terminus

> Where google's clearly winning? Ideological propaganda. The whole "open vs. closed" campaign has people actually believing that Google is good and Apple is evil. Apple which has never spied on its users or sold them out to advertisers.

Umm, iAds?

Not particulary fond of Flash myself, but:

> Flash was installed with a bit of vomiting involved. If you don’t use ClickToFlash you are insane.

Flamebait.

Or your .bash_history might be very large.

> You cannot read about the errors in Apple Maps without realizing that these maps were being visually examined and used for the first time by Apple’s customers and not by Apple’s QC teams.

Wasn't iOS6 in public beta for a few months?

Then again, being Exxon hasn't harmed Exxon's bottomline. Granted, consumer goods might be a whole different ballgame.

Wouldn't be too sure of that. There's a world of fan-fiction (canon and otherwise) that exists for Harry Potter. One (rather excellent one) by HN frequenter less-wrong: http://www.fanfiction.net/u/2269863/Less_Wrong.

Your comment seems reasonable at first sight. However, your argument presumes there being an "Apple aesthetic."

Rounded rectangles, bounce-back, swipe to unlock are refinements on what existed already. That does not imply they are novel. Apple, really is standing on the shoulders of giants(or-otherwise.)

Refinements and a reality distortion field does not an aesthetic make.

> On this site I've seen many claims that Apple's patents are covered by "prior art" but the "art" cited is generally nonsensical (eg: 2001: a space odessy having square tablets)

I'm curious, why is the Space Odyssey tablet "obviously nonsensical"?

See for instance the Waterbed patent denied because of Henlein's writings: http://www.techrepublic.com/article/geek-trivia-strange-wate...

So South Korea is an "obscure remote country?" Wow.

> Funny how the Samsung apologists have gone from saying "of course it's not a copy, they had these designs before Apple" to "what else could they do?". This defence of plagiarism as being somehow in the better interest of consumers is laughable. "intellectual property is first and foremost intended to protect users"? What have you been smoking?

Intellectual property has always been a temporary monopoly granted to provide economic incentives to inventors/writers/what-have-you for societal advancement.

Quoting from http://en.wikipedia.org/wiki/Intellectual_property#Objective...: "The stated objective of most intellectual property law (with the exception of trademarks) is to "Promote progress."[12] By exchanging limited exclusive rights for disclosure of inventions and creative works, society and the patentee/copyright owner mutually benefit, and an incentive is created for inventors and authors to create and disclose their work."

That said, I don't like your tone. Arguing, for or against a position does not make one an apologist.

> So let me get this straight: rich kid at Harvard gives his bright friend some money to rent servers to run a service that gets popular. Rich kid doesn't contribute any more.

Not terribly different from Seed/VC funding.

Quite disingenuous to state that "Android is open" is bullshit and at the same time the article finds no mention of Apple's overarching "closed is better for you" attitude.

(Yes, the article hints at Apple's closed-ness. However, only relatively minor, disconnected, issues. Not the overall attitude.)

Just to add to what you said: RMS and the FSF worked up the GPLv3 in response to this "Tivoization" of Software.

Linus and the kernel crowd at that time were on the other side of the debate.

Linus' quote: "" [Stallman] calls it "tivoization", but that's a word he has made up, and a term I find offensive, so I don't choose to use it. It's offensive because Tivo never did anything wrong, and the FSF even acknowledged that. The fact that they do their hardware and have some DRM issues with the content producers and thus want to protect the integrity of that hardware.

The kernel license covers the kernel. It does not cover boot loaders and hardware, and as far as I'm concerned, people who make their own hardware can design them any which way they want. Whether that means "booting only a specific kernel" or "sharks with lasers", I don't care. ""

Back then Tivoization was about "consumer devices." Now that "Tivoization" is threatening to breach the walls of hacking devices, it feels a lot more personal.

Yeah. That would be a whole interesting can of worms. Would need PCI/USB/whatever bus your ethernet card was on. Plus emulation of the selected ethernet card itself.

