Skip to contents

Element-wise log(1 + x), more accurate for small x.

Usage

nvl_log1p(operand)

Arguments

operand

(tensorish)
Tensorish value of data type floating-point.

Value

tensorish
Has the same shape and data type as the input. It is ambiguous if the input is ambiguous.

Implemented Rules

  • stablehlo

  • backward

StableHLO

Lowers to stablehlo::hlo_log_plus_one().

See also

Examples

jit_eval({
  x <- nv_tensor(c(0, 0.001, 1))
  nvl_log1p(x)
})
#> AnvilTensor
#>  0.0000
#>  0.0010
#>  0.6931
#> [ CPUf32{3} ]