cuda.tile.divmod

cuda.tile.divmod(x, y, /)

Elementwise divmod() on two tiles.

For integer inputs, returns (x // y, x % y). For floating-point inputs, not yet implemented.

Can also use the builtin operation divmod(x, y).

Parameters:

• x (Tile) – dividend tile.

• y (Tile) – divisor tile.

The shape of x and y will be broadcasted and dtype promoted to common dtype.

Returns:

Tuple of two tiles (quotient and remainder).

Return type:

tuple[Tile | int | float | ScalarProtocol, Tile | int | float | ScalarProtocol]

Examples

SnippetComplete Example

tx = ct.arange(4, dtype=ct.int32)
print(divmod(tx, 3))

Copy

import cuda.tile as ct
import torch

@ct.kernel
def kernel():
    tx = ct.arange(4, dtype=ct.int32)
    print(divmod(tx, 3))


torch.cuda.init()
ct.launch(torch.cuda.current_stream(), (1,), kernel, ())
torch.cuda.synchronize()

Output

([0, 0, 0, 1], [0, 1, 2, 0])