Catch up on stories from the past week (and beyond) at the Slashdot story archive

 



Forgot your password?
typodupeerror
×

Comment Re:x86 IS efficient (Score 1) 168

Thumb-2 is a great idea but unfortunately it is not supported for 64 bit mode. 64 bit mode is AArch64 which used 32 bit fixed length instructions

http://www.arm.com/files/downl...

That being said it's not as bad as ARM32

https://groups.google.com/d/to...

So far, the LZSS routine in my code looks like this:
      THUMB2: 76 bytes
      THUMB: 76 bytes
      ARM64: 96 bytes
      ARM32: 116 bytes
(for comparison, x86 is 63 bytes)

Still it is quite a bit worse than x86. x64 incidentally is the same code size as x86

http://www.deater.net/weave/vm...

8086 58 bytes
x86_x32 66 bytes
x86_64 66 bytes
arm_thumb2 76 bytes
arm_thumb 76 bytes
m68k 88 bytes
arm64 96 bytes
z80 96 bytes
arm eabi 116 bytes

Of course this benchmark is a bit silly.

Comment Re:Despite it's name (Score 2) 168

. I mean, the instruction set has specialized instructions for handling packed decimal! And then there's the near worthless string search REPNE CMPSB family of instructions. The Boyer-Moore string search algorithm is much faster, and dates back to 1977. Another sad thing is that for some CPUs, the built in DIV instruction was so slow that sometimes it was faster to do integer division with shifts and subtracts. That's a serious knock on Intel that they did such a poor job of implementing DIV. A long time criticism of the x86 architecture has been that it has too few registers, and what it does have is much too specialized. Like, only AX and DX can be used for integer multiplication and division. And BX is for indexing, and CX is for looping (B is for base and C is for count you know-- it's like the designers took their inspiration from Sesame Street's Cookie Monster and the Count!) This forces a lot of juggling to move data in and out of the few registers that can do the desired operation. This particular problem has been much alleviated by the addition of more registers and shadow registers, but that doesn't address the numerous other problems. Yet another feature that is obsolete is the CALL and RET and of course the PUSH and POP instructions, because once again they used a stack. Standard thinking 40 years ago.

It was standard on the 8086 (introduced in 1978). The 80368 (1985) is a general purpose register machine and can use a 0:32 flat memory mode. And modern x64 (2003) has twice as many registers and the ABI specified SSE for floating point, not 8087. Also in 64 bit mode segment bases and limits for code and data (i.e any instruction which does not have a segment override prefix) are ignored.

I.e pretty much all the things you're complaining about have been fixed and if you look at benchmarks x64 chips have been faster than their Risc competitors pretty much since x64 was introduced. Going on about segments, floating point stacks and REPNE MOVSD now is absurd.

And if you look at the way the 8086 took over from the 8080 what they did made a lot of sense. You could machine convert a CPM 8080 program to a MS DOS 8086 one and have it run fine. Meanwhile a native 8086 program had access to 1M of address space, up from 64K on 8080 and Z80. Like CPM MSDOS ran on commodity hardware which was cheaper than the big iron boxes and given most people were running things like Visicalc and Wordstar it was perfectly sufficient.

Comment Re:Smurftastic! (Score 1) 144

And a police officer has the technical capacity to walk into my house and shoot me dead. That I can appreciate his likely skill with a service revolver doesn't mean he gets to shoot me dead at a whim.

Right but you accept the fact that the police need to have the capability to shoot people, right? Because if you were an armed robber or something they'd need to be able to do that to stop you.

Similarly the NSA needs to have the capability to spy on people - terrorists, Russian or Chinese spies, or - if WWIII starts - Russian or Chinese soldiers are all people the NSA needs to be able to spy on. In fact it's highly irritating when people who tweet their every thought and bowel movement whine about this. The NSA aren't going to spy on them because a) everything they think is public and b) they're not interesting to anyone, let alone the NSA. Logically given limited resources it's more likely that people like the Boston Bombers are the target of surveillance than people someone memorably referred to as 'twitter cunts'.

If you look at WWII Anglo American SIGINT like breaking the Enigma code was absolutely vital to the war effort and saved the UK from defeat. As China moves towards parity with the West and confronts Japan over the Senkakus it's not impossible the US may find itself in a similar situation. In the long run it's not impossible that Russia will threaten the Ukraine militarily - after all it did more than threaten Georgia.

And in fact having a major SIGINT advantage over Russia and China is likely to act as a deterrent on them doing something like this. Conversely Snowden visiting both and telling them the US's capabilities is likely to make them think they're the ones with the advantage.

