rsqrt

nvtripy.rsqrt(input: Tensor) → Tensor

Computes the elementwise reciprocal square root of the elements of the input tensor.

Parameters:

input (Tensor) – The input tensor.

Returns:

A new tensor of the same shape as the input tensor.

Return type:

Tensor

INPUT REQUIREMENTS:

input.dtype is one of [float32, float16, bfloat16]

OUTPUT GUARANTEES:

return[0].dtype == input.dtype

Example

input = tp.arange(3, dtype=tp.float32) + 1.0
output = tp.rsqrt(input)

Local Variables

>>> input
tensor([1, 2, 3], dtype=float32, loc=gpu:0, shape=(3,))

>>> output
tensor([1, 0.707107, 0.57735], dtype=float32, loc=gpu:0, shape=(3,))