cuda.tile.log2

cuda.tile.log2(x, /)

Perform log2 on a tile.

Parameters:

x (Tile)

Return type:

Tile

Examples

SnippetComplete Example

tx = ct.full((4,), 8.0, dtype=ct.float32)
print(f"{ct.log2(tx):.1f}")

Copy

import cuda.tile as ct
import torch

@ct.kernel
def kernel():
    tx = ct.full((4,), 8.0, dtype=ct.float32)
    print(f"{ct.log2(tx):.1f}")


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

Output

[3.0, 3.0, 3.0, 3.0]