New ppc board by Acube/A-Eon: A1222 "Tabor"

[Iggy]

No official price for Tabor has been announced.
Figure quoted is not correct.


http://amigaworld.net/modules/newbb/viewtopic.php?mode=viewtopic&topic_id=40622&forum=2&start=300&viewmode=flat&order=0#770615

'

AND, with that in mind, I've buried my hatchet (and, no, not in this guy's skull).
IF priced in line with its value...it could start a trend that leads to future affordable hardware.
So...I'm not buying one, BUT I could see a market for it.

[Iggy]

True, C does lack a fixed floating point type. That doesn't mean that using a float is in any way a good idea though. Just that the consequences doesn't trump the laziness of implementing with fixed point maths. You can also stir paint with a screwdriver.

Weird analogy.
"That doesn't mean that using a float is in any way a good idea though."

Seriously?

[Iggy]

...However there are situations where software does require the use of an FPU (both 68k & PPC) so new hardware should support them.

Your last statement seems to run counter to the "That doesn't mean that using a float is in any way a good idea though" argument.

[Iggy]

Yeah, cos what would Hyperion know about that

Not that much actually, since they subbed the OS out to the Friedens.

And I am willing to give the brothers more credit than many, as they have gotten OS4 this far.

But we now know they are expecting to emulate unsupported fpu instructions.
Calling those illegal ops traps 'transparent' isn't exactly accurate nor is the claim that the impact will not exist.
And the OS will have to implement the emulation code, BUT its not nearly as bad as I may have made out originally.

However...you guys can consider whether or not you want to buy it.
If I buy anything its still going to be an X5000 with its e5500 cored processors.

[Iggy]

one news... despite different rumours AmigaOS is still not running on Tabor

FPU emulation is slow and not tested. They have plans for a better one later.

Well that wasn't completely unexpected, otherwise they could have shown it running at AmiWest.

It DOES take time to do the porting work.

We will have to wait and see how this compares to the SAM460.

But remember, even though this only has a 100MHz advantage, it could turn out that even with the disadvantage of having to trap and emulate fpu instructions that the Freescale cpu is still more powerful than the Applied Micro cpu used in the SAM.

Yes, I still maintain the e500v2 is not the best choice, but it may not be the worst either.

[Iggy]

The P1022 core should be about 30% faster than the 460ex in single core integer performance . The Mplayer decode benchmarks single core results under Linux are Tabor (SPE) 214s . Sam460ex 469s .
By the way Trever did confirm in his Amiwest 2015 presentation the the T series cpus were not available when the Tabor design was started.

Then Sir, I owe you an apology for being a rather obnoxious, aggressive  and somewhat self centered a-hole.

I rather suspected that the e500 core would outperform an Applied Micro core.
So it is a move forward, especially in consideration of the fact that it is a dual core cpu.

That 30% will more than cover any deficit that fpu emulation will cost.

Further, Applied Micro has essentially abandoned further PPC development in favor of ARM.

While Freescale is also moving in this direction, they are still planning a few new cpus.
And their existing product line is stronger.

[Iggy]

30% faster integer performance will make some applications feel snappier while others with heavy floating point use (like Blender) will likely run at a fraction of the speed of a PPC with standard FPU. It's kind of like hiring a motivated worker who is missing one arm. He may be a little faster than average at some jobs but is going to have major trouble doing some work.

Well, one vote for 'poor decision' but not a lethal one.

Is there an NG port of Blender?

I have two different dual cpu systems (one a dual quad Xeon the other dual hex core Opteron) both with 32GB of memory for that monster.

I can't picture it working well on a single core system with memory limitations.

And PPCs won't die out for awhile.

Current e6500 based cpus could extend the life of the platform for several years.

[Iggy]

Yet many masochists *do* choose to run it on AmigaONE branded hardware. ;-)

Nicholas, I am a PPC fanatic, but even if I get a chance to buy an X5000/040 next year, I won't be running something like Blender on it (even if it is quad core, that feature isn't supported by NG OS' yet).

I have X64 hardware that is cheaper and more powerful set up specifically for that.
Frankly, I wasn't even aware that there was a PPC NG port.

[Iggy]

In modern computing code density and code size have very little to do with memory requirements. PPC code requires 50% more space (versus 68k code) but we are still talking few hundred kilobytes.

It is the data that counts.

True, for instance we take 16 , 24, and 32 bit color for granted, but the amount of storage needed to support these modes is vastly larger than a 4, 16, or even 256 color mode.

As we support greater features, the size of the data needed to be handled has also grown, but in some areas its almost a geometric growth.

[Iggy]

I could do some constructive Amiga work but the Amiga situation takes away my motivation.

If you are not up to challenges presented by hardware or software limitations, then you probably shouldn't code at all.

There have always been difficulties to overcome in writing code.

And advocating an FPGA 68K while dismissing a PPC (in comparison to an X64 cpu) is silly.
No FPGA project available or in development comes close to a PPC's level of performance.

And at comparable clock speeds, X64 does not have that great an advantage over PPCs.

Then again, I am off enough to wish that MIPS had continued to receive as much support as the PPC (or better yet, ARM).

RISC still offers advantages over CISC, and at their core many CISC cpus use RISC architecture.

[Iggy]

@JJ

nope. i've used it as well as andy's port for AOS4.

-- eliyahu

Wow, and I built X64 hardware just to run that.

Then again, a single core PPC system, compared to the recommended hardware specs?

[Iggy]

...this way i could do it on an amiga. not the smartest way certainly, but very geeky. sort of one of those 'because i can' things.

-- eliyahu

I DO get that.
And even on an X64, Blender still has a few issues.
I wish it supported video cards that are common to CAD design.
Quadro cards, if they were fully supported, would be a nice option.

Even a low end K600 does some amazing things when its fully supported, and a K2000 is outstanding in CAD software.

BTW - Where can I find the MorphOS port of Blender?
It makes sense to install it, after all I already have it on a couple (but not all) of my X64 computers.

[Iggy]

you can grab it here. you'll also want to grab the latest release of python for MOS while you're at it.

-- eliyahu

That link appears broken as it only takes you to Yomgui's primary web page.
Any idea how to find the actual software?

[Iggy]

@Iggy

whoops. try morph-files instead.

-- eliyahu

VERY cool!
Thanks.

BTW - I just noticed you were in the US, and on the East coast.

[Iggy]

... Bad: Trapping all the standard PPC FPU instructions and emulation of the standard FPU has major overhead for each trapped instruction but recompiling is not needed...

-
Uh oh.

[Iggy]

With Linux Mplayer SPE binary yes.
regular Linux Mplayer video not working with emulation under powerpc32 .

OK, its a start.
Maybe Hyperion needs your input as recompilation seems to be the best course with this cpu.
Recompiling what can be, and resorting to trapping/emulation as only a secondary method for execution.