AltiVec version. According to results posted by stevieu AltiVec enabled MPlayer benchmark it is 69 seconds.
-
Sure. And what happens when they get tired of ARM? Or is that going to be as indisputably eternal as x86 seemed five years ago?
ARM is going forward on every fronts. Even DSPs and media processors include ARM core these days.
-
ARM is going forward on every fronts. Even DSPs and media processors include ARM core these days.
Indeed it is, and more power to it. But that doesn't mean it will reign forevermore eternal.
-
"The whining about the benchmarks is hilarious. If I dumped over 3,000 bucks on this crap I probably wound't want to see it either."
You wouldn't want to know the truth?
Mac mini is apparently just as fast and I just saw 2 on ebay for 185.00$ buy it now.
Thats quite a difference in price for such similar hardware when the mac is just about the same speed...
Steven
-
@ Tuxedo
A 3 ghx OS4 machine will run our non existant, not yet coded programs that ship on $20 smartphones by default, OS4 software that we need at rapid speeds in 3 ghz ranges, which does not exist....
I'm a big fan of OS4. But I bet Blender crashes just as nice on a X1000 as it does on my SAM 440.
honestly here on my Pegasos2@1131 blender was quite usable and get some sporadic crash only when try to save rendered picture(but seems a my software problem with some weir dlib...
So why you have so much crashes?
-
By some people's standards, I guess Blender could be considered usable on OS4/SAM 440ep, and to be fair the version I used was one of the very early OS4 releases so perhaps I should give it a little more leeway. I don't do a whole lot of 3d rendering anyways, and any that I do is generally done in programs I am already more familiar with, programs that get the job done 100x quicker and better on my 4+ ghz SLI PC. One crash is too many crashes when I have other options, so I got annoyed quickly with the fact it had a habit of crashing/locking up when I tried to save/load projects on the OS4 version. Blender is likely a lot more stable now for OS4, but when I tried it it was not much more than a novelty to me, was too unstable to really use - but again, that was likely one of the very first OS4 releases.
I'm a bit picky about software stability, especially if there is a PC counterpart/version I can run. Some folks are head over heels in love with Blender, where as I find it a bit oddball to use interface wise on any of the platforms it comes on, be it OS4, Windows, or Linux.
-
All this is boring to me.... I prefer real world stuff.
How about Srec performance so we perhaps see X1000 screen capturing videos on YouTube? Thats what I wanna see.
-
All this is boring to me.... I prefer real world stuff.
How about Srec performance so we perhaps see X1000 screen capturing videos on YouTube? Thats what I wanna see.
Blender, Lame and Mplayer are real world stuff.
-
True sorry, just under the weather atm, I just don't find it particularly interesting. I'll sod off and leave you it. Perhaps I'll open a new thread, see if any takers.
-
After some benchmarks x1000 is more overpriced and underpowered than ever.
-
As I think someone already said (Karlos?), the really interesting benchmarks won't roll in until we see Linux performance compared on X1000 vs. PPC Mac. That will be a fairer comparison, as we don't know how optimised current AmigaOS builds are for the X1000.
-
After some benchmarks x1000 is more overpriced and underpowered than ever.
If you ask me, I would say it's... insane!
-
As I think someone already said (Karlos?), the really interesting benchmarks won't roll in until we see Linux performance compared on X1000 vs. PPC Mac. That will be a fairer comparison, as we don't know how optimised current AmigaOS builds are for the X1000.
+1
-
As I think someone already said (Karlos?), the really interesting benchmarks won't roll in until we see Linux performance compared on X1000 vs. PPC Mac. That will be a fairer comparison, as we don't know how optimised current AmigaOS builds are for the X1000.
Compare it like you want but the result its the same, (someone on another thread wants to see bf2 under wine, thats crazy). We are talking about a 2500eur computer please.
-
If you ask me, I would say it's... insane!
These people of hyperion and aeon are wasting the name "amiga"
-
As I think someone already said (Karlos?), the really interesting benchmarks won't roll in until we see Linux performance compared on X1000 vs. PPC Mac. That will be a fairer comparison, as we don't know how optimised current AmigaOS builds are for the X1000.
