Linaro Launches an Open-Source Spec For ARM SBCs 35
DeviceGuru writes: Not content to just standardize ARM-based Linux and Android software, Linaro has just launched 96Boards, an open-source spec for ARM-based single board computers. Along with the spec's rollout, Linaro also announced a $129 HiKey SBC based on a HiSilicon 64-bit, octa-core Kirin 620 SoC, and compatible with the 96Boards Consumer Edition (CE) spec's 85 x 54mm 'standard' form factor option. The 96Boards initiative plans to offer a series of specs for small-footprint 32- and 64-bit Cortex-A boards, including an Enterprise Edition (EE) of its spec in Q2.
Does this give us anything Raspberry Pi didn't (Score:2, Interesting)
Re: (Score:1)
Performance, connectivity (PCIe).
Re: (Score:1)
This board gives more CPU power, at least if the workload utilizes SMP and/or the 64 bit instruction set. Otherwise it is just a expensive PI 2, with the ethernet jack being replaced with wifi. Perhaps this has its users, just as the PI has. Competition is good as it keeps the prices reasonable.
Re:Does this give us anything Raspberry Pi didn't (Score:5, Interesting)
This is the first low-cost aarch64 silicon on the market. There are piles of piles of developers that will get it just for porting their software for arm64
This. Just logged in because I wanted to say exactly the same. Until now, afaik the cheapest option was actually a jailbroken iPad Mini 2 (and you obviously can't run Linux on that).
Re: (Score:2)
Actually, the cheapest option up to now was the HTC Desire 510 (quad core A53). Second cheapest (Linux at least) would be Nexus 9 (Nvidia Tegra K1 Denver).
Re: (Score:2)
Re: (Score:2)
But is there really a point of having ARM64 on an ultra low cost system? Its not like you are gonna be using the increased bandwidth or large memory amounts that 64bits brings to the table on a sub $150 SoC, hell I seriously doubt the board will have enough bandwidth on its I/O to even saturate a 32bit pipeline.
I think the main point is to have a low-cost development board that people can use to port their software to AArch64 and/or test it on that platform (as said by the AC I originally replied to). I'm also sure that even with bandwidth limitations, the octocore will prove its worth when running our compiler test suite.
Additionally, the AArch64 instruction set has been redesigned from scratch and a lot of historical baggage and special cases have been thrown out (e.g. no more arbitrary changing the PC with half
It's an attempt at a PC-like standard for ARM (Score:3)
If successful, it would give the ARM world a PC-like, vendor-neutral standard architecture, and so it would counteract the horrible balkanization of ARM communities by every manufacturer's boards being different.
Even if this doesn't succeed, standardization is a very worthwhile goal for ARM (just as it was for x86 PCs), and it's quite important that a broadly funded organization has recognized the need. It will also usher in the days of ARM64, at last.
There is
Re: (Score:1)
Re: (Score:3)
if nothing else, it provides a ARMv8 (64bit and 8 cores) dev board that doesn't cost multiple internal organs.
Re: (Score:1)
64-bit CPU, 8 cores, and 10x the speed (in Dhrystone VAX MIPS) for about 3x the cost. The more players in this space the better is my thought.
Re: (Score:2, Funny)
An actually sane design, non-faked USB, for starters. The people that designed the RPi, including the model B+, are incompetent hacks. Yes, I have both a B and a B+, but that is it. I am not financing them learning EE 101 any further.
multiple manufacturers, possibly (Score:2)
multiple manufacturers and clones. raspberry had just one clone company and they only managed to buy chips for one test run... raspberry doesn't really like competition and broadcomm is working with them to that end.
raspberry pi(2) is really engineered to be manufactured by one company to make money for one company.
more expansion pins as well, it seems. how many of them are usable as gpio pins, I don't know and possibly remains to be seen(there's several dedicated to that use but if the i2c pins etc can be
Re: (Score:2)
'cos your machine is riddled with shit?
ARM is cheap (Score:2)
And of course it would fail, because every OEM claiming to support the spec, in cost-cutting attempts, would cripple their implementations.
ARM is all about being cheap. And Linux is cheap too. Sadly that also attracts manufacturers who are cheap too. With all the consequences.
