Intel powers an Arduino for the first time with new “Galileo” board (ars technica) [LWN.net]

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 7:45 UTC (Fri) by geertj (guest, #4116) [Link] (6 responses)

It it just me, or does it seem that every time someone creates a new and interesting computer not based on the Intel architecture, Intel launch an inferior alternative that has less performance or uses more power, costs more, and then use their marketing prowess to try and make it stick?

OLPC -> Classmate
Raspberry Pi -> Minnowboard
Arduino -> Galileo

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 10:37 UTC (Fri) by allesfresser (guest, #216) [Link]

It's not just you.

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 10:44 UTC (Fri) by ledow (guest, #11753) [Link] (1 responses)

The problem is, I've never heard anything more of those on the right-hand-side. Intel just don't know how to compete in that area, so they have to trail by which time people don't touch them.

It's a shame - a Pentium-on-a-chip would have sold millions some years ago. Now it's just a waste of power. I still have a NetPortExpress based on a Intel 386SL chip, they obviously knew how to do this stuff at one point, but it's just a question of power, heat and size which Intel haven't been very good at for a long time.

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 16:34 UTC (Fri) by khim (subscriber, #9252) [Link]

it's just a question of power, heat and size which Intel haven't been very good at for a long time.

It was not “heat and size” per se. Intel manufactured Intel 80376 for many years, after all. But it refused to license cores and it refused to make a proprietary SOC designs on it's own fabs which made them useless in a time when everyone started switching to custom SOCs with CPU just one small part of the whole chip.

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 10:55 UTC (Fri) by lkundrak (subscriber, #43452) [Link]

On the other hand, it has real mode and vm86!

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 12:18 UTC (Fri) by gnb (subscriber, #5132) [Link] (1 responses)

Seems a perfectly reasonable strategy. The devices you list as their targets are all cheap. Producing an equal or superior alternative at a similar price would risk cannibalising some sales of higher-end Intel processors. This way, they hopefully muddy the waters and reduce sales of the competing device without diverting too many people to the bottom end of their product range.

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 4, 2013 12:24 UTC (Fri) by stumbles (guest, #8796) [Link]

Aye, its called pissing in their (the competitions) Wheaties.

Intel powers an Arduino

Posted Oct 4, 2013 17:12 UTC (Fri) by pboddie (guest, #50784) [Link] (31 responses)

From the FAQ:

Can I use this board without a power supply?
No. You MUST use a power supply at all times.

Intel certainly aren't doing much to lose their reputation for excessive power consumption. The Arduino Yún can be powered from the USB port, just like many of the other boards.

Anyway, the Arduino product page is arguably a better summary for those of us who don't enjoy downloading PDFs as much as those in the semiconductor industry seem to. Still, it's nice to see additional diversity in this scene.

Intel powers an Arduino

Posted Oct 4, 2013 21:05 UTC (Fri) by khim (subscriber, #9252) [Link] (30 responses)

It's also funny to compare these three lines:

1. Arduino Uno: 32 KB (ATmega328) of which 0.5 KB used by bootloader
2. Arduino Mega: 256 KB of which 8 KB used by bootloader
3. Arduino DUE: The SAM3X has 512 KB (2 blocks of 256 KB) of flash memory for storing code. The bootloader is preburned in factory from Atmel and is stored in a dedicated ROM memory.
4. Intel Galileo: 8 MByte Legacy SPI Flash main purpose is to store the firmware (or bootloader) and the latest sketch. Between 256KByte and 512KByte is dedicated for sketch storage.

So it's hundreds of times more powerful then typical Arduino, about 10-20 times more powerful then ARM-based DUE, but all that power is actually used just to boot it up? Ouch.

Still it's nice to have somewhat overpowered "big brother" in Arduino family. But more testing in the field is needed before we'll know what can you use it for.

Intel powers an Arduino

Posted Oct 4, 2013 21:16 UTC (Fri) by drag (guest, #31333) [Link] (17 responses)

Such is the price of having hardware convert the x86 code to something the processor can process.

Intel powers an Arduino

Posted Oct 6, 2013 2:40 UTC (Sun) by oshepherd (guest, #90163) [Link] (16 responses)

Erm, what?

The processor in this thing runs x86 code. That's, you know, a prerequisite of being an x86...

