diff options
Diffstat (limited to 'numpy/core/include')
| -rw-r--r-- | numpy/core/include/meson.build | 1 | ||||
| -rw-r--r-- | numpy/core/include/numpy/_dtype_api.h | 408 | ||||
| -rw-r--r-- | numpy/core/include/numpy/arrayscalars.h | 4 | ||||
| -rw-r--r-- | numpy/core/include/numpy/experimental_dtype_api.h | 161 | ||||
| -rw-r--r-- | numpy/core/include/numpy/ndarraytypes.h | 33 | ||||
| -rw-r--r-- | numpy/core/include/numpy/npy_3kcompat.h | 26 | ||||
| -rw-r--r-- | numpy/core/include/numpy/npy_common.h | 60 | ||||
| -rw-r--r-- | numpy/core/include/numpy/npy_cpu.h | 2 | ||||
| -rw-r--r-- | numpy/core/include/numpy/npy_math.h | 14 | ||||
| -rw-r--r-- | numpy/core/include/numpy/numpyconfig.h | 137 | ||||
| -rw-r--r-- | numpy/core/include/numpy/ufuncobject.h | 6 |
11 files changed, 599 insertions, 253 deletions
diff --git a/numpy/core/include/meson.build b/numpy/core/include/meson.build index 0f9fbe76b..be07a07b8 100644 --- a/numpy/core/include/meson.build +++ b/numpy/core/include/meson.build @@ -2,6 +2,7 @@ installed_headers = [ 'numpy/_neighborhood_iterator_imp.h', 'numpy/arrayobject.h', 'numpy/arrayscalars.h', + 'numpy/_dtype_api.h', 'numpy/experimental_dtype_api.h', 'numpy/halffloat.h', 'numpy/ndarrayobject.h', diff --git a/numpy/core/include/numpy/_dtype_api.h b/numpy/core/include/numpy/_dtype_api.h new file mode 100644 index 000000000..c397699c7 --- /dev/null +++ b/numpy/core/include/numpy/_dtype_api.h @@ -0,0 +1,408 @@ +/* + * DType related API shared by the (experimental) public API And internal API. + */ + +#ifndef NUMPY_CORE_INCLUDE_NUMPY___DTYPE_API_H_ +#define NUMPY_CORE_INCLUDE_NUMPY___DTYPE_API_H_ + +#define __EXPERIMENTAL_DTYPE_API_VERSION 10 + +struct PyArrayMethodObject_tag; + +/* + * Largely opaque struct for DType classes (i.e. metaclass instances). + * The internal definition is currently in `ndarraytypes.h` (export is a bit + * more complex because `PyArray_Descr` is a DTypeMeta internally but not + * externally). + */ +#if !(defined(NPY_INTERNAL_BUILD) && NPY_INTERNAL_BUILD) + + typedef struct PyArray_DTypeMeta_tag { + PyHeapTypeObject super; + + /* + * Most DTypes will have a singleton default instance, for the + * parametric legacy DTypes (bytes, string, void, datetime) this + * may be a pointer to the *prototype* instance? + */ + PyArray_Descr *singleton; + /* Copy of the legacy DTypes type number, usually invalid. */ + int type_num; + + /* The type object of the scalar instances (may be NULL?) */ + PyTypeObject *scalar_type; + /* + * DType flags to signal legacy, parametric, or + * abstract. But plenty of space for additional information/flags. + */ + npy_uint64 flags; + + /* + * Use indirection in order to allow a fixed size for this struct. + * A stable ABI size makes creating a static DType less painful + * while also ensuring flexibility for all opaque API (with one + * indirection due the pointer lookup). + */ + void *dt_slots; + /* Allow growing (at the moment also beyond this) */ + void *reserved[3]; + } PyArray_DTypeMeta; + +#endif /* not internal build */ + +/* + * ****************************************************** + * ArrayMethod API (Casting and UFuncs) + * ****************************************************** + */ +/* + * NOTE: Expected changes: + * * probably split runtime and general flags into two + * * should possibly not use an enum for typedef for more stable ABI? + */ +typedef enum { + /* Flag for whether the GIL is required */ + NPY_METH_REQUIRES_PYAPI = 1 << 0, + /* + * Some functions cannot set floating point error flags, this flag + * gives us the option (not requirement) to skip floating point error + * setup/check. No function should set error flags and ignore them + * since it would interfere with chaining operations (e.g. casting). + */ + NPY_METH_NO_FLOATINGPOINT_ERRORS = 1 << 1, + /* Whether the method supports unaligned access (not runtime) */ + NPY_METH_SUPPORTS_UNALIGNED = 1 << 2, + /* + * Used for reductions to allow reordering the operation. At this point + * assume that if set, it also applies to normal operations though! + */ + NPY_METH_IS_REORDERABLE = 1 << 3, + /* + * Private flag for now for *logic* functions. The logical functions + * `logical_or` and `logical_and` can always cast the inputs to booleans + * "safely" (because that is how the cast to bool is defined). + * @seberg: I am not sure this is the best way to handle this, so its + * private for now (also it is very limited anyway). + * There is one "exception". NA aware dtypes cannot cast to bool + * (hopefully), so the `??->?