Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

RTX2010 – Radiation-hardened stack machine microprocessor

en.wikipedia.org

Post reply on HN
Print view View original

51–60 of 61 posts

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#51

Post by tailrecursion »

samatman wrote: post #50

The yearly Forth Day meeting is happening right now, and Chuck Moore (inventor of Forth, designer of the RTX2010) is going to give his annual fireside chat in a matter of hours. I'm honored to be in attendance. So if HN has any questions, this is a good time to ask them. The hangout is here: https://plus.google.com/u/0/115269917987589859757/posts

Sam, Chuck designed the Novix but the Harris RTX 2000, which is very similar, was designed by others.

These are 16-bit chips (the Novix addressed 128 KB) that use dedicated stack memories, that's 3 ports to memory total. The RTX puts the stacks on chip.

The nice thing about these CPUs is they can do stack, alu, and return in parallel, interrupts are cheap, timings are predictable, and programming model is nice if you like Forth. One disadvantage of the design is that clock rate is limited. RAM fetch and instruction processing have to fit between pulses meaning RAM has to be approx twice as fast as clock.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#52

Post by jacquesm »

gus_massa wrote: post #44
wlievens wrote: post #31

Earlier quoted context omitted.

I know that, but I don't think every material has the interesting properties that Si does for image sensors , i.e. it needs to basically turn photons of the right wavelength range into electrons.

Sorry. I misread your comment. Other users have answered the question, but I'd like to add a little more information. http://en.wikipedia.org/wiki/LED_circuit#LED_as_light_sensor > As a photodiode, an LED is sensitive to wavelengths equal to or shorter than the predominant wavelength it emits. For example, a green LED is sensitive to blue light and to some green light, but not to yellow or red light. If you want to m…

You could use Selenium as well.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#53

Post by jacquesm »

naland wrote: post #23
mud_dauber wrote: post #21

How cool - I joined Harris after grad school expressly to work on RTX architecture issues. (Previously I was a Forth developer.) Nice to see this neat-but-underappreciated architecture in the news.

>Nice to see this neat-but-underappreciated architecture in the news. It's already appreciated. Let me recall here the 'scientist' character (A&B Srugatsky) who explains the World as a huge inertial mass to the good or evil in the same. Tertium non datur it is a principle of our mind sometimes used in computers.

What does Russian SF have to do with the Forth high level machine?

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#54

Post by sehugg »

CHY872 wrote: post #37
wlievens wrote: post #14

Earlier quoted context omitted.

Optimal register allocation is an NP-complete problem. By doing away with it, you don't need to allocate registers. How that compares on a practical level, I have no idea. But it's one of the reasons the JVM has a stack-based model and no registers: it makes writing compilers for JVM byte code a lot easier.

This isn't quite right - we don't in general really care whether we're allocating optimally (for example, if we have 16 registers we don't care if we can potentially allocate to 10), and heuristic based approaches are practically very useful (and cheap). In terms of compiler writing, if you wanted to write any optimisations you'd probably want to manipulate 3-address code internally, if only because the data flow bas…

Don't forget bytecode verification which is easier with just a stack rather than a stack + registers. Java was not originally envisioned to become the default server side + JIT technology it eventually became, it was meant for embedded apps which meant small simple bytecode.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#55

Post by analog31 »

userbinator wrote: post #17
lelf wrote: post #3

Philae is controlled by 2 RTX2010 CPUs (hot red), further 8 control the Experiments. 13 CPUs (10* RTX2010, 1* ADSP-21020, 2* 80C3x) in total. © https://twitter.com/philae2014/status/427842417920712704

> 80C3x An 8051-family microcontroller, the CPU architecture that's found almost everywhere - including space. I wonder if they're running Forth too, as this old discussion I found also mentions 80C32 and RTX2010 together with Forth: https://groups.google.com/d/topic/comp.lang.forth/7PK44n68I_...

The 8052AH-BASIC is better known because of a Byte Magazine article, but there was also a commercially available 8051 variant that was mask programmed with a built in Forth interpreter. I've never seen one.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#56

Post by analog31 »

wlievens wrote: post #15
Osmium wrote: post #8

Earlier quoted context omitted.

