MIPS Tempts Hackers With Raspbery Pi-like Dev Board

DeviceGuru (1136715) writes "In a bid to harness the energy and enthusiasm swirling around today's open, hackable single board computers, Imagination Technologies, licensor of the MIPS ISA, has unveiled the Creator C120 development board, the ISA's counter to ARM's popular Raspberry Pi and BeagleBone Black SBCs. The MIPS dev board is based on a 1.2GHz dual-core MIPS32 system-on-chip and has 1GB RAM and 8GB flash, and there's also an SD card slot for expansion. Ports include video, audio, Ethernet, both WiFi and Bluetooth 4.0, and a bunch more. OS images are already available for Debian 7, Gentoo, Yocto, and Arch Linux, and Android v4.4 is expected to be available soon. Perhaps the most interesting feature of the board is that there's no pricing listed yet, because the company is starting out by giving the boards away free to developers who submit the most interesting projects."

Comments

Sweet

[Anonymous Coward]

I imagine this'll turn up in CS courses that use Patterson and Hennessey's Computer Organization and Design textbook, which uses the MIPS ISA as the canonical example.

no price?

[Anonymous Coward]

The entire appeal of the raspberry pi was that it cost only $35. This new thing, you won't even tell us the price. If you need to ask, you can't afford it...

Re:no price?

[gigaherz]

It's a MIPS board. I have been waiting for this for SO long that I'd consider anything with less than 4 digits. And probably decide not to get it if it turns out to be > $200. I don't apply for the free ones since I just want to toy around with it, not do some specific project with it. ;P

Re:no price?

[amiga3D]

I'm surprised no one has simply cloned the pi and sold it cheaper. I guess the pi's price is as low as it's possible to get on this hardware, Broadcom must be just about giving away the hardware. When you think about what they've accomplished at this price point it's truly impressive.

Re:no price?

[TheRaven64]

There's no price yet because they're giving away the first production run to people who are going to do interesting things with them. Unfortunately, this is a really bad time to do anything MIPS related (and I say this as someone who hacks on a MIPS IV compatible softcore and the LLVM MIPS back end). Imagination has just released the MIPS64r6 and MIPS32r6 specs. These are the biggest revisions to the MIPS ISA since MIPS III, which introduced 64-bit support. They've removed a load of legacy crap like the lwr and lwl instructions and the branch-likely instruction family and added things like compact (no delay slot) branch instructions, the requirement that hardware supports unaligned loads and stores (or, at least, that the OS traps and emulates them), and added much better support for PC-relative addressing. The result is a nice ISA, which is not backwards compatible with MIPS32r2 or MIPS64r2, the ISA that these boards use. Any investment in software for MIPS now is going to be wasted when products with the new ISA come out.

Re:no price?

[Anonymous Coward]

Wouldn't it be just a matter of re-compiling your code though?

I love MIPS and, that is the case in large part, because of its current instruction set. It seems like a bad idea to mess with the current instruction set and break backward compatibility. Why did they decide to do that?

Re:no price?

[LoRdTAW]

It doesn't always have to boil down to price. This is the same argument over and over again from some maker/hacker types who want to turn platforms into religions.

The Raspberry Pi is a lackluster board with a crummy SoC and limited I/O and no FPU. Not to say that the Raspberry Pi is total crap, it does its intended job very well and there is a lot of community support. Plus where else can you buy a $35 board that runs Linux and X with HDMI USB and Audio?

But it falls flat in a few areas that is frustrating. First off it has *ONE* PWM output. Anyone looking to use this for motor control has to add an external PWM chip. Not a big deal but an annoying one. Next problem is there is the Ethernet is a USB-Ethernet chip on board, there is no hardware Ethernet NIC on the SoC which robs the CPU of cycles. Next up, and this is my gripe with many boards: no high speed interface. There is so much more these boards could do if we could attach an FPGA to them. Sure there is SPI but it simply isn't fast enough for certain things. The only board that can do this is the Beagle Bone which gives you an external bus interface but that disables the HDMI as the pins are shardes on the SoC. So its a trade off.