Intel powers an Arduino

Posted Oct 6, 2013 7:45 UTC (Sun) by drag (guest, #31333) [Link] (15 responses)

> The processor in this thing runs x86 code. That's, you know, a prerequisite of being an x86...

Intel (and AMD) processors are actually RISC. They have not produced a true CISC processor since the Pentium 2 I think.

What they do have, however, is a hardware translation layer that dynamically translates x86/x86_64 machine code to another machine code format that is actually executed on the core processors.

The x86 or x86_64 is the 'ISA', a standard language interface of sorts. Another way to think about it is that you really have a x86 'virtual machine', but instead of doing the processor emulation in software Intel does it in hardware.

This is a very complex thing to do in hardware and maintain good performance. Normally this is not a big deal because the logic required to do the translation was much smaller then the rest of the processor, however as Intel tries to simplify their processors and scale them down they can't get away from the huge ISA translation layer.

ARM, on the other hand, comes out with new architectures on a regular basis. They don't mind breaking their machine language compatibility and will add and changes things as they see fit.

This reflects the different goals and successes of the original architectures.

This one of the major reasons why ARM has, so far, been ahead of Intel in terms of performance per watt even though people that license their processor designs have cpu manufacturing processes tend to be a few years behind.

Intel powers an Arduino

Posted Oct 6, 2013 10:56 UTC (Sun) by khim (subscriber, #9252) [Link] (1 responses)

Intel (and AMD) processors are actually RISC. They have not produced a true CISC processor since the Pentium 2 I think.

Apparently it's still true for AMD, but no longer true for Intel. I'm not 100% convinced that it's just a shrink of P54C but something like this highly likely: this will explain all observable quite well: that's how you can make it five times smaller and ten times more energy-efficient then Atom, etc. Five times smaller means that it has about the same number of transistors as Pentium !!! core and there are a lot of other things besides core!

Intel powers an Arduino

Posted Oct 6, 2013 12:31 UTC (Sun) by pboddie (guest, #50784) [Link]

I'm sure you can dig something up about this, but I'm also sure that various AMD product lines went through a transition to RISC (or started out life as RISC) with some kind of x86 translation being used to satisfy the needs of everyone who can't manage to recompile their software. See this page on the Nx586 with a note about RISC86 instructions, for instance.

Of course, AMD have acquired technologies that should have allowed them to put desktop-class products into low power devices. The Geode CPUs (which will supposedly be discontinued fairly soon) are an example of this, although they apparently use traditional microcode implementing x86 instructions directly. Maybe AMD didn't see any future for this approach either in terms of power or performance, effectively bringing to an end a product line that in fact originally came from another x86 competitor, Cyrix. The NexGen approach was the one that worked best for AMD, I guess.

Intel powers an Arduino

Posted Oct 6, 2013 17:03 UTC (Sun) by marcH (subscriber, #57642) [Link] (6 responses)

> Normally this is not a big deal because the logic required to do the translation was much smaller then the rest of the processor, however as Intel tries to simplify their processors and scale them down they can't get away from the huge ISA translation layer.

In SoCs like Quark, the *entire* CPU core is small compared to the rest of the SoC anyway.

I suspect power is a different question than you think it is.

Intel powers an Arduino

Posted Oct 6, 2013 17:39 UTC (Sun) by khim (subscriber, #9252) [Link] (3 responses)

In SoCs like Quark, the *entire* CPU core is small compared to the rest of the SoC anyway.

That's true for most SoCs, but I doubt it's true for Quark. Quark is billed as ⅕ of Atom. Atom has about 50 million transistors thus Quark should have about 10 million. If you'll recall that even original Pentium had 3.1 million and also consider the fact that Quark is supposed to be synthesizable we should expect between 3 and 5 million transistors just for that single core. That's hardly small compared to the rest of the SoC anyway.

P.S. Of course Intel could have used 80486 core which only had ~1.2 million transistors but in that case it's 400MHz will deliver pretty pitiful performance by today's standards thus I hope it's at least Pentium-class CPU. And even in that case it'll be ⅒ of the whole SoC!

