MorphZone

MorphOS on AmigaOne X5000?

Andreas_Wolf

# 251
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> If we had hardware that used those processors then I would agree with you. But the
> X5000 variant soon to be launched (in two weeks?) is P5020 based. A dual core.

Indeed, I was using the announced P5040-based X5000/40 to illustrate the top e5500 core count and performance.

>> I think it's a given that the non-SIMD per-clock performance of the e6500 is less
>> than 22% higher than that of the e5500 so won't make up for the clock rate decrease.

> the performance increase of the e6500 seems to provide exactly what is necessary to
> cover the decreased frequency. [...] So, in a non-SIMD application we have parity [...].
> [...] Without SIMD, the e6500 based cpus [...] offer parity with the P5020/P5040

As said, this required increase would be 22% to be on par with P5040 and 11% to be on par with P5020. Increase of DMIPS per clock and thread is between 3% and 10% (depending on source) in single-thread use according to Freescale documents, btw.

>> SMP would be fine with 4 e5500 cores in the P5040 and the T1042, and I have doubts
>> that more cores can be frequently saturated with common desktop computing tasks.

> e6500 cores are dual threaded and [...] the minimum number of cores is 4. [...] with
> SMP we have four times the processing power than with a P5020. That is still twice
> what the P5040 could manage. [...] it really would take SMP support to really make
> the 6500 based cpus perform optimally.

As said, I doubt that more than 4 threads can be frequently saturated with common desktop computing tasks.

> then there is the issue of Altivec....

Yes, that's the glimmer of hope if used extensively.

> this is about the X5000 and the P5020 and P5040 processors used on those boards.
> My primary objection to those two cpus is price, A T1042, T2081, or even a T2080
> would all be cheaper solutions. The T1042 is obviously slower than the P5040, but
> at about $200 less, it could provide a significant price reduction. [...]
> the e6500 based cpus [...] have a price advantage over the cpus used in the X5000.

We are talking about whether or not the e6500 can be the real performance upgrade the e5500 apparently isn't (according to first benchmarks, that is), so T1 is out of this discussion obviously.
1.8 GHz T2080 is less than 100 USD cheaper than 2.2 GHz P5040. The question is if 100 USD really matter with a 2000+ USD board. That's less than 5% price difference.

> I was hoping that the performance of the X5000 would be a significant improvement
> over our current hardware

Over G4 yes, over G5 no (in terms of CPU performance, that is).

> it may top our G4 based systems

1.5 GHz G4 in terms of CPU performance, yes. This will look differently with faster G4 systems.

> the G5 is still probably the more powerful solution.

I guess so.

> that would be the comparison I'd like to see, X5000 vs PCIe G5.

I'd be content with a comparison with pre-PCIe G5. After all, it runs MorphOS for better comparability, and single-core CPU performance wasn't increased significantly (2.7 GHz PPC970FX is probably faster than 2.5 GHz PPC970MP in single-core performance).
»19.01.16 - 14:55

Jim

# 252
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

>As said, I doubt that more than 4 threads can be frequently saturated with common desktop computing tasks.

I would have to agree with you that more than four cores is rarely used on desktop PCs. I have one dual four core Xeon system and one 8 core AMD FX based system, and the overall performance of these in real world use is only marginally better than my older four core Phenom II based system.

But, if I am buying a desktop system, I want a minimum of four cores. Additional threading doesn't hurt.
However, without SIMD, the performance of P5020, P5040, and P2080 cpus is all fairly close.

So the primary differences between the P5040 and the P2080 once SMP is factored in are limited to price, additional threads that might not see much uses, and the slight disadvantage presented by the clock speed/performance issues we have discussed with the T2080.

As the T2080 was not available when the X5000 was designed, and since the performance of the P5040 model should be comparable to a T2080 based system, I am not going to denigrate the performance of this model.

>The question is if 100 USD really matter with a 2000+ USD board. That's less than 5% price difference.

Well...even with P50XX cpus, this price seems a bit high, but given that A-eon is not a charity or a community driven organization its certainly better than the cost of a development system.

>I'd be content with a comparison with pre-PCIe G5. After all, it runs MorphOS for better comparability, and single-core CPU performance wasn't increased significantly (2.7 GHz PPC970FX is probably faster than 2.5 GHz PPC970MP in single-core performance).

