MorphZone

ARM for the future?

Andreas_Wolf

# 345
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

> Andre, don't you work on AROS as well as MorphOS?

You can read about his involvement with AROS in his posting history on aros-exec.org:

http://aros-exec.org/modules/newbb/viewpost.php?uid=1147
»15.10.12 - 08:49

Jim

# 346
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Thanks Andreas,
I can't believe he can afford to devote this much time.
Inspiring.

Fabien Coeurjoly (helped me getting my Comcast e-mail via OWB), Frank Mariak and Mark Olsen (developing R300 3D drivers), André Siegel (and his work on behalf of both MorphOS and AROS), and Harry Sintonen (who I have exchanged messageon the Amiga.org board) - just a few of the developers that have really impressed me.

Its very uncommon to be allowed this much info and access to the developers you're relying on.
"Never attribute to malice what can more readily explained by incompetence"
»15.10.12 - 19:18

minator

# 347
Order of the Butterfly

Posts: 365 from 2003/3/28

This is just getting silly, a quad core USB computer!

http://liliputing.com/2012/10/hiapad-hi-802-pc-on-a-stick-with-freescale-quad-core-cpu.html

[ Edited by minator 17.10.2012 - 22:56 ]
»17.10.12 - 22:55

Jim

# 348
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

OOO, I like that!
But I wonder what the clock speed is.

Hey Andreas, which GPU does this Freescale component use?

But I'm probably going to buy a DroidX as it probably has a faster cpu.

[ Edited by Jim 18.10.2012 - 06:55 ]
"Never attribute to malice what can more readily explained by incompetence"
»18.10.12 - 04:13

Andreas_Wolf

# 349
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

> I wonder what the clock speed is.

1.2 GHz (which is the max for the i.MX6Q) or below ;-)

> Hey Andreas, which GPU does this Freescale component use?

Already mentioned in this thread 1.5 years ago:

https://morph.zone/modules/newbb_plus/viewtopic.php?forum=3&topic_id=7675&start=162

From http://www.freescale.com/webapp/sps/site/prod_summary.jsp?code=i.MX6Q can be seen:

- GPU 3D: Vivante GC2000 (200Mtri/s 1000Mpxl/s, OpenGL ES 2.0 & Halti, CL EP)
- GPU 2D (Vector Graphics): Vivante GC355 (300Mpxl/s, OpenVG 1.1)
- GPU 2D (Composition): Vivante GC320 (600Mpxl/s, BLIT)

More info:
http://en.wikipedia.org/wiki/Vivante_Corporation
http://www.vivantecorp.com/Product_Brief.pdf
http://www.vivantecorp.com/Vivante_GC320_Technical_Reference_Manual_V1.0_A.pdf

> DroidX [...] probably has a faster cpu.

Yes, 1.4 GHz of the Exynos 4412 in the ODROID-X is faster than 1.2 GHz or below of the i.MX6Q.
»18.10.12 - 08:47

Andreas_Wolf

# 350
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

Update:

> this is the new revised list: [...]

New list of DMIPS per MHz and core figures for ARM cores, taking the Swift core of the Apple A6 SoC into account (only with an estimation unfortunately):

ARM Cortex-A7: 1.9
ARM Cortex-A8: 2.0
Qualcomm Scorpion: 2.1
Marvell Sheeva PJ4: 2.4
ARM Cortex-A9: 2.5
Marvell Sheeva PJ4B: 2.6
Qualcomm Krait: 3.3
Apple Swift: 3.3...3.5 (estimated)
ARM Cortex-A15: 3.5
»18.10.12 - 10:14

minator

# 351
Order of the Butterfly

Posts: 365 from 2003/3/28

Quote:

ARM Cortex-A15: 3.5

Talking of which...

http://www.theverge.com/2012/10/18/3521492/google-new-samsung-chromebook-249-monday
»18.10.12 - 20:43

Andreas_Wolf

# 352
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

Update:

> I think Applied Micro (X-Gene) or even Cavium (Project Thunder) might
> arrive in high-end ARM land before nVidia (Project Denver/Boulder).