No, no, no, OS4 is the reason the X1000 exist, the reason to why people buy this 2007 level HW instead of the 3-4 2012 level Core-i7 Gaming System's (http://www.dell.com/us/p/alienware-x51/pd) they could get for the same money! Linux is completely irrelevant, you want a Linux machine there are both cheaper and more powerful systems. You see, "currently un-optimized" seems to be the constant state of OS4. In all benchmarks and all comparisons during the last decade we have always heard of "currently un-optimized". Look at the discussions after the extensive MorphOS/OS4 performance comparisons by "obligement.free.fr" some years ago. Always the same "not really optimized now, but will improve". But it never does. Look at the driver situation for the Sam HW. Still not there. But this doesn't stop people from talking about SMP, 3D for Radeon HD, and whatever. It's hilarious! Aeon and Hyperion has now released their $3,000 product, consisting of a combination of HW and OS. This is what people buy, this is what should be bench marked and compared. Whenever (if ever) things gets more "optimized", there could always be new tests and comparisons. But for now, look at the product they are *currently* selling!
-
These people of hyperion and aeon are wasting the name "amiga"
Speak for yourself. I would rather spend 2500Euro than use a crappy macmini any day. If i bought an x1000 it wouldn't be for the performance anyway.
-
I speak for myself dont worry, i dont talk about mac mini or morphos in any moment, chill out boy, but if you buy a x1000 then... is for what?
-
Linux is completely irrelevant
Of course Linux benchmarks are relevant. What they will show is the potential waiting to be unlocked in the X1000 hardware, or at least they will more accurately show this potential as the Linux builds have been maturing for longer.
Anyone with half a brain understands that early software builds for new hardware platforms are not the most optimised. Early adopters buy for the hardware, with the promise that the software that runs on it will improve. There is no reason to suspect this pattern won't be repeated with the X1000 too, as OS4 is still in active development, and X1000 is the flagship system of this OS.
So, bring on the Linux benchmarks, let's get a better picture of what the X1000 can do.
-
Of course Linux benchmarks are relevant. What they will show is the potential waiting to be unlocked in the X1000 hardware, or at least they will more accurately show this potential as the Linux builds have been maturing for longer.
Anyone with half a brain understands that early software builds for new hardware platforms are not the most optimised. Early adopters buy for the hardware, with the promise that the software that runs on it will improve. There is no reason to suspect this pattern won't be repeated with the X1000 too, as OS4 is still in active development, and X1000 is the flagship system of this OS.
So, bring on the Linux benchmarks, let's get a better picture of what the X1000 can do.
Well, Linux benchmarks are making only little sense. They will show the theoretical potential of the X1000. But it would be as intelligent as to measure/demonstrate a dual cpu PowerMac G5 with Bluetooth, Flash, latest 3D Hardware expansion under OS X/Linux to get a measure how well a PowerMac performs when MorphOS is the target.
Compare what's there here and now and not the theory. In theory MorphOS can even run on an i7 or Power7, well it's not much uptimized yet, hence take linux benchmark to show the potential of that machine that will of course get full support in two more weeks. But better buy that i7 now - you can easily wait the two weeks after the purchase antil MorphOS will support it.
The X1000 is more than 1.5 years delayed already, how long should users wait again? Two more weeks?
-
Yeah its already a year and a half late. How long till the second core works in amiga os? I'd say never.
How long till the xmos thing works?
How long till the built in networking works?
Sound?
I can't help thinking its ludicrous to pay 3k for a machine thats missing drivers, using only one core, that performs about as good as a 6 year old mac mini.
Add to that the ridiculous NDA they want users to sign so you can't complain publicly when something does not work right.
While I applaud anyone who dreams a dream, the reality is this is just another big disappointment.
Power pc is dead dead dead. Nothing like this will change that anytime soon.
Why anyone would pay 3k for this I don't know, but I do wish them luck with it and I hope they think it was a worthwhile investment.
