32-bit Processors, Cheap

An anonymous reader writes "Atmel is sampling the first in a new line of 32-bit system-on-chip processors that could spell the death of the venerable 8-bit microcontroller market by offering 32-bit performance at 8-bit pricing. Priced as low as $3 each, the AT91SAM7 chips with ARM7TDMI RISC CPU cores and built-in RAM/flash memory may even be able to run a form of Linux called uClinux. The death of the 8-bit uC market has long been predicted -- sounds like the end is nigh!"

Comments

Death of 8-bit

[Anonymous Coward]

The death of the 8-bit uC market has long been predicted

Has Netcraft confirmed it?

Overkill

[jsin]

There are so many embedded applications that do just fine with 8-bit controllers that there is no reason they should dissapear just because something more powerful comes along.

Anyone who has done this design knows that there is more cost in what happens on the whiteboard than something like this at the component level.

Not everything in the world has the "upgrade or else" fear that surrounds the personal computer industry.

Re:Overkill

[Pxtl]

Well, consider how much more complicated embedded apps are getting - think about the onboard computer in the Audi, and the increasing numbes of mp3 players, movie players and whatnot. While "upgrade or else" is stupid, damn if this thing won't be useful.

So, when do I get my full-pentium-PC-on-a-chip so I can play X-Com on my watch?

Re:Overkill

[Rolo Tomasi]

Exactly, sounds like marketing hype ... I mean, a lot of (most?) consumer electronics still use 4-bit MCUs.

Actually, I don't see much demand for these "medium speed" controllers. For control applications, they're overkill most of the time, and for multimedia stuff, they're too slow/small.

Re:Overkill

[LurkerXXX]

Well, that kind of depends on the application. Say we are talking about stuff controlling machines in factories...

The Reg just put out a story how all sorts of embedded controllers in factory machines are a huge risk for attacks because the chips in them don't have the horsepower to do new things that the equipment's designer didn't originally take into account.

http://www.theregister.co.uk/2004/10/08/cyber_thre ats_menace_factories/

Sometimes you don't realize when you will actually need more horsepower (perhaps for things like encryption and authentication) than you originially thought you would.

Re:Overkill

[Tenareth]

Yes, but this isn't the consumer market. Heck, 80186's are still made and used today.

Also, 32bit probably drains more power and generates more heat. Staying 8bit was not generally a $$$ thing, it's that it's the right tool for the job.

Re:Overkill

[Tassach]

There are so many embedded applications that do just fine with 8-bit controllers that there is no reason they should dissapear just because something more powerful comes along.

Manufacturers are not stupid, therefore I'd be shocked if the 32-bit uC's are not backward-compatible with the older 8-bit models. Not just code-level backward compatibility, but pin-level backward compatibility too.

The main cost in a chip is the design, as you've noticed. Once you've masked out the die, it doesn't cost significantly more to fab a 32-bit chip as it does to fab an 8-bit chip. A 32-bit core implies that they're using a more modern process, so it's likely that they can now make a more powerful uC which uses less power & generates less heat than the previous generation.

Re:Overkill

[jsin]

Fair enough, I just hate to see hundreds of yuppies running to Williams-Sonoma to find an upgrade for Mr. Coffee....

Re:Overkill

[temojen]

So, when do I get my full-pentium-PC-on-a-chip so I can play X-Com on my watch?

AMD.

Re:Overkill

[Grayputer]

Actually, you are correct, which is why you are wrong:). As you correctly state, whiteboard (and setup) costs are significant. SO when a standard 32 bit design arrives that costs 'the same' as an 8 bit design, everyone will move to the off-the-shelf (OTS) 32 bit design manufactured in quantity instead of paying for custom runs of old 8 bit stuff that is no longer in stock. Now it will not happen overnight as stocks of 4/8/16 bit designs exist and tooling still exists BUT to use an OTS 32 bit item will become cheaper than retooling for a new run of old 4/8/16 bit stuff eventually. Consequently at some point all new development will move to the new 'standard controller' (admittedly rewriting old controller code may be more expensive than retooling so old products may go to 'mature mode'). The key is cost and a true 'standard controller'. If the cost of the 32 bit standard controller is not 'the same' as the 8 bit controller then it may still be cheaper to use 8 bit in some cases. If the 32 bit market fragments then a 'standard controller' may not exist and software retooling expense may make it non viable.

