The arguments did not involve whether Apple knew about the patent, since the first phase of the trial (the one that concluded Monday evening) was not interested in determining whether infringement, if any, was willful. Instead, they did things like show the RTL, ask expert witnesses from both sides to explain the similarities and differences between Apple's implementation and the patent, and question both patent inventors and Apple engineers who worked on that part of the system. They also looked at prior work. Based on this information, the jury decided that the patent is valid and that apple did infringe.
They're currently (at least as of around noon) in the damages phase, and after they finish that, they'll move onto determining whether Apple knew about the patent or not.
It is not branch prediction or instruction prefetching, and it only makes sense for large, out-of-order cores with large instruction windows. Intel was sued for infringing about five years ago but settled out of court (and ended up paying some money and getting a license). The A7 was the first of the Apple chips that infringed; no one is claiming that any previous ones did. It was Apple that added the infringing hardware.
It's something Apple added (and it's not about branch prediction). Other ARM processors would not infringe.
It does also occur, and WARF has filed a second lawsuit a few weeks ago, I think.
WARF does pay a substantial share to the inventors: http://www.warf.org/for-uw-inv...
From the link: "20% of royalties (before expenses) will go to you [the inventor]."
The linked article is just wrong -- this is not in any way a branch predictor. It's predicting when to perform load-store speculation. The idea is that when you execute a load, you may not know whether there are any in-flight stores to overlapping addresses that are earlier in program order. If there are, once you detect it, you will have to squash the load (because it might have gotten a wrong value) and re-execute, flushing the pipeline. That's bad from a performance and energy standpoint (for the same reason branch misprediction is bad). You could always wait until you know that the load won't conflict, but that really hurts performance as well.
The innovation in the patent is that most of the squashes come from a relatively small number of load-store pairs, so by keeping track of them in a prediction table, you can get a large performance benefit for a small area overhead. The patent wasn't terribly useful in 1997 because instruction windows were small, but the authors thought that it would be once chips hit order of 1 billion transistors, which is pretty much what happened.
Wordpad is basically Write- they more or less just renamed the application for 95.
So basically something we haven't invented the technology for is impossible until the technology is invented.
I'm so shocked.
Gimp is not just not "exactly like photoshop", it's not layed out like any other Windows application. If you're on Mac or Linux is fine, but someone accustomed to Gimp will struggle needlessly with the (incidentally monstrously ugly [to the point of making it difficult to use]) interface. Gimpshop and gimphoto are fine but are several major revisions behind gimp proper.
Google wants to close android in order to keep the manufacturers from closing android further.
Openness advocates are fighting to protect the rights of the manufacturers (that of closing Android)
I'm not sure who to root for here, so I'll just say GO LOCAL SPORTS TEAM
One good reason why computers can do more work than people is that they never have to stop and answer the phone.