"only amiga makes it possible."
-
Well, Linux benchmarks are making only little sense. They will show the theoretical potential of the X1000.
Actually, they don't show the 'theoretical' potential at all, they show the potential as it exists now... if you run Linux.
Anyway, with regards to benchmarking, it's fairly simple. When it comes to measuring anything in a scientific way, the best bet is to remove as many extraneous variables as possible, to isolate that which you are trying to measure. The question then is, what are you trying to measure? If you want to compare the performance of X1000 vs PPC Mac hardware, then your best bet is to make the software you use for testing these machines as similar as possible, so that the relative strengths of the hardware being tested shines through. This is why Linux benchmarks are a fairer test.
-
(http://sintonen.fi/pics/blender_benchmark.png)
Benchmarks were run with:
blender_binary -b projects/bricks_and_water_plugin.blend -o ram:pool -F JPEG -f 0
Sorry guys, if I spoil the party...
But I totally fail the point in shelling out such an amount for a machine to run Blender on when an el-cheapo 250€ box will run that benchmark in [...] 0.56s. (Actually, that's pretty depressing...)
The video playing stuff is much more relevant as it shows what a potential "everyday-use, allround" machine can or can't do at all (since video needs to be played realtime).
-
Speak for yourself. I would rather spend 2500Euro than use a crappy macmini any day.
I don't get the infatuation with the Mini, myself...it's really pretty much just an iMac G4 minus the art deco lamp case, and frankly the iMac G4 is no great shakes in anything other than the aesthetics department as it is. Power Mac G4s can be had for chump change (or less, if you make a lucky find at your local recycle center,) any of them will best a similarly-clocked iMac/Mini, later models are commonly available in dual-CPU configurations, and they're infinitely more expandable. Unless you're extremely strained for desk space, I don't see why the Mini is worth the bother.
-
I don't get the infatuation with the Mini, myself...it's really pretty much just an iMac G4 minus the art deco lamp case, and frankly the iMac G4 is no great shakes in anything other than the aesthetics department as it is. Power Mac G4s can be had for chump change (or less, if you make a lucky find at your local recycle center,) any of them will best a similarly-clocked iMac/Mini, later models are commonly available in dual-CPU configurations, and they're infinitely more expandable. Unless you're extremely strained for desk space, I don't see why the Mini is worth the bother.
Macmini is quieter (even after replacing the MDDs fans with ultraquiet ones), has lower power consumption (important when ~always-on), and a smaller footprint (sits next to the TV nicely without taking up half the room).
Downside is that the audio sucks, at least on mine (loads of interference from usb, graphics operations, network transfers). I still find it frustrating that we don't have isochronous transfers over USB just for this reason.
-
My Macmini is useful as a home theatre system. I love the way it can fit inside any backpack so easily. I am also seriously lacking in desk space. In fact my Macmini, at the time i am writing this post, is sitting on top of my switched on laptop (which is connected to external monitor and keyboard) so the compact design definitely comes in handy ;)
-
...
PowerBook G4 1.67GHz and Mac mini G4 1.5GHz are my own machines. Mac mini is running stock MorphOS 2.7.
Some of us would also like to run benchmarks (among other things) on our PowerBook G4's with MorphOS 3.0.
Is MorphOS waiting for the next news cycle?
(Code: Ambiguous reply for 'Yes, in two weeks', and Evasive reply for 'They don't tell me squat'.)
:)
-
Macmini is quieter (even after replacing the MDDs fans with ultraquiet ones), has lower power consumption (important when ~always-on), and a smaller footprint (sits next to the TV nicely without taking up half the room).
Downside is that the audio sucks, at least on mine (loads of interference from usb, graphics operations, network transfers). I still find it frustrating that we don't have isochronous transfers over USB just for this reason.
The VGA quality of mine sucks. DVI looks great.
Some of the G4 minis has infamously bad VGA quality. I remember being really disappointed when I bought it. I remember searching on forums and finding other people with similar complaints.