Bottomline, not much new development is done on 4 bit controllers, which used to own the market. Eventually not much new development will be happening on 8 bit controllers as 32 bit controllers mature and become more price competitive. IF a standard 32 bit controller emerges, people will move to it to reduce the whiteboard costs you mention. Especially if it runs something remotely standard and feature robust, like a version of Linux.

Re:Overkill

[Doesn't_Comment_Code]

The Atmel company has always gone to great pains ensuring that their chips are compatible. That's very smart, because developers can switch chips with little or no adjustments.

This is a pretty big, fundamental change. But based on their repuation, I think Atmel will provide the maximum amount of compatibility possible without being silly about it.

Re:Overkill

[Christopher Thomas]

Actually, I don't see much demand for these "medium speed" controllers. For control applications, they're overkill most of the time, and for multimedia stuff, they're too slow/small.

I've been playing with Atmel's 8-bit line. What makes these chips nice is that they're fast enough to do a lot of things in software that would otherwise require dedicated hardware (PWM, audio input/output/processing), while still leaving enough cycles free to do the high-level control work. Atmel also has a habit of throwing everything including the kitchen sink as peripherals into the controllers, making them very versatile. Yet, you can clock them down and turn off peripherals you don't need in order to get the same kind of power consumption you'd get with a simpler chip, when needed.

From Atmel's point of view, this type of architecture makes sense - instead of 20 similar lines of microcontrollers with different peripherals, they have two or three (for different voltages, mainly).

From a widget designer's point of view, this saves on learning curve and equipment (become familiar with and buy equipment for one or two families of device instead of dozens), and gives them a chip they can use as all-purpose glue with only a modest hit over an application-specific solution.

In summary: Go Atmel :).

[As for 8 vs. 32 bits, the 8 bit family will likely always be lower power for digital functions, due to fewer nodes being switched per operation.]

Re:Overkill

[joe270]

With 32 bit processors, you need four times the memory to run the same program as an 8 bit CPU. That makes these parts less flexible than their 8 bit counterparts

Not true...32 bit designs can still have memory that is addressable by the byte, and single bytes can still be loaded to or stored from the core registers. You just sign extend the upper 24 bits of the registers (fill with 0 if it's a positive value or 1 if it's negative). So you don't lose any flexibility there.

even though they are a bit faster

Actually, the speed of the processor is only dependent on its clock speed, not the size of the word that it can handle. If your words are 32 bits, then a 32 bit processor is much faster because you don't have the overhead of using 4 registers to hold the word (and manually coding for carries in addition, etc.) So, without a specific model or application in mind, you can't really say anything definitive about speed.

Re:Overkill

[the morgawr]

Don't forget Automobiles: Engine, ABS, HVAC, and Airbag controllers all still use (well for the most part anyway) slow, cheep 8-bit micro-controllers.

Re:Overkill

[letxa2000]

Very true. Many people today just don't understand what "embedded" really means. As much as some people would like to call Palm, WinCE, a Pentium-in-a-small-box, or any computer in a small enclosure "embedded" that completely redefines what embedded traditionally meant. It meant that the the microcontroller was embedded within the rest of the product. The microcontroller wasn't the focus of the product but rather it significantly reduced part counts by doing what used to take lots of ICs and board space. You can bet that anything that includes this kind of 32-bit chip for $3 is going to be doing some heavy marketing for browsing rights on what drives the product. But do you really think anyone cares if their washing machine is 32-bit?

8-bit microcontrollers aren't going anywhere. Many 8051's are still less than a tenth of the cost of these 32-bit chips. And many 8051's have on-board "everything." Your program is flashed onto the MCU, you have a built in serial port which requires, at most, a MAX232 to convert to RS232 levels, many have A/D and D/A converters, some even have MP3 decoding capability (Atmel if I remember correctly).

In short, these cheap 32-bit micros don't mean the "end of anything." They're a good tool for the right jobs, which probably include cell phones, PDAs, etc. But microcontrollers are not microprocessors. That's why you're not going to see a 32-bit CPU in your TV's remote control, inside your microwave (probably), controlling your fridge, inside the remote control of your car's remote key entry system, inside an alarm clock, inside your PC keyboard, blah blah blah.

Not the death, but certainly less market

[Anonymous Coward]

The 8-bit MCU market has been shrinking for over a decade. It's no secret. Of course there will always be a market for small-time CPUs; certainly hobbyists will want them. But traditional places like your car computers need more real-time DSP computation and the like, and require the MCU to grow with them.

