diff options
Diffstat (limited to 'numpy')
| -rw-r--r-- | numpy/core/src/multiarray/cblasfuncs.c | 105 | ||||
| -rw-r--r-- | numpy/core/src/multiarray/common.c | 100 | ||||
| -rw-r--r-- | numpy/core/src/multiarray/common.h | 13 | ||||
| -rw-r--r-- | numpy/core/src/multiarray/multiarraymodule.c | 98 |
4 files changed, 120 insertions, 196 deletions
diff --git a/numpy/core/src/multiarray/cblasfuncs.c b/numpy/core/src/multiarray/cblasfuncs.c index c941bb29b..6460c5db1 100644 --- a/numpy/core/src/multiarray/cblasfuncs.c +++ b/numpy/core/src/multiarray/cblasfuncs.c @@ -12,32 +12,6 @@ #include "npy_cblas.h" #include "arraytypes.h" #include "common.h" -#include "mem_overlap.h" - - -/* - * Helper: call appropriate BLAS dot function for typenum. - * Strides are NumPy strides. - */ -static void -blas_dot(int typenum, npy_intp n, - void *a, npy_intp stridea, void *b, npy_intp strideb, void *res) -{ - switch (typenum) { - case NPY_DOUBLE: - DOUBLE_dot(a, stridea, b, strideb, res, n, NULL); - break; - case NPY_FLOAT: - FLOAT_dot(a, stridea, b, strideb, res, n, NULL); - break; - case NPY_CDOUBLE: - CDOUBLE_dot(a, stridea, b, strideb, res, n, NULL); - break; - case NPY_CFLOAT: - CFLOAT_dot(a, stridea, b, strideb, res, n, NULL); - break; - } -} static const double oneD[2] = {1.0, 0.0}, zeroD[2] = {0.0, 0.0}; @@ -227,6 +201,7 @@ _bad_strides(PyArrayObject *ap) return 0; } + /* * dot(a,b) * Returns the dot product of a and b for arrays of floating point types. @@ -379,77 +354,9 @@ cblas_matrixproduct(int typenum, PyArrayObject *ap1, PyArrayObject *ap2, } } - if (out != NULL) { - int d; - - /* verify that out is usable */ - if (PyArray_NDIM(out) != nd || - PyArray_TYPE(out) != typenum || - !PyArray_ISCARRAY(out)) { - - PyErr_SetString(PyExc_ValueError, - "output array is not acceptable (must have the right datatype, " - "number of dimensions, and be a C-Array)"); - goto fail; - } - for (d = 0; d < nd; ++d) { - if (dimensions[d] != PyArray_DIM(out, d)) { - PyErr_SetString(PyExc_ValueError, - "output array has wrong dimensions"); - goto fail; - } - } - - /* check for memory overlap */ - if (!(solve_may_share_memory(out, ap1, 1) == 0 && - solve_may_share_memory(out, ap2, 1) == 0)) { - /* allocate temporary output array */ - out_buf = (PyArrayObject *)PyArray_NewLikeArray(out, NPY_CORDER, - NULL, 0); - if (out_buf == NULL) { - goto fail; - } - - /* set copy-back */ - Py_INCREF(out); - if (PyArray_SetWritebackIfCopyBase(out_buf, out) < 0) { - Py_DECREF(out); - goto fail; - } - } - else { - Py_INCREF(out); - out_buf = out; - } - Py_INCREF(out); - result = out; - } - else { - double prior1, prior2; - PyTypeObject *subtype; - PyObject *tmp; - - /* Choose which subtype to return */ - if (Py_TYPE(ap1) != Py_TYPE(ap2)) { - prior2 = PyArray_GetPriority((PyObject *)ap2, 0.0); - prior1 = PyArray_GetPriority((PyObject *)ap1, 0.0); - subtype = (prior2 > prior1 ? Py_TYPE(ap2) : Py_TYPE(ap1)); - } - else { - prior1 = prior2 = 0.0; - subtype = Py_TYPE(ap1); - } - - tmp = (PyObject *)(prior2 > prior1 ? ap2 : ap1); - - out_buf = (PyArrayObject *)PyArray_New(subtype, nd, dimensions, - typenum, NULL, NULL, 0, 0, tmp); - if (out_buf == NULL) { - goto fail; - } - - Py_INCREF(out_buf); - result = out_buf; + out_buf = new_array_for_sum(ap1, ap2, out, nd, dimensions, typenum, &result); + if (out_buf == NULL) { + goto fail; } numbytes = PyArray_NBYTES(out_buf); @@ -617,10 +524,10 @@ cblas_matrixproduct(int typenum, PyArrayObject *ap1, PyArrayObject *ap2, NPY_BEGIN_ALLOW_THREADS; /* Dot product between two vectors -- Level 1 BLAS */ - blas_dot(typenum, l, + PyArray_DESCR(out_buf)->f->dotfunc( PyArray_DATA(ap1), PyArray_STRIDE(ap1, (ap1shape == _row)), PyArray_DATA(ap2), PyArray_STRIDE(ap2, 0), - PyArray_DATA(out_buf)); + PyArray_DATA(out_buf), l, NULL); NPY_END_ALLOW_THREADS; } else if (ap1shape == _matrix && ap2shape != _matrix) { diff --git a/numpy/core/src/multiarray/common.c b/numpy/core/src/multiarray/common.c index c70f8526e..4f695fdc7 100644 --- a/numpy/core/src/multiarray/common.c +++ b/numpy/core/src/multiarray/common.c @@ -15,6 +15,7 @@ #include "buffer.h" #include "get_attr_string.h" +#include "mem_overlap.h" /* * The casting to use for implicit assignment operations resulting from @@ -852,3 +853,102 @@ _may_have_objects(PyArray_Descr *dtype) return (PyDataType_HASFIELDS(base) || PyDataType_FLAGCHK(base, NPY_ITEM_HASOBJECT) ); } + +/* + * Make a new empty array, of the passed size, of a type that takes the + * priority of ap1 and ap2 into account. + * + * If `out` is non-NULL, memory overlap is checked with ap1 and ap2, and an + * updateifcopy temporary array may be returned. If `result` is non-NULL, the + * output array to be returned (`out` if non-NULL and the newly allocated array + * otherwise) is incref'd and put to *result. + */ +NPY_NO_EXPORT PyArrayObject * +new_array_for_sum(PyArrayObject *ap1, PyArrayObject *ap2, PyArrayObject* out, + int nd, npy_intp dimensions[], int typenum, PyArrayObject **result) +{ + PyArrayObject *out_buf; + + if (out) { + int d; + + /* verify that out is usable */ + if (PyArray_NDIM(out) != nd || + PyArray_TYPE(out) != typenum || + !PyArray_ISCARRAY(out)) { + PyErr_SetString(PyExc_ValueError, + "output array is not acceptable (must have the right datatype, " + "number of dimensions, and be a C-Array)"); + return 0; + } + for (d = 0; d < nd; ++d) { + if (dimensions[d] != PyArray_DIM(out, d)) { + PyErr_SetString(PyExc_ValueError, + "output array has wrong dimensions"); + return 0; + } + } + + /* check for memory overlap */ + if (!(solve_may_share_memory(out, ap1, 1) == 0 && + solve_may_share_memory(out, ap2, 1) == 0)) { + /* allocate temporary output array */ + out_buf = (PyArrayObject *)PyArray_NewLikeArray(out, NPY_CORDER, + NULL, 0); + if (out_buf == NULL) { + return NULL; + } + + /* set copy-back */ + Py_INCREF(out); + if (PyArray_SetWritebackIfCopyBase(out_buf, out) < 0) { + Py_DECREF(out); + Py_DECREF(out_buf); + return NULL; + } + } + else { + Py_INCREF(out); + out_buf = out; + } + + if (result) { + Py_INCREF(out); + *result = out; + } + + return out_buf; + } + else { + PyTypeObject *subtype; + double prior1, prior2; + /* + * Need to choose an output array that can hold a sum + * -- use priority to determine which subtype. + */ + if (Py_TYPE(ap2) != Py_TYPE(ap1)) { + prior2 = PyArray_GetPriority((PyObject *)ap2, 0.0); + prior1 = PyArray_GetPriority((PyObject *)ap1, 0.0); + subtype = (prior2 > prior1 ? Py_TYPE(ap2) : Py_TYPE(ap1)); + } + else { + prior1 = prior2 = 0.0; + subtype = Py_TYPE(ap1); + } + + out_buf = (PyArrayObject *)PyArray_New(subtype, nd, dimensions, + typenum, NULL, NULL, 0, 0, + (PyObject *) + (prior2 > prior1 ? ap2 : ap1)); + + if (out_buf != NULL && result) { + Py_INCREF(out_buf); + *result = out_buf; + } + + return out_buf; + } +} + + + diff --git a/numpy/core/src/multiarray/common.h b/numpy/core/src/multiarray/common.h index ae9b960c8..db0a49920 100644 --- a/numpy/core/src/multiarray/common.h +++ b/numpy/core/src/multiarray/common.h @@ -283,4 +283,17 @@ blas_stride(npy_intp stride, unsigned itemsize) #include "ucsnarrow.h" +/* + * Make a new empty array, of the passed size, of a type that takes the + * priority of ap1 and ap2 into account. + * + * If `out` is non-NULL, memory