But the memory used in Late G5s is faster (DDR2) which does help performance.
My guess is that single thread performance in a 2.5 GHz late G5 will be a close match for the earlier 2.7 GHz PowerMac.
And, of course, if SMP is factored in the 2.5 GHz system should be close to twice as powerful.

Since we have no commitment to SMP (like the OS4 community), I am rebuilding my 2.3 GHz system with one cpu board from a 2.5 GHz quad.
That will have a speed advantage over the X5000, but with only one dual core cpu power draw will be lower (of course the P50XX cpus will have an advantage in this area regardless).

However, if we do get a four core X5000, I would still have to consider it.

After all, the 2.7 GHz G5 and the 2.5 GHz Quad G5 are serious power hogs.
"Never attribute to malice what can more readily explained by incompetence"
»19.01.16 - 19:44

Zylesea

# 253
Yokemate of Keyboards

Posts: 2053 from 2003/6/4

All in all it shows that ppc is an even deader end than I expected.
Lets make a clear cut and go x64 ASAP.
--
http://via.bckrs.de

Whenever you're sad just remember the world is 4.543 billion years old and you somehow managed to exist at the same time as David Bowie.
...and Matthias , my friend - RIP
»19.01.16 - 20:01

Jim

# 254
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Quote:

Zylesea wrote:
All in all it shows that ppc is an even deader end than I expected.
Lets make a clear cut and go x64 ASAP.

Well Zylesea, its less than encouraging.
But, PPC ports can be created from our current OS.
What you are talking about is a new OS and that is going to take some time.

In the meanwhile I can soldier on with PPCs.
It certainly would help if we could point to something that offered more performance than our ten year old systems.
"Never attribute to malice what can more readily explained by incompetence"
»19.01.16 - 20:13

amigadave

# 255
Yokemate of Keyboards

Posts: 2794 from 2006/3/21

From: Northern Calif...

Quote:

Zylesea wrote:
All in all it shows that ppc is an even deader end than I expected.
Lets make a clear cut and go x64 ASAP.

I am not against moving to x64 at all, in fact I support it completely, but with new ARM products coming soon that offer 64bit and 4 cores at over 1GHz in speed (like the Pine64 on Kickstarter at the moment), I can't help wondering if low priced but still quite powerful solutions wouldn't be better for our community, where many are concerned about price, as well as energy usage, performance and availability.

I will be getting the Pine64+ with 2GB RAM, when it is available and think that MorphOS would be a perfect match as an OS for that product.
MorphOS - The best Next Gen Amiga choice.
»21.01.16 - 23:22

Zylesea

# 256
Yokemate of Keyboards

Posts: 2053 from 2003/6/4

Quote:

amigadave schrieb:
Quote:

Zylesea wrote:
All in all it shows that ppc is an even deader end than I expected.
Lets make a clear cut and go x64 ASAP.

I am not against moving to x64 at all, in fact I support it completely, but with new ARM products coming soon that offer 64bit and 4 cores at over 1GHz in speed (like the Pine64 on Kickstarter at the moment), I can't help wondering if low priced but still quite powerful solutions wouldn't be better for our community, where many are concerned about price, as well as energy usage, performance and availability.

I will be getting the Pine64+ with 2GB RAM, when it is available and think that MorphOS would be a perfect match as an OS for that product.

The Pine64 is (like most ultra cheap arm gadgets) using an Allwinner SoC AFAIK. Undocumented and rather half ready cooked. Have fun writing drivers for it.
Plus, 2GB RAM is too little. When making the cut, do't do it for small steps (my powerbook has 1.5 GB already), but for a huge jump (like i7 with plenty RAM etc.) just to be on the safe side for the next 10 years or more.

[ Editiert durch Zylesea 22.01.2016 - 01:31 ]
--
http://via.bckrs.de

Whenever you're sad just remember the world is 4.543 billion years old and you somehow managed to exist at the same time as David Bowie.
...and Matthias , my friend - RIP
»22.01.16 - 00:29

amigadave

# 257
Yokemate of Keyboards

Posts: 2794 from 2006/3/21

From: Northern Calif...