What I want to see in a dev board: dual core SoC w/FPU, 1GB RAM+, GPU, HDMI, SD card, SPI, I2C, 6-8 channels of 16 bit PWM, 8 channels of Analog 12bit-16bit, hardware 10/100 or gbit, 4xUSB host, *external bus interface not shared with I/O*. That's it. Just let me plug an FPGA daughter card that gives me the option to load bit files from the CPU and we are golden. Then we can do what ever crazy thing we want: more custom PWM (e.g. directly drive 3 phase bridges), quadrature encoders, faster ADC's, delta-sigma DAC's, high speed I/O, custom bus interfaces, etc. And make it cost $75. We are close to having a board like this, we just need the interest and the right SoC.

Re:no price?

[topham]

Sold it cheaper? Why?

The Rpi has an excellent price, it's low enough that price is not the deciding factor on using it.

Re:no price?

[obarthelemy]

What makes the Pi attractive is relative openness.
There are a lot way more powerful Android sticks that end up cheaper ( http://www.geekbuying.com/item... , $43 w/8GB Flash, WiFi, BT and a PSU are included)
The hardware could be more open, but the libraries and documentation for the CPU/pinouts, and above all the GPU, would require a lot of work and hit a lot of walls. It's telling that the Pi's competitors are all chipset-maker driven.

Re:no price?

[TheRaven64]

Wouldn't it be just a matter of re-compiling your code though?

Assuming that your code doesn't do anything that is vaguely MIPS specific. If it is, then there is little benefit in using MIPS32r2 now - ARMv7 is likely to be closer than MIPS32r2 to MIPS32r6 in terms of compatibility with C (or higher-level language) source code compatibility.

I love MIPS and, that is the case in large part, because of its current instruction set. It seems like a bad idea to mess with the current instruction set and break backward compatibility. Why did they decide to do that?

Basically, because the MIPS ISA sucks as a compiler target. Delay slots are annoying and provide little benefit with modern microarchitectures. The only way to do PC-relative addressing is an ugly hack in the ABI, requiring that every call uses jalr with $t9 in the call, which means that you can't use bal for short calls. The lwl / lwr instructions for unaligned loads are just horrible and introduce nasty pipeline dependencies. The branch likely instructions are almost always misused, but as they're the only way of doing a branch without a delay slot there's often no alternative.

Re:no price?

[mark-t]

There's no price yet because they're giving away the first production run to people who are going to do interesting things with them...

If that were actually the real reason that they don't have a price on it, then that would also imply that they do not want anyone to have one who doesn't already know what they want to do with it, and has an idea that *THEY* approve of.

Re:no price?

[tepples]

Wouldn't it be just a matter of re-compiling your code though?

Good luck convincing publishers of existing proprietary applications, libraries, operating systems, and drivers to recompile their code.

Re:no price?

[mark-t]

I would suggest that the much bigger problem with a lack of price means that it's currently impossible to get one at all, since the giveaway period has also expired.

Re:no price?

[Fnord666]

There's no price yet because they're giving away the first production run to people who are going to do interesting things with them.

The program is now closed anyway, so I guess we'll just have to wait and see

Thanks for your interest in the MIPS Creator CI20 development board. While the current programme is now closed, stay tuned for more information as the Creator programme progresses as part of the Imagination community.

Re:no price?

[Anonymous Coward]

$43 + TV = Total

Re:no price?

[goarilla]

I've been looking for some of those features as well (gbit ethernet, extra USB and faster cpu and SATA)
and the closest thing i found was the Banana PI.

Re:no price?

[Anonymous Coward]

I just want a cheap TPU with an open compiler.

Re:no price?

[niftymitch]

It doesn't always have to boil down to price. .......

The Raspberry Pi is a lackluster board with a crummy SoC and limited I/O and no FPU. Not to say that the Raspberry Pi is total crap, it does its intended job very well and there is a lot of community support. .........

OK I am a child of the 60s. Time not the drug thing...

The Raspberry Pi is an astounding teaching tool.
It is open at all the important levels (hardware and software) that
are impossible or impracticable for a student and class to explore
on any other computer.

At the current price it is less expensive than most textbooks.

It supports all the tool chains a student needs support on and
supports virtually any programming language worth teaching
and worth learning.

The last turn of the Raspberry Pi gave it more USB ports and
a better connector for the OS flash media (mSD). All good stuff.

I have built small MPI clusters with them and noticed that I quickly
ran into problems that plague programmers of million dollar clusters that I have
worked on. The Beaglebone Black is a nice baby step forward in ARM land.

This MIPS board that started this does need to match the price and features
of the R-Pi or BBB if it is to have legs. I am a fan of the MIPS ISA but with
modern compilers the ISA is almost a don't care.

