axpby#

nvmath.device.axpby(
alpha: float,
x_tensor: OpaqueTensor,
beta: float,
y_tensor: OpaqueTensor,
) → None[source]#

AXPBY operation: y = alpha * x + beta * y

Parameters:

  • alpha (float) – Scalar multiplier for x_tensor.

  • x_tensor (OpaqueTensor) – Input tensor x.

  • beta (float) – Scalar multiplier for y_tensor.

  • y_tensor (OpaqueTensor) – Input/output tensor y, which will be updated with the result.

Refer to the cuBLASDx documentation for more details on how to use this function: https://docs.nvidia.com/cuda/cublasdx/api/other_tensors.html#imported-tensor-utilities

On this page