pub fn conv2d_backward_dw<T: Triton, D: Num, const KH: i32, const KW: i32, const STRIDE_H: i32, const STRIDE_W: i32, const PAD_H: i32, const PAD_W: i32, const G: i32, const BLOCK_OW: i32>(
dy_ptr: T::Pointer<D>,
x_ptr: T::Pointer<D>,
dw_ptr: T::Pointer<D>,
_B: i32,
C_IN: i32,
C_OUT: i32,
H: i32,
W: i32,
OH: i32,
OW: i32,
)where
T::I32Tensor: Tensor<i32, 1> + Comparison<i32, BoolTensor = T::BoolTensor>,
T::BoolTensor: BitAnd<Output = T::BoolTensor>,
T::Pointer<D>: AddOffsets<i32, 1, T::I32Tensor, Output = T::Tensor<T::Pointer<D>>>,Expand description
2-D convolution backward pass — gradient with respect to weights (dw).
Uses the same grid as the forward pass. Each CTA at (b, c_out, oh, ow_tile)
accumulates partial sums into dw via atomic_add (one per (c_in_local, kh, kw)
combination within the group).
G — number of groups. Weight layout: [C_OUT, C_IN/G, KH, KW].
Grid: pid = ((b * C_OUT + c_out) * OH + oh) * num_ow_tiles + ow_tile
dw must be zero-initialised before launch.