Intel powers an Arduino

Posted Oct 7, 2013 5:36 UTC (Mon) by nhippi (subscriber, #34640) [Link] (2 responses)

From the Quark Developers manual, quark is clearly a 486 core. Even if the manual is quite clear not spell it out loud, all the instruction timings match with the 486 counts...

This is the first rasberry pi killer that is actually slower than rasberry pi.

Intel powers an Arduino

Posted Oct 7, 2013 6:31 UTC (Mon) by Cyberax (✭ supporter ✭, #52523) [Link] (1 responses)

They can clock 486 to much higher frequency.

Intel powers an Arduino

Posted Oct 8, 2013 5:53 UTC (Tue) by khim (subscriber, #9252) [Link]

Probably. But they are not doing that: this thing is only clocked @ 400MHz. If it's Pentium then 400MHz is in “not superfast, but faster than many others” ballpack, if it's 80486 then it's in “WTF?” ballpack. Adruino says it's 400MHz 32-bit Intel® Pentium instruction set architecture (ISA)-compatible processor o 16 KBytes on-die L1 cache which does not say us much: 80846 and Pentium has very little difference from is ISA POV and later models of both had 16 KByte cache thus 80486 looks plausible, too.

Intel powers an Arduino

Posted Oct 7, 2013 13:57 UTC (Mon) by drag (guest, #31333) [Link] (1 responses)

> In SoCs like Quark, the *entire* CPU core is small compared to the rest of the SoC anyway.

I don't understand how that matters to what I said.

They obviously do the SoC thing because it's cheaper to produce computers were everything is in one big integrated circuit and it's more power efficient. It significantly reduces cost of the device because you can significantly reduce the complexity of the mainboard and such things. All the little chips and power converters you would need otherwise adds up considerably.

But that doesn't nullify or contradict the fact that x86 ISA causes significant overhead for the CPU that ARM doesn't have to deal with.

Intel powers an Arduino

Posted Oct 7, 2013 21:14 UTC (Mon) by marcH (subscriber, #57642) [Link]

> But that doesn't nullify or contradict the fact that x86 ISA causes significant overhead for the CPU that ARM doesn't have to deal with.

It does not nullify or contradict it (another discussion); it makes it irrelevant.

Intel powers an Arduino

Posted Oct 7, 2013 9:13 UTC (Mon) by renox (guest, #23785) [Link] (3 responses)

> Intel (and AMD) processors are actually RISC.

Oh, they ditched the x86 ISA, now they have a reduced INSTRUCTION SET cpu(computer)?
Tell me how you or your compiler can access directly these RISC instructions?

You can't so the external instruction set is still CISC, whether it is implemented internally using a RISC or not doesn't change the external instruction set accessible.

Intel powers an Arduino

Posted Oct 7, 2013 13:52 UTC (Mon) by drag (guest, #31333) [Link] (2 responses)

> Oh, they ditched the x86 ISA, now they have a reduced INSTRUCTION SET cpu(computer)?

They didn't?

> Tell me how you or your compiler can access directly these RISC instructions?

It doesn't.

> You can't so the external instruction set is still CISC, whether it is implemented internally using a RISC or not doesn't change the external instruction set accessible.

Irrelevant to what I was talking about.

Intel powers an Arduino

Posted Oct 7, 2013 14:26 UTC (Mon) by renox (guest, #23785) [Link] (1 responses)

> Irrelevant to what I was talking about.

And? You still wrote an incorrect assertion..
*Using* internally a RISC or *being* a RISC i.e having an externally accessible ISA which is "reduced" are different things, whether it is relevant to your discussion or not I don't care.

Intel powers an Arduino

Posted Oct 7, 2013 15:44 UTC (Mon) by pboddie (guest, #50784) [Link]

RISC design principles are about more than just how many instructions there are and what they look like, even though you can argue that most RISC CPUs drifted away from those principles pretty quickly. One can argue that x86 instructions translated to "RISC instructions" does resemble x86 instructions being implemented by microcode, but I imagine that refactoring the microcode and working out a better set of directly implemented instructions is very much taking the RISC approach, even if all this is hidden by the x86 layer in the final design.