Obligatory XKCD (Score:3)
options means consumer confusion (Score:4, Interesting)
i'm the author of the EOMA standards, including EOMA68, so i have spent something like two years developing and refining hardware standards that will not confuse end-users. http://elinux.org/Embedded_Ope... [elinux.org]
the 1.0 (i.e. final and absolute unchangeable) version of the 96boards "consumer" standard from 96boards will be going on the list of alternative standards, as, sadly, another example of a standard that will result in end-user confusion, annoyance, product returns and, ultimately, failure.
the reason is incredibly simple: an end-user standard MUST NOT have optional interfaces. i do not understand why people developing standards do not understand this. page 7 of the 27 page v1.0 specification states, clearly, "1 OR 2 MIPI CSI-2 ports MAY be provided on the expansion bus interface" and "From 1-2 lanes MAY be implemented on the CSI1 port interface". now whilst the latter is absolutely fine (because negotiation takes place at the hardware-level, so either host or client will correctly negotiate 1 or 2 lanes), the former most definitely is NOT.
let's think it through. here's a simple scenario. an end-user buys a 2-lane box, and a lot of expensive camera equipment. they then find that the box is too slow, and need to upgrade. so they go out and buy another box, and, BY MISTAKE, when they get it home, they discover that they only bought a 1-lane box. as there is NOTHING WRONG with it, they may NOT return it as faulty under warranty.
additional confusion results from page 8, over the options that the 3rd USB port MAY be a USB-OTG port. again, people will buy a system and a set of peripherals, relying on the USB-OTG capabilities... and then upgrade at a later date and make the mistake of not knowing what the hell is going on until it's too late. they investigate further and find "whoops, i bought the wrong system: this one doesn't have USB-OTG power damnit".
DC power requirements, page 8: again, more confusion when upgrading.
2nd (optional) UART, page 9: more confusion results.
a summary is given on page 12, where the moment you see the word "optional", count them. that becomes a permutation of the number of possible things that an end-user has to check when first selecting and then double-checking on upgrading the device. i count (if you include the USB confusion and the power options) at least *SEVEN* possible "options", giving... someone else can do the math here, it's what... over a hundred different permutations at least.
and then, when you get to the end of page 12 only then do you discover that the expansion board connections may be used as GPIO!
*sigh* i have to say that this really does not look like a very well-thought-out standard, at all.
Re: (Score:2)
How is it any different from a pc?
how is 96boards different from a pc? or how is the situation that 96boards presents different from a pc? apologies, because the question, in its brevity (but mainly through the use of the word "it"), is very unclear.
So how do I upgrade an eoma standard system if no-one makes them?
working on it. i'm creating products on either side of the standard to get it started, and will continue to do so for at least a decade until the standards reach critical mass.
Re: (Score:2)
How is 96board's "standard" any different to an ATX motherboard?
The upgrade problem you mention is there. I had to buy a new DVD-RW drive when I upgraded my motherboard/cpu/ram because the new motherboard didn't have an IDE controller. The new drive is the same speed as the old one, it just has a SATA port on it.
It's not just computers either. I have a media player connected to my CRT TV. It has no HDMI connections. I'm severely restricted in upgrading the media player because most of the new ones are HDMI
Re: (Score:2)
How is it any different from a pc?
For PC parts, the standard needed for full compatibility can be boiled down a single name, sometimes accompanied by a version number. e.g. RAM is DDR3, CPU socket is AM3+, drives are SATA rev. 3, graphics cards are PCIe x16, USB3, etc. These are easy for consumers to understand because all of the relevant information for inter-compatibility can be stored in a short, memorable string. This can be contrasted with power supplies, where you need to look at the power rating, number of SATA connectors, 6 and 8 pi
Linux Workstation? (Score:2)
NB: I'm not expecting Core i7 performance nor Windows compatibility.
I recently replaced a noisy home desktop with a fanless Intel NUC - which based on energy usage, should save me around $AU65 a year on power bills, with a payback within Intel's 3 warranty, assuming I don't trade-in for the latest NUC or Brix in the meantime. (NB, I'm not a fan of laptops, having gone through 3 in 6 years - broken screen connectors and power supplies plus preferring full size keyboards and multi-monitors)
Some have mentioned
Re: (Score:2)
sure but only 1GB of RAM, which would appear not to be configurable.
Waiting for the EE (Score:2)
Hopefully it has SATA and Gigabit Ethernet.
I need something decent to replace my Cubietruck board.