` loop should error even with this flag. + * But a second NA fallback loop will be necessary. + */ + _NPY_METH_FORCE_CAST_INPUTS = 1 << 17, + + /* All flags which can change at runtime */ + NPY_METH_RUNTIME_FLAGS = ( + NPY_METH_REQUIRES_PYAPI | + NPY_METH_NO_FLOATINGPOINT_ERRORS), +} NPY_ARRAYMETHOD_FLAGS; + + +typedef struct PyArrayMethod_Context_tag { + /* The caller, which is typically the original ufunc. May be NULL */ + PyObject *caller; + /* The method "self". Publically currentl an opaque object. */ + struct PyArrayMethodObject_tag *method; + + /* Operand descriptors, filled in by resolve_descriptors */ + PyArray_Descr **descriptors; + /* Structure may grow (this is harmless for DType authors) */ +} PyArrayMethod_Context; + + +/* + * The main object for creating a new ArrayMethod. We use the typical `slots` + * mechanism used by the Python limited API (see below for the slot defs). + */ +typedef struct { + const char *name; + int nin, nout; + NPY_CASTING casting; + NPY_ARRAYMETHOD_FLAGS flags; + PyArray_DTypeMeta **dtypes; + PyType_Slot *slots; +} PyArrayMethod_Spec; + + +/* + * ArrayMethod slots + * ----------------- + * + * SLOTS IDs For the ArrayMethod creation, once fully public, IDs are fixed + * but can be deprecated and arbitrarily extended. + */ +#define NPY_METH_resolve_descriptors 1 +/* We may want to adapt the `get_loop` signature a bit: */ +#define _NPY_METH_get_loop 2 +#define NPY_METH_get_reduction_initial 3 +/* specific loops for constructions/default get_loop: */ +#define NPY_METH_strided_loop 4 +#define NPY_METH_contiguous_loop 5 +#define NPY_METH_unaligned_strided_loop 6 +#define NPY_METH_unaligned_contiguous_loop 7 +#define NPY_METH_contiguous_indexed_loop 8 + +/* + * The resolve descriptors function, must be able to handle NULL values for + * all output (but not input) `given_descrs` and fill `loop_descrs`. + * Return -1 on error or 0 if the operation is not possible without an error + * set. (This may still be in flux.) + * Otherwise must return the "casting safety", for normal functions, this is + * almost always "safe" (or even "equivalent"?). + * + * `resolve_descriptors` is optional if all output DTypes are non-parametric. + */ +typedef NPY_CASTING (resolve_descriptors_function)( + /* "method" is currently opaque (necessary e.g. to wrap Python) */ + struct PyArrayMethodObject_tag *method, + /* DTypes the method was created for */ + PyArray_DTypeMeta **dtypes, + /* Input descriptors (instances). Outputs may be NULL. */ + PyArray_Descr **given_descrs, + /* Exact loop descriptors to use, must not hold references on error */ + PyArray_Descr **loop_descrs, + npy_intp *view_offset); + + +typedef int (PyArrayMethod_StridedLoop)(PyArrayMethod_Context *context, + char *const *data, const npy_intp *dimensions, const npy_intp *strides, + NpyAuxData *transferdata); + + +typedef int (get_loop_function)( + PyArrayMethod_Context *context, + int aligned, int move_references, + const npy_intp *strides, + PyArrayMethod_StridedLoop **out_loop, + NpyAuxData **out_transferdata, + NPY_ARRAYMETHOD_FLAGS *flags); + +/** + * Query an ArrayMethod for the initial value for use in reduction. + * + * @param context The arraymethod context, mainly to access the descriptors. + * @param reduction_is_empty Whether the reduction is empty. When it is, the + * value returned may differ. In this case it is a "default" value that + * may differ from the "identity" value normally used. For example: + * - `0.0` is the default for `sum([])`. But `-0.0` is the correct + * identity otherwise as it preserves the sign for `sum([-0.0])`. + * - We use no identity for object, but return the default of `0` and `1` + * for the empty `sum([], dtype=object)` and `prod([], dtype=object)`. + * This allows `np.sum(np.array(["a", "b"], dtype=object))` to work. + * - `-inf` or `INT_MIN` for `max` is an identity, but at least `INT_MIN` + * not a good *default* when there are no items. + * @param initial Pointer to initial data to be filled (if possible) + * + * @returns -1, 0, or 1 indicating error, no initial value, and initial being + * successfully filled. Errors must not be given where 0 is correct, NumPy + * may call this even when not strictly necessary. + */ +typedef int (get_reduction_initial_function)( + PyArrayMethod_Context *context, npy_bool reduction_is_empty, + char *initial); + +/* + * The following functions are only used by the wrapping array method defined + * in umath/wrapping_array_method.c + */ + +/* + * The function to convert the given descriptors (passed in to + * `resolve_descriptors`) and translates them for the wrapped loop. + * The new descriptors MUST be viewable with the old ones, `NULL` must be + * supported (for outputs) and should normally be forwarded. + * + * The function must clean up on error. + * + * NOTE: We currently assume that this translation gives "viewable" results. + * I.e. there is no additional casting related to the wrapping process. + * In principle that could be supported, but not sure it is useful. + * This currently also means that e.g. alignment must apply identically + * to the new dtypes. + * + * TODO: Due to the fact that `resolve_descriptors` is also used for `can_cast` + * there is no way to "pass out" the result of this function. This means + * it will be called twice for every ufunc call. + * (I am considering including `auxdata` as an "optional" parameter to + * `resolve_descriptors`, so that it can be filled there if not NULL.) + */ +typedef int translate_given_descrs_func(int nin, int nout, + PyArray_DTypeMeta *wrapped_dtypes[], + PyArray_Descr *given_descrs[], PyArray_Descr *new_descrs[]); + +/** + * The function to convert the actual loop