News for hackers. Stuff that matters.
Re:Libcu++: Nvidia C++ Standard Library by roel_v on Saturday September 19, 2020 @06:29AM (#24526440)
Yeah, really tiny... At first I thought 'wow this is a game changer', but then I looked at your link and thought 'what's the point?'. Can someone explain what real problems you can solve with just the headers in the link above?
Re:Libcu++: Nvidia C++ Standard Library by jpz on Saturday September 19, 2020 @07:07AM (#24526600)
I guess that the point is that when writing CUDA code (which looks like C++), you can use these libraries which are homogenous with CPU code.

Looking at the functions, chrono/barrier etc require CPU level abstractions, so using the STL versions (which are for the CPU) aren't going to work really.

Re:Libcu++: Nvidia C++ Standard Library by happyweasel on Saturday September 19, 2020 @06:38AM (#24526488)
It runs on the GPU?
Re:Libcu++: Nvidia C++ Standard Library by roel_v on Saturday September 19, 2020 @12:57PM (#24528792)
What runs on the gpu?
Re:Libcu++: Nvidia C++ Standard Library by jcelerier on Saturday September 19, 2020 @03:12PM (#24529746)
this library
Re:Libcu++: Nvidia C++ Standard Library by blelbach on Saturday September 19, 2020 @06:00PM (#24530594)
Re:Libcu++: Nvidia C++ Standard Library by TillE on Saturday September 19, 2020 @01:02PM (#24528835)
I would have expected the <algorithm> header, but instead...synchronization primitives? std::chrono? I'm completely baffled about how that would be useful, but that's probably because I know very little about CUDA.
Re:Libcu++: Nvidia C++ Standard Library by blelbach on Saturday September 19, 2020 @05:58PM (#24530580)
GPUs are parallel processors. So, yes, synchronization primitives are the highest priority.

We focused on things that require /different/ implementations in host and device code.

The way you implement std::binary_search is the same in host and device code. Sure, we can stick `__host__ __device__` on it for you, but it's not really high value.

Synchronization primitives? Clocks? They are completely different. In fact, the machinery that we use to implement both the synchronization primitives and clocks has not previously been exposed in CUDA C++.