Quote:

You missed the Cortex-A7

> You missed the Cortex-A7 ;-)

I surely didn't miss ARM Ltd's today's announcement of the Cortex-A7 core :-) The reason it's not been on my list yet simply is that I hadn't read about the DMIPS figure for it. Doing so now I can see that it's as low as 1.9 DMIPS per MHz and core (and the figure for the Krait core is in that article as well). So this is the new revised list:

ARM Cortex-A7: 1.9
ARM Cortex-A8: 2.0
Qualcomm Scorpion: 2.1
Marvell Sheeva PJ4: 2.4
ARM Cortex-A9: 2.5
Qualcomm Krait: 3.3
ARM Cortex-A15: 3.5 (estimated)

Update:

> "T50/Tegra 5 is now known as Denver, but the x86 part has been dropped for legal reasons."
> http://semiaccurate.com/2011/04/06/nvidia-in-full-philosophical-retreat-for-tegra-3/

More on what Project Denver has/had to do with x86:

"T50 was going to be a full 64-bit x86 CPU, not ARM cored chip, but Nvidia lacked the patent licenses to make hardware that was x86 compatible. [...] Publicly, Nvidia's stance was that there was no need for any license because the company was not making x86 hardware. Technically, this is true, T50 is a software/firmware based 'code morphing' CPU like Transmeta. The ISA that users see is a software layer, not hardware, the underlying ISA can be just about anything that Nvidia's engineers feel works out best. T50 is not x86 under all the covers, nor is it ARM, it is something else totally that users will never be privy to. The idea was that this emulation of x86 in software would be more than enough to dodge any x86 patents that would stop the chip from coming to market. SemiAccurate has it on very good authority that this cunning plan would not have succeeded, and based on what the sources showed us, the chip never would have gotten to market. [...] So, where does a core go from here? That one is easy, it becomes an ARM core, or if you believe Nvidia PR, it was ARM all along. T50 was never ARM hardware based, we had originally heard it was an A15 or the follow-on part, that emulated x86, that information turned out to be wrong. T50 is its own unique ISA, and emulates the exposed ISA as embedded software. Think of it as an on chip x86 or ARM compiler to the low level instructions. So, between last fall and CES, out went x86, and in came ARM, specifically the ARM-64 core that is the follow up to the A15 chip."
http://semiaccurate.com/2011/08/05/what-is-project-denver-based-on/

Well, Transmeta reloaded then. Fine, and who developes a "Power compiler" for T50 then ?

Quote:

"The ARM Cortex™-A7 MPCore™ processor is the most efficient application processor ARM has ever developed and dramatically extends ARM’s low-power leadership in future entry level smart phones, tablets and other advanced mobile devices.
The architecure and feature set of the Cortex-A7 processor are identical to the Cortex-A15 processor, with differences in the Cortex-A7 processor's microarchitecture focused on providing optimum energy efficiency, enabling the two processors to operate in tandem in a big.LITTLE configuration to provide the ultimate combination of high-performance with ultra low power consumption.

As a standalone processor, the Cortex-A7 will enable entry level smartphones at below $100 price point in the 2013-2014 timeframe that are equivalent to a $500 high-end smarphone in 2010. These entry level smartphones will redefine connectivity and internet usage in the developing world."
http://www.arm.com/products/processors/cortex-a/cortex-a7.php

Sounds *very* interesting IMHO! This one together with the Cortex-A15 becomes the new ARM "dynamic duo"!

Quote:

Quite literally - read up on the "big.little" tech that Freescale licensed:

http://media.freescale.com/phoenix.zhtml?c=196520&p=irol-newsArticle&ID=1619038&highlight=

Quote:

So if I read this correctly, they plan on putting one Cortex-A7 core in the same physical chip as one (or more) Cortex-A15 cores, and then either of these can seamlessly be powered up/down and be "taking over the show", depending on performance needs contra power consumption?

Sounds a bit complicated, but very interesting!

> if I read this correctly, they plan on putting one Cortex-A7 core in the
> same physical chip as one (or more) Cortex-A15 cores, and then either
> of these can seamlessly be powered up/down and be "taking over the
> show", depending on performance needs contra power consumption?

Yes, that's exactly what this "big.LITTLE configuration" the quote from ARM Ltd. in your previous posting is talking about means (except that it's two Cortex-A7 cores, not one). See:

http://www.arm.com/products/processors/technologies/bigLITTLEprocessing.php
http://www.arm.com/files/downloads/big.LITTLE_Final.pdf

Adding low-power core(s) for lower overall power consumption is by the way a popular concept in ARM land:

http://www.marvell.com/company/news/pressDetail.do?releaseID=1486
http://blogs.nvidia.com/2011/09/quad-core-kal-el%E2%80%99s-stealth-fifth-core-lets-it-save-on-energy/
http://www.ti.com/ww/en/omap/omap5/omap5-OMAP5432.html
http://www.ti.com/ww/en/omap/omap5/omap5-OMAP5430.html

Quote:

It's configurable, you can have 1 - 4 A7s with 1 - 4 A15s or various combinations thereof.

Quote:

Using a smaller core to do a specific task is nothing new.
The most similar idea is Nvidia's but their system doesn't appear to be cache coherent so you have to flush the caches when switching between cores.