Not saying ARM instead of X64, and doing both is too much to expect from the limited development resources, just pointing out that MorphOS would be a great OS for such a cheap, small, power efficient, computing device. Maybe some day in the distant future, there will be an opportunity to have both X64 and ARM versions of MorphOS.

A $15 to $20 portable MorphOS computer (okay, it would be more like $75 to $100 with a screen, keyboard and trackpad) is really appealing.
MorphOS - The best Next Gen Amiga choice.
»22.01.16 - 01:55

pampers

# 258

Paladin of the Pegasos

Posts: 1061 from 2009/2/26

From: Tczew, Poland

Updated results.

AmigaMark are under the same links, updated already.

dnetc:

Code:


[Jan 21 17:18:21 UTC] Automatic processor type detection did not
                      recognize the processor (tag: "MOS:0x8024")
[Jan 21 17:18:21 UTC] OGR-NG: using core #0 (KOGE 3.1 Scalar).
[Jan 21 17:18:40 UTC] OGR-NG: Benchmark for core #0 (KOGE 3.1 Scalar)
                      0.00:00:16.37 [20,136,464 nodes/sec]
[Jan 21 17:18:40 UTC] OGR-NG benchmark summary :
                      Default core : #-1 (undefined) 0 nodes/sec
                      Fastest core : #0 (KOGE 3.1 Scalar) 20,136,464 nodes/sec
[Jan 21 17:18:40 UTC] RC5-72: using core #0 (MH 2-pipe).
[Jan 21 17:18:59 UTC] RC5-72: Benchmark for core #0 (MH 2-pipe)
                      0.00:00:16.32 [5,378,031 keys/sec]
[Jan 21 17:18:59 UTC] RC5-72: using core #1 (KKS 2-pipe).
[Jan 21 17:19:17 UTC] RC5-72: Benchmark for core #1 (KKS 2-pipe)
                      0.00:00:16.08 [5,476,368 keys/sec]
[Jan 21 17:19:17 UTC] RC5-72: using core #2 (KKS 604e).
[Jan 21 17:19:36 UTC] RC5-72: Benchmark for core #2 (KKS 604e)
                      0.00:00:16.07 [5,590,276 keys/sec]
[Jan 21 17:19:37 UTC] RC5-72: using core #5 (MH 1-pipe).
[Jan 21 17:19:55 UTC] RC5-72: Benchmark for core #5 (MH 1-pipe)
                      0.00:00:16.70 [5,258,979 keys/sec]
[Jan 21 17:19:56 UTC] RC5-72: using core #6 (MH 1-pipe 604e).
[Jan 21 17:20:15 UTC] RC5-72: Benchmark for core #6 (MH 1-pipe 604e)
                      0.00:00:16.08 [5,160,960 keys/sec]
[Jan 21 17:20:15 UTC] RC5-72 benchmark summary :
                      Default core : #-1 (undefined) 0 keys/sec
                      Fastest core : #2 (KKS 604e) 5,590,276 keys/sec

Stream:

Code:


-------------------------------------------------------------
STREAM version $Revision: 5.10 $
-------------------------------------------------------------
This system uses 8 bytes per array element.
-------------------------------------------------------------
Array size = 10000000 (elements), Offset = 0 (elements)
Memory per array = 76.3 MiB (= 0.1 GiB).
Total memory required = 228.9 MiB (= 0.2 GiB).
Each kernel will be executed 10 times.
 The *best* time for each kernel (excluding the first iteration)
 will be used to compute the reported bandwidth.
-------------------------------------------------------------
Your clock granularity/precision appears to be 1 microseconds.
Each test below will take on the order of 134446 microseconds.
   (= 134446 clock ticks)
Increase the size of the arrays if this shows that
you are not getting at least 20 clock ticks per test.
-------------------------------------------------------------
WARNING -- The above is only a rough guideline.
For best results, please be sure you know the
precision of your system timer.
-------------------------------------------------------------
Function    Best Rate MB/s  Avg time     Min time     Max time
Copy:            1148.2     0.140391     0.139346     0.142811
Scale:           1210.7     0.133642     0.132151     0.135742
Add:             1650.2     0.146227     0.145436     0.148499
Triad:           1654.9     0.145661     0.145028     0.147620
-------------------------------------------------------------
Solution Validates: avg error less than 1.000000e-13 on all three arrays
-------------------------------------------------------------

nbench

Code:


