Skip to main content

circular_pad1d_forward

teeny_kernels::nn::pad::circular_pad1d

Function circular_pad1d_forward 

Source 
pub fn circular_pad1d_forward<T: Triton, D: Num, const PAD_LEFT: i32, const PAD_RIGHT: i32, const BLOCK_OL: i32>(
    input_ptr: T::Pointer<D>,
    output_ptr: T::Pointer<D>,
    _B: i32,
    C: i32,
    L: i32,
    OL: i32,
)
where
    T::I32Tensor: Tensor<i32, 1> + Comparison<i32, BoolTensor = T::BoolTensor>,
    T::BoolTensor: BitAnd<Output = T::BoolTensor> + BitOr<Output = T::BoolTensor>,
    T::Pointer<D>: AddOffsets<i32, 1, T::I32Tensor, Output = T::Tensor<T::Pointer<D>>>,
Expand description

1-D circular padding forward pass.

Grid: pid = (b * C + c) * num_ol_tiles + ol_tile

For output position op:

  • ip_raw = op - PAD_LEFT
  • if ip_raw < 0: wraps to ip_raw + L
  • if ip_raw >= L: wraps to ip_raw - L
  • else: ip_raw

Constraints: PAD_LEFT <= L, PAD_RIGHT <= L.