Re this MIPS board do wish it had dual+ GigE networking. I do wish it
had more DRAM. I do wish I knew more about it in detail.

Of interest the SD card, case and wall wart power supply cost as much as the
board itself. All together it costs less than most textbooks....

But golly folks do not ignore the Raspberry Pi.

Re:no price?

[Brane2]

Just curious, what's so wrong with branch with delay slot and isn't that more native way to look at branch ?

Everywhere where it matters ( loops) there is at least one instruction that can be inserted into slot, so this shouldn't be a problem.

Isn't this more problem of compilers that weren't designed to use such feature than architecture's wart ?

It probably can eb hidden within modern implementations, but still it seems nice to have in smallest implementations, possibly on FPGA.

Re:no price?

[amiga3D]

A lot of pi's don't use a monitor but are run headless. They do however need a charger and an SD card.

Re:no price?

[amiga3D]

Price always matters.

Re:no price?

[TheRaven64]

Just curious, what's so wrong with branch with delay slot and isn't that more native way to look at branch ?

They're a pain for people on both sides of the ISA.

The compiler has to find an instruction that can run after the branch. This is normally trivial for calls, but for conditional branches within a function it's often difficult to find an instruction that you can put there. It has to be one that is either from before the jump (or in both basic blocks after the jump), but that the branch doesn't depend on (because it's executed after the branch instruction). This means that you quite often end up padding the delay slots with nops, which bloats your instruction cache usage. On a superscalar implementation this is the only cost, but on a simple in-order pipeline it's also a completely wasted cycle.

On the other side, it's a pain to implement. It made sense for a three-stage pipeline in the original MIPS, because you always knew the next instruction to fetch. A modern simple pipeline is 5-7 stages though, so your branch is still in register fetch (if there) by the time the delay slot is needed. It doesn't buy anything and it means that, if you're doing any kind of speculative execution (even simple branch prediction, which you really need to do to get moderately good performance) then you have an extra dependency to track - you can't just use the branch as the marker and flush everything after it, you need to do some reordering. In a superscalar implementation, you need to do even more complex things in register renaming to make it work.

Re:no price?

[Anonymous Coward]

> But golly folks do not ignore the Raspberry Pi.

Don't ignore all the better platforms in the exploding ARM ecosystem. Freescale, Allwinner, TI and lots more are shipping inexpensive ($100) ARM linux SBCs with far more capabilities than the Pi. BeagleBone (TI's chip IIRC) is just one of many options.

Re:no price?

[Anonymous Coward]

I think you hit the nail on the head.

$100 ARM boards.

Comapred with th Raspberry Pi at $25/$35. 3 or 4 times the price....

So, clearly these boards at 3-4x the price are going to have better features. You get what you pay for.

Re:no price?

[Agripa]

What makes the Pi attractive is relative openness.

Isn't the BeagleBone Black even more open?

Re:no price?

[Anonymous Coward]

Unique ISA gets dumped in favor of boring me-too features. And this should interest me as a hacker how exactly? If I wanted to tinker with code generation or low-level assembly code, easy just means boring. I also very much doubt that any of the peripherals will come with full documentation. I get to run C code on an outdated OS full of proprietary drivers all running on a board with substandard performance.
Hey, but the compiler back-end writer had an easier time this time around, yay!
And how is this MIPS2^nr6 thing going to run all that legacy code which I presume is the reason anyone is still running on MIPS CPUs?
If anything, this board sounds like the best it will get, and that's not saying much.

Re: no price?

[ajlitt]

Outside of the 1gb RAM, dual core, and dedicated bus, BeagleBone Black is your board. Unfortunately the new revision have more eMMC and not more RAM for the money.

As for the bus, the manufacturer has to decide between bringing everything out on high density connectors that are useless for hobbyists, or be selective and use common .1" pitch box headers. BB/BBB, Arduino, and RasPi all owe some of their popularity to that accessibility. The BBB has some limitations imposed by the peripheral choice, though eMMC and HDMI can be disabled to get access to the full 16 bit GPMC bus. I've used this on a project before and had a NAND cape and FPGA hanging off it with a bunch of pins left over for peripherals.

What we would both probably like is a BeagleBone like board with the Freescale I.MX6 quad, like the Udoo without the Arduino or a cost reduced Novena.

Re:no price?

[Narishma]

Except for the GPU, which is more open on the Pi.

Re:no price?

