Looking Back at 1984 Report On "Radical Computing" 183
An anonymous reader writes "The Department of Defense has just released a long restricted report (PDF) by the JASON group entitled Radical Computing. This 1984 study outlines a number of alternate computing methods that could 'result in a radical improvement in computing.' The study attempts to explain the paradox of how the Russian lag in developing VLSI chips curiously did not critically hinder their accomplishments in space missions, ICBMs and chess computation. The authors speculate that the Russians might have achieved breakthroughs in alternative computing methods such as residue arithmetic and symbolic computing. (More cynical types assume the Russians bought or stole US chips from the French or other too-helpful go-betweens.)"
"The paper, published by the Government Attic website, also mentions how, eventually, highly parallel computers could make use of these alternative computational methods. Also discussed are such things as functional programming, interval arithmetic, recursive machines, multiple processor concurrency, fast recurrence evaluation, DDA machines, data-flow, and hyper-column cortex model. Which of these ideas ever came to fruition?"
Re:Well, that's the Pentagon for you.. (Score:5, Interesting)
Pffft. (Score:3, Interesting)
Clones (Score:5, Interesting)
For further reading, see Byte Magazine from April 1991. Surely all good /. readers have a copy somewhere?
Re:Well, that's the Pentagon for you.. (Score:4, Interesting)
>... and symbolic computing.
The report states that MIR-2 had some symbolic computation capabilities the US seemed to have caught up with only slowly. Read the report, it's on page three.
This report shows that the US was driven by the competition with the USSR. Who knows, it probably helped push MACSYMA along and people had some incentive to make some impractical sounding products out of this, like the little known Mathematica or also Maple.
I'm beginning to think that the computing world became so boring lately mainly because the cold war is over. Just look at the table listing all those technologies on page 5. It doesn't mention Quantum computing alright, but things like the hypercolumn cortex model might finally materialize in form of the Blue Brain project. It could very well be, that this initiative was a driver for some computing projects that wouldn't have happened otherwise.
Soviet vs. American engineering (Score:5, Interesting)
One of the main serious uses of computing, especially in the cold war, was solving partial differential equations. Whether these be for orbital calculations, stability analysis, EM simulation, etc..., solving partial differential equations is a critical part of any advanced engineering program.
The American approach really started in the 50s with the advent of programmable computers, and is very stereotypical: just find a decent approximation. Modern western engineering is all about using pretty advanced computers to find arbitrary numerical approximations to tricky PDEs. It's reached its culmination in modern engineering design, where most advanced products are designed and simulated in computers, and prototyping only occurs at the very end of the process.
The Soviets had computers.... some home built, some Western, but generally speaking they weren't very good. The Soviet approach was also very stereotypical: get an army of mathematicians and engineers to find exact analytic solutions to the problems you're trying to solve. You'd have armies of engineers and technicians designing things that in the west we'd give to a couple of engineers with some computer time.
The end result is that some Soviet engineering is stunningly brilliant. And a lot is absolute crap. One of the reasons the west won the cold war is that we were just much better at solving partial differential equations. This report is unsurprising... the Soviet approach just seems so stupid to any Western engineer unfamiliar with it, that you'd have to assume they had some magic trick up their sleeve. But nope, just a lot of brainpower misdirected into a lot of horribly inefficient pursuits.
Re:Eh. (Score:5, Interesting)
I think it's safe to say they didn't have any exotic computer technology. Of course, hindsight is 20-20. ^.^
No? It's well known that the Soviets developed computers based on ternary logic [computer-museum.ru] (rather than binary) -- that seems pretty exotic to me. I thought it was equally well understood that it was more expedient to switch to clones of Western technology, so that's what happened.
Re:Soviet vs. American engineering (Score:3, Interesting)
One of the main serious uses of computing, especially in the cold war, was solving partial differential equations. Whether these be for orbital calculations, stability analysis, EM simulation, etc..., solving partial differential equations is a critical part of any advanced engineering program.
The American approach really started in the 50s with the advent of programmable computers, and is very stereotypical: just find a decent approximation. Modern western engineering is all about using pretty advanced computers to find arbitrary numerical approximations to tricky PDEs. It's reached its culmination in modern engineering design, where most advanced products are designed and simulated in computers, and prototyping only occurs at the very end of the process.
