Mojo struct
IteratorScatterGatherAmd
struct IteratorScatterGatherAmd[thread_layout: Layout, num_threads: Int = thread_layout.size(), thread_scope: ThreadScope = ThreadScope(0), block_dim_count: Int = 1]
Iterator-based AMD data movement delegate for scatter-gather operations.
This struct provides an iterator-based approach for data movement between DRAM and registers on AMD GPUs.
Parameters
- thread_layout (
Layout): The layout defining thread organization. - num_threads (
Int): Total number of threads (defaults to thread_layout size). - thread_scope (
ThreadScope): The scope of thread execution (block or warp). - block_dim_count (
Int): Number of block dimensions.
Fields
- buffer (
AMDBufferResource):
Implemented traits
AnyType,
UnknownDestructibility
Aliases
__del__is_trivial
alias __del__is_trivial = True
Methods
__init__
__init__(out self, tensor: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], tensor_iter: LayoutTensorIter[dtype, layout, origin, address_space=address_space, alignment=alignment, circular=circular, axis=axis, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked])
Initialize the iterator-based scatter-gather delegate.
Args:
- tensor (
LayoutTensor): The layout tensor for bounds information. - tensor_iter (
LayoutTensorIter): The layout tensor iterator for creating the AMD buffer resource.
copy
copy(self, dst_reg_tile: LayoutTensor[dtype, layout, origin, address_space=address_space, element_layout=element_layout, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked, alignment=alignment], src_gmem_tile_iter: LayoutTensorIter[dtype, layout, origin, address_space=address_space, alignment=alignment, circular=circular, axis=axis, layout_int_type=layout_int_type, linear_idx_type=linear_idx_type, masked=masked])
Copy data from DRAM to registers using an iterator.
Args:
- dst_reg_tile (
LayoutTensor): Destination register tile. - src_gmem_tile_iter (
LayoutTensorIter): Source global memory tile iterator.
Was this page helpful?
Thank you! We'll create more content like this.
Thank you for helping us improve!