[Narishma]

The RPi SoC has an FPU. It also has some limited form of SIMD.

Nice, but...

[Anonymous Coward]

They are apparently overwhelmed with interest and have thus closed the free giveaway offer! :(

why submit a project without knowing the price ?

[Anonymous Coward]

Why would anyone want to waste time on a project for this board without even knowing what the board eventually is going to cost ?
Price is an important factor in evaluating the platforms chance for success and developers do not want to develop for a platform that is doomed a priori because it is simply to expensive.

Unavailable

[Anonymous Coward]

The "current programme is now closed", and still no word on pricing.

So, empty promises. Oh well. NEXT!

PowerVR graphics

[Anonymous Coward]

When will they learn?

Re:PowerVR graphics

[lisaparratt]

You expected a different graphics solution from Imagination Technologies?

Re:PowerVR graphics

[Carewolf]

You expected a different graphics solution from Imagination Technologies?

At least they could have provided drivers if they want Linux developers using it. Just shipping an unsupported GPU that doesn't even have decent binary drivers is kind of pointless.

Re:PowerVR graphics

[Narishma]

What makes you think they aren't providing drivers?

Re:PowerVR graphics

[Carewolf]

What makes you think they aren't providing drivers?

That they are providing their normal drivers which are no good. They either need to make better drivers (which I don't think they can), or they need to help the production of open source drivers which this could have been a good move to do, but as it is, they just going the NVidia route without the manpower, quality or anything.

Re:why submit a project without knowing the price

[topham]

Because I don't care what it costs YOU to develop the project, I care what it costs me...

Ok, that's an over simplification. The board looks pretty sweet and would be an excellent choice for a project I'm working on. I expect that Imagination Technologies is trying to gauge demand, which will affect the price point of the final board / production. I've submitted an entry, however due to timing and their site problems (it initially crashed because of the load) it was a pretty short paragraph or two and I doubt my project will be selected. But I'm looking at other contenders rather than my initial plan of the Rpi because it has various short comings (of which, this board seems to sidestep quite nicely).

Re:why submit a project without knowing the price

[FyRE666]

On the projects I work on at least, the cost of the MCU hardware is almost irrelevent. In fact in most commercial projects involving microcontrollers or embedded systems, the cost of development boards is not that important. If you're rolling out a large volume of devices you're almost certainly going to be using a custom board anyway. Aside from all this, I can't imagine the cost of the board will be far out of line with similar products; as it'll need to compete when it's released for sale.

Power supply

[goarilla]

The site mentions a power supply so what's the power envelope ?

Re:why submit a project without knowing the price

[petes_PoV]

Why would anyone want to waste time on a project for this board

You wouldn't waste time on a project for this board as the specs for it seem to be entirely generic. So your project would work just as well on many of the other SBCs out there. There don't seem to be any killer features on this product (possibly the camera) so whatever you were planning to create for a Cubie, or an Olimex or any of the others would work on this one, too. And if it didn't then just toss this variant and continue working on the more mature SBCs

Re:why submit a project without knowing the price

[Anonymous Coward]

Another important factor is having a reliable source for your components (grumble)

Fragmented

[Circlotron]

I can see this small board stuff getting as fragmented as the bazillions of Linux distributions available. Choosing which board you want to play with will get as complicated as choosing a phone plan. Too much choice is not good. What the right amount of choice is, I don't know.

Re:Fragmented

[Anonymous Coward]

Just use what you're going to use and fuck all to the rest. Why the fuck do you people get so hung up on what other people use?

Re:Fragmented

[Anonymous Coward]

I can see this small board stuff getting as fragmented as the bazillions of Linux distributions available.

This is nothing new. Things have been fragmented from day one when there was the 8080 and 6502. Latter embedded processors such as the 8051 and PIC would exist also.

This board does have a very compelling feature set with bluetooth and wifi built in. The primary concern will be price point.

Re:Fragmented

[phantomfive]

More choice in ISAs is always good.

Re:Fragmented

[mark-t]

I agree with your first sentence entirely, but to answer your question, standardization makes it a lot simpler, and often less expensive, to find technical information or support for whatever it is you are using.

Not giving away free anymore

[Anonymous Coward]

http://store.imgtec.com/mips-creator-ci20/

Running heavy on ads lately

[zephvark]

Slashdot's been running awfully heavy on marketing promotional material, lately, with things that aren't even available yet. This one doesn't even have a price? I thought I checked the "ads disabled" checkbox.

