top | item 10828823 (no title) tadlan | 10 years ago Numbs compiles entire functions on and allows array expressions with allocation and loop fusion. I don't see the problem discuss order hn newest bionsuba|10 years ago The benchmarked code is ALREADY a comiled C function called from Python and it still lost. tadlan|10 years ago Numba would still be faster. It would fuse away any intermediates in the code and remove any Overhead to the compiled code.also have the option of devecting to loops.both of which are generally faster than vectorized jumpy code. load replies (2)
bionsuba|10 years ago The benchmarked code is ALREADY a comiled C function called from Python and it still lost. tadlan|10 years ago Numba would still be faster. It would fuse away any intermediates in the code and remove any Overhead to the compiled code.also have the option of devecting to loops.both of which are generally faster than vectorized jumpy code. load replies (2)
tadlan|10 years ago Numba would still be faster. It would fuse away any intermediates in the code and remove any Overhead to the compiled code.also have the option of devecting to loops.both of which are generally faster than vectorized jumpy code. load replies (2)
bionsuba|10 years ago
tadlan|10 years ago
also have the option of devecting to loops.
both of which are generally faster than vectorized jumpy code.