Would computers accelerated to high speeds compute "faster" from our point of view?

If B stays with you, you will always get the results from B before you get the results from A.

Sylvia.

That is basically the twins paradox:

Hi Sylvia,

I could argue that my accelerating computer 'loses time' thus its clock moves slower. Computers ultimately work on clock cycles. Thus it is fair to say that, as its clocking is ticking slower -- from my POV-- the computer on my desk will finish first?

The question is close enough to one that has been subject to experimental test - admittedly with atomic clocks rather than computers

Mohammad Halai snipped-for-privacy@ugcloud.ca wrote in news: snipped-for-privacy@googlegroups.com:

The speed at which you are moving does not change the speed at which the computer in your phone does its processing compared to a stationary phone. The bits toggle at the same rate in both.

Special relativity say otherwise. This has been tested moving devices do run more slowly

Of course, general relativity came into it too, bu that effect could be more or less cancelled out.

So, that "central" computer is following A at 0.25c? Do you *imagine* the transport delays from each are zero? (i.e., you've not thought through your initial hypothesis)

And where, exactly, are *you*?

And where are *we*? At what fraction of c will A's broadcast occur?

The whole point of relativity is you can't be in two places at once -- so there is no real way to compare "there1" and "there2", while they are separated in space (and, thus, time).

Some years ago, Hawking presented an experiment in time dilation, here, as part of the "Genius" TV series.

It's really amusing when you see such esoteric bits of science actually

The twin that travels at relativistic speed always returns younger than the stay at home. It is quite likely that if we ever do develop space vehicles capable of true relativistic speeds the first one to set off will be quickly overtaken by later models (who will also return first).

There is an interesting corollary to this in the real world for absolute cutting edge hefty computing problems like ab initio computation of the masses of fundamental practicals and the like.

If your problem will take more than 2 years to execute on currently available bleeding edge hardware the quickest way to get your results is to do something else for 18 months and only then run the program!

ISTR the original quote suggests going to the beach and surfing.

It needn't be "bleeding edge" but, rather, any design that is "up against the stops" imposed by it's design criteria (e.g., cost limitations).

The more practical corollary (for those of us that build hardware devices) is not to dick around with minor optimizations unless they provide ~2X "performance" (for some definition of "performance") increase.

In day-to-day terms, that means:

- delay hardware finalization

- write portable code (so you can change processors easily)

- automate testing (so you can rerun test suites on other toolchains)

- avoid crippling a design by limiting it to "today's" technology

In my case, I use three different compiler families (i.e., not gcc with three different back ends!) on three different hardware platforms (SPARC, x86 and ARM) and implement the "processor choice" as a hierarchical block in the (SBC) design so I can replace it easily. This also means taking deliberate care to keep the I/O system very generic so it doesn't rely on any exotic parts or peculiarities of a specific processor/-family. (I have a whole suite of compilers/emulators to verify the performance of a particular I/O subsystem)

Every ~18 months, I get the opportunity to decide if I want to lower the product cost (to capitalize on technological advances) *or* increase the capabilities of the hardware. It's intoxicating! :>

Somebody wrote a paper like that 30 or so years ago, based on algorithmic complexity and Moore's Law, that gave a formula for when one should begin a computation in order to finish fastest.

Fun paper--I should try pulling it up sometime.

Cheers

Phil Hobbs

Yes. This is not a matter of speed, since speed is simply relative. It is a matter of acceleration which only one experiences. Unfortunately for scientists wanting their results faster, the accelerating computer is the slow one.

I'm not going to deal with any of the issues of getting the results, since that is an even more sticky wicket and does not change the basic issue of acceleration resulting in time dilation.

The only way to make this work to get faster computing, is for the scientist to be the one accelerating, which slows his own clock, so he returns sooner (by his clock) and the computations are complete. Meanwhile, everything else unaccelerated has also moved on in time without the scientist, like cities and people. But if the scientist doesn't have anything to do for a year, a tour of the solar system at 0.9 times the speed of light might be a fun thing to do while waiting and it won't be so long this way. A perk of being a scientist.

"Relatively easy"? Is that a pun?

Bzzzt! Sorry, wrong answer, even if it is technically correct. You didn't read the problem statement. "the A computer being accelerated to 0.5c" is the part you missed or ignored.

It isn't even technically correct. Special relativity points out that a moving phone is going to be clocked more slowly than a stationary phone. Acceleration is indistinguishable from gravity, so general relativity requires you to pay attention to the acceleration as well, but gravitational red-shift is a different thing from Lorentz time-dilation.

Not sure what you mean about the moving vs. stationary clocks. I suppose I did not explain adequately. Since constant motion is purely relative, each clock is *observed* to be slower by the observer in the other time frame. So clearly, it makes no sense to talk about one clock actually running slower due to constant motion. It's just an effect of observation, with no actual change in time elapsing.

When one observer experiences acceleration, by either actual acceleration or a gravitational field, the effects are not relative, but absolute. So one observer does experience time differently as illustrated in the twin paradox.

From Wikipedia

Reciprocity Given a certain frame of reference, and the "stationary" observer described earlier, if a second observer accompanied the "moving" clock, each of the observers would perceive the other's clock as ticking at a slower rate than their own local clock, due to them both perceiving the other to be the one that is in motion relative to their own stationary frame of reference.

Common sense would dictate that, if the passage of time has slowed for a moving object, said object would observe the external world's time to be correspondingly sped up. Counterintuitively, special relativity predicts the opposite. When two observers are in motion relative to each other, each will measure the other's clock slowing down, in concordance with them being in motion relative to the observer's frame of reference.

So what point are you trying to make?

The really difficult problem is how to calculate the astronaut's pay when they return.

It's more that your explanation misses some of the detail and is inadequate that that extent.

Also from Wikipedia

That there is experimental evidence that if you send an atomic clock around the earth in the same direction that the earth is spinning, it runs slower than one that has been sent around the earth in the opposite direction.Of course they both run a bit faster than the third atomic clock that stayed at home on the ground and was thus more red-shifted by the influence of the earth's gravitational field (which is weaker when you are up in an aircraft).

Clearly both moving clocks were subjected to much the same accelerations every time their plane took off and landed - that won't be affected by the direction in which they flew around the world.

The effects are separable. Looking up what "reciprocity" means seems to be a less useful exercise.

Clive Arthur snipped-for-privacy@nowaytoday.co.uk> wrote in news:t50m0b$l5i$ snipped-for-privacy@dont-email.me:

By the time they return, society will have moved to cashless system. Problem solved, they get nothing.

Ok, so you are talking about something different from the rest of us. Fine, glad we got that straight.