Parallelizing issues in Cython with OpenMP

问题:

In order to make some speed comparisons between Cython with SIMD intrinsics (AVX) VS Numpy methods (which from what i know, also provides vectorizing), i have build this simple sum function:

import time
import numpy as np
cimport numpy as np
cimport cython

cdef extern from 'immintrin.h':

    ctypedef double __m256d

    __m256d __cdecl _mm256_load_pd(const double *to_load) nogil
    void __cdecl _mm256_store_pd(double *to_store, __m256d __M) nogil
    __m256d __cdecl _mm256_add_pd(__m256d __M1, __m256d  __M2) nogil

@cython.boundscheck(False)  # Deactivate bounds checking
@cython.wraparound(False)   # Deactivate negative indexing
def sum(len,n_sums):

    cdef __m256d __madd1, __madd2 , __msum
    cdef double sum4[4]

    len=len-(len%4)
    a=np.random.rand(len)
    cdef double [::1] a_view=a
    cdef np.ndarray[np.float64_t,ndim=1] ca=np.copy(a)

    cdef long N=n_sums, L=len, i
    cdef double s=0.0
    cdef Py_ssize_t j

    t1=time.clock()

    for i in range(N):
        s=0.0
        with nogil:
            __madd1=_mm256_load_pd(&a_view[0])
            for j in range(4,L,4):
                __madd2=_mm256_load_pd(&a_view[j])
                __msum=_mm256_add_pd(__madd1,__madd2)
                __madd1=__msum
            _mm256_store_pd(&sum4[0],__msum)
            s=sum4[0]+sum4[1]+sum4[2]+sum4[3]

    t2=time.clock()
    print(s, sum4)
    print("Cython sum", t2-t1)

    t1=time.clock()
    for i in range(N):
        s=np.sum(ca)
    t2=time.clock()
    print(s)
    print("np sum", t2-t1)

Which gives nice speed up with cython sum, especially with small size arrays.

Now to go further, i would like to parallelize the nogil block with OpenMP. Unfortunately, i can't find a way to do this with cython.parallel.prange/parallel