Here is one example of an allocator that should work on all platforms. It is shamelessly based on this:

https://sites.google.com/site/ruslancray/lab/bookshelf/interview/ci/low-level/write-an-aligned-malloc-free-function

There are not many ways to do this and similar code is floating around on the net, so extending it in this way is probable ok. (And besides it does not implement realloc.)

Dropping this code into numpy/core/include/numpy/ndarraytypes.hshould ensure that freshly allocated ndarrays are properly aligned on all platforms.

This platform-independent code could possibly be replaced with posix_memalign() on POSIX and _aligned_malloc() on Windows. However, combining posix_memalign() with realloc() is not possible, so implementing it ourselves is probably better.

#define NPY_MEMALIGN 32   /* 16 for SSE2, 32 for AVX, 64 for Xeon Phi */ 

static NPY_INLINE
void *PyArray_realloc(void *p, size_t n)
{
    void *p1, **p2, *base;
    size_t old_offs, offs = NPY_MEMALIGN - 1 + sizeof(void*);    
    if (NPY_UNLIKELY(p != NULL)) {
        base = *(((void**)p)-1);
        if (NPY_UNLIKELY((p1 = PyMem_Realloc(base,n+offs)) == NULL)) return NULL;
        if (NPY_LIKELY(p1 == base)) return p;
        p2 = (void**)(((Py_uintptr_t)(p1)+offs) & ~(NPY_MEMALIGN-1));
        old_offs = (size_t)((Py_uintptr_t)p - (Py_uintptr_t)base);
        memmove(p2,(char*)p1+old_offs,n);    
    } else {
        if (NPY_UNLIKELY((p1 = PyMem_Malloc(n + offs)) == NULL)) return NULL;
        p2 = (void**)(((Py_uintptr_t)(p1)+offs) & ~(NPY_MEMALIGN-1));   
    }
    *(p2-1) = p1;
    return (void*)p2;
}    

static NPY_INLINE
void *PyArray_malloc(size_t n)
{
    return PyArray_realloc(NULL, n);
}

static NPY_INLINE
void *PyArray_calloc(size_t n, size_t s)
{
    void *p;
    if (NPY_UNLIKELY((p = PyArray_realloc(NULL,n*s)) == NULL)) return NULL;
    memset(p, 0, n*s);
    return p;
}

static NPY_INLINE        
void PyArray_free(void *p)
{
    void *base = *(((void**)p)-1);
    PyMem_Free(base);
}

Uh oh!

Use an aligned allocator for NumPy? #5312

Description

Metadata

Metadata

Assignees

Labels

Type

Projects

Milestone

Relationships

Development

Issue actions