It does close the gap.

Before:

  cc -shared -fPIC -Os -s -o empty.so empty.c
  cc -std=c99 -Wall -Wextra -O3 -g3 -fpie -pie -o benchmark benchmark.c ./empty.so -ldl

  jit: 1.541608 ns/call
  plt: 2.309939 ns/call
  ind: 1.540583 ns/call
  

After:

  cc -shared -fPIC -Os -s -o empty.so empty.c
  cc -std=c99 -Wall -Wextra -O3 -g3 -fpie -fno-plt -pie -o benchmark benchmark.c ./empty.so -ldl

  jit: 1.541836 ns/call
  plt: 1.539239 ns/call
  ind: 1.542874 ns/call

I've heard OEMs make more money from pre-installing adware/spyware/trialware than what they pay for the Windows license.

You can always decline the EULA and try to get a refund for the bundled Windows license. In Europe it is supposedly easy to get a refund due to a European Union directive on unfair commercial practices: http://no.more.racketware.info/en/europe

Yea, the slow scrolling on Android is annoying. I believe it's caused by not using the native functionality, which I hope gets fixed soon: https://bugzilla.mozilla.org/show_bug.cgi?id=776030

That bug is not about using the native scrolling infrastructure. I don't see a reason why the native Android functionality would be better than what Gecko already does.

(I wrote the initial version of Firefox for Android's scrolling code.)

It's likely talking about all future dividends (discounted for time value). Startups will naturally reinvest their earnings to grow, but at some point, pursuing growth will be too costly and the best use of their earnings will be to return it to the owners as dividends.

If a company were guaranteed to never return anything to owners, then it would be more like speculating in the future value of a baseball card than an actual investment.

It may not be a practical way to calculate value, but it's not crazy either.

Probably the largest application written in Rust is the Rust compiler itself.

Yes, I'd say a language runtime definately falls in that critical 3% Knuth referred to in the original quote.

Makes sense if you are the only person running your programs (and you are allowed to ignore things like hardware and power costs).

Also, 2 minutes per change to compile the object files affected and link the executable seems a bit excessive considering the entire Linux kernel can generally be built from scratch in less time than that (assuming a modern system).

They're headings, not sentences...

I like both Dota 2 and HoN, but HoN definitely has the upper hand with regards to fast-pace twitch-based gameplay. The first thing a HoN player notices when trying out Dota 2 for the first time is that input delay.

Supposedly part of the problem is that Dota 2 uses the Source engine with netcode designed for FPS games; hence it does prediction and interpolation which works well for those games but not as well for RTS games. For more info: http://pastebin.com/ekk07PKn

What? That doesn't sound right... how does the distribution method affect copyright? Think of all the free software (with licenses dependent on copyright) that's made available over BitTorrent. Or World of Warcraft game updates, or humble bundle games, or ...