Use warp votes to branch on argument size to select fastest algo

data61 / cuda-fixnum

Extended-precision modular arithmetic library that targets CUDA.

Other

41 stars 28 forks source link

Open unzvfu opened 6 years ago

unzvfu commented 6 years ago

Something like this for example:

if (__all(bits < digit::BITS))
    algo_small_params(...);
else
    algo_generic(...);

unzvfu commented 4 years ago