Re:Generics in C without void* or macros – enabled by psychec
by dragontamer on Monday September 09, 2019 @06:54PM
(#20923388)
Pretty much any CUDA programmer can talk about how they got 1024 threads working on 64kB "shared memory" with their C++ compiler. That "shared memory" region is exceptionally fast, so its a good idea to hyper-optimize your memory accesses to use that region.
There are some very interesting constraints in GPU-programming. Fitting C++ classes and even some data-structures in the "shared memory" region is pretty nifty.
There are some very interesting constraints in GPU-programming. Fitting C++ classes and even some data-structures in the "shared memory" region is pretty nifty.