Re:Not the death, but certainly less market

[feloneous cat]

The 8-bit MCU market has been shrinking for over a decade. It's no secret. Of course there will always be a market for small-time CPUs; certainly hobbyists will want them. But traditional places like your car computers need more real-time DSP computation and the like, and require the MCU to grow with them.

Has the 8-bit MCU market shrunk? Sounds like "repeat it enough and EVENTUALLY some dumbass will believe it".

I've been writing 8 bit code for nigh 20 years. Somehow, whether it be luck or skill, I have remained employed. And so have a lot of programmers who, oddly enough, are still programming those "dead" 8 bitters.

"I'm not dead."
"What?"
"Nothing. There's your ninepence."
"I'm not dead."
"'Ere, he says he's not dead."
"Yes he is."
"I'm not."
"He isn't."
"Well, he will be soon, he's very ill."

Pretty much sez where we are with the 8 bitters. They aren't dead but there are those just ready to club them over the head (over and over and over) to try to make it so.

Re:And so it begins

[garcia]

Who wants to be able to program their TV to record TV from work? Who wants to program their lights to come on from work? Who wants to program their heat/AC to turn on/off from work? Who wants their oven to preheat from work?

I know I do.

Enough already!

[Anonymous Coward]

While I love to hear news of the latest whizbang doohicky, I cannot stand when people have to add "This is surely going to end anyone on the planet ever using last years widget..." As geeks we should be aware and PROUD of old technology. Serial ports? I use them every day at work. 8 bit microcontrollers. I love them to death. They work nice, are cheap enough, and are very easy to design for and around. So yes, many places where someone might have used X in the past will now be replaced with Y, but so freakin what? But part of the joy of hacking is taking what someone else thought was worthless and using it anyway. Hence the stories of people salvaging old laptops or modding their Amigas to be a multimedia console, etc. Yes, the newest latest greatest toys are spiffy and should be discussed, but how about we all just settle down and stop dumping on anything not cutting edge?

Sure they're cheap, but there's more that matters

[Anonymous Coward]

What about the heat dissipation and power usage? Sometimes that's a lot more important than the price. If it's just as cheap but uses more power, you might need a bigger power supply, more batteries, better heat dissipation, possibly a fan, etc., it doesn't help.

I'm pretty sure standard 8-bit uCs are overkill for most applications -- what would 32-bits buy you?

OK, you *can* put a web browser in your gas pump, but should you? Having seen BP's implementation, I would say not.

aQazaQa

I think 8 bit has more life left in it.

[Dzimas]

I use Microchip processors extensively for work, and there's a heck of a lot that I can accomplish with their limited architecture -- my most recent design required less than 8K of flash memory and was mostly written in assembler. For low-end applications, 32-bit doesn't make sense, especially if its going to add $1 to the cost of manufacture. Given that small 8-bit MCUs can be purchased for well under $1 in large volume, I think there's a market for them.

Wrong..

[taharvey]

"Unit volume is dominated today by the 8-bit control and instrumentation segment with over 389,000,000 units shipped this calendar year. This is followed by the 4-bit watch segment and the 8-bit PC peripherals segment." - In-Stat 2003

8 bits is all the majority of embedded applications need. Its lower power, and cheaper.

8 bits rules the world and will continue to do so for a long time.

8bit price, but how about 8bit power?

[RealAlaskan]

These are micro controllers, where 32 instead of 8 bits may not be an advantage. Even if they cost no more than the 8bit chip, they'll still have to have more transistors, and thus draw more power than an 8bit chip using the same technology. Since these will be going into embedded applications where power matters, even a little more current draw could be a big drawback.

If your application needs the extra capabilities that a 32 bit chip offers, this is a big deal, but if the old 8bit standby does the job an draws a few milliwatts less, you're better off sticking with the old fashioned, 8bit chip.

I think it's a little too early to say goodbye to 8bit microcontrollers.

Re:And so it begins

[zoobaby]

Would be good to know if your frozen burrito has cooked or needs another minute. You could add more time from the comfort of your desk chair.

Re:Misleading Summary

[RadioheadKid]

No, not really. That's how electronic components are priced. Unless your doing some custom one-time job, bulk pricing is how you price your build-of-materials. In fact, many times the actual price is even lower than the list price. Especially if you order larger quantities.

Re:And so it begins

[Oliver Wendell Jones]

Who wants to worry about someone hacking their TV and deleting all their recordings? Who wants to worry about whether or not you're lights will stay on/off because some scriptkiddie wrote a BlinkenLitez for your neighborhood? Who wants to come home to find out their house is heated to a balmy 97 degrees because someone hacked their thermostat? Who wants to come home to find their oven has been running all day on Broil?