BYTEmark* Native Mode Benchmark ver. 2 (10/95)
Index-split by Andrew D. Balsa (11/97)
Linux/Unix* port by Uwe F. Mayer (12/96,11/97)

TEST                : Iterations/sec.  : Old Index   : New Index
                    :                  : Pentium 90* : AMD K6/233*
--------------------:------------------:-------------:------------
NUMERIC SORT        :          657.77  :      16.87  :       5.54
STRING SORT         :          79.605  :      35.57  :       5.51
BITFIELD            :      2.1514e+08  :      36.90  :       7.71
FP EMULATION        :          72.453  :      34.77  :       8.02
FOURIER             :           30404  :      34.58  :      19.42
ASSIGNMENT          :          14.892  :      56.67  :      14.70
IDEA                :          3865.7  :      59.12  :      17.55
HUFFMAN             :          1107.1  :      30.70  :       9.80
NEURAL NET          :          16.248  :      26.10  :      10.98
LU DECOMPOSITION    :          503.67  :      26.09  :      18.84
==========================ORIGINAL BYTEMARK RESULTS==========================
INTEGER INDEX       : 36.054
FLOATING-POINT INDEX: 28.663
Baseline (MSDOS*)   : Pentium* 90, 256 KB L2-cache, Watcom* compiler 10.0
==============================LINUX DATA BELOW===============================
CPU                 :
L2 Cache            :
OS                  :
C compiler          : gcc version 2.95.3 20020615 (experimental/emm)
libc                :
MEMORY INDEX        : 8.544
INTEGER INDEX       : 9.352
FLOATING-POINT INDEX: 15.897
Baseline (LINUX)    : AMD K6/233*, 512 KB L2-cache, gcc 2.7.2.3, libc-5.4.38
* Trademarks are property of their respective holder.

Monolith doesn't work for me at the moment so cannot post results.

MorphOS 3.x

»22.01.16 - 09:12

Andreas_Wolf

# 259
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> Updated results. [...]

Updated comparison:

dnetc

1.32 | 0.99 : KOGE 3.1 Scalar
0.94 | 0.70 : MH 2-pipe
0.97 | 0.73 : KKS 2-pipe
0.97 | 0.73 : KKS 604e
1.00 | 0.75 : MH 1-pipe
0.99 | 0.74 : MH 1-pipe 604e

AmigaMARK CPU

1.34 | 1.00 : BogoMIPS ppc-assembler inline
1.27 | 0.96 : Dhrystones
1.43 | 1.07 : 40th Fibonacci number
1.18 | 0.88 : FPU query [Double Precision] - Al Aburto
1.32 | 0.99 : LibJPEG - libjpeg [v6b]
1.17 | 0.88 : Mars chiper
1.50 | 1.13 : MD5 checksuming (RFC 1321) L. Peter Deutsch
1.15 | 0.87 : MP3 -> CDDA [mpega.library]
1.34 | 1.00 : Serpent chiper
1.37 | 1.03 : ZLib functions [v1.1.4]
1.17 | 0.88 : TOTAL CPU

AmigaMARK Memory

1.33 | 1.00 : Read CPU-Cache
2.24 | 1.68 : Read FAST byte [8]
2.13 | 1.60 : Read FAST word [16]
2.10 | 1.58 : Read FAST long [32]
1.96 | 1.47 : Write FAST byte [8]
2.14 | 1.61 : Write FAST word [16]
2.16 | 1.62 : Write FAST long [32]
1.14 | 0.85 : Copy FAST 2 FAST
1.71 | 1.28 : Allocate Memory FAST
1.39 | 1.04 : Initialize Memory FAST
1.68 | 1.26 : TOTAL MEM

nbench

1.14 | 0.85 : NUMERIC SORT
1.91 | 1.43 : STRING SORT
1.00 | 0.75 : BITFIELD
1.06 | 0.80 : FP EMULATION
1.31 | 0.98 : FOURIER
1.05 | 0.79 : ASSIGNMENT
1.05 | 0.79 : IDEA
1.04 | 0.78 : HUFFMAN
1.14 | 0.86 : NEURAL NET
1.08 | 0.81 : LU DECOMPOSITION
1.15 | 0.87 : INTEGER INDEX
1.18 | 0.88 : FLOATING-POINT INDEX
1.27 | 0.95 : MEMORY INDEX
1.08 | 0.81 : INTEGER INDEX

stream

2.35 | 1.76 : Copy
2.56 | 1.92 : Scale
2.98 | 2.23 : Add
2.94 | 2.20 : Triad
»22.01.16 - 11:25

Jim

# 260
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Interesting figures Andreas,
Most seem to point to an interesting parity between your G4 and the P5020 in the X5000 (once frequency differences are considered).
Occasionally the X5000 pulls ahead, but not as often as I would have expected.