The big-little system is cache coherent so is a lot faster and doesn't require cache flushes. The switching can also be done at the hypervisor level so the OS doesn't even know it's happened.

The Nvidia also only uses a lower power A9 rather than the much lower power A7.


What's going to be interesting is how Intel are going to respond to this. Their super 22nm FinFET process was meant to get them down to ARM's power levels. That might happen compared with the A15 but the A7 is a complete different ball game, they don't have anything to compete with it.

>> except that it's two Cortex-A7 cores, not one

> you can have 1 - 4 A7s

I stand corrected then. Thanks for the info.

> Using a smaller core to do a specific task is nothing new.

Yes, I know that.

> The most similar idea is Nvidia's but their system doesn't appear to be
> cache coherent so you have to flush the caches when switching between
> cores. The big-little system is cache coherent so is a lot faster and doesn't
> require cache flushes. The switching can also be done at the hypervisor
> level so the OS doesn't even know it's happened.

Yes, ARM Ltd's "big.LITTLE Processing" concept is without doubt the most sophisticated one compared to the concepts currently being implemented by nVidia, TI and Marvell.

> when this guy gets so much PR with his 25$ ARM stick, maybe it would be
> worthwhile to do something similar (probably a little bit more expensive
> though) with the 5125? [...] I would join such an effort immediately.

"I [...] still have a project ongoing with an e300/400 based processor (5125)."
http://amigaworld.net/modules/newbb/viewtopic.php?topic_id=34459&forum=33&start=240#634260

Has anything happened in the last 5 months you might want to share? :-)

Quote:

There's not much to share yet, but I am working on something - though not at a high pace or with a high priority (yet). I am still open for ideas, know how, a helping hand, whatever, #?.

Definately keep us in the loop Zylesea.
Right now I'm looking at the P5010/5020 as a way of understanding how the T5s will work.

But any project based on the T5 would be complicated and expensive.

Applied Micro (aka AMCC - the company that does the CPUs in the Sam 440 and 460) have announced a new processor.

You were probably not expecting this

Though not directly relevant for the MorphOS world this is an interesting approach. A basis for rather cheap and energy efficient highly parallel systems - could work out well for Applied Micro.

> You were probably not expecting this :-D

Absolutely. This comes most unexpected. I'd have never thought someone would supersede nVidia regarding ARM64/ARMv8, and certainly not Applied Micro. And they're not even taking an ARM64 core from ARM Ltd. but implementing their very own core based on ARMv8. Much respect to them.
I'm now asking myself whether this is what Applied Micro was referring to when they one year ago had a multicore 2.5 GHz 64-bit architecture on their roadmap.

Edit:

"Applied Micro has been working with ARM Holdings for the past three years to not only come up with an ARM chip suitable for modern, cloudy servers, but to make sure that Applied Micro is the first out the door with such a 64-bit chip."
http://www.theregister.co.uk/2011/10/28/applied_micro_arm_x_gene_server_chip/

[ Edited by Andreas_Wolf 29.10.2011 - 19:51 ]

> There's not much to share yet, but I am working on something - though
> not at a high pace or with a high priority (yet). I am still open for
> ideas, know how, a helping hand, whatever, #?.

Ah okay, I can see that it's about some kind of existing "business proposal".

On my harddiskthere are several business proposals covering pretty different topics. Some of them rather draft, some others matured and detailed. But they are not generally intended for the public. In early spring I participated my first business plan competition, but haven't won. Well, next time - maybe .

> In early spring I participated my first business plan competition, but haven't won.

It wasn't this one, was it? ;-)

No . It wasn't computer related at all.
Main prob was it was too much text and too few pictures and easy slogans. I may try another competition soon.

Wow!
http://investor.appliedmicro.com/phoenix.zhtml?c=78121&p=irol-newsArticle&ID=1622781&highlight=

Hard to believe they have the resources to create this.

> http://investor.appliedmicro.com/phoenix.zhtml?c=78121&p=irol-newsArticle&ID=1622781&highlight=

Minator beat you by one day ;-)

Since they are aimming at the server market, this looks to be an expensive processor.

That would negate one of the primary advantages of ARM.

Quote:

I doubt that very much, low price is a big weapon they can use against against Intel.

> Hard to believe they have the resources to create this.

They even talk about future chips incorporating both X-Gene and PowerPC core(s):

"[...] we were one of the first companies to release a Power PC and ARM on the same die about three years ago, and that's doing really well today, so you'll start to see a very interesting mix of products as we go forward. Where you'll start to see all of our best-at-breed Power PC technology start to blend with versions of pieces of X-Gene for various applications. That will be a very, very, very important intersection point, because [...] we want to maximize the investments that we are making in all of these areas, right, so if we are going to build the world's first world class server class 64-bit core, we want to make sure that we can use that core in some form or fashion going forward along with a Power PC per our customers' request so that they can have the ability to run all their legacy code and run their new code on the ARM."
http://www.sec.gov/Archives/edgar/data/711065/000119312511300076/d253150dex992.htm

Btw, does anybody know which Applied Micro chip had "a Power PC and ARM on the same die about three years ago"? I'm well aware of the fact that at the heart of PacketPro's SLIMpro subsystem is a 250 MHz ARM Cortex-M3 core, but the PacketPro family was only announced (not even released) in September 2010, which hardly qualifies as "three years ago".