static PyObject * THPStorage_(newSharedFd)(PyObject *_unused, PyObject *args)
{
HANDLE_TH_ERRORS
THPUtils_assert(PyTuple_GET_SIZE(args) == 2, "tuple of 2 items expected");
PyObject *_tmp_fd = PyTuple_GET_ITEM(args, 0);
PyObject *_size = PyTuple_GET_ITEM(args, 1);
if (!THPUtils_checkLong(_tmp_fd) || !THPUtils_checkLong(_size)) {
THPUtils_invalidArguments(args, NULL, "_new_shared in file descriptor mode",
1, "a file descriptor (int) and storage size (int)");
return NULL;
}
int fd;
int tmp_fd = (int) THPUtils_unpackLong(_tmp_fd);
int64_t size = THPUtils_unpackLong(_size);
if ((fd = dup(tmp_fd)) == -1) {
THPUtils_setError("could not duplicate a shared memory file descriptor");
return NULL;
}
int flags = TH_ALLOCATOR_MAPPED_SHAREDMEM |
TH_ALLOCATOR_MAPPED_NOCREATE |
TH_ALLOCATOR_MAPPED_KEEPFD |
TH_ALLOCATOR_MAPPED_FROMFD;
THMapAllocatorContext *ctx = THMapAllocatorContext_newWithFd(NULL, fd, flags);
return THPStorage_(New)(THStorage_(newWithAllocator)(size, &THMapAllocator,
(void*)ctx));
END_HANDLE_TH_ERRORS
}
static PyObject * THPStorage_(newSharedCuda)(PyObject *_unused, PyObject *args)
{
HANDLE_TH_ERRORS
THPUtils_assert(PyTuple_GET_SIZE(args) == 5, "tuple of 5 items expected");
PyObject *_device = PyTuple_GET_ITEM(args, 0);
PyObject *_handle = PyTuple_GET_ITEM(args, 1);
PyObject *_size = PyTuple_GET_ITEM(args, 2);
PyObject *_offset = PyTuple_GET_ITEM(args, 3);
PyObject *_view_size = PyTuple_GET_ITEM(args, 4);
if (!(THPUtils_checkLong(_device) && THPUtils_checkLong(_size)
&& (_handle == Py_None || PyBytes_Check(_handle))
&& THPUtils_checkLong(_offset) && THPUtils_checkLong(_view_size))) {
THPUtils_invalidArguments(args, NULL, "_new_shared in CUDA mode", 1,
"(int device, bytes handle, int storage_size, int offset, int view_size");
return NULL;
}
size_t storage_size = (size_t)THPUtils_unpackLong(_size);
ptrdiff_t offset = (ptrdiff_t)THPUtils_unpackLong(_offset);
size_t view_size = (size_t)THPUtils_unpackLong(_view_size);
int64_t device = THPUtils_unpackLong(_device);
AutoGPU __autogpu(device);
char *buffer;
Py_ssize_t handle_size;
if (PyBytes_AsStringAndSize(_handle, &buffer, &handle_size) == -1) {
return NULL;
}
THPUtils_assert(handle_size == CUDA_IPC_HANDLE_SIZE, "incorrect handle size");
cudaIpcMemHandle_t handle = *(cudaIpcMemHandle_t*)buffer;
void *devPtr = NULL;
THCudaCheck(cudaIpcOpenMemHandle(&devPtr, handle, cudaIpcMemLazyEnablePeerAccess));
THStoragePtr base(THStorage_(newWithDataAndAllocator)(
LIBRARY_STATE (real*)devPtr, storage_size, &THCIpcAllocator, (void*)device));
base->flag = TH_STORAGE_REFCOUNTED | TH_STORAGE_FREEMEM;
if (offset != 0 || view_size != storage_size) {
return THPStorage_(newTHView)(base.get(), offset, view_size);
}
return THPStorage_(New)(base.release());
END_HANDLE_TH_ERRORS
}
static PyObject * THPStorage_(newSharedFilename)(PyObject *_unused, PyObject *args)
{
HANDLE_TH_ERRORS
THPUtils_assert(PyTuple_GET_SIZE(args) == 3, "tuple of 3 items expected");
PyObject *_manager_handle = PyTuple_GET_ITEM(args, 0);
PyObject *_object_handle = PyTuple_GET_ITEM(args, 1);
PyObject *_size = PyTuple_GET_ITEM(args, 2);
if (!PyBytes_Check(_manager_handle) || !PyBytes_Check(_object_handle) || !THPUtils_checkLong(_size)) {
THPUtils_invalidArguments(args, NULL, "_new_shared in file system mode", 1,
"a handle (string/bytes) and storage size (int)");
return NULL;
}
const char *manager_handle = PyBytes_AS_STRING(_manager_handle);
const char *object_handle = PyBytes_AS_STRING(_object_handle);
int64_t size = THPUtils_unpackLong(_size);
int flags = TH_ALLOCATOR_MAPPED_SHAREDMEM |
TH_ALLOCATOR_MAPPED_NOCREATE;
libshm_context *ctx = libshm_context_new(manager_handle, object_handle, flags);
return THPStorage_(New)(THStorage_(newWithAllocator)(size,
&THManagedSharedAllocator, (void*)ctx));
END_HANDLE_TH_ERRORS
}
static PyObject * THPStorage_(pynew)(PyTypeObject *type, PyObject *args, PyObject *kwargs)
{
HANDLE_TH_ERRORS
Py_ssize_t num_args = args ? PyTuple_Size(args) : 0;
THPStoragePtr self((THPStorage *)type->tp_alloc(type, 0));
THPUtils_assert(self, "failed to allocate a " THPStorageStr " object");
THAllocator* allocator = NULL;
// Internally we allow constructing with a keywoard only argument cdata
