The greatest challenges lie in accommodating arbitrary control flow among threads within a cooperative thread array. NVIDIA GPUs are SIMD multiprocessors, but they include a thread activity stack that enables serialization of threads when they reach diverging branches. Without hardware support, this kind of thing becomes difficult on SIMD processors which is why Ocelot doesn't include support for SSE yet. It is also one of the obstacles for supporting AMD/ATI IL at the moment, though solutions are in order.

Translation from PTX to LLVM to multicore x86 does not necessarily throw away information concerning the PTX thread hierarchy initially. The first step is to express a PTX kernel using LLVM instructions and intrinsic function calls. This phase is [theoretically] invertible and no information concerning correctness or parallelism is lost.

To get to multicore from here, a second phase of transformations insert loops around blocks of code within the kernel to implement fine-grain multithreading. This is the part that isn't necessarily invertible or easy to translate back to GPU architectures and is what is referenced in the note you are citing.

Disclosure: I'm one of the core contributors to the Ocelot project.

They weren't obligated to do it, but let's be honest: they were somewhat forced to. NVIDIA bought PhysX not too long ago and announced they were implementing it with CUDA so GPUs could provide physics acceleration.

The NVIDIA PhysX binary-only SDK has been available for a while now.

http://developer.nvidia.com/object/physx.htm

Kindness? Neigh: competition.

Hydrogen peroxide powered rocket packs fly for around 30 seconds, because they have a specific impulse of around 125, meaning that one pound of propellant can make 125 pound-seconds of thrust, meaning that it takes about two pounds of propellant for every second you are in the air. Mass ratios are low for anything strapped to a human, so the exponential nature of the rocket equation can be safely ignored.

A pretty hot (both literally and figuratively) bipropellant rocket could manage about twice the specific impulse, and you could carry somewhat heavier tanks, but two minutes of flight on a rocket pack is probably about the upper limit with conventional propellants.

However, an actual jet pack that used atmospheric oxygen could have an Isp ten times higher, allowing theoretical flights of fifteen minutes or so. Here, it really is a matter of technical development, since jet engines have thrust to weight ratios too low to make it practical. There is movement on this technical front, but it will still take a while.

John Carmack