Re:why submit a project without knowing the price

[Anonymous Coward]

Shut the fuck up and stop wasting everyone's time with your whiny trollish nonsense. Go shove an arduino and raspberry pi up your ass hole and let the big boys play with their new toys. Price isn't everything.

competitive features? generally available? not yet

[keneng]

This mips board is dual-core 32-bit. Other manufacturers have shipped mini-pc form factor boards with: -Intel octacore 64-bit, -ARM octa-core 32-bit, -ARM quad-core 32-bit, -ARM dual-core 64-bit.

It's very interesting to have another alternative, but MIPS manufacturers will have play catch up in terms of core-count, price and GNU/Linux open-source support with respect to the kernel and the graphics chipset aspect in order to turn some heads and have people fork out cash for them. I'm still conservative. In my humble-opinon dual-core ARM or MIPS running at ~ 1GHz doesn't compare well-enough with >3GHz dual-core Intel product in terms of GUI responsiveness. Battery life isn't the only concern and never will be. INTEL/AMD rock my world on the desktop, but ARM QUAD-CORE is adequate and I'll admit that. I have no problems recommending QUAD-CORE anything, provided they have 4-8 GB RAM, SATA, USB 3.0, and Gigabit Ethernet. Anything else will frustrate users or users will end up wanting for more a couple of days after the purchase. I'm not talking mobile devices here. I'm talking wanna-be hybrid tv-box/mini-PC as desktop replacements. Why are we still selling 1GB RAM to 2GB RAM devices? I'll tell you why: MANUFACTURERS want to dump their legacy product before they ship the newer gen stuff. I won't sell that stuff because nobody wants that or will be frustrated with that stuff. Is it just me or do the manufacturers have a "TAKE IT OR LEAVE IT" attitude towards the consumers. Didn't dual/quad core-32bit exist 15 years ago? Something doesn't smell right in this picture. Shouldn't we be octa-core 64-bit on the desktop/mobile already?

Re:competitive features? generally available? not

[Bert64]

Linux support for MIPS is actually pretty good, and has been around at least as long as ARM support if not longer... The rest of the toolchain, like gcc etc also has good MIPS support. There is already 64bit MIPS support in the Linux kernel and has been for a long time too, MIPS is actually one of the oldest 64bit architectures out there.
MIPS would actually be better off focusing on this, as they have a good head start on ARM when it comes to 64bit and multiprocessing. I used to have a 24 cpu (discrete cpus, not cores) 64bit MIPS years ago in the form of an SGI Onyx.

No, that makes it uninteresting

[drinkypoo]

Wake me up when there is pricing, and I'll decide how interested I am. I'm not interested in a product which could cost $INFINITY dollars.

Re:No, that makes it uninteresting

[Anonymous Coward]

A dumb fuck is going to be a dumb fuck. That should be your motto.

Re:No, that makes it uninteresting

[drinkypoo]

A dumb fuck is going to be a dumb fuck. That should be your motto.

Actually, it should be what you see when you click on Anonymous Coward's name.

Re:why submit a project without knowing the price

[Anonymous Coward]

Oh the irony. What's up, did you grab your Fisher Price soldering iron by the wrong end again?

Imagination PowerVR? KEEP CLEAR!

[Anonymous Coward]

I'd rather burn the fucker than bother with it.

PowerVR is the absolutely worst GPU core. The company is hostile to open source development and the chip is incredibly (uselessly?) complex. People have being driven to insanity trying to reverse-engineer it. So unless Imagination also "does a RasPi" and helps develop proper open source drivers they can keep their sucky boards.

Re:Imagination PowerVR? KEEP CLEAR!

[Viol8]

Right, because obviously with a board like this someone is going to try and create a Call of Duty clone rather than say some sort of controller system.

Or not.

Re:Imagination PowerVR? KEEP CLEAR!

[Anonymous Coward]

Because the only thing someone could possibly want do with a wide vector FPU on a embedded board is create a Call of Duty clone.
*facepalm*

MIPS asm vs x86 asm

[Anonymous Coward]

This is a good way to learn assembly language.

Re:why submit a project without knowing the price

[drinkypoo]

Aside from all this, I can't imagine the cost of the board will be far out of line with similar products;

Depending on how you write the definition, "similar products" can cost anywhere from about $35 on up to about $500.