overlap is checked with ap1 and ap2, and an + * updateifcopy temporary array may be returned. If `result` is non-NULL, the + * output array to be returned (`out` if non-NULL and the newly allocated array + * otherwise) is incref'd and put to *result. + */ +NPY_NO_EXPORT PyArrayObject * +new_array_for_sum(PyArrayObject *ap1, PyArrayObject *ap2, PyArrayObject* out, + int nd, npy_intp dimensions[], int typenum, PyArrayObject **result); + #endif diff --git a/numpy/core/src/multiarray/multiarraymodule.c b/numpy/core/src/multiarray/multiarraymodule.c index f78a748c0..e6af5a81e 100644 --- a/numpy/core/src/multiarray/multiarraymodule.c +++ b/numpy/core/src/multiarray/multiarraymodule.c @@ -800,102 +800,6 @@ PyArray_CanCoerceScalar(int thistype, int neededtype, return 0; } -/* - * Make a new empty array, of the passed size, of a type that takes the - * priority of ap1 and ap2 into account. - * - * If `out` is non-NULL, memory overlap is checked with ap1 and ap2, and an - * updateifcopy temporary array may be returned. If `result` is non-NULL, the - * output array to be returned (`out` if non-NULL and the newly allocated array - * otherwise) is incref'd and put to *result. - */ -static PyArrayObject * -new_array_for_sum(PyArrayObject *ap1, PyArrayObject *ap2, PyArrayObject* out, - int nd, npy_intp dimensions[], int typenum, PyArrayObject **result) -{ - PyArrayObject *out_buf; - - if (out) { - int d; - - /* verify that out is usable */ - if (PyArray_NDIM(out) != nd || - PyArray_TYPE(out) != typenum || - !PyArray_ISCARRAY(out)) { - PyErr_SetString(PyExc_ValueError, - "output array is not acceptable (must have the right datatype, " - "number of dimensions, and be a C-Array)"); - return 0; - } - for (d = 0; d < nd; ++d) { - if (dimensions[d] != PyArray_DIM(out, d)) { - PyErr_SetString(PyExc_ValueError, - "output array has wrong dimensions"); - return 0; - } - } - - /* check for memory overlap */ - if (!(solve_may_share_memory(out, ap1, 1) == 0 && - solve_may_share_memory(out, ap2, 1) == 0)) { - /* allocate temporary output array */ - out_buf = (PyArrayObject *)PyArray_NewLikeArray(out, NPY_CORDER, - NULL, 0); - if (out_buf == NULL) { - return NULL; - } - - /* set copy-back */ - Py_INCREF(out); - if (PyArray_SetWritebackIfCopyBase(out_buf, out) < 0) { - Py_DECREF(out); - Py_DECREF(out_buf); - return NULL; - } - } - else { - Py_INCREF(out); - out_buf = out; - } - - if (result) { - Py_INCREF(out); - *result = out; - } - - return out_buf; - } - else { - PyTypeObject *subtype; - double prior1, prior2; - /* - * Need to choose an output array that can hold a sum - * -- use priority to determine which subtype. - */ - if (Py_TYPE(ap2) != Py_TYPE(ap1)) { - prior2 = PyArray_GetPriority((PyObject *)ap2, 0.0); - prior1 = PyArray_GetPriority((PyObject *)ap1, 0.0); - subtype = (prior2 > prior1 ? Py_TYPE(ap2) : Py_TYPE(ap1)); - } - else { - prior1 = prior2 = 0.0; - subtype = Py_TYPE(ap1); - } - - out_buf = (PyArrayObject *)PyArray_New(subtype, nd, dimensions, - typenum, NULL, NULL, 0, 0, - (PyObject *) - (prior2 > prior1 ? ap2 : ap1)); - - if (out_buf != NULL && result) { - Py_INCREF(out_buf); - *result = out_buf; - } - - return out_buf; - } -} - /* Could perhaps be redone to not make contiguous arrays */ /*NUMPY_API @@ -1101,7 +1005,7 @@ PyArray_MatrixProduct2(PyObject *op1, PyObject *op2, PyArrayObject* out) NPY_BEGIN_THREADS_DESCR(PyArray_DESCR(ap2)); while (it1->index < it1->size) { while (it2->index < it2->size) { - dot(it1->dataptr, is1, it2->dataptr, is2, op, l, out_buf); + dot(it1->dataptr, is1, it2->dataptr, is2, op, l, NULL); op += os; PyArray_ITER_NEXT(it2); } |