if (kwargs != NULL) {
PyObject *allocator_ptr = PyDict_GetItemString(kwargs, "allocator");
if (allocator_ptr) {
THPUtils_assert(THPUtils_checkLong(allocator_ptr), "invalid allocator");
allocator = (THAllocator*) PyLong_AsVoidPtr(allocator_ptr);
PyDict_DelItemString(kwargs, "allocator");
}
Py_ssize_t num_kwargs = PyDict_Size(kwargs);
if (num_args == 0) {
PyObject *cdata_ptr = PyDict_GetItemString(kwargs, "cdata");
if (num_kwargs == 1 && cdata_ptr && THPUtils_checkLong(cdata_ptr)) {
THStorage *ptr = (THStorage*)PyLong_AsVoidPtr(cdata_ptr);
self->cdata = ptr;
return (PyObject*)self.release();
}
}
THPUtils_assert(num_kwargs == 0, THPStorageStr "(): invalid keyword arguments");
}
// torch.Storage()
if (num_args == 0) {
if (allocator) {
self->cdata = THPStorage_(newWithAllocator)(0, allocator);
} else {
self->cdata = THStorage_(new)(LIBRARY_STATE_NOARGS);
}
return (PyObject*)self.release();
}
PyObject *first_arg = PyTuple_GET_ITEM(args, 0);
// torch.Storage(size)
if (num_args == 1 && THPUtils_checkLong(first_arg)) {
int64_t size = THPUtils_unpackLong(first_arg);
if (allocator) {
self->cdata = THPStorage_(newWithAllocator)(size, allocator);
} else {
self->cdata = THStorage_(newWithSize)(LIBRARY_STATE size);
}
return (PyObject*)self.release();
}
// torch.Storage(view_source, [offset, [size]])
if (num_args < 4 && THPStorage_(Check)(first_arg)) {
#ifdef THD_GENERIC_FILE
THPUtils_setError("distributed storages don't support storage views");
return NULL;
#else
THPStorage *storage_arg = (THPStorage *)first_arg;
int64_t numel = storage_arg->cdata->size;
int64_t offset = 0;
if (num_args >= 2) {
PyObject *second_arg = PyTuple_GET_ITEM(args, 1);
if (!THPUtils_checkLong(second_arg))
goto invalid_arguments;
offset = THPUtils_unpackLong(second_arg);
}
int64_t size = numel - offset;
if (num_args >= 3) {
PyObject *third_arg = PyTuple_GET_ITEM(args, 2);
if (!THPUtils_checkLong(third_arg))
goto invalid_arguments;
size = THPUtils_unpackLong(third_arg);
}
THPUtils_assert(offset >= 0 && offset <= numel, "specified an offset of "
"%" PRId64 ", but the viewed storage has only %" PRId64 " element(s)", offset, numel);
THPUtils_assert(size >= 1 && size <= numel - offset, "specified a size of "
"%" PRId64 ", but the viewed storage has only %" PRId64 " element(s) after offset %" PRId64,
size, numel - offset, offset);
real *data_ptr = THStorage_(data)(LIBRARY_STATE storage_arg->cdata) + offset;
THStoragePtr storage(THStorage_(newWithData)(LIBRARY_STATE data_ptr, size));
storage->flag = TH_STORAGE_REFCOUNTED | TH_STORAGE_VIEW;
storage->view = storage_arg->cdata;
THStorage_(retain)(LIBRARY_STATE storage_arg->cdata);
self->cdata = storage.release();
return (PyObject*)self.release();
#endif
}
// torch.Storage(sequence)
if (num_args == 1 && PySequence_Check(first_arg)) {
#ifdef THD_GENERIC_FILE
THPUtils_setError("distributed storages don't support construction from a sequence");
#else
Py_ssize_t length = PySequence_Length(first_arg);
THPUtils_assert(length >= 0, "couldn't obtain the length of %s",
THPUtils_typename(first_arg));
self->cdata = THStorage_(newWithSize)(LIBRARY_STATE length);
THPObjectPtr item;
try {
for (Py_ssize_t i = 0; i < length; i++) {
item = PySequence_GetItem(first_arg, i);
real value = THPUtils_(unpackReal)(item.get());
#if !defined(THC_GENERIC_FILE)
self->cdata->unsafe_data<real>()[i] = value;
#else
// TODO: this might be slow - consider batched updates?
THCStorage_(set)(LIBRARY_STATE self->cdata, i, value);
#endif
}
} catch (std::runtime_error &e) {
THPUtils_setError("tried to construct a storage from a sequence (%s), "
"but one of the items was of type %s instead of %s",
THPUtils_typename(first_arg),
THPUtils_typename(item.get()),
THPUtils_typeTraits<real>::python_type_str);
return NULL;
}
return (PyObject*)self.release();
#endif
}
#ifndef THD_GENERIC_FILE
invalid_arguments:
#endif
THPUtils_invalidArguments(args, kwargs, THPStorageStr " constructor", 6,
"no arguments",
"(int size)",
"(Sequence data)",
"(" THPStorageStr " view_source)",
"(" THPStorageStr " view_source, int offset)",
"(" THPStorageStr " view_source, int offset, int size)");
return NULL;
END_HANDLE_TH_ERRORS
}