The Soviets had computers.... some home built, some Western, but generally speaking they weren't very good. The Soviet approach was also very stereotypical: get an army of mathematicians and engineers to find exact analytic solutions to the problems you're trying to solve. You'd have armies of engineers and technicians designing things that in the west we'd give to a couple of engineers with some computer time.
The end result is that some Soviet engineering is stunningly brilliant. And a lot is absolute crap. One of the reasons the west won the cold war is that we were just much better at solving partial differential equations. This report is unsurprising... the Soviet approach just seems so stupid to any Western engineer unfamiliar with it, that you'd have to assume they had some magic trick up their sleeve. But nope, just a lot of brainpower misdirected into a lot of horribly inefficient pursuits.
I heard something similar from my older relatives who grew up in Communist countries.
Their take was that the Soviet computers were about 10x slower or even worse. For them, it was worthwhile writing software as "hand tuned assembler" to optimise it to the point that it would run 10x faster. However, this takes a lot more programmer time for the same amount of functionality.
Re:Well, that's the Pentagon for you.. (Score:3, Interesting)
This was deliberate misinformation by the US government, to justify defense spending, wars and a bunch of other stuff. And also, to scare people.
Use of residual arithmetic in GPUs? (Score:3, Interesting)
A lot of people are dismissing this report, but the ideas of residual arithmetic may in fact be plausible for things like GPUs, which are good at doing parallel computations and where the magnitude of the results are finite and known (two things the report mentions as making a problem suitable for residual arithmetic).
One thing which caught my eye is when they demonstrate how to evaluate polynomials using table look ups. It might be conceivable that things like ray/surface intersections in a ray-tracer, for example, could be represented by tables in a GPU specially built for ray-tracing. Without working through the math (which would be quite a chore), it certainly seems like a fairly plausible idea.
Well, actually... (Score:4, Interesting)
(More cynical types assume the Russians bought or stole US chips from the French or other too-helpful go-betweens.)
Back in the early '90s, one of my professors had come over from the USSR to teach Comp Sci. The local ACM chapter, at least a couple of times if not more, had him give a talk on the state of computing in Russia. This was exactly what he laid out. That shell companies were setup in France to lease IBM equipment (all you could do in those days for this very reason). The shell would fly-by-night the IBM to Russia where they would part it out. Notably, iirc, Romania was where they reverse engineered the machine code of the OS back into a somewhat usable assembly language. This, he would explain, was why all the really nasty viruses for PCs came from Romania - because the writers could eyeball instruction code and tell you what it was going to do. They also knew every crevice of the system, which became the advent of viruses hanging out in BIOS's and system clock memory.
He eventually became uncomfortable giving the talks and stopped, to my knowledge.
Re:Don't Modern Spaceflight and ICBMs Use Old CPUs (Score:1, Interesting)
I may be wrong in my recollection but I think I have heard a Russian technician (I once worked a bit with him) telling me that some (?) space and ballistic engines were equiped with mecanical "computers". Highly radiation tolerant things, BTW.
He also told me how, during his military service, his team used the parabolic antenna of a truck-borne radar to capture and cook rabbits for their meals...
However, I have a lot of respect for the Russians. It is always fascinating to discover the logic behind their choices.
Re:Soviet vs. American engineering (Score:3, Interesting)
The Soviets had computers.... some home built, some Western, but generally speaking they weren't very good. The Soviet approach was also very stereotypical: get an army of mathematicians and engineers to find exact analytic solutions to the problems you're trying to solve. You'd have armies of engineers and technicians designing things that in the west we'd give to a couple of engineers with some computer time.
But in the 1960s, the US didn't have *that many* computers. We got to the Moon mainly on the backs of slide-rules and rooms of women continuously punching tabulator machines.
Re:Clones DEC was very popular too (Score:4, Interesting)
I worked in a college computer lab with a Russian expat
He was extremely familiar with DCL (Digital Command Language) and VAX architecture. Apparently, he had spent years working on DEC VAX clones in the old Soviet Union.
I also remember reading that DEC would etch stuff like "check six" in Russian onto integrated circuits to let the Russians know that they knew it was being reverse engineered
Re:Eh. (Score:2, Interesting)
1) Just look around you : where does ternary logic live ? in some Russians' fond memory. OK.
"If it was a good idea, everybody would already be doing it!"
This horrific fallacy automatically and completely discredits the speaker. You are not a "computer designer" or any other sort of useful human being. You are a pointy-haired boss.