I know I don't.

Re:Not just "Power"

[cmowire]

Ummm.. There's no provisions for external memory. This is aimed at AVR designers who want more oomph, so all memory and flash is internal. No address bus.

The problem, of course, is that a TQFP package is not quite as hobyist-hackable as the old DIP packages because it requires you to have etched PCBs or a prototype adapter, which makes breadboarding harder.

About the OS

[doombob]

Does anyone else think that uClinux looks like a dirty word? But seriously folks, has anyone tried this out on anything? I need to hear someone who's used it on Slashdot.

Re:And so it begins

[infinite9]

Who wants their oven to preheat from work?


As a father of six, I know I would never preheat the oven without first looking inside. It would be unfortunate if an action figure, or worse the cat, were to meet an early demise.

Clue alert: $3 in volume is EXPENSIVE

[Anonymous Coward]

As an embedded systems consumer product design engineer by trade, I can state with great confidence that $3 is NOT cheap.

In fact, for everyone who's pointed out that PIC's cost well under a dollar:
That's not cheap either.

4-bit watch micros and the kind of thing that runs your toaster are priced in the 0-25cents range in volume -- that's right, a few *cents*.

To wit: $3 is greater than the complete cost-of-goods for much of the consumer electronics market. A TINY 4-bit chip, engineered with the same modern techniques as a 32-bit one, will be able to conserve even more power. This may not matter if it's a toaster, but if you want something to run off a battery for 10 years, you better start hunting for the smallest, simplest die you can find.

Coding for older platforms is also very easy, very fast, and easy to certify as bug-free. Put that in your kernel forum and smoke it.

Don't get me wrong, a dirt-cheap linux-capable uCs make me as happy as the next dork, but they're for a very different kind of task. Consider the myriad PDAs with flashy graphics/media capabilities already running on ARM processors and similar...

Dev kit costs?? That's what I find critical.

[francisew]

Having an inexpensive 32 bit uC is great. How much are the development kits? 500$?

The basic stamps are great. For an 8-bit 10kHz platform that runs PBASIC.

The SX & PIC chips are great for 8-bit systems that run at a few MHz (sx up to 50 MHz), that are programmed in assembly.

The TI MSP430 is a great 16-bit platform that runs at 8MHz, programmed in C/C++ (in a few weeks they will probably unveil a 25MHz version). They also include lots of things that I don't like to have to add-on myself. (12-bit A/D & D/A, op-amps, HW uarts/I2C, and so on)

There would definitely be a market for these things, but I'd like to see if they can match development costs for small developers. It seems to me that a key is opening development to the masses. That's what impresses me about the few I listed above. Dev kits from TI are 100$, and from Parallax are

I use uC's for embedding scientific devices onto smaller/cheaper/faster chips. That's great. Now for me to be able try it, and learn to use it, I can't go buy an expensive dev kit. Regardless of the end cost of the chip, I prefer to pay 30-50$ for a board with a chip, that I put in a box and use, than a uC with smt leads that I can't get to work in place without a few hundred to thousand dollars of dev costs.

"The death of the 8-bit uC market"

[bani]

there are a lot of reasons to use 8-bit uCs. price is only one of them, and rarely the most significant factor. often, uC price is the least significant factor.

pin count, component size, power consumption, and overall complexity are the other major factors in embedded designs. all of these factors are higher in 32bit uCs.

8bit designs arent used solely because they're less powerful, but because they are far simpler than the mess of logic required to support 16bit or 32bit uCs.

8bit uCs aren't in any danger of being killed off by this.

Good reasons for using 4/8/16 bit SOC controllers:

[earthforce_1]

1) High code density: Even if you need more instructions to perform an operation, if the instructions are only 8 or 16 bits wide, you wind up with a smaller executable. Hence, you need fewer bytes of ROM to store the firmware. And if a lot of your data is byte sized anyway, (processing strings, or reading an 8 bit ADC or setting an 8 bit PWM) the code may be smaller still, since there is no byte packing/unpacking into a 32 bit space required. (Incidentally, this is a major problem with 64 bit and VLIW computing.)