Re:competitive features? generally available? not

[Anonymous Coward]

> Why are we still selling 1GB RAM to 2GB RAM devices?

Microchip still sells the PIC10F200, with 16 bytes of RAM. SoCs exist in every imaginable configuration from there on up to chips which are comparable to a low-end PC, and will continue to do so for the foreseeable future. The top-end will continue to grow, but the bottom-end and middle won't disappear.

For a "device" which is supposed to run a specific program, with no ability to install additional software, you can determine an upper bound on the resources the system actually needs, so there's no point in paying for any more than that.

Re:competitive features? generally available? not

[Anonymous Coward]

so there's no point in paying for any more than that.

or using more power to refresh more RAM.

Patent on this new feature

[tepples]

MIPS32r6 [...] added things like [...] the requirement that hardware supports unaligned loads and stores (or, at least, that the OS traps and emulates them)

What kind of patent does Imagination Technologies have on features essential to MIPS32r6? And how is it licensed, compared to (say) ARM? If you'll recall, unaligned loads and stores were one of the few things about the original MIPS ISA that were patented.

Re:Patent on this new feature

[TheRaven64]

No idea. I don't know if the instructions for computing PC-relative addresses in an ISA without an architectural PC are patentable. They also exist in RISC V (not sure which came first), so if they do then it's going to be a problem for Kriste et al. Nothing else in there is especially novel: like ARMv8, it's a nicely designed compilation target, but it doesn't do anything that's especially exciting.

I didn't look at the floating point stuff in much detail, so there may be something there, although the biggest changes in recent versions of the MIPS specs have been that they're more closely aligned with the IEEE floating point standards, so it's hard to imagine anything there.

The biggest difference between MIPS64r6 and ARMv8 is that the MIPS spec explicitly reserves some of the opcode space for vendor-specific extensions (we use this space, although our core predates the current spec - it's largely codifying existing opcode use). This allows, for example, Cavium to add custom instructions that are useful for network switches but not very useful for other things. ARMv8, in contrast, expects that any non-standard extensions are in the form of accelerator cores with a completely different ISA. This means that any code compiled for one ARMv8 core should run on any ARMv8 implementation, which is a big advantage. With MIPS, anything compiled for the core ISA should run everywhere, but people using custom variants (e.g. Cisco and Juniper, who use the Cavium parts in some of their products) will ship code that won't run on another vendors' chips.

Historically, this has been a problem for the MIPS ecosystem because each MIPS vendor has forked GCC and GNU binutils, hacked it up to support their extensions, but done so in a way that makes it impossible to merge the code upstream (because they've broken every other MIPS chip in the process) and left their customers with an ageing toolchain to deal with. I've been working with the Imagination guys to try to make sure that the code in LLVM is arranged in such a way that it's relatively easy to add vendor-specific extensions without breaking everything else.

Imagination doesn't currently have any 64-bit cores to license, but I expect that they will quite soon...

Re:why submit a project without knowing the price

[mark-t]

Consider that without a price, a person doesn't even have the OPTION of buying one...

And of course, price *IS* important in the real world... most people don't pay more money for something if they do not genuinely believe that it carries a value that is worth the amount of time and energy that it took to earn that amount of money. That's all very well and good if you have infinite amounts of cash, but most of us do not, and have to do menial things like budget. That involves knowing what your expenses are likely to be, and what kind of time frame it would take to pay for things that you do get.

no Gbit, no sale

[dltaylor]

There appears to be enough RAM and enough compute power, but the Ethernet interface is pathetic. Even in an inexpensive experimenters' board, GBit Ethernet should be standard. For one thing, it's hard to judge the real processing power needed (as a fraction of the available) for networking, when the network, itself, is the bottleneck.

Re:competitive features? generally available? not

[Misagon]

1GHz doesn't compare well-enough with >3GHz dual-core Intel product in terms of GUI responsiveness.

GUI responsiveness is more a matter of software bloat than about hardware.

A Commodore 64 at 1 MHz running GEOS can sometimes be more responsive than a PC with dual eight-core Haswell Xeons.

Re:competitive features? generally available? not

[Anonymous Coward]

So what you're saying is:
1)Android and GNU/Linux(Debian for example) both suffer from GUI software bloat.
2)you would rather see Commodore 64 GEOS desktop applications running on this hardware.

