Anaconda Acclerate / NumbaPro Communication Error CUDA OSX

The overall goal is to use NumbaPro to run certain functions on the GPU (in OSX 10.8.3).

Before starting, I just wanted everything to be configured. According to this page, I installed CUDA, registered as a CUDA developer, downloaded the compiler SDK and set NUMBAPRO_NVVM = / path / to / libnvvm.dylib.

However, by running this basic test function:

from numbapro import autojit

@autojit(target='gpu')
def my_function(x):
    if x == 0.0:
        return 1.0
    else:
        return x*x*x

print my_function(4.4)
exit()

Causes this error:

File ".../anaconda/lib/python2.7/site-packages/numba/decorators.py", line 207, in compile_function
    compiled_function = dec(f)
File "...lib/python2.7/site-packages/numbapro/cudapipeline/decorators.py", line 35, in _jit_decorator
File "...lib/python2.7/site-packages/numbapro/cudapipeline/decorators.py", line 128, in __init__
File "...lib/python2.7/site-packages/numbapro/cudapipeline/environment.py", line 31, in generate_ptx
File "...lib/python2.7/site-packages/numbapro/cudapipeline/environment.py", line 186, in _link_llvm_math_intrinsics
KeyError: 1

I tried @ vectorize'ing instead of autojit, same error. @autojit by itself, without purpose, works great.

Any ideas?

+5
source share
1 answer

Continuum. :

, CUDA 1.x. NVVM CC2.0 . NumbaPro .

+5

All Articles