They pirated US technology (Score:1, Interesting)
A few years ago, I worked for a French computing company that was trying to make inroads into the US market. One of their older marketing guys used to tell stories about how he was recruited by the KGB to buy Digital VAX computers using a French puppet company, which would then reship them to Poland, and from there to the USSR. He was convinced that the US computer manufacturers knew about the deals, but were cool with it as long as they had "plausible deniability". When a company like Lock-Mart plays one of those bogus commercials where a US flag is waving and they recite their mantra "We never forget who we're working for..." I always picture a dollar bill instead of a US flag. These greedy multi-national corporations make their money supplying guns to both sides of any given conflict. Whose missiles do you think the Mujaheddin are shooting at US helicopters?
Re:Eh. (Score:1, Interesting)
MUAHAHAHA.
huhu.
hmm.
Let me rephrase and insist :-)
If ternary computers were such a good idea, you would point to at least a few overwhelming advantages. You gave nothing, no fact, you even claim a false thing (YES I design computers, I even have my own lab). But I don't care, because you would play the "argument by authority" card. So let's see the facts and use some brain.
If it was even better, you could point to at least a few implementations, many web links or even start your own ternary computer architecture. All one could find is a couple of Russian implementations that the proponent claim was killed by the Party because it did not adhere to the (arguable) program/policy of unified architecture (based on IBM's 360/370). So they have a good scape goat.
You can easily try to make your own ternary (or whatevery) automatic computation engine, for example using the VHDL language : its "std_logic" type reprensents a 9-value wire, with unknown, uninitialised, don't care, weak, forced, floating and standard values for the binary world. You could expand on this easily and start creating your own gates, units, circuits... So yes it is possible to examine and explore alternative systems. There are even Free SW for this now.
Now, believe me (or not if you don't want to but you'll always have to face the facts) : there are dumb people in computer and electronics design circles (I know some, both academic and industrial) but ALL the electronic design options have been tried, examined, compared, tested and published. Just look at the fucking huge collection of papers from universities, conferences and the ACM, IEEE and others... Every stone has been turned.
Ternary may make sense in *some* computations but not 99% of a computer's use : storage and manipulations. Simply because it's a waste of wires. And wires cost a lot, particularly when communicating between different chips. Recoding from binary to ternary (and vice versa) WASTES time and gates, some precious nanoseconds that make the difference between "an interesting idea" and "a commercially viable product". You may want to believe that it is a close-minded point of view, but ANY method that can make computers better is used (and patented). However, "better" depends on who decides it : some believe in "sexy" features, but the real engineers examine the problems before choosing and applying a solution (instead of the reverse). Read "Computer Architecture : a Quantitative Approach", the famous book by Patterson & Hennessy, creators of the MIPS and SPARC architectures. They take statistics, perform measurements, try several approach and keep the one with the best result for the most uses.
BTW I'm not a PHB, I'm (trying to be) pragmatic and I have accumulated experience and knowledge. They help me do things that work. Others more experienced than me (Industry veterans) will give you similar arguments. Go ask on Usenet : comp.arch has a lot of very talented, experienced and professionals (even from Intel and others). Ternary has been tested and was not compelling enough to be furthered.
Now it's your turn to give arguments, facts and links, instead of just denying reality. Try at least to be credible and interesting, instead of spewing a few unsubstanciated claims. I'm not against ternary, but if it was better than binary, I would use it without problem. Like everybody.
Re:The Soviets really WERE behind, but in other ar (Score:4, Interesting)
Your post Sir, is a fine example of brainwash. Anybody with a bit of background in remote sensing can tell you that in the beginning of the 90s satellite pics with a resolution of about 0.5 metres could easily be bought on the market, coming from decommissioned Soviet-Union satellites. And them pics surely weren't sent to earth by canister either (that practice ended in the 60s, thank you very much).
I won't make any remark about your admiration of the precision bombing from the F-117 and the associated cost/effectiveness comparison (at least not until I've visited Iraq and Afghanistan), but really, using the Iraqi Army, after 12 years of embargo, as an example force in comparing the effectiveness of the US military versus the Warschau Pact?
What I do wonder about, really, is that after your headlong demonstration of the inferiority of Soviet material, you come to the next conclusion: "One lesson is that the technological capabilities of Chinese weaponry today shouldn't be underestimated." Underestimated?