cuda.bindings._v2.nvrtc.get_cubin#

cuda.bindings._v2.nvrtc.get_cubin(intptr_t prog) → bytes#

nvrtcGetCUBIN stores the cubin generated by the previous compilation of prog in the memory pointed by cubin. No cubin is available if the value specified to -arch is a virtual architecture instead of an actual architecture. The cubin does not contain code for the Tile functions (__tile__ / __tile_global__) or variables (__tile__); use get_tile_ir() to extract the cuda_tile IR generated for Tile code.

Parameters:: prog (intptr_t) – CUDA Runtime Compilation program.
Returns:: Compiled and assembled result.
Return type:: bytes