arcsin_op

→TensorImplPtr

int arcsin_op(const int & a)

Compute $y = \arcsin(x)$ element-wise. Allocates a fresh output of the same shape and dtype as a and delegates to AsinBackward::forward.

See Also

AsinBackward — backward node.

aTensorImplPtr

Input tensor with values in

[-1, 1]

. Out-of-domain values produce NaN, matching the reference framework's behaviour.

TensorImplPtr

Output tensor of the same shape and dtype, values in $[-\tfrac{\pi}{2}, \tfrac{\pi}{2}]$ .

Loading…