Live data from Hacker News

Forth Inventor Chuck Moore's $20 144 core CPU now in full production

greenarraychips.com

11–20 of 100 posts

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#11
post #5

I think the only thing Chuck is missing is a few 20-somethings hackers, bent on solving an 'impossible' problem with his chips.

That's why I'm posting it here.

Some possible ideas

====================

- Sound processing (think 144 cores preforming Fourier Transforms)

- Pico Satellites (This chip has a surprisingly extreme low power requirement).

- Wireless communication (small power requirement means small batteries)

- Computer Vision processing. Imagine toys or tools that can process visual information faster than an Xbox.

- Basically anything that can be done in parallel, that is suited for small size and low power, but doesn't require much on chip memory.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#12
The Propeller chip http://www.parallax.com/propeller/ is another embedded market chip in the same vein although nowhere near as many cores. Having something like this make for some interesting embedded designs.

Also, check the site for the arrayForth stuff.

On another note, it would be interesting if something like these existed in the 64-bit size. Larrabee is interesting, but if it was a simpler stack machine at around this price point then perhaps some work could be done on different ways to do parallelism.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#13
post #4

Love the guy and his passion for its chips, but this 144-computer chip looks like a solution in search of a problem: what is trying to solve? How's the inter-core communication handled? On the other hand, creating weird chips like these, just because you can, is awesome and stimulating a hacker's mind.

Not sure if it's a legitimate "problem" or not, but how about the availability of single chips, or 10-packs?

Assuming someone wanted to produce a prototype board, but didn't want to purchase 1000's of CPU chips, are there many CPU chip makers who offer low quantities like this?

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#14
post #4

Love the guy and his passion for its chips, but this 144-computer chip looks like a solution in search of a problem: what is trying to solve? How's the inter-core communication handled? On the other hand, creating weird chips like these, just because you can, is awesome and stimulating a hacker's mind.

It appears that CM's intent with the F18A core is to create an extremely low power processor that scales the number of cores to the complexity of the problem being addressed -- look at the reference sheets about what the requirements are to maintain core states.

The design makes more sense when you stop trying to think of it as an ARM or AVR competitor, and more like a replacement for FPGA's.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#15
post #11
post #5

I think the only thing Chuck is missing is a few 20-somethings hackers, bent on solving an 'impossible' problem with his chips.

That's why I'm posting it here. Some possible ideas ==================== - Sound processing (think 144 cores preforming Fourier Transforms) - Pico Satellites (This chip has a surprisingly extreme low power requirement). - Wireless communication (small power requirement means small batteries) - Computer Vision processing. Imagine toys or tools that can process visual information faster than an Xbox. - Basically anythi…

Had a rough look on it's instruction set and didn't see anything resembling DSP instructions. So i'm not sure it would be great for all those uses.

On the other hand, picochip sells a 200-300 core DSP , that is being used for the wireless industry.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#16
post #3

Let me get this straight: It's basically a microcontroller timed 144? Can anyone explain to a nonhardware geek?

I've done many write-ups on this if you look under my profile. Basically the idea is that most of the big problems in software engineering can't be solved easily in a serial fashion with current methodologies, and many of the existing parallel solutions are either too expensive or two complicated to advance the state of the art. I wish I had this chip 15 years ago...

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#17

The Propeller chip http://www.parallax.com/propeller/ is another embedded market chip in the same vein although nowhere near as many cores. Having something like this make for some interesting embedded designs. Also, check the site for the arrayForth stuff. On another note, it would be interesting if something like these existed in the 64-bit size. Larrabee is interesting, but if it was a simpler stack machine at aro…

Tilera does a 64-bit CPU with 64/100cores.If they would offer access to it using a pay-per-hour model, that would be interesting.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#18
post #15
post #11

Earlier quoted context omitted.

That's why I'm posting it here. Some possible ideas ==================== - Sound processing (think 144 cores preforming Fourier Transforms) - Pico Satellites (This chip has a surprisingly extreme low power requirement). - Wireless communication (small power requirement means small batteries) - Computer Vision processing. Imagine toys or tools that can process visual information faster than an Xbox. - Basically anythi…

Had a rough look on it's instruction set and didn't see anything resembling DSP instructions. So i'm not sure it would be great for all those uses. On the other hand, picochip sells a 200-300 core DSP , that is being used for the wireless industry.

From this PDF http://www.greenarraychips.com/home/documents/greg/PB001-100... GreenArrays seems to think it would support DSP

"SUITABILITY: The GA144 is designed to support the largest and most demanding computing challenges that can be addressed with a modest sized die in a relatively inexpensive and easy to use package while still using well less than 650 mW in most practical applications. The geometry allows for generous numbers of parallel paths and/or pipeline stages, or for complex flowgraphs in control, simulation, or DSP applications. Clusters of nodes devoted to functions such as cryptographic algorithms are easily placed in the large array, and the cluster needed to control external memory and run a high level language from it is well out of the way but has good surface area for interaction with other functions. Use it also as a universal protoytping platform for applications destined to run on our smaller chips. "

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#19

Not being much of a hardware geek, I'm having a hard time evaluating how fast each core is. From the site: "With instruction times as low as 1400 picoseconds and consuming as little as 7 picojoules of energy, each of the 144 computers can do its work with unprecedented speed for a microcontroller and yet at unprecedentedly low energy cost, transitioning between running and suspended states in gate delay times. When s…

If 1400 picoseconds is the time it takes for a clock cycle (and therefore the minimum instruction time for 1-cycle instructions), that'd be about 700 MHz, which actually seems pretty high compared to what I would've guessed.

Re: Forth Inventor Chuck Moore's $20 144 core CPU now in full production

#20
post #6

May be if you use 100+ of these (~14400 'computers') you can build a machine with emerging behavior, brain-like?

I knew it. The name "Moore" sounded suspicious to me immediately. Now I know his real name is Chuck Testa!!!

On a more serious note, what we need much more of is not the processing speed. What we need much more of is what I call "memory processability", which roughly means "how many times per second can you process the whole memory" - or something like that. Basically how much CPU is there per RAM. Indexing is a great hack, but a hack it still is. Memory and processing cells must be merged into a single, massively parallel chip.

Post reply on HN