warp.fixedarray#
- class warp.fixedarray(*args, **kwargs)[source]#
A fixed-size, stack allocated, array containing values of the same type.
Only used during codegen, and for type hints, but otherwise not intended to be used at the Python scope.
Methods
assign(src)Wrap
srcin anwarp.arrayif it is not already one and copy the contents toself.contiguous()Return a contiguous array with this array's data.
cptr()Return a ctypes cast of the array address.
fill_(value)Set all array entries to value
flatten()Return a zero-copy view of the array collapsed to 1-D.
ipc_handle()Return an IPC handle of the array as a 64-byte
bytesobjectlist()Return a flattened list of items in the array as a Python list.
mark_init()Reset this array's read flag.
mark_read()Mark this array as having been read from in a kernel or recorded function on the tape.
mark_write(**kwargs)Detect if we are writing to an array that has already been read from.
numpy(*[, _suppress_bfloat16_warning])Convert the array to a
numpy.ndarray(aliasing memory through the array interface protocol) If the array is on the GPU, a synchronous device-to-host copy (on the CUDA default stream) will be automatically performed to ensure that any outstanding work is completed.reshape(shape)Return a reshaped array.
to(device[, requires_grad])Return a Warp array with this array's data moved to the specified device, no-op if already on device.
transpose([axes])Return a zero-copy view of the array with axes transposed.
view(dtype)Return a zero-copy view of this array's memory with a different data type.
zero_()Zero out the array entries.
Attributes
gradmemory_kindObserved memory kind backing this array.
requires_gradretain_grad