Intel powers an Arduino

Posted Oct 7, 2013 11:04 UTC (Mon) by k8to (guest, #15413) [Link]

The complexity of Intel instruction decode logic has pretty much nothing to do with the size of the flash storage used for boot code. Generations of cpu design prior (1996-ish especially), the complicated Intel instruction decode logic had a number of ramifications. It greatly increased the number of transistors necessary to implement an x86 chip as compared to competing simpler instruction sets. It also had a tendency to cause instruction pipeline stalls as parallelism in instruction handling grew in CPUs, limiting performance.

None of that has to do with the size of the instructions as stored in memory or flash, though. In fact all the higher performing comptemporary designs (mips, sparc, power(pc), etc) all had *larger* memory footprints for the same program compiled to their instruction streams. They eschewed complexity in instructions in order to have simpler decode, and many things took multiple instructions that in x86 could be done in one. The most obvious example (though not the most significant in overall size) was the way that function calls were typically encoded.

Of the popular arches around that time, only the 68k instruction set tended to be a bit smaller than x86, but that's certainly not RISC-like at all, only less baroque.

There were some very compact instruction sets emerging a bit later in the 32bit space (like 1997ish?), notably Arm "thumb", which was a 16-bit packed conceptually 32bit instruction stream. It certainly saved a bunch of space, but the much *more* complex decode logic limited the performance too much for most users.

However, in the deeply embedded space, where 32bit flat memory models weren't valued, there were a variety of instruction sets more optimized for size. This was both for a desire to may very inexpensive CPUs but more significantly to make inexpensive total parts, including storage and cpu. I'm not an expert on these arches, but that's the heritage of Arduino, PIC, etc. It's not that they're "risc" or "simple", it's that the designers wanted to run programs out of tiny flash spaces or on-cpu memory.

But even this isn't really enough to explain the difference between sizes like 32kb and 8MB. Either the 8MB rom has a lot of functionality the 32kb doesn't, or it's meant as user-burn space to run out of rom, or it's written by jokers. Any are possible. A lot of 32bit development boards in the 90s came with completely jokey roms that you immediately erased and replaced with something reasonable. I left that world around 2000, so I couldn't say now.

Intel powers an Arduino

Posted Oct 8, 2013 7:48 UTC (Tue) by paulj (subscriber, #341) [Link]

Note that decoding a complex instruction stream and using microcode to then orchestrate the inner workings of the CPU in simpler steps accordingly is pretty much the epitome of CISC. :)

Intel powers an Arduino

Posted Oct 4, 2013 21:33 UTC (Fri) by marcH (subscriber, #57642) [Link]

Inside the 8M SPI there is:
- EDK2-based firmware (BIOS)
- GRUB legacy
- a Linux kernel and a tiny but functional Yocto system.

Arduino sketches run in user space.

The "bootloader" term is only kept not to confuse Arduino users - some haven't and will never hear about Linux.

Note GRUB is configured to boot (a bigger) Linux system from microSD (or USB) instead of SPI when a GRUB config file is found there in a predefined location.

Intel powers an Arduino

Posted Oct 5, 2013 12:32 UTC (Sat) by tzafrir (subscriber, #11501) [Link] (10 responses)

There are quite a few USB-powered devices with an ARM (Cortex-Ax) core out there. They are about the same performance level as this board.

Intel powers an Arduino

Posted Oct 5, 2013 15:29 UTC (Sat) by khim (subscriber, #9252) [Link] (9 responses)

Sure, but can they be used with Arduino IDE?

Intel powers an Arduino

Posted Oct 6, 2013 9:26 UTC (Sun) by kreijack (guest, #43513) [Link] (3 responses)

> Sure, but can they be used with Arduino IDE?

I am not sure if this is a advantage or not. You have a PC-like, which could hosts a real OS, which all the capabilities:
- networking
- storage
- mPCI/USB buses

I think that thinking this board as an Arduino compatible board is quite limiting. You have the cons of both the world (low power, low storage of Arduino and high consummation and a complexity of an x86 board)
The only gain is that an hobbyist can start from a quite know environment.

Intel powers an Arduino

Posted Oct 6, 2013 11:31 UTC (Sun) by khim (subscriber, #9252) [Link] (2 responses)

I think that thinking this board as an Arduino compatible board is quite limiting.

Oh, sure. But the important thing is that this is “Arduino board plus something” (similar to Arduino Yún in the spirit if not in capabilities).