The only reason you'd think Snowden did the right thing is if you think the US is the sole source of evil in the world and Russia and China are both governed by people who act robotically in the best interests of humanity eschewing any personal gain. How likely is it really that the people who govern the US are the only ones vulnerable to corruption and the far less open political systems of Russia and China magically produce incorruptible leaders?

I'd say as bad as the US's politicians are the openness of the system means they are likely a lot less bad than those in China or Russia. In which case I'd rather the US has the SIGINT advantage. Snowden did exactly the wrong thing in taking US secrets to Russia and China and the Guardian is wrong to publish US secrets.

Comment Re:Tesla (Score 1) 103

If someone wants to spend more to be at the forefront, why not congratulate them and allow the march of progress continue?

Because they're doing enough of that congratulation themselves whilst whizzing past you in the carpool lane or while making passive aggressive comments about how 'gas guzzlers' should be banned by the government.

Comment Re:Knock-Offs (Score 1) 103

My favourite Chinese salesman-ism is, when encouraging you to try some food that looks, sounds or tastes a bit horrible is "...very good for you" said it a suitably serious tone.

E.g.

"Black dog. Very good for you"

Or, if you have a nasty rash from eating the food or breathing the air for an extended period

"Very good for skin".

Comment Re:Diatomacious earth is natural and deadly (Score 2) 72

With the increase of insect resistance to pesticides we'd going to need some novel countermeasures. I propose widespread deployment of Diatomaceous Earth. Sure some people will die but the rest will evolve resistance.

Now you'll say "That's complete madness. Humans are the ultimate K selected species so they've got no chance of out evolving r selected insects" Ordinarily that would be true but by careful use of mutagens and radiation and encouraging r selected traits like promiscuity and abandoning your kids. I think we can win.

And we need too, to ensure that human civilisation, not bed bug, dominates New York. NOW AND FOREVER.

Comment Re:Sad to hear (Score 2) 444

They are not legally required to so why would they?

Because they can put it up on blog and make money out of ads? Because it works as a loss leader for their other paid services. Because it's cheap to publish these days and if you're going to do the research for your own curiosity why not publish?

Look at OkCupid. Publishing things like this

http://blog.okcupid.com/index....

Makes me like them a whole lot. Now I'm not really in the market for a US centric dating service but if I were I'd use them. Plus they could always write a book full of this sort of stuff.

Does everyone publish all their data? No of course not. Still the trend is that people increasingly do do it for the reasons mentioned.

Comment Re:Show me a climate model for the past 16 years (Score 1) 846

I don't know your reference for saying that "the models are broken". In my understanding the models used e.g. in IPCC reports, are quite good.

It is completely unreasonable to dismiss them just because they are not perfect. The proper approach is to study the discrepancies, reason about their possible causes and estimate the effect of the errors on the question you are seeking to answer with the model.

Look at this

http://www.drroyspencer.com/20...

What I don't get is why they don't chuck out the models that are bad, keep the ones that are good and invent ones that are better. Right now it almost seems like they do the opposite - the ones that predict OMG! Runaway Global Warming! get loads of press time. And the ones that don't predict anything too drastic get largely ignored and the people that made them called evil deniers.

Actually that's what denier really means. If you think the world is warming slowly but it's no great problem like the satellite temperature measurements say you're an evil denier. In fact unless you support massive CO2 cuts now on the basis of the most alarmist model you're a denier. I.e. it's really an argument about policy, not whether you think the world will be 0.5 degree C or 1.0 degree C warmer in a hundred years time.

You can see that when geoengineering is brought up. The Royal Society did a study that showed that Sulphate aerosols for example could be used to effect "a reduction of solar input by about 2%" to "balance the effect on global mean temperature of a doubling of CO2" for "total annual cost at 10s of billion dollars". So we don't need to rely on the precautionary principle to tell us we need to cut our CO2 emissions to zero now just in case. We can go on as we are, monitor temperature and build ourselves a planetary thermostat quickly and cheaply if it becomes necessary. Of course the 'cut CO2 now' lobby hate this.

They also hate it when you point out that CO2 emissions in Europe and the US are trending down. China's CO2 emissions are increasing massively. If you want a global CO2 cut you'd need to get China to stop industrializing. Which they won't do

http://photos.mongabay.com/09/...

Or of course that the actual satellite measurements of temperature are undershooting all the models - you need to use the adjusted temperature measurements from ground stations. And the adjusted temperature measurements only do that because the past has been getting cooler. Those cavemen better watch out, pretty soon it will be below absolute zero when they are.

What this is really about is that you've got people who'd make a load of money if everyone was forced to by CO2 permits. It's pure rent seeking by them. Or people who know deep down we're all sinners for our materialistic lifestyle and want to force everyone into the modern equivalent of sackcloth and ashes to repent.

Slashdot Top Deals

"One lawyer can steal more than a hundred men with guns." -- The Godfather

Working...