Or we can use alternative semiconductors that are more radiation-resistant. One of many reasons why materials discovery is still very important even if initial chips will never match the performance of silicon.

Wouldn't work for all applications, tough, if I'm not mistaken, as you specifically need Silicon for imaging chips (CCD/CMOS). Or is that nonsense?

I work with optical detectors. There are certainly other materials that can be used for imaging. There are some things going for silicon -- depending on the application of course. Notably, it's sensitive to the visible wavelength range, up into the UV, and can be turned into detectors with extremely low self-noise. It can be manufactured at a level of purity that allows for extremely low electrical leakage that would otherwise add noise. Any system of two or more elements can't reach this purity because it would require an absolutely perfect stoichiometric mixture.

Large "scientific" CCD's benefit from large geometries (typ. 25 micron pixels), which probably contributes to radiation hardening. But it's hard to protect a chip from radiation without keeping it in the dark.

There's also the fact that silicon has received such refinement thanks to the overall semiconductor industry.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#57

Post by wtracy »

noselasd wrote: post #9
tinco wrote: post #4

I wonder how hard it is to create a radiation hardened CPU. Is the premise that radiation can flip bits in the on-die cache and registers? would simply making those redundant be a solution? Or could a single flash of radiation invalidate all memory on the device?

Yes, one of the premises is it flips bits, a phenomena called Single Event Upset(SEU) - e.g. the open source LEON FT ( http://www.gaisler.com/index.php/products/processors/leon3ft ) processor, is designed to be able to correct and detect such errors - in addition to being manufactured with materials that block radiation. In spacecrafts such radiation hardened processors are often used in addition to having redundancy…

Would optical processors be immune to some of these problems?

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#58

Post by na85 »

Someone wrote: post #16
wlievens wrote: post #15

Earlier quoted context omitted.

Wouldn't work for all applications, tough, if I'm not mistaken, as you specifically need Silicon for imaging chips (CCD/CMOS). Or is that nonsense?

Why would you need silicon for that? Even if it were the only process we use now (which it isn't. As a simple example, Germanium-based photo diodes do exist), materials research could conceivably produce other materials that work, too. There are even more exotic examples to think of. Eyes turn light into electricity without (AFAIK) Silicon. Maybe part of that physics/chemistry can be practically used elsewhere?

/nitpick:

Nerve impulses are not electricity. There is a moving charge gradient which is not the same as an electric current.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#59

Post by wlievens »

analog31 wrote: post #56
wlievens wrote: post #15

Earlier quoted context omitted.

Wouldn't work for all applications, tough, if I'm not mistaken, as you specifically need Silicon for imaging chips (CCD/CMOS). Or is that nonsense?

I work with optical detectors. There are certainly other materials that can be used for imaging. There are some things going for silicon -- depending on the application of course. Notably, it's sensitive to the visible wavelength range, up into the UV, and can be turned into detectors with extremely low self-noise. It can be manufactured at a level of purity that allows for extremely low electrical leakage that would…

Cool, where do you work? I work for an image sensor company (CMOS - not CCD), though I'm a pure software engineer (wafer and assembly test software among other tools) so I don't know that much of device physics, only that which I've gleaned from company-wide presentations and the such.

Re: RTX2010 – Radiation-hardened stack machine microprocessor

#60

Post by miga »

Sanddancer wrote: post #6
tinco wrote: post #4

I wonder how hard it is to create a radiation hardened CPU. Is the premise that radiation can flip bits in the on-die cache and registers? would simply making those redundant be a solution? Or could a single flash of radiation invalidate all memory on the device?

There's all sorts of problems you have to deal with. Memory flipping is one of the most visible, but that radiation also will damage the lattice of the processor, making some transistors harder to flip on, and some much easier to flip on, leading to transient glitches, etc. Redundancy's definitely one solution, which is one reason why spacecraft tend to have multiple processors and/or processors with redundant logic…

Like silicon on sapphire?
Post reply on HN