2) Power consumption. An 8 bit processor has only 25% the bus width of a 32 bit processor. Registers, instruction decoders, and ALU are 25% as complex. Ergo, for the same manufacturing process and clock rate, an 8 bit core will always consume a lot less power. If you are trying to run an algorithm off a watch battery, this really matters. That is chiefly why the venerable 8 bit PIC with its horrid assembly code, continues to be popular.

3) Less die space. Same reasoning as above. if you are doing an ASIC and can get away with an an onboard 8 bit controller core, why would you waste silicon using 32 bits?

3) Backwards compatability, ability to run legacy code. Even in embedded systems, stuff gets reused. 95% of you will be reading this on an x86 PCm which happens to trace back to a 4.7 MHz 8 bit ancestor found in the original IBM PC, the 8088.

What it ultimately boils down to, is selecting the right tool for the job. And there will always be a niche somewhere for humble little lightweight 4 and 8 bit controllers.

Let's compare...

[Anonymous Coward]

I read the article and the part looks like a good next step in the evolution of 32-bit MCUs. However, it will not kill off the market for 8-bit MCUs. 8-bit MCUs still beat this part in a few areas:

• Package size: The AT91SAM7A is impressive in how much it packs into a 64-pin TSSOP package, but Atmel's 8-bit ATtiny15L is also impressive in what it packs into an 8-pin SOIC. And if that's too big, Microchip just released the PIC10F 8-bit microcontroller in a 6-pin SOT23 package. Don't sneeze.
• Price: 8 bit MCUs are still cheaper, most under $1 in quantity, while the AT91SAM7A is $3 in quantity.
• Power supplies: The ATtiny15L works with one supply between 2.7V to 5.5V, so it could run off a loosely-regulated supply, or straight off batteries, eliminating the need for a regulator. The AT91SAM7A needs a 3.3V core supply, and a second 5.0V supply if any of the I/O pins need the higher voltage. There are some parts that you still can't get in 3.3V.
• Power consumption: That ATtiny15L takes 3.0 mA active and 0.001 mA sleeping. The AT91SAM7A uses 0.24 mA sleeping and up to 78 mA when running (those figures are buried in the full data sheet). Good to know when battery life is an issue.
• Compiler support: both ARM and AVR architectures are supported by GCC.
• Architecture: Both AVR and ARM architectures are RISC architectures.
• Clock: The AT91SAM7A can run up to 8 MHz with an external crystal or 30 MHz with an external oscillator (using an internal PLL). The AVRs can run to 8 MHz on an internal oscillator (no extra parts) or 16 MHz from an external oscillator (though the ATmega26 has a trick where you can run at 16 MHz from the internal oscillator).

I would have loved to compare to the AT91SAM7S described in the article, but data sheets weren't available on the web site. All that said, I think the more impressive product is on the horizon: the AT91SAM7X series with built-in Ethernet.

Best of luck to the uClinux folks trying to pack everything into 64K of RAM. I've never tried to use less than 1 MB. A better choice, IMHO, would be something like eCos, which can be stripped down more, because in embedded systems, you don't always need a POSIX-style file system hierarchy.

While there have been many advances in 32-bit MCUs, it would be foolish to assume that the 8-bit MCU market is still stuck in the land of the 6502/8051/6800 CISC architectures. It's had its share of advances as well. And nobody really wants to use a 32-bit MCU for a mouse or keyboard.

Cutting through the fog

[Anonymous Coward]

1) 8 bit CPU are lower power than 32bit CPU's
Not so. Manufacturers, including ATMEL, run new and high volume products through the latest small geometry low voltage processes; Older 16/8/4bit parts in the main get left behind on higher power consumption lines, never to be die shrunk.

2) Goodbye 8bit
There will always be a place for the smaller parts. Rice Cookers for example are manufacutered in *huge* quantities; Do you think they will spend 10 cent more on a CPU because it is 'easier to code on'? No.

LQFP 40 and 64 pin packages can be soldered by your average electronics ham; I for one am looking forward to playing with an ARM CPU finally. If I can ever get one, which is unlikely. Atmel are not Microchip, sadly

Mike.

Not for those with a shaky hand...

[arabagast]

Reading in the article, it states that it will be delivered in LQFP packages, which means that it will be a pain in the a.. to solder it yourself. offcourse it's possible, but i believe many DIY projects don't include either the equipment, or skill to manage to solder this thing. For the more advanced it's offcourse pretty cool, but I guess i'll still stick with the PIC - there's currently no need to use this chip for 99% (yes, I picked this number randomly, and it is therefore not valid but..) of all the DIY projects out there.
..as I strike down upon thee..