It's easy to create cheap development board (think STM32), but if it's not in “Arduino family” then people can not start using it easily.

The only gain is that an hobbyist can start from a quite know environment.

Sure, but this is large gain. Before you can learn to run you need to learn to walk! That's why Arduino (which is very underpowered and significantly overpriced) is so popular!

And if you started with Arduino then obviously you'll want to work with something Arduino-compatible.

Intel powers an Arduino

Posted Oct 19, 2013 19:08 UTC (Sat) by emj (guest, #14307) [Link] (1 responses)

You can buy Arduino UNO clones for 9 USD, and versions with less io for ~5 USD. So I would hardly say it's overpriced. If you are arguing it's underpowered, that's another debate, it's not about speed or massive IO.

Intel powers an Arduino

Posted Oct 19, 2013 19:41 UTC (Sat) by khim (subscriber, #9252) [Link]

I think you misunderstood me.

The fact that

you can buy Arduino UNO clones for 9 USD, and versions with less io for ~5 USD.

means that Arduino itself with it's €20 price it's horribly overpriced. Yet it's still more popular than other, less expensive and more powerful development boards! Cheaper clones are even more popular, obviously, but that's different story.

Intel powers an Arduino

Posted Oct 6, 2013 9:36 UTC (Sun) by fabo (guest, #49199) [Link] (1 responses)

Arduino TRE: http://arduino.cc/en/Main/ArduinoBoardTre

Intel powers an Arduino

Posted Oct 6, 2013 11:09 UTC (Sun) by khim (subscriber, #9252) [Link]

Well, to me “is expected to be available in spring 2014” means “it's not available right now”. And it's also very different from all other Arduino boards. But yes, when (and if) it'll become available it'll be interesting to compare it to Intel Gallileo. A lot will depend on price. Beagleboards are $45 nowadays and this thing is somewhat more complex then Beagleboard thus we are reaching the same $60 ballpark as Intel Galileo, but a lot of things can happen in the next half-year!

Intel powers an Arduino

Posted Oct 7, 2013 12:40 UTC (Mon) by pboddie (guest, #50784) [Link]

To answer your question - rather than argue about the benefits ;-) - the answer is "yes". See the Energia IDE for an example of where another kind of prototyping system (TI LaunchPad) has adopted the Arduino IDE.

Try the Teensy 3.0

Posted Oct 11, 2013 4:09 UTC (Fri) by cdmiller (guest, #2813) [Link] (1 responses)

Comes with a full set of open source Arduino compatible libraries in the modified Arduino IDE and uses the Arm realtime chip:

http://www.pjrc.com/store/teensy3.html
http://forum.pjrc.com/forum.php

Try the Teensy 3.0

Posted Oct 11, 2013 9:37 UTC (Fri) by khim (subscriber, #9252) [Link]

Modified Arduino IDE is kind of a problem, but bigger one is the fact that Cortex-Ax and Cortex-Mx are very different beasts (first one is in the same ballpack as Intel's Quark, second one is at least 10 times slower). Teensy3 uses the latter while tzafrir talked about the former.

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 7, 2013 17:04 UTC (Mon) by Neowin (guest, #93001) [Link] (2 responses)

BTW, in real world, many universities still teaches Intel 8086/8088.

Where proprietary emu8086 is 100 times better open source i8086emu.
(i8086emu is basically crap, run it on Windows you see it. Many people struggle to compile it on Linux though, hope that it can replace emu8086.)

Where long dead DOSware TASM is still used.
(I love NASM as much as you. But is there a sane linker for 16bit exists on Linux?)

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 7, 2013 23:57 UTC (Mon) by pboddie (guest, #50784) [Link] (1 responses)

At my "real world" university in the early 1990s, computer scientists were taught 68000 assembly language whereas some other disciplines were taught 8086 assembly language. Make of that what you want to. (Being familiar with ARM assembly language at that point, it wasn't particularly thrilling to take a step back in either direction, but the case for "industry relevance" can always be made, I suppose.)

Intel powers an Arduino for the first time with new “Galileo” board (ars technica)

Posted Oct 8, 2013 10:47 UTC (Tue) by Neowin (guest, #93001) [Link]

Today, computer scientists are taught MIPS assembly language whereas some other disciplines are taught 8086 assembly language.