64-bit ARM coming

[ncalipari]

[/B]

10^x vs 10^y, order of magnitude compares the difference between x and y.

2 = 10^X
log(2) = X * log 10
0.301029995 = X
2 = 10^0.301029995

10 = 10^X
log(10)=xlog(10)
1=X

I was reading your post and other people post with my gf (she's an engineer) and we had a pretty bad laugh.

there's no need to take in account logarithms here.

the scientific notation of 2.0 is 2.0*10^0

the scientific notation of 9.0 is 9.0*10^0


the scientific notation of 10 is 1.0*10^1

So 10 is one order of magnitude greater than 9 or 2.

Order of magnitudes are integer numbers.

:thumbsup:

Thank God someone on here knows math!

The only application I am aware of where a 9.0 is an order of magnitude smaller than 10.0 is when measuring earthquakes.

It's pretty simple...

10 - 100 One order of magnitude larger
10 - 1000 Two orders of magnitude larger
So forth

and that someone is not you as you are confusing the logarithmic scale with order of magnitude.




Guys I hope all of you doesn't have a college degree in any scientific subject, or you should go back to your college and ask for your money back.

You don't need to be a mathematician. Even a CS understand this when he learns how floats are handled.

 

[Schmide]

Magnitude means relative difference. While you can say 0.1 is an order of magnitude, it is only an order of magnitude relative to 0.01 and and 1.

Edit:

I was reading your post and other people post with my gf (she's an engineer) and we had a pretty bad laugh.

(snip)

Guys I hope all of you doesn't have a college degree in any scientific subject, or you should go back to your college and ask for your money back.

You don't need to be a mathematician. Even a CS understand this when he learns how floats are handled.

Dude. Many of us have degrees and none of us would make such statements even when we're wrong.

the scientific notation of 2.0 is 2.0*10^0

the scientific notation of 9.0 is 9.0*10^0


the scientific notation of 10 is 1.0*10^1

The true irony is you're attempting to change the definition of order of magnitude. The notation you are using is a scalar and an order of magnitude. The only time you can say something differs in order of magnitude is when the scalar is 1 even if you change the base.

(scalar) * (base)^(magnitude)

 

[Voo]

I'm more astonished by how many people think the only possible base that exists is 10. "order of magnitude" without more context is completely useless. Could be base 2, 10, e, -2 - well take your pick. The actual definition (look it up) doesn't define one..

 

[Ferzerp]

Why are you guys even bothering arguing with a guy who says "9.990 and 10.000 are an order of magnitude aparts" at this point?

Either he's beyond help, or a huge troll.

 

[Schmide]

Could be base 2, 10, e, -2 - well take your pick. The actual definition (look it up) doesn't define one..

I can't imagine having negative base. Then they would differ by a disorder of magnitude. Fractally speaking.

 

[Voo]

I can't imagine having negative base. Then they would differ by a disorder of magnitude. Fractally speaking.

You may not be able to imagine it, but the mathematical definition for bases works just fine for -2. Personally base (i - 1) is more interesting though - that allows to specify all complex integers without signs and other irregularities.

Since "order of magnitude" isn't really a mathematical concept, it doesn't work sensibly with that, but oh well - that just shows how useless it is..

 

[Cogman]

I'm more astonished by how many people think the only possible base that exists is 10. "order of magnitude" without more context is completely useless. Could be base 2, 10, e, -2 - well take your pick. The actual definition (look it up) doesn't define one..

It is a safe assumption. So safe, that if someone REALLY means a "base 2 order of magnitude" they will say "A base 2 order of magnitude". The whole world uses base 10 by default. It has nothing to do with "everyone thinks that only base 10 exists" and everything to do with "everyone assumes that we are using base 10 unless otherwise specified".

 

[Ferzerp]

I'm more astonished by how many people think the only possible base that exists is 10. "order of magnitude" without more context is completely useless. Could be base 2, 10, e, -2 - well take your pick. The actual definition (look it up) doesn't define one..

In the normal world, when we discuss numbers, unless we specify a base, it's safe to assume it's base 10.

Regardless, his weird claims of orders of magnitude greater for 2 and 10 work in no numerical base. (the nice thing about orders of magnitude are regardless of the base, we can just add a 0 on the end of the first number to find the number that is an order of magnitude greater in that base. 2(base 3) needs 20(base 3) which is 6 base 10 to be an order of magnitude in base 3 more. In fact, in no numerical base that contains a 2 digit is 10 more than half the necessary value needed to be a full order of magnitude greater.

