There is: AVX. The difference is that to cope with the workloads GPUs are NOT good at, a lot of the CPU transistors are dedicated to things other than AVX units and registers so the peak is lower.

Why would you not expect all of the participants to (statistically speaking) modify their behaviour in the same way? If the people who get the real anti-HIV drug modify, and the people who get the placebo modify then the chances are good that the modifications will be evenly spread with a large enough sample pool. If, given the modified behaviour, the HIV drug performs with statistically meaningful results then you have a positive result from the study.

er... each of those cores has 16 things that aren't cores so they have lots of cores?

Each of the Cores on a i7 has an AVX pipe (or two, depending on how you look at it) with 8 ALUs in it. Does that mean a quad i7 has 32 cores?

Texture units clearly aren't cores, they're largely passive data pipelines. If you really look at a GPU more closely you can of course get far more complicated, The AMD architecture at the high end has two control flow cores with 24 SIMD coprocessors that execute blocks of non-control flow non-memory work. It is true that even those are hard to qualify as cores given their limited capabilities.

Without question a single SIMD lane is not a core, though.

One thing I've been really keen to know is what the utilisation is like on those supercomputers. We know they can do LINPACK really fast and more efficiently than the CPUs do, that's what you get for having a high ALU density, a few threads per core and wide SIMD structures. The question is: out of the algorithms that people intended to run on those supercomputers, then what level of efficiency are they hitting.

Are they still a net gain over a standard opteron-based machine? They may be, but I don't know the answer. What I heard about Roadrunner with its Cell chips was not so good.

No they don't, let's stop such silliness.

The GTX580 has 16 cores. The GTX280 has 32. The AMD 6970 has 24. The AMD Magny-Cours CPUs can have up to 16 (ish, if you don't mind that it's an MCM).

292 indeed. NVIDIA does an even better job of marketing than they do of building chips.

And python compiles to the same x86 assembly as C++, so clearly turning C++ into python won't change any of the code that exists. A scala compiler doesn't have to compile the Java code that the entire industry expects to still compile perfectly 10 years after they first wrote it.

And who didn't have to deal with backward compatibility. Designing a language from scratch is a completely different problem from evolving one that's heavily used.

Although that's such a bad dialog you have to copy it into a text editor and copy it back to be able to edit it properly.

It's never occurred to me to look where I would set that in a config file (short of checking if the old DOS batch files still work).

The City of London police covers 1.1 square miles with 813 police officers. That's one policeman for every 10 residents, interestingly, though obviously number of residents in the city is a fairly meaningless number.

The NYPD covers 468.9 with 35,284 police officers, or 75 per square mile.