Calxeda revealed as new ARMv8 contender with "Lago":

http://www.calxeda.com/calxeda-lays-out-a-vision-for-the-hyper-efficient-datacenter/

Edit: Seems like Calxeda won't design its own ARMv8 core but will use a ready-made core from ARM Ltd. instead:

"Announced licensees of the new processor series include AMD, Broadcom, Calxeda, HiSilicon, Samsung and STMicroelectronics."
http://www.arm.com/about/newsroom/arm-launches-cortex-a50-series-the-worlds-most-energy-efficient-64-bit-processors.php

[ Edited by Andreas_Wolf 30.10.2012 - 23:44 ]
»18.10.12 - 23:03

Andreas_Wolf

# 353
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

>> ARM Cortex-A15: 3.5

> Talking of which...
> http://www.theverge.com/2012/10/18/3521492/google-new-samsung-chromebook-249-monday

Nice :-) Samsung made its promise true and beat TI.
»18.10.12 - 23:07

Jim

# 354
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Hits the shelf on Monday?
OMG! Guess I need to figure out what $250 expense has to be foregone.
"Never attribute to malice what can more readily explained by incompetence"
»19.10.12 - 00:49

takemehomegrandma

# 355
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

minator,
Quote:

Talking of which...

http://www.theverge.com/2012/10/18/3521492/google-new-samsung-chromebook-249-monday

Well, being the first(?) Cortex-A15 in a consumer product is kind of cool, and so is the price, but the display seems a bit tacky judging from the article (a poor display is usually a deal-breaker IMHO, no matter the price), and it's a bit worrying if it can't properly play HD videos on true HD displays? Maybe that CPU was really tailored for a future Galaxy S IV smartphone, and less suitable in a device like this? And the lack of both Ethernet and 3G/4G wireless makes it even less usable, and puts it even further down my wishlist...
MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»19.10.12 - 07:00

Andreas_Wolf

# 356
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

> lack of [...] 3G/4G wireless

http://www.samsung.com/us/computer/chrome-os-devices/XE303C12-H01US-specs
»19.10.12 - 14:06

takemehomegrandma

# 357
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

Indeed, but then it's $330 and with a plan with a phone company I don't have access to where I live.

I'll just keep looking, better deals are bound to happen a bit further down the road...
MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»19.10.12 - 14:24

Andreas_Wolf

# 358
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

> it's [...] with a plan with a phone company I don't have
> access to where I live.

Yes, obviously, as that's the US release, which is the initial one. Releases for other parts of the world will follow I guess.
I just wanted to give the correct information that there is a version with hardware for 3G connectivity included, rather than imply that this version was currently suited for where you live.
»19.10.12 - 14:29

Jim

# 359
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

Since all I want is wifi (for the casino I work in and at home) I couldn't care less about the 3G or 4G features.
Gotta have one.
And then a hosted version of AROS.
"Never attribute to malice what can more readily explained by incompetence"
»19.10.12 - 19:56

minator

# 360
Order of the Butterfly

Posts: 365 from 2003/3/28

Quote:

and it's a bit worrying if it can't properly play HD videos on true HD displays? Maybe that CPU was really tailored for a future Galaxy S IV smartphone,

The previous chips could do it so I'm guessing it's a software problem.
»20.10.12 - 20:27

takemehomegrandma

# 361
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

Quote:

The previous chips could do it so I'm guessing it's a software problem.

Possible, or it's an issue of premature/rushed HW...
MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»20.10.12 - 20:34

Andreas_Wolf

# 362
Yokemate of Keyboards

Posts: 12085 from 2003/5/22

From: Germany

Update:

> I doubt the A6 will clock higher than 1.2 GHz in the iPhone.
> Maybe later in the next iPad, as the tablet form factor
> allows for a bit more power consumption.

As we know, the A6 chip in the new iPhone clocks at 1.3 GHz. The A6X chip in the new iPad announced yesterday is said to run at 1.5 GHz and thus faster than A6, as expected:

http://arstechnica.com/apple/2012/10/deducing-details-about-apples-a6x-processor/
»24.10.12 - 12:54

minator

# 363
Order of the Butterfly

Posts: 365 from 2003/3/28

Quote:

Possible, or it's an issue of premature/rushed HW...