If you take 2 and 10 in base 10 and convert them to base 5 then you end up with 2 and 20 in base 5 and *those* are a base 5 order of magnitude apart, but you aren't going to convince anyone that that is what he means. Especially with 9.990 and 10.000...

 

[Cogman]

In the normal world, when we discuss numbers, unless we specify a base, it's safe to assume it's base 10.

Regardless, his weird claims of orders of magnitude greater for 2 and 10 work in no numerical base. (the nice thing about orders of magnitude are regardless of the base, we can just add a 0 on the end of the first number to find the number that is an order of magnitude greater in that base. 2(base 3) needs 20(base 3) which is 6 base 10 to be an order of magnitude in base 3 more. In fact, in no numerical base that contains a 2 digit is 10 more than half the necessary value needed to be a full order of magnitude greater.

If you take 2 and 10 in base 10 and convert them to base 5 then you end up with 2 and 20 in base 5 and *those* are a base 5 order of magnitude apart, but you aren't going to convince anyone that that is what he means. Especially with 9.990 and 10.000...

Yeah... where he was going with that is beyond funny. He was basically trying to make the case that 9.999... (repeating) and 10 are an order of magnitude different... But wait! They are the same number... hmmm how does that work?

 

[Ferzerp]

Yeah... where he was going with that is beyond funny. He was basically trying to make the case that 9.999... (repeating) and 10 are an order of magnitude different... But wait! They are the same number... hmmm how does that work?

That's where he would have ended up he kept extrapolating. 9.9... 10.0... are an order of magnitude apart.

 

[ncalipari]

Yeah... where he was going with that is beyond funny. He was basically trying to make the case that 9.999... (repeating) and 10 are an order of magnitude different... But wait! They are the same number... hmmm how does that work?

that proves me that you dont know anything about scientific notation.


Hey guys, how many of you have been in a academic experiment? How many of you ever published a paper?

 

[Voo]

It is a safe assumption. So safe, that if someone REALLY means a "base 2 order of magnitude" they will say "A base 2 order of magnitude". The whole world uses base 10 by default. It has nothing to do with "everyone thinks that only base 10 exists" and everything to do with "everyone assumes that we are using base 10 unless otherwise specified".

Depending on the problem area assuming base 2 isn't that far off actually. And orders of magnitude is most of the time only used to specify a much larger value without qualifying it specifically (because if you need exact values using such a imprecise term isn't the best idea anyhow).

Now that ncalipari is nuts is beyond doubt - but for the original problem? I don't see much problems with that.

 

[Ferzerp]

The problem area is Wattage.

Who discusses Watts in binary?

Furthermore, the digit used was 2. In what world does binary have a 2 digit (or a 9 digit for that matter)?

 

[Cogman]

Depending on the problem area assuming base 2 isn't that far off actually. And orders of magnitude is most of the time only used to specify a much larger value without qualifying it specifically (because if you need exact values using such a imprecise term isn't the best idea anyhow).

Now that ncalipari is nuts is beyond doubt - but for the original problem? I don't see much problems with that.

Truth be told, I don't see too much of an issue with saying that 10 is an order of magnitude different from 2... It is stretching a little, but not TOO far off. I do, however, have a problem with saying 9.9 is an order of magnitude different from 10. That is just plain wrong.

 

[Cogman]

that proves me that you dont know anything about scientific notation.


Hey guys, how many of you have been in a academic experiment? How many of you ever published a paper?

Does this really matter? http://en.wikipedia.org/wiki/Argument_from_authority This is a common logical fallacy. Even if you are published, it doesn't make you any less wrong here.

 

[Schmide]

You may not be able to imagine it, but the mathematical definition for bases works just fine for -2. Personally base (i - 1) is more interesting though - that allows to specify all complex integers without signs and other irregularities.

Since "order of magnitude" isn't really a mathematical concept, it doesn't work sensibly with that, but oh well - that just shows how useless it is..

From my original reply you didn't get my math humor.

Buzzword? Imagine - Imaginary.

However, "order of magnitude" is very much a mathematical concept?

The reason you can't have a negative base and have numbers differ in orders of magnitude is the solutions to negative bases have many to one mappings and therefore cannot differ in orders of magnitude, thus my "disorders of magnitude" statement.