So, its a pretty good guess that a single thread benchmark of a T1042 based system would be quite close to your Mac Mini.

Hmm...so, would I pay an arm and a leg for a P5020 based based system when a T10XX based board the would perform almost 3/4s as well (basically, would I pay for a system that is only about 1/3rd faster than a Mac Mini)?
I don't know, I the idea of a new system is appealing, especially if its logo'd as an AmigaOne.

I might have to wait for the P5040 based variant.

But even then, I suspect the PowerMac G5 will have an advantage over the A-eon boards.
Even if SMP were supported the G5 would probably still come out on top.

And while a T2080 1.8 GHz based board might beat both of those (with SMP) in synthetic benchmarks, its additional threads would probably not provide as much of a boost in real world use as as they might in theory.

We should get to see AMD's Zen core this year.
And Intel's hardware is performing nicely.
An ISA shift could provide a 2-4 times performance boost.

I LIKE PPCs, but with under performing, over priced hardware as our only recourse, maybe Zylesea is right.
"Never attribute to malice what can more readily explained by incompetence"
»23.01.16 - 22:36

amigadave

# 261
Yokemate of Keyboards

Posts: 2794 from 2006/3/21

From: Northern Calif...

Has anyone evaluated the performance difference between the X5000 and X1000 yet? I'm too old and too busy with other work to try to figure out what those figures mean, and then try to find the same test results for my X1000 to see how much faster the X5000 is. If it is only slightly faster than the 1.5GHz G4 in most benchmarks (other than memory read/write benchmark results), then it must not be much better than the X1000.

Edit: Of course it does have the advantage that it will run MorphOS, as the X1000 probably never will be able to do that.

[ Edited by amigadave 23.01.2016 - 15:01 ]
MorphOS - The best Next Gen Amiga choice.
»23.01.16 - 23:00

Andreas_Wolf

# 262
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> would I pay an arm and a leg for a P5020 based based system when
> a T10XX based board the would perform almost 3/4s as well

This may depend on the price of such T1-based system, I reckon.

> Even if SMP were supported the G5 would probably still come out on top.

This would depend on the specific PowerMac G5 model and the scalability of the task. With a task scaling well to four cores, four 2.2 GHz e5500 cores would be slower than four 2.5 GHz PPC970MP cores but faster than two 2.7 GHz PPC970FX cores.
»24.01.16 - 17:41

Andreas_Wolf

# 263
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> Has anyone evaluated the performance difference between the X5000 and X1000 yet?

Probably yes, but OS4 betatesters on X5000 are bound by NDA so aren't allowed to publish any figures. There might be Linux benchmark comparisons between X5000 and X1000 out there, though.
»24.01.16 - 18:04

Jim

# 264
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Quote:

Andreas_Wolf wrote:
> would I pay an arm and a leg for a P5020 based based system when
> a T10XX based board the would perform almost 3/4s as well

This may depend on the price of such T1-based system, I reckon.

> Even if SMP were supported the G5 would probably still come out on top.

This would depend on the specific PowerMac G5 model and the scalability of the task. With a task scaling well to four cores, four 2.2 GHz e5500 cores would be slower than four 2.5 GHz PPC970MP cores but faster than two 2.7 GHz PPC970FX cores.

So 2.5 dual, 2.7 dual and 2.5 Quad systems would probably beat the P5020 based model and might also beat the P5040 model if SMP is not utilized.
And, if SMP is somehow supported, then the only Mac G5 system that would lead the P5040 model is a Quad 2.5.

Well, the X5000 P5040 model doesn't look like a bad choice, except we are not likely to see SMP support under PPC MorphOS.
"Never attribute to malice what can more readily explained by incompetence"
»24.01.16 - 20:22

Andreas_Wolf

# 265
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> 2.5 dual, 2.7 dual and 2.5 Quad systems would probably beat the P5020 based
> model and might also beat the P5040 model if SMP is not utilized.

