unltd.mlir

func.func @time_out(%arg0: tensor<1x1x288x8x4xf32>, %arg1: tensor<1152xf32>) -> tensor<1x1x1152xf32>  {
    %c0 = arith.constant 0 : index
    %5 = tensor.empty() : tensor<1x1x1152xf32>
    %unpack = tensor.unpack %arg0 outer_dims_perm = [0, 1, 2] inner_dims_pos = [1, 2] inner_tiles = [8, 4] into %5  : tensor<1x1x288x8x4xf32> -> tensor<1x1x1152xf32>
    %6 = linalg.generic {indexing_maps = [affine_map<(d0, d1, d2) -> (d2)>, affine_map<(d0, d1, d2) -> (d0, d1, d2)>, affine_map<(d0, d1, d2) -> (d0, d1, d2)>], iterator_types = ["parallel", "parallel", "parallel"]} ins(%arg1, %unpack : tensor<1152xf32>, tensor<1x1x1152xf32>) outs(%5 : tensor<1x1x1152xf32>) {
    ^bb0(%in: f32, %in_0: f32, %out: f32):
      %7 = arith.addf %in, %in_0 : f32
      linalg.yield %7 : f32
    } -> tensor<1x1x1152xf32>
    return %6: tensor<1x1x1152xf32>
}