descriptors (as returned by the + * original `resolve_descriptors` function) to the ones the output array + * should use. + * This function must return "viewable" types, it must not mutate them in any + * form that would break the inner-loop logic. Does not need to support NULL. + * + * The function must clean up on error. + * + * @param nargs Number of arguments + * @param new_dtypes The DTypes of the output (usually probably not needed) + * @param given_descrs Original given_descrs to the resolver, necessary to + * fetch any information related to the new dtypes from the original. + * @param original_descrs The `loop_descrs` returned by the wrapped loop. + * @param loop_descrs The output descriptors, compatible to `original_descrs`. + * + * @returns 0 on success, -1 on failure. + */ +typedef int translate_loop_descrs_func(int nin, int nout, + PyArray_DTypeMeta *new_dtypes[], PyArray_Descr *given_descrs[], + PyArray_Descr *original_descrs[], PyArray_Descr *loop_descrs[]); + + +/* + * A traverse loop working on a single array. This is similar to the general + * strided-loop function. This is designed for loops that need to visit every + * element of a single array. + * + * Currently this is used for array clearing, via the NPY_DT_get_clear_loop + * API hook, and zero-filling, via the NPY_DT_get_fill_zero_loop API hook. + * These are most useful for handling arrays storing embedded references to + * python objects or heap-allocated data. + * + * The `void *traverse_context` is passed in because we may need to pass in + * Intepreter state or similar in the future, but we don't want to pass in + * a full context (with pointers to dtypes, method, caller which all make + * no sense for a traverse function). + * + * We assume for now that this context can be just passed through in the + * the future (for structured dtypes). + * + */ +typedef int (traverse_loop_function)( + void *traverse_context, PyArray_Descr *descr, char *data, + npy_intp size, npy_intp stride, NpyAuxData *auxdata); + + +/* + * Simplified get_loop function specific to dtype traversal + * + * It should set the flags needed for the traversal loop and set out_loop to the + * loop function, which must be a valid traverse_loop_function + * pointer. Currently this is used for zero-filling and clearing arrays storing + * embedded references. + * + */ +typedef int (get_traverse_loop_function)( + void *traverse_context, PyArray_Descr *descr, + int aligned, npy_intp fixed_stride, + traverse_loop_function **out_loop, NpyAuxData **out_auxdata, + NPY_ARRAYMETHOD_FLAGS *flags); + + +/* + * **************************** + * DTYPE API + * **************************** + */ + +#define NPY_DT_ABSTRACT 1 << 1 +#define NPY_DT_PARAMETRIC 1 << 2 +#define NPY_DT_NUMERIC 1 << 3 + +/* + * These correspond to slots in the NPY_DType_Slots struct and must + * be in the same order as the members of that struct. If new slots + * get added or old slots get removed NPY_NUM_DTYPE_SLOTS must also + * be updated + */ + +#define NPY_DT_discover_descr_from_pyobject 1 +// this slot is considered private because its API hasn't beed decided +#define _NPY_DT_is_known_scalar_type 2 +#define NPY_DT_default_descr 3 +#define NPY_DT_common_dtype 4 +#define NPY_DT_common_instance 5 +#define NPY_DT_ensure_canonical 6 +#define NPY_DT_setitem 7 +#define NPY_DT_getitem 8 +#define NPY_DT_get_clear_loop 9 +#define NPY_DT_get_fill_zero_loop 10 + +// These PyArray_ArrFunc slots will be deprecated and replaced eventually +// getitem and setitem can be defined as a performance optimization; +// by default the user dtypes call `legacy_getitem_using_DType` and +// `legacy_setitem_using_DType`, respectively. This functionality is +// only supported for basic NumPy DTypes. + + +// used to separate dtype slots from arrfuncs slots +// intended only for internal use but defined here for clarity +#define _NPY_DT_ARRFUNCS_OFFSET (1 << 10) + +// Cast is disabled +// #define NPY_DT_PyArray_ArrFuncs_cast 0 + _NPY_DT_ARRFUNCS_OFFSET + +#define NPY_DT_PyArray_ArrFuncs_getitem 1 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_setitem 2 + _NPY_DT_ARRFUNCS_OFFSET + +#define NPY_DT_PyArray_ArrFuncs_copyswapn 3 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_copyswap 4 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_compare 5 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_argmax 6 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_dotfunc 7 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_scanfunc 8 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_fromstr 9 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_nonzero 10 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_fill 11 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_fillwithscalar 12 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_sort 13 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_argsort 14 + _NPY_DT_ARRFUNCS_OFFSET + +// Casting related slots are disabled. See +// https://github.com/numpy/numpy/pull/23173#discussion_r1101098163 +// #define NPY_DT_PyArray_ArrFuncs_castdict 15 + _NPY_DT_ARRFUNCS_OFFSET +// #define NPY_DT_PyArray_ArrFuncs_scalarkind 16 + _NPY_DT_ARRFUNCS_OFFSET +// #define NPY_DT_PyArray_ArrFuncs_cancastscalarkindto 17 + _NPY_DT_ARRFUNCS_OFFSET +// #define NPY_DT_PyArray_ArrFuncs_cancastto 18 + _NPY_DT_ARRFUNCS_OFFSET + +// These are deprecated in NumPy 1.19, so are disabled here. +// #define NPY_DT_PyArray_ArrFuncs_fastclip 19 + _NPY_DT_ARRFUNCS_OFFSET +// #define NPY_DT_PyArray_ArrFuncs_fastputmask 20 + _NPY_DT_ARRFUNCS_OFFSET +// #define NPY_DT_PyArray_ArrFuncs_fasttake 21 + _NPY_DT_ARRFUNCS_OFFSET +#define NPY_DT_PyArray_ArrFuncs_argmin 22 + _NPY_DT_ARRFUNCS_OFFSET + +// TODO: These slots probably still need some thought, and/or a way to "grow"? +typedef struct { + PyTypeObject *typeobj; /* type of python scalar or NULL */ + int flags; /* flags, including parametric and abstract */ + /* NULL terminated cast definitions. Use NULL for the newly created DType */ + PyArrayMethod_Spec **casts; + PyType_Slot *slots; + /* Baseclass or NULL (will always subclass `np.dtype`) */ + PyTypeObject *baseclass; +} PyArrayDTypeMeta_Spec; + + +typedef PyArray_Descr *(discover_descr_from_pyobject_function)( + PyArray_DTypeMeta *cls, PyObject *obj); + +/* + * Before making this public, we should decide whether it should pass + * the type, or allow looking at the object. A possible use-case: + * `np.array(np.array([0]), dtype=np.ndarray)` + * Could consider arrays that are not `dtype=ndarray` "scalars". + */ +typedef int (is_known_scalar_type_function)( + PyArray_DTypeMeta *cls, PyTypeObject *obj); + +typedef PyArray_Descr *(default_descr_function)(PyArray_DTypeMeta *cls); +typedef PyArray_DTypeMeta *(common_dtype_function)( + PyArray_DTypeMeta *dtype1, PyArray_DTypeMeta *dtype2); +typedef PyArray_Descr *(common_instance_function)( + PyArray_Descr *dtype1, PyArray_Descr *dtype2); +typedef PyArray_Descr *(ensure_canonical_function)(PyArray_Descr *dtype); + +/* + * TODO: These two functions are currently only used for experimental DType + * API support. Their relation should be "reversed": NumPy should + * always use them internally. + * There are open points about "casting safety" though, e.g. setting + * elements is currently always unsafe. + */ +typedef int(setitemfunction)(PyArray_Descr *, PyObject *, char *); +typedef PyObject *(getitemfunction)(PyArray_Descr *, char *); + + +#endif /* NUMPY_CORE_INCLUDE_NUMPY___DTYPE_API_H_ */ diff --git a/numpy/core/include/numpy/arrayscalars.h b/numpy/core/include/numpy/arrayscalars.h index a20a68016..258bf95b6 100644 --- a/numpy/core/include/numpy/arrayscalars.h +++ b/numpy/core/include/numpy/arrayscalars.h @@ -139,7 +139,9 @@ typedef struct { /* note that the PyObject_HEAD macro lives right here */ PyUnicodeObject base; Py_UCS4 *obval; + #if NPY_FEATURE_VERSION >= NPY_1_20_API_VERSION char *buffer_fmt; + #endif } PyUnicodeScalarObject; @@ -149,7 +151,9 @@ typedef struct { PyArray_Descr *descr; int flags; PyObject *base; + #if NPY_FEATURE_VERSION >= NPY_1_20_API_VERSION void *_buffer_info; /* private buffer info, tagged to allow warning */ + #endif } PyVoidScalarObject; /* Macros diff --git a/numpy/core/include/numpy/experimental_dtype_api.h b/numpy/core/include/numpy/experimental_dtype_api.h index 5f5f24317..120d33324 100644 --- a/numpy/core/include/numpy/experimental_dtype_api.h +++ b/numpy/core/include/numpy/experimental_dtype_api.h @@ -3,6 +3,9 @@ * NEPs 41 to 43. For background, please check these NEPs. Otherwise, * this header also serves as documentation for the time being. * + * The header includes `_dtype_api.h` which holds most definition while this + * header mainly wraps functions for public consumption. + * * Please do not hesitate to contact @seberg with questions. This is * developed together with https://github.com/seberg/experimental_user_dtypes * and those interested in experimenting are encouraged to contribute there. @@ -114,7 +117,13 @@ #include <Python.h> #include "ndarraytypes.h" +#include "_dtype_api.h" +/* + * The contents of PyArrayMethodObject are currently opaque (is there a way + * good way to make them be `PyObject *`?) + */ +typedef struct PyArrayMethodObject_tag PyArrayMethodObject; /* * There must be a better way?! -- Oh well, this is experimental @@ -154,66 +163,6 @@ #endif -/* - * DTypeMeta struct, the content may be made fully opaque (except the size). - * We may also move everything into a single `void *dt_slots`. - */ -typedef struct { - PyHeapTypeObject super; - PyArray_Descr *singleton; - int type_num; - PyTypeObject *scalar_type; - npy_uint64 flags; - void *dt_slots; - void *reserved[3]; -} PyArray_DTypeMeta; - - -/* - * ****************************************************** - * ArrayMethod API (Casting and UFuncs) - * ****************************************************** - */ -/* - * NOTE: Expected changes: - * * invert logic of floating point error flag - * * probably split runtime and general flags into two - * * should possibly not use an enum for typedef for more stable ABI? - */ -typedef enum { - /* Flag for whether the GIL is required */ - NPY_METH_REQUIRES_PYAPI = 1 << 1, - /* - * Some functions cannot set floating point error