...and 2.3 dual systems probably as well, and maybe even 2.0 dual systems.
»24.01.16 - 23:19

Acill

# 266
Paladin of the Pegasos

Posts: 1914 from 2003/10/19

From: Port Hueneme, Ca.

Quote:

Andreas_Wolf wrote:
> 2.5 dual, 2.7 dual and 2.5 Quad systems would probably beat the P5020 based
> model and might also beat the P5040 model if SMP is not utilized.

...and 2.3 dual systems probably as well, and maybe even 2.0 dual systems.

We will sure as hell beat them in price for a G5 system over what a X5000 will run! I cant see any reason to spend that kind of money when you can get a fantastic Mac system. If they want to sell those things in significant numbers the price needs to come way down. It cant be even slightly near the X1000 prices!

yet again they did sell out of those, but know knows. The "Amiga" market is nuts.
Powermac Dual 2.0 GHZ G5 PCI-X (Registration #1894)
Powerbook 1.67GHZ
Powermac Dual 2.0 GHZ G5 PCIE (Registration #6130)
A4000T CSPPC, Mediator
Need Repairs, upgrades or a recap in the USA? Visit my website at http://www.acill.com
»25.01.16 - 05:56

pampers

# 267
Paladin of the Pegasos

Posts: 1061 from 2009/2/26

From: Tczew, Poland

Quote:

I cant see any reason to spend that kind of money when you can get a fantastic Mac system.

Noise, weight and size are three main reasons for me ;)
MorphOS 3.x
»25.01.16 - 10:14

Andreas_Wolf

# 268
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> We will sure as hell beat them [...]

If MorphOS runs on both Apple PowerMac G5 and A-Eon AmigaOne X5000/CyrusPlus, who is "we" and who is "them"? :-)
»25.01.16 - 11:30

Zylesea

# 269
Yokemate of Keyboards

Posts: 2053 from 2003/6/4

Quote:

pampers schrieb:
Quote:

I cant see any reason to spend that kind of money when you can get a fantastic Mac system.

Noise, weight and size are three main reasons for me ;)

Add energy uptake for me.
Nonetheless these 4 things are probably not worth about 2000 EUR for me.
--
http://via.bckrs.de

Whenever you're sad just remember the world is 4.543 billion years old and you somehow managed to exist at the same time as David Bowie.
...and Matthias , my friend - RIP
»25.01.16 - 13:38

AltiVeced

# 270
Caterpillar

Posts: 31 from 2011/10/25

I don't want to say anything, but ... it isn't that easy to compare CPUs just the way like this.
Have you all ever considered that you have to optimize the code for a new CPU?
In the days the Pentium IV 1.4GHz pops up, it was as fast as a Pentium III 1GHz.
The same with the G5s ... at the early days a G4 2GHz was "nearly" as fast as a G5 2GHz, despite higher memory bandwidth etc.. And the G4 (upgrade cards) at 2GHz were only overclocked 1.7GHz. The same with the 2.7GHz G5, they were overclocked 2.5GHz ones.

All in all, if you have a new CPU core, you have to optimized the code for it.
An e600 core isn't the same as an e5500 or e6500 core.

The problem is, I don't see the developer (Morph or AOS) to squeeze the maximum out of this new CPUs.
Do you really think, FreeScale is that silly? To develop a new core (approx. ten years later) and the new one is slower than the old one?
»25.01.16 - 15:14

takemehomegrandma

# 271
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

Quote:

AltiVeced wrote:

Have you all ever considered that you have to optimize the code for a new CPU?

What makes you suggest that the code would be particulary "un-optimized"?

Quote:

In the days the Pentium IV 1.4GHz pops up, it was as fast as a Pentium III 1GHz.

Those were AFAIK two different microarchitectures, and while the "Netburst" architecture might have had its upsides, it also had certain issues. It's telling that Intel went back to an evolved version of Pentium III's "P6" architecture (the Pentium M) for their "Core" CPU's that came later.

Quote:

The same with the G5s ... at the early days a G4 2GHz was "nearly" as fast as a G5 2GHz, despite higher memory bandwidth etc..