I will respond to both points:
1)Android and GNU/Linux(Debian for example) both suffer from GUI software bloat.
MY ANSWER:Perhaps Android and GNU/Linux both do have GUI SOFTWARE BLOAT, BUT slower hardware will run GUI software more slowly....BLOATED OR NOT! You may not dispute the fact that DUAL-CORE 32-BIT MIPS BOARD QUAD-CORE 32-bit ARM BOARD QUAD-CORE 64-bit INTEL/AMD BOARD when all of them are running GNU/LINUX or ANDROID on them. I'm not trying to run a leaner less-familiar less-versatile GEOS desktop on smaller-form factor hardware. I'm trying to run my current DESKTOP GNU/Linux software on ULTRA-QUIET ULTRA-SMALL HARDWARE without any concerns for lower-power.

2)you would rather see Commodore 64 GEOS desktop applications running on this hardware.
I took a look and found it was open-sourced:
http://lyonlabs.org/commodore/onrequest/geos.html
It would be masochistic to consider GEOS as a tool for developer. Any C/C++ coder could appreciate the assembler presented yes, but ask any of them if they prefer coding in assembler all the time and they'll tell you the same: MASOCHISTIC. I'll take c++ or golang any day over assembly.
Not to mention no tcp/ip no web server no NOTHING FOR GEOS. GEOS SOFTWARE: NO THANKS for me. I'll stick to Contemporary DEBIAN GNU/Linux with all it's GNOME BLOATWARE which I have love to use.
For posterity's sake you can recompile and run it for this hardware, but you'll be wasting your time. It would be more constructive to focus on GNU/Linux sources than GEOS sources if you're aiming for others across the planet to reuse something you have built.

Imagination fail

[Anonymous Coward]

Lots of people are commenting on the lack of pricing, this isn't really a release in any sense most developers who'd pick up a minnow/beagle/RPi would consider one.

There's a completely separate fact to consider here, there are no SGX drivers for linux. We've personally felt this pain before, having considered TI OMAP processors a while back - only to realise that 'SGX' support from TI is them telling you to approach IT to get the DDK, and write your own drivers under an NDA, with ridiculous terms that involve large legal costs, technical limitations, and licensing considerations.

You'd be better off going with a board that doesn't have a PowerVR GPU if you need OpenGL/OpenCL/OpenVG. nVidia (tegra), Qualcomm (adreno), or ARM (mali) - are all better supported, either with binary closed-source drivers, open-source drivers in the worst case, and some even go as far as TRMs if you want to use the GPU in some other fashion (in some cases under NDA, in some not).

Re:Imagination fail

[Anonymous Coward]

It's happened in places besides TI OMAP, the original HardKernel ODROID-XU had a samsung exy5-quad SoC with a PowerVR SGX - they had similar issues, where they were told to write their own drivers from scratch which they eventually ditched for undisclosed reasons.

HardKernel's (an entire team, whose entire business is making and supporting dev boards) attempt to use PowerVR SGX is quite telling with respect to how bad Imagination Technologies really are. The ODROID-XU is now being discontinued (http://www.hardkernel.com/main/products/prdt_info.php?g_code=G137510300620) and HardKernel released a whole new ODROID-XU3 (http://www.hardkernel.com/main/products/prdt_info.php?g_code=G140448267127) that uses ARM Mali instead to avoid the PowerVR nightmare.

Re:Imagination fail

[Anonymous Coward]

Vivante GPUs are also quite great, and very well supported on linux. (in addition to those you listed)

Worse than that -- no Ethernet on the SoC

[Anonymous Coward]

You point out that that the Ethernet is not gigabit so it's poor in comparison with the rest of the specs, but the situation is far worse than just that.

The Ingenic JZ4780 SoC doesn't have any kind of Ethernet controller built in whatsoever, so this board uses an external Davicom DM9000C (datasheet pdf) device and the SoC talks to it through an 8-bit interface.

That's going to make the networking performance not just "poor" but probably terrible. The test results are going to be "fun".

Wait for RISC-V

[Anonymous Coward]

If we have to change everything when upgrading from MIPS 32 bit to MIPS 64 bit anyway -- why not wait for (even contribute to) RISC-V -- instead of submitting to Imagination's burdensome license restrictions?

Re:Wait for RISC-V

[mark-t]

Iirc, MIPS32 ISA is wholly compatible with MIPS64 ISA, the latter being a proper superset of the former.

How not to do it.

[Anonymous Coward]

Way to announce something I can't buy.

Re:competitive features? generally available? not

[Brane2]

So what ?