flags, this flag - * gives us the option (not requirement) to skip floating point error - * setup/check. No function should set error flags and ignore them - * since it would interfere with chaining operations (e.g. casting). - */ - NPY_METH_NO_FLOATINGPOINT_ERRORS = 1 << 2, - /* Whether the method supports unaligned access (not runtime) */ - NPY_METH_SUPPORTS_UNALIGNED = 1 << 3, - - /* All flags which can change at runtime */ - NPY_METH_RUNTIME_FLAGS = ( - NPY_METH_REQUIRES_PYAPI | - NPY_METH_NO_FLOATINGPOINT_ERRORS), -} NPY_ARRAYMETHOD_FLAGS; - - -/* - * The main object for creating a new ArrayMethod. We use the typical `slots` - * mechanism used by the Python limited API (see below for the slot defs). - */ -typedef struct { - const char *name; - int nin, nout; - NPY_CASTING casting; - NPY_ARRAYMETHOD_FLAGS flags; - PyArray_DTypeMeta **dtypes; - PyType_Slot *slots; -} PyArrayMethod_Spec; - - typedef int _ufunc_addloop_fromspec_func( PyObject *ufunc, PyArrayMethod_Spec *spec); /* @@ -267,92 +216,6 @@ typedef int _ufunc_addpromoter_func( #define PyUFunc_AddPromoter \ (*(_ufunc_addpromoter_func *)(__experimental_dtype_api_table[1])) - -/* - * The resolve descriptors function, must be able to handle NULL values for - * all output (but not input) `given_descrs` and fill `loop_descrs`. - * Return -1 on error or 0 if the operation is not possible without an error - * set. (This may still be in flux.) - * Otherwise must return the "casting safety", for normal functions, this is - * almost always "safe" (or even "equivalent"?). - * - * `resolve_descriptors` is optional if all output DTypes are non-parametric. - */ -#define NPY_METH_resolve_descriptors 1 -typedef NPY_CASTING (resolve_descriptors_function)( - /* "method" is currently opaque (necessary e.g. to wrap Python) */ - PyObject *method, - /* DTypes the method was created for */ - PyObject **dtypes, - /* Input descriptors (instances). Outputs may be NULL. */ - PyArray_Descr **given_descrs, - /* Exact loop descriptors to use, must not hold references on error */ - PyArray_Descr **loop_descrs, - npy_intp *view_offset); - -/* NOT public yet: Signature needs adapting as external API. */ -#define _NPY_METH_get_loop 2 - -/* - * Current public API to define fast inner-loops. You must provide a - * strided loop. If this is a cast between two "versions" of the same dtype - * you must also provide an unaligned strided loop. - * Other loops are useful to optimize the very common contiguous case. - * - * NOTE: As of now, NumPy will NOT use unaligned loops in ufuncs! - */ -#define NPY_METH_strided_loop 3 -#define NPY_METH_contiguous_loop 4 -#define NPY_METH_unaligned_strided_loop 5 -#define NPY_METH_unaligned_contiguous_loop 6 - - -typedef struct { - PyObject *caller; /* E.g. the original ufunc, may be NULL */ - PyObject *method; /* The method "self". Currently an opaque object */ - - /* Operand descriptors, filled in by resolve_descriptors */ - PyArray_Descr **descriptors; - /* Structure may grow (this is harmless for DType authors) */ -} PyArrayMethod_Context; - -typedef int (PyArrayMethod_StridedLoop)(PyArrayMethod_Context *context, - char *const *data, const npy_intp *dimensions, const npy_intp *strides, - NpyAuxData *transferdata); - - - -/* - * **************************** - * DTYPE API - * **************************** - */ - -#define NPY_DT_ABSTRACT 1 << 1 -#define NPY_DT_PARAMETRIC 1 << 2 - -#define NPY_DT_discover_descr_from_pyobject 1 -#define _NPY_DT_is_known_scalar_type 2 -#define NPY_DT_default_descr 3 -#define NPY_DT_common_dtype 4 -#define NPY_DT_common_instance 5 -#define NPY_DT_ensure_canonical 6 -#define NPY_DT_setitem 7 -#define NPY_DT_getitem 8 - - -// TODO: These slots probably still need some thought, and/or a way to "grow"? -typedef struct{ - PyTypeObject *typeobj; /* type of python scalar or NULL */ - int flags; /* flags, including parametric and abstract */ - /* NULL terminated cast definitions. Use NULL for the newly created DType */ - PyArrayMethod_Spec **casts; - PyType_Slot *slots; - /* Baseclass or NULL (will always subclass `np.dtype`) */ - PyTypeObject *baseclass; -} PyArrayDTypeMeta_Spec; - - #define PyArrayDTypeMeta_Type \ (*(PyTypeObject *)__experimental_dtype_api_table[2]) typedef int __dtypemeta_fromspec( @@ -458,16 +321,14 @@ PyArray_GetDefaultDescr(PyArray_DTypeMeta *DType) */ #if !defined(NO_IMPORT) && !defined(NO_IMPORT_ARRAY) -#define __EXPERIMENTAL_DTYPE_VERSION 5 - static int import_experimental_dtype_api(int version) { - if (version != __EXPERIMENTAL_DTYPE_VERSION) { + if (version != __EXPERIMENTAL_DTYPE_API_VERSION) { PyErr_Format(PyExc_RuntimeError, "DType API version %d did not match header version %d. Please " "update the import statement and check for API changes.", - version, __EXPERIMENTAL_DTYPE_VERSION); + version, __EXPERIMENTAL_DTYPE_API_VERSION); return -1; } if (__experimental_dtype_api_table != __uninitialized_table) { diff --git a/numpy/core/include/numpy/ndarraytypes.h b/numpy/core/include/numpy/ndarraytypes.h index 45ecb6955..742ba5261 100644 --- a/numpy/core/include/numpy/ndarraytypes.h +++ b/numpy/core/include/numpy/ndarraytypes.h @@ -44,23 +44,6 @@ #define NPY_FAIL 0 #define NPY_SUCCEED 1 -/* - * Binary compatibility version number. This number is increased - * whenever the C-API is changed such that binary compatibility is - * broken, i.e. whenever a recompile of extension modules is needed. - */ -#define NPY_VERSION NPY_ABI_VERSION - -/* - * Minor API version. This number is increased whenever a change is - * made to the C-API -- whether it breaks binary compatibility or not. - * Some changes, such as adding a function pointer to the end of the - * function table, can be made without breaking binary compatibility. - * In this case, only the NPY_FEATURE_VERSION (*not* NPY_VERSION) - * would be increased. Whenever binary compatibility is broken, both - * NPY_VERSION and NPY_FEATURE_VERSION should be increased. - */ -#define NPY_FEATURE_VERSION NPY_API_VERSION enum NPY_TYPES { NPY_BOOL=0, NPY_BYTE, NPY_UBYTE, @@ -729,11 +712,15 @@ typedef struct tagPyArrayObject_fields { int flags; /* For weak references */ PyObject *weakreflist; +#if NPY_FEATURE_VERSION >= NPY_1_20_API_VERSION void *_buffer_info; /* private buffer info, tagged to allow warning */ +#endif /* * For malloc/calloc/realloc/free per object */ +#if NPY_FEATURE_VERSION >= NPY_1_22_API_VERSION PyObject *mem_handler; +#endif } PyArrayObject_fields; /* @@ -1671,11 +1658,13 @@ PyArray_CLEARFLAGS(PyArrayObject *arr, int flags) ((PyArrayObject_fields *)arr)->flags &= ~flags; } -static inline NPY_RETURNS_BORROWED_REF PyObject * -PyArray_HANDLER(PyArrayObject *arr) -{ - return ((PyArrayObject_fields *)arr)->mem_handler; -} +#if NPY_FEATURE_VERSION >= NPY_1_22_API_VERSION + static inline NPY_RETURNS_BORROWED_REF PyObject * + PyArray_HANDLER(PyArrayObject *arr) + { + return ((PyArrayObject_fields *)arr)->mem_handler; + } +#endif #define PyTypeNum_ISBOOL(type) ((type) == NPY_BOOL) diff --git a/numpy/core/include/numpy/npy_3kcompat.h b/numpy/core/include/numpy/npy_3kcompat.h index 8e5e4000a..62fde943a 100644 --- a/numpy/core/include/numpy/npy_3kcompat.h +++ b/numpy/core/include/numpy/npy_3kcompat.h @@ -167,6 +167,26 @@ static inline int PyInt_Check(PyObject *op) { #endif /* NPY_PY3K */ +/* + * Macros to protect CRT calls against instant termination when passed an + * invalid parameter (https://bugs.python.org/issue23524). + */ +#if defined _MSC_VER && _MSC_VER >= 1900 + +#include <stdlib.h> + +extern _invalid_parameter_handler _Py_silent_invalid_parameter_handler; +#define NPY_BEGIN_SUPPRESS_IPH { _invalid_parameter_handler _Py_old_handler = \ + _set_thread_local_invalid_parameter_handler(_Py_silent_invalid_parameter_handler); +#define NPY_END_SUPPRESS_IPH _set_thread_local_invalid_parameter_handler(_Py_old_handler); } + +#else + +#define NPY_BEGIN_SUPPRESS_IPH +#define NPY_END_SUPPRESS_IPH + +#endif /* _MSC_VER >= 1900 */ + static inline void PyUnicode_ConcatAndDel(PyObject **left, PyObject *right) @@ -242,13 +262,17 @@ npy_PyFile_Dup2(PyObject *file, char *mode, npy_off_t *orig_pos) /* Convert to FILE* handle */ #ifdef _WIN32 + NPY_BEGIN_SUPPRESS_IPH handle = _fdopen(fd2, mode); + NPY_END_SUPPRESS_IPH #else handle = fdopen(fd2, mode); #endif if (handle == NULL) { PyErr_SetString(PyExc_IOError, - "Getting a FILE* from a Python file object failed"); + "Getting a FILE* from a Python file object via " + "_fdopen failed. If you built NumPy, you probably " + "linked with the wrong debug/release runtime"); return NULL; } diff --git a/numpy/core/include/numpy/npy_common.h b/numpy/core/include/numpy/npy_common.h index ea4a818c8..fb976aa6a 100644 --- a/numpy/core/include/numpy/npy_common.h +++ b/numpy/core/include/numpy/npy_common.h @@ -40,39 +40,6 @@ #define NPY_GCC_OPT_3 #endif -/* compile target attributes */ -#if defined HAVE_ATTRIBUTE_TARGET_AVX && defined HAVE_LINK_AVX -#define NPY_GCC_TARGET_AVX __attribute__((target("avx"))) -#else -#define NPY_GCC_TARGET_AVX -#endif - -#if defined HAVE_ATTRIBUTE_TARGET_AVX2_WITH_INTRINSICS -#define HAVE_ATTRIBUTE_TARGET_FMA -#define NPY_GCC_TARGET_FMA __attribute__((target("avx2,fma"))) -#endif - -#if defined HAVE_ATTRIBUTE_TARGET_AVX2 && defined HAVE_LINK_AVX2 -#define NPY_GCC_TARGET_AVX2 __attribute__((target("avx2"))) -#else -#define NPY_GCC_TARGET_AVX2 -#endif - -#if defined HAVE_ATTRIBUTE_TARGET_AVX512F && defined HAVE_LINK_AVX512F -#define NPY_GCC_TARGET_AVX512F __attribute__((target("avx512f"))) -#elif defined HAVE_ATTRIBUTE_TARGET_AVX512F_WITH_INTRINSICS -#define NPY_GCC_TARGET_AVX512F __attribute__((target("avx512f"))) -#else -#define NPY_GCC_TARGET_AVX512F -#endif - -#if defined HAVE_ATTRIBUTE_TARGET_AVX512_SKX && defined HAVE_LINK_AVX512_SKX -#define NPY_GCC_TARGET_AVX512_SKX __attribute__((target("avx512f,avx512dq,avx512vl,avx512bw,avx512cd"))) -#elif defined HAVE_ATTRIBUTE_TARGET_AVX512_SKX_WITH_INTRINSICS -#define NPY_GCC_TARGET_AVX512_SKX __attribute__((target("avx512f,avx512dq,avx512vl,avx512bw,avx512cd"))) -#else -#define NPY_GCC_TARGET_AVX512_SKX -#endif /* * mark an argument (starting from 1) that must not be NULL and is not checked * DO NOT USE IF FUNCTION CHECKS FOR NULL!! the compiler will remove the check @@ -83,21 +50,6 @@ #define NPY_GCC_NONNULL(n) #endif -#if defined HAVE_XMMINTRIN_H && defined HAVE__MM_LOAD_PS -#define NPY_HAVE_SSE_INTRINSICS -#endif - -#if defined HAVE_EMMINTRIN_H && defined HAVE__MM_LOAD_PD -#define NPY_HAVE_SSE2_INTRINSICS -#endif - -#if defined HAVE_IMMINTRIN_H && defined HAVE_LINK_AVX2 -#define NPY_HAVE_AVX2_INTRINSICS -#endif - -#if defined HAVE_IMMINTRIN_H && defined HAVE_LINK_AVX512F -#define NPY_HAVE_AVX512F_INTRINSICS -#endif /* * give a hint to the compiler which branch is more likely or unlikely * to occur, e.g. rare error cases: @@ -120,7 +72,7 @@ /* unlike _mm_prefetch also works on non-x86 */ #define NPY_PREFETCH(x, rw, loc) __builtin_prefetch((x), (rw), (loc)) #else -#ifdef HAVE__MM_PREFETCH +#ifdef NPY_HAVE_SSE /* _MM_HINT_ET[01] (rw = 1) unsupported, only available in gcc >= 4.9 */ #define NPY_PREFETCH(x, rw, loc) _mm_prefetch((x), loc == 0 ? _MM_HINT_NTA : \ (loc == 1 ? _MM_HINT_T2 : \ @@ -153,6 +105,14 @@ #define NPY_FINLINE static #endif +#if defined(_MSC_VER) + #define NPY_NOINLINE static __declspec(noinline) +#elif defined(__GNUC__) || defined(__clang__) + #define NPY_NOINLINE static __attribute__((noinline)) +#else + #define NPY_NOINLINE static +#endif + #ifdef HAVE___THREAD #define NPY_TLS __thread #else @@ -177,7 +137,7 @@ #define NPY_STEALS_REF_TO_ARG(n) #endif -/* 64 bit file position support, also on win-amd64. Ticket #1660 */ +/* 64 bit file position support, also on win-amd64. Issue gh-2256 */ #if defined(_MSC_VER) && defined(_WIN64) && (_MSC_VER > 1400) || \ defined(__MINGW32__) || defined(__MINGW64__) #include <io.h> diff --git a/numpy/core/include/numpy/npy_cpu.h b/numpy/core/include/numpy/npy_cpu.h index 78d229e7d..a19f8e6bb 100644 --- a/numpy/core/include/numpy/npy_cpu.h +++ b/numpy/core/include/numpy/npy_cpu.h @@ -77,7 +77,7 @@ #elif defined(__ARMEL__) || defined(__AARCH64EL__) || defined(_M_ARM64) #if defined(__ARM_32BIT_STATE) #define NPY_CPU_ARMEL_AARCH32 - #elif defined(__ARM_64BIT_STATE) || defined(_M_ARM64) + #elif defined(__ARM_64BIT_STATE) || defined(_M_ARM64) || defined(__AARCH64EL__) #define NPY_CPU_ARMEL_AARCH64 #else #define NPY_CPU_ARMEL diff --git a/numpy/core/include/numpy/npy_math.h b/numpy/core/include/numpy/npy_math.h index a1fd11396..2fcd41eb0 100644 --- a/numpy/core/include/numpy/npy_math.h +++ b/numpy/core/include/numpy/npy_math.h @@ -184,30 +184,22 @@ NPY_INPLACE double npy_atan2(double x, double y); #define npy_fmod fmod #define npy_floor floor #define npy_expm1 expm1 +#define npy_log1p log1p #define npy_acosh acosh +#define npy_asinh asinh #define npy_atanh atanh #define npy_rint rint #define npy_trunc trunc #define npy_exp2 exp2 #define npy_frexp frexp #define npy_ldexp ldexp +#define npy_copysign copysign #define npy_exp exp #define npy_sqrt sqrt #define npy_pow pow #define npy_modf modf #define npy_nextafter nextafter -#if defined(__arm64__) && defined(__APPLE__) -/* due to a build problem with scipy, export these as functions */ -NPY_INPLACE double npy_asinh(double x); -NPY_INPLACE double npy_copysign(double y, double x); -NPY_INPLACE double npy_log1p(double x); -#else -#define npy_asinh asinh -#define npy_copysign copysign -#define npy_log1p log1p -#endif - double npy_spacing(double x); /* diff --git a/numpy/core/include/numpy/numpyconfig.h b/numpy/core/include/numpy/numpyconfig.h index 308923b12..1c25aa5fc 100644 --- a/numpy/core/include/numpy/numpyconfig.h +++ b/numpy/core/include/numpy/numpyconfig.h @@ -3,31 +3,136 @@ #include "_numpyconfig.h" +/* + * On Mac OS X, because there is only one configuration stage for all the archs + * in universal builds, any macro which depends on the arch needs to be + * hardcoded. + * + * Note that distutils/pip will attempt a universal2 build when Python itself + * is built as universal2, hence this hardcoding is needed even if we do not + * support universal2 wheels anymore (see gh-22796). + * This code block can be removed after we have dropped the setup.py based + * build completely. + */ +#ifdef __APPLE__ + #undef NPY_SIZEOF_LONG + #undef NPY_SIZEOF_PY_INTPTR_T + + #ifdef __LP64__ + #define NPY_SIZEOF_LONG 8 + #define NPY_SIZEOF_PY_INTPTR_T 8 + #else + #define NPY_SIZEOF_LONG 4 + #define NPY_SIZEOF_PY_INTPTR_T 4 + #endif + + #undef NPY_SIZEOF_LONGDOUBLE + #undef NPY_SIZEOF_COMPLEX_LONGDOUBLE + #ifdef HAVE_LDOUBLE_IEEE_DOUBLE_LE + #undef HAVE_LDOUBLE_IEEE_DOUBLE_LE + #endif + #ifdef HAVE_LDOUBLE_INTEL_EXTENDED_16_BYTES_LE + #undef HAVE_LDOUBLE_INTEL_EXTENDED_16_BYTES_LE + #endif + + #if defined(__arm64__) + #define NPY_SIZEOF_LONGDOUBLE 8 + #define NPY_SIZEOF_COMPLEX_LONGDOUBLE 16 + #define HAVE_LDOUBLE_IEEE_DOUBLE_LE 1 + #elif defined(__x86_64) + #define NPY_SIZEOF_LONGDOUBLE 16 + #define NPY_SIZEOF_COMPLEX_LONGDOUBLE 32 + #define HAVE_LDOUBLE_INTEL_EXTENDED_16_BYTES_LE 1 + #elif defined (__i386) + #define NPY_SIZEOF_LONGDOUBLE 12 + #define NPY_SIZEOF_COMPLEX_LONGDOUBLE 24 + #elif defined(__ppc__) || defined (__ppc64__) + #define NPY_SIZEOF_LONGDOUBLE 16 + #define NPY_SIZEOF_COMPLEX_LONGDOUBLE 32 + #else + #error "unknown architecture" + #endif +#endif + + /** - * To help with the NPY_NO_DEPRECATED_API macro, we