 

[Ferzerp]

Truth be told, I don't see too much of an issue with saying that 10 is an order of magnitude different from 2... It is stretching a little, but not TOO far off. I do, however, have a problem with saying 9.9 is an order of magnitude different from 10. That is just plain wrong.

You're pretty generous when 10 is only half the number that is a true order of magnitude greater than 2 (20).

 

[Cogman]

You're pretty generous when 10 is only half the number that is a true order of magnitude greater than 2 (20).

20 and 10 are the same order of magnitude. When talking about a logarithmic scale (which is what the order of magnitude scale is) an order of magnitude from 2 is really not that far from an order of magnitude from 1.

In my mind, how far off it is from an order of magnitude can be calculated by saying log(20) - log(10) = the how many orders of magnitude off it is. In this case, 20 is ~.3 orders of magnitudes off of 10. I can live with that much error. It is somewhere around .5 that I get uneasy calling something an order of magnitude different.

 

[Ferzerp]

I can see that, but I am more wont to be generous like that when it's being used to compare two neutral numbers. When you're trying to win an argument by saying that numbers are a whole order of magnitude apart when they are that far from truly being so... I'm not likely to agree.

 

[Voo]

From my original reply you didn't get my math humor.

Buzzword? Imagine - Imaginary.

Ups sorry

However, "order of magnitude" is very much a mathematical concept?

The reason you can't have a negative base and have numbers differ in orders of magnitude is the solutions to negative bases have many to one mappings and therefore cannot differ in orders of magnitude, thus my "disorders of magnitude" statement.

Ok not the best wording, yes.

But there's no many to one mapping for base -2. Warren has a proof in his book where he shows that the 2^n bit patterns in a n-bit word uniquely represent all integers in a range. That's not necessarily true for rationals, but that shouldn't matter there. The question is how you'd intelligently define an order of magnitude there though.

Truth be told, I don't see too much of an issue with saying that 10 is an order of magnitude different from 2... It is stretching a little, but not TOO far off. I do, however, have a problem with saying 9.9 is an order of magnitude different from 10. That is just plain wrong.

Then we agree there - as I said ncalipari is nuts

 

[blckgrffn]

HAH - epic misdirection of a thread

 

[Ferzerp]

don't worry, there will be another OMG ARM RULEZ! thread in a day or two.

 

[Cogman]

Then we agree there - as I said ncalipari is nuts

Hurrah! Let's eat cake!

Since this is a little neffish... Ultimately I think that x64 instructions for a mobile processor are really not all that important or impressive. There aren't TOO many cases when programming that register sizes really causes your program to be slower. There are even less cases where an ARM processor has a program that needs to allocate over 4gb of ram.. Even in the cases where 64bit registers may be useful, they are usually the same cases where the NEON instruction set is useful. In other words, wider general registers are just not all that exciting.

It is far more important to have wide vector registers than it is to have wide general registers.

 

[Ferzerp]

Big news would be an improvement of I/O by *cough* wait for it *cough*




an order of magnitude.

 

[MisterMac]

^this.

ARM vs x86 brings out the weird.

Intel is to big a bussiness to just get pushed out.
They *sit* on 80%+ marketshare.

ARM eventually gets close to x86, Intel works out something new, gets AMD to go along with it, and put out a product that can match ARM's current tech, or best it.

Intel has so much money, so much marketshare, and brilliant engineers.
Hell I can imagine even just removeing some old legacy stuff in x86 would make it more power effecient (enough so to compete with arm for along time).

If x86 falls, its because Intel came up with something better, and got AMD to go along with it.

Holy shit, EPIC sidetrail.


You come home and see a shitstorm



but to above poster:

This.


By the time ARM has 64bit for speeding up numbercrunching basics for any server enviroment, intel will stepped up both the atom platform and perfected haswell.

By the pure design goals of these and knowing that intel can indeed deliver, atleast past 6 years - you simply cannot deny that while ARM sits on the really low form factor device, intel most likely will start eating that out, from the top of the LFFD spectrum.

Just like NehalemEX in cost vs performance is came way too close to SPARC/Power7 - WITH emulation mind you - than most of the people building datawarehouses.

Once Romley hits theyll again start at the middle, til SandyBridgeEX and IvyBridge EX Xeon's hit the market - in dense quaters im quite sure they'll start to really chip a nasty tooth in Sparc/Power7.


We can't predict the future - we can just see tech companies promising this and that, and for the most part Intel seems one of the few with a good track record and seems to continue that to the extreme end of computing power to the low end.