Loopback (which is present) is so much simpler.

Neat. You can mount sysfs like so:

  # mkdir /sys; mount -t sysfs /sys /sys

That would allow you to look at the emulated hardware that is present. Looks like only virtual devices are present -- ram, loopback network etc.

Makes sense to me. The MVP here is cpu emulation.

I'm getting this too. Chromimum 8.0. I'm on Ubuntu 10.10.

Not mine. But, a nice detailed writeup here: http://valerieaurora.org/lasik.html (Valerie Aurora is a kernel programmer)

I'd say that being a startup founder is less about code hacking abilities and more about hacking real-life (product, market, customer, code, whatsit.)

Personally I'd go with GeneralMaximus.

Yes I have read the article. It is in the seven or so parts. You seem to be talking only about the first page.

Part 5 deals with cache optimization. Part 6 deals with multi-threaded optimizations. Other parts deal with various layers of the memory hierarchy (VM, caches etc.)

How are you so positive about the lack of value to the programmer? What if you are programming at a low level?

Performance-optimization/OS kernel/HPC inner loops/Power-sensitive code (think mobile devices)?

That's a false dilemma.

Higher level thinking, more expressive languages and tools don't preclude you from looking at low levels of your abstractions.

Edit: Looks like we were talking past each other. I was talking about the complete article (the non-EE bits are about VM, cache, NUMA awareness, memory management for multi-threaded programs etc.) The tail end of the OP's link, links to the rest of the parts.

Well, part of the faster-than-DRAM is because the cache is limited in size. Addressing 512 MB (and keeping it close enough to the CPU) would require a lot more address lines/multiplexing and CPU die real estate [1] that it would be prohibitively expensive and not as fast.

It'll still be faster than DRAM so you still have a point.

[1] In this die-shot (http://en.wikipedia.org/wiki/File:Barcelona_die.jpg) of AMD's Barcelona (4 core) all the regular grid like pattern is the cache (total is about 4MB + 512KB or so.) That takes about half the chip's real estate.

You are welcome. We could extend your observation about the earth to the universe: the universe is the way it is because had it been any other way, we wouldn't be there to observe it (and to comment on intelligent design or the lack of it!)

The term used in Physics for this is the Anthropic principle http://en.wikipedia.org/wiki/Anthropic_principle.

Sounds like a clear case of Survivor bias: http://blog.asmartbear.com/business-advice-plagued-by-surviv....

The analysis on the article details goes into the odds and is actually quite good.

Already. The article mentions read, write ordering. That is essentially about in what order other processors see reads, writes being done by this processor: thus if procA does a bunch of writes will procB see them in the order (program order) in which they were done or in a different other order. There can be other interleavings when you introduce read into the mix.

Architectures like the late lamented Alpha (this is around late 90's) had fairly weak ordering requirements so you needed explicit memory barriers to tell the processor that you needed ordering preserved (think spinlocks for instance.) Mainstream processors (x86/x86-64) have always had strict write ordering but not read ordering. Let's see how long that lasts.

For freighters take a look at http://wikitravel.org/en/Freighter_travel and findacrew.net

This looks like cumulative lines of code for all the projects that go into Android (across all the platforms that they are supported on.)

For instance C#, DOS Batch, IDL etc are listed. I don't believe that Android has a runtime for any of these.

Could you try the same query after deleting all the google cookies?

For the intel the L2 cache (and the L1 of course) are shared for both the hyperthreads, so each hyperthread would get even less than 256K. On AMD, however each thread gets the full 512K. The L3 latency is much larger than the L2 (~40 cycles IIRC) so the smaller L2 would limit the performance of a cache hungry (but not too hungry: see next paragraph) application.

One place where the larger L3 is a win is on low parallelism, memory hungry loads -- they have a much larger L3 all to themselves.

Linux kernel for some time. Not the most well documented, but is full of great examples of how to wring every little ounce of performance from the machine. And, inspite of the low level nature of the code, it's beautifully modular.