Many ARMs are sold as unicore 50MHz Cortex 3 for example. Not every application needs 16 cores at 2+GHz, for more than one reason.

And 64 bits is more of an ograde on x86 than other machines especially if one doesn't have more than 3GiB of RAM.

Re:why submit a project without knowing the price

[FyRE666]

Which product(s) have the same specs as a RPi and cost $500?

For those who got the board...

[Anonymous Coward]

Did you have them sign a non-disclosure agreement or was your "intellectual property" worth the price of a board?

Re:competitive features? generally available? not

[Anonymous Coward]

All very well wanting octacores, loads of memory, gigabit ethernet, but all those things cost money. Lots of it. Putting 8 cores on a silicon die takes a lot of space. That directly sets the price of the chip. So the manufacturing cost will be considerably higher, with consequent increases in end user prices. Its the same with ethernet, RAM etc. You want more features? You WILL have to pay more to get them, just in silicon die area.

It's one of the reasons the Raspberry Pi has stayed at its price point. The SoC hasn't changed in price - the die hasn't got smaller so the manufacturing of it is still costing the same as it has always done, and since the RPF already get a decent deal on the chip, there is no room to drop the price even though the chip is quite an old design.

Re:competitive features? generally available? not

[Anonymous Coward]

I'd argue it's not software bloat, but just badly written software that mean slow GUI's (and yes, they are slow for what they do). For example, GT and GTK over X windows attempt to mimic in some ways the Windows API, presumably to make it easier to transition. However, this means a huge amount of inefficient X traffic bouncing around the place, even for something that should be low impact, like just moving the mouse around. Work done in this area on Raspberry Pi showed extremely good improvements to the user experience.

My opinion when it comes to inefficient software is that you should fix it, rather than just throw a faster CPU at it. Going quad code only really helps a slow app when you have multithreaded code in the app. It does help with overall performance, but really, get the software right first and everything gets better.

Re:why submit a project without knowing the price

[drinkypoo]

Which product(s) have the same specs as a RPi and cost $500?

If you haven't seen ARM dev boards with lower specs than a RPi which cost that much, then you haven't actually priced them.

Re: competitive features? generally available? not

[ajlitt]

Certainly longer, at least by a few years.

Re:competitive features? generally available? not

[armanox]

We're selling them because there is demand for them.

Also, this device clearly is not targeted to be a desktop replacement.

Re:why submit a project without knowing the price

[mark-t]

I would imagine that the reason price hasn't been announced yet is because they don't know just how much they will ultimately be able to make them for themselves, and the giveaway they are doing is to gauge demand so they can figure out how much they have to charge.

If that's the case, the more ideas that got submitted to them, the better it will be.

Of course, it also might mean that giving them a preview into what kind of demand to expect, they might know for sure just how much they will able to fleece future customers. So hey... what do I know?

Fragmented: too little vs too much

[unixisc]

When we had SPARC, MIPS, POWER (w/ all its internal variants - PowerPC/POWER/Power), Motorola's 88K, Intel's i860, Intergraph's Clipper and then DEC went on to add the Alpha to the list, that was too many choices. Instead of a gazillion Linuxes, you had a gazillion Unixes - one for each CPU, such as SunOS, AIX, DG/UX, CLIX, and more for some specific CPUs, such as SCO, Unixware (then separate), Interactive Unix, Dynix for the x86 and Irix/Ultrix/RiscOS for the MIPS II, such a situation was not good. It was tough to standardize any software targeting all these platforms. So initially, Sun, and later Linux, won out. A fewer ISAs would have been better

But all of the above diminishing or going away hasn't been good either - we have a duopoly of just x64 and ARM. I'd like to see MIPS, SPARC and Power return, the latter 2 not b'cos of IBM or Oracle, but rather smaller vendors taking the initiative and creating boards of this. On the software end, I'd like to see not just the various Linuxes, but also Minix, the BSDs and even Windows RT get ported to such platforms, so that people can choose what they want to build.

Re:Fragmented: too little vs too much

[phantomfive]

that was too many choices.

Now it wasn't. Maybe from some obscure business standpoint it was 'better,' but to me it was like having more playgrounds.

The reason there are fewer now has nothing to do with standardization, it's because they weren't able to keep up with the manufacturing processes. At the embedded level, where manufacturing process doesn't matter as much, there are still a lot of different ISAs. Recently I've been playing with the Parallax Propeller