Rushing a 32nm SoC would be a very bad idea given the exorbitant cost of even taping it out.
»25.10.12 - 00:43

takemehomegrandma

# 364
Yokemate of Keyboards

Posts: 2720 from 2003/2/24

@minator

As far as I know, some problems is only/can only be spotted *after* you have it in real silicon, and AFAIK it's not very uncommon that you have to taping out a few revisions before reaching a level that can be judged good enough for end-users. For example: Freescale did at least 3 tapeouts of the i.MX515, and Genesi used the TO2 in early board designs/targeted at early developers. Only the TO3 was used in the final, end-user products:

Quote:

There exist three revisions of the Smarttop, using different Tape-Out (TO) revisions of the i.MX515;

l Revision 1.0 - a limited release developer edition, i.MX515 TO2. 4GB SSD. Internal MicroSD. Board Only.
l Revision 1.1 - Project and limited sale. Utilizing i.MX515 TO2. 4GB SSD. Internal MicroSD. Black case.
l Revision 1.2 - Production version. Utilizing i.MX515 TO3. 8GB SSD. Black case.

In general Genesi refers to the 1.1 board as TO2 and the 1.2 board as TO3. The revision 1.0 board is very rare and Genesi offers only limited support for this model.

The i.MX515 TO2 has a known errata which causes the Cortex-A8 NEON vector unit to misbehave, and as such the Linux kernel will not report it as supporting NEON code, in order to preserve system stability. This errata was fixed in TO3.

This is what I meant with "being rushed"; maybe the chip hasn't reached its final tapeout revision yet, but Samsung/Google is eager to push a first version of their Cortex-A15 smarttop to the market? Some things can be worked around in drivers, other things can't and will need an updated chip. I guess we'll see.

MorphOS is Amiga done right!
MorphOS NG will be AROS done right!
»25.10.12 - 09:29

minator

# 365
Order of the Butterfly

Posts: 365 from 2003/3/28

You can find out for yourself now with an Arndaleboard.

$250, same chip as the Chromebook.
»26.10.12 - 20:11

Jim

# 366
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

minator,
Quote:

$250, same chip as the Chromebook.

And only another $250 for the LCD screen, $160 for the SSD, $120 for the connectivity and sound boards, $60 for the camera, and $60 for the accesory package (including cables, pwr supply, and micro SD card).

$900 anyone?

I'll take the Chromebook.
"Never attribute to malice what can more readily explained by incompetence"
»26.10.12 - 20:36

minator

# 367
Order of the Butterfly

Posts: 365 from 2003/3/28

Jim,
Quote:

And only another $250 for the LCD screen, $160 for the SSD, $120 for the connectivity and sound boards, $60 for the camera, and $60 for the accesory package (including cables, pwr supply, and micro SD card).

The basic board includes Sound and I/O cards (the $120 is for different versions). I don't think you really need any of the rest as they are pretty much standard parts.

Quote:

I'll take the Chromebook.

I might get one myself, might try some OpenCL on it.

[ Edited by minator 26.10.2012 - 23:30 ]
»26.10.12 - 23:29

minator

# 368
Order of the Butterfly

Posts: 365 from 2003/3/28

Quote:

I might get one myself, might try some OpenCL on it.

OTOH if you were say developing something, I don't know, say, an OS. the Arndale board might be a better bet.

There's certainly a lot of information on that site, including fairly comprehensive information on the processor.
»27.10.12 - 14:14

Jim

# 369
Yokemate of Keyboards

Posts: 4977 from 2009/1/28

From: Delaware, USA

minator,
Quote:

OTOH if you were say developing something, I don't know, say, an OS. the Arndale board might be a better bet.

Yes, say as a basis for a Ubuntu system, the board probably would be the better choice.
"Never attribute to malice what can more readily explained by incompetence"
»28.10.12 - 02:34