That's how the G5 wins over G4, by clock!

Quote:

All in all, if you have a new CPU core, you have to optimized the code for it.
An e600 core isn't the same as an e5500 or e6500 core.

The problem is, I don't see the developer (Morph or AOS) to squeeze the maximum out of this new CPUs.

You don't? Exactly what are you suggesting then?

Quote:

Do you really think, FreeScale is that silly? To develop a new core (approx. ten years later) and the new one is slower than the old one?

They are squeezing out the last dollars of their IP by introducing SoC chips packed with new features they feel can be of value to their particular target markets (which is *NOT* desktop).

The PPC lives on legacy. For new developments in all markets previously covered by PPC, there are much better ARM offerings.
MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»25.01.16 - 16:12

ASiegel

# 272
Posts: 1370 from 2003/2/15

From: Central Europe

Quote:

AltiVeced wrote:
All in all, if you have a new CPU core, you have to optimized the code for it. An e600 core isn't the same as an e5500 or e6500 core.

Newer does not automatically equal "faster", however, especially not if the processor was not designed with maximum performance in mind in the first place.

Quote:

Do you really think, FreeScale is that silly? To develop a new core (approx. ten years later) and the new one is slower than the old one?

This is not about being silly but about target applications. The G4 and G5 CPUs used by Apple were specifically designed to be used in desktop computers. For this particular use case, there was a lot more leeway regarding energy consumption and thermal management than there would be for many embedded and industrial applications.

The P5020 processor has always been marketed for networking applications and was designed to use a mere 30 Watt. Networking devices tend to be constantly powered-on so power consumption is a much bigger factor than it would be for desktop computers that, even when used for business, would rarely be used for more than 8 hours a day on average.

As others have pointed out, Altivec is one part of the puzzle when you compare the performance of various MorphOS-compatible systems. Clearly, Freescale did not think it made sense to include it in a processor for networking devices, which may have been a sensible decision for that specific target market. In the context of "unintended uses" such as desktop computing, it is clearly a disadvantage and I think it is fair to point that out along with any other limitations.
»25.01.16 - 16:18

Andreas_Wolf

# 273
Yokemate of Keyboards

Posts: 12078 from 2003/5/22

From: Germany

> you have to optimize the code for a new CPU [...]. [...] if you have a new CPU
> core, you have to optimized the code for it. [...] The problem is, I don't see
> the developer (Morph or AOS) to squeeze the maximum out of this new CPUs.

With high-level programming languages it's rater the compiler which optimizes the scalar code for the respective microarchitecture if you provide the proper compiler switch(es). And indeed, because of the variety of microarchitectures, generation of optimized code is an issue also on MorphOS and OS4 as I described some time back:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7675&start=564

> An e600 core isn't the same as an e5500 or e6500 core.

Exactly. The e6500 and e5500 cores stem from the e500v1 core (via e500v2 and e500mc), which was conceived around 2001, i.e. back when G4/e600 was still going strong. So it was a parallel development for different markets with different demands than G4/e600 and never meant as e600 successor (also indicated by the smaller number).

> Do you really think, FreeScale is that silly? To develop a new core (approx. ten years later)
> and the new one is slower than the old one?

As a general note (i.e. not meant for the e6500/e5500 vs. e600 case specifically) semiconductor companies develop/release new cores that are slower than old cores of theirs all the time, especially if the new core is intended for different markets with different demands.
»25.01.16 - 18:05

pampers

# 274
Paladin of the Pegasos

Posts: 1061 from 2009/2/26

From: Tczew, Poland

Quote:

Zylesea wrote:
Add energy uptake for me.
Nonetheless these 4 things are probably not worth about 2000 EUR for me.

I wouldn't spend 2000 euro neither :) I wonder what final price will be.
MorphOS 3.x
»25.01.16 - 18:26

takemehomegrandma

# 275
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

Quote:

pampers wrote:
Quote:

Zylesea wrote:
Add energy uptake for me.
Nonetheless these 4 things are probably not worth about 2000 EUR for me.

I wouldn't spend 2000 euro neither :) I wonder what final price will be.

They (Aeon) have said the AmigaOne X5000 will have an entry price tag of ~€2,220 (for Europeans paying the 20% UK VAT).
MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»25.01.16 - 18:33