include API version - * numbers for specific versions of NumPy. To exclude all API that was - * deprecated as of 1.7, add the following before #including any NumPy - * headers: + * To help with both NPY_TARGET_VERSION and the NPY_NO_DEPRECATED_API macro, + * we include API version numbers for specific versions of NumPy. + * To exclude all API that was deprecated as of 1.7, add the following before + * #including any NumPy headers: * #define NPY_NO_DEPRECATED_API NPY_1_7_API_VERSION + * The same is true for NPY_TARGET_VERSION, although NumPy will default to + * a backwards compatible build anyway. */ #define NPY_1_7_API_VERSION 0x00000007 #define NPY_1_8_API_VERSION 0x00000008 -#define NPY_1_9_API_VERSION 0x00000008 -#define NPY_1_10_API_VERSION 0x00000008 -#define NPY_1_11_API_VERSION 0x00000008 -#define NPY_1_12_API_VERSION 0x00000008 -#define NPY_1_13_API_VERSION 0x00000008 -#define NPY_1_14_API_VERSION 0x00000008 -#define NPY_1_15_API_VERSION 0x00000008 -#define NPY_1_16_API_VERSION 0x00000008 -#define NPY_1_17_API_VERSION 0x00000008 -#define NPY_1_18_API_VERSION 0x00000008 -#define NPY_1_19_API_VERSION 0x00000008 +#define NPY_1_9_API_VERSION 0x00000009 +#define NPY_1_10_API_VERSION 0x0000000a +#define NPY_1_11_API_VERSION 0x0000000a +#define NPY_1_12_API_VERSION 0x0000000a +#define NPY_1_13_API_VERSION 0x0000000b +#define NPY_1_14_API_VERSION 0x0000000c +#define NPY_1_15_API_VERSION 0x0000000c +#define NPY_1_16_API_VERSION 0x0000000d +#define NPY_1_17_API_VERSION 0x0000000d +#define NPY_1_18_API_VERSION 0x0000000d +#define NPY_1_19_API_VERSION 0x0000000d #define NPY_1_20_API_VERSION 0x0000000e #define NPY_1_21_API_VERSION 0x0000000e #define NPY_1_22_API_VERSION 0x0000000f #define NPY_1_23_API_VERSION 0x00000010 #define NPY_1_24_API_VERSION 0x00000010 -#define NPY_1_25_API_VERSION 0x00000010 +#define NPY_1_25_API_VERSION 0x00000011 + + +/* + * Binary compatibility version number. This number is increased + * whenever the C-API is changed such that binary compatibility is + * broken, i.e. whenever a recompile of extension modules is needed. + */ +#define NPY_VERSION NPY_ABI_VERSION + +/* + * Minor API version we are compiling to be compatible with. The version + * Number is always increased when the API changes via: `NPY_API_VERSION` + * (and should maybe just track the NumPy version). + * + * If we have an internal build, we always target the current version of + * course. + * + * For downstream users, we default to an older version to provide them with + * maximum compatibility by default. Downstream can choose to extend that + * default, or narrow it down if they wish to use newer API. If you adjust + * this, consider the Python version support (example for 1.25.x): + * + * NumPy 1.25.x supports Python: 3.9 3.10 3.11 (3.12) + * NumPy 1.19.x supports Python: 3.6 3.7 3.8 3.9 + * NumPy 1.17.x supports Python: 3.5 3.6 3.7 3.8 + * NumPy 1.15.x supports Python: ... 3.6 3.7 + * + * Users of the stable ABI may wish to target the last Python that is not + * end of life. This would be 3.8 at NumPy 1.25 release time. + * 1.17 as default was the choice of oldest-support-numpy at the time and + * has in practice no limit (comapared to 1.19). Even earlier becomes legacy. + */ +#if defined(NPY_INTERNAL_BUILD) && NPY_INTERNAL_BUILD + /* NumPy internal build, always use current version. */ + #define NPY_FEATURE_VERSION NPY_API_VERSION +#elif defined(NPY_TARGET_VERSION) && NPY_TARGET_VERSION + /* user provided a target version, use it */ + #define NPY_FEATURE_VERSION NPY_TARGET_VERSION +#else + /* Use the default (increase when dropping Python 3.9 support) */ + #define NPY_FEATURE_VERSION NPY_1_19_API_VERSION +#endif + +/* Sanity check the (requested) feature version */ +#if NPY_FEATURE_VERSION > NPY_API_VERSION + #error "NPY_TARGET_VERSION higher than NumPy headers!" +#elif NPY_FEATURE_VERSION < NPY_1_15_API_VERSION + /* No support for irrelevant old targets, no need for error, but warn. */ + #warning "Requested NumPy target lower than supported NumPy 1.15." +#endif + #endif /* NUMPY_CORE_INCLUDE_NUMPY_NPY_NUMPYCONFIG_H_ */ diff --git a/numpy/core/include/numpy/ufuncobject.h b/numpy/core/include/numpy/ufuncobject.h index bb0633100..9e00f2e56 100644 --- a/numpy/core/include/numpy/ufuncobject.h +++ b/numpy/core/include/numpy/ufuncobject.h @@ -197,7 +197,7 @@ typedef struct _tagPyUFuncObject { npy_uint32 iter_flags; /* New in NPY_API_VERSION 0x0000000D and above */ - + #if NPY_FEATURE_VERSION >= NPY_1_16_API_VERSION /* * for each core_num_dim_ix distinct dimension names, * the possible "frozen" size (-1 if not frozen). @@ -211,13 +211,15 @@ typedef struct _tagPyUFuncObject { /* Identity for reduction, when identity == PyUFunc_IdentityValue */ PyObject *identity_value; + #endif /* NPY_FEATURE_VERSION >= NPY_1_16_API_VERSION */ /* New in NPY_API_VERSION 0x0000000F and above */ - + #if NPY_FEATURE_VERSION >= NPY_1_22_API_VERSION /* New private fields related to dispatching */ void *_dispatch_cache; /* A PyListObject of `(tuple of DTypes, ArrayMethod/Promoter)` */ PyObject *_loops; + #endif } PyUFuncObject; #include "arrayobject.h" |