For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /get-started.md).
Mojo struct
ReduceTier
struct ReduceTier
GPU tier discriminator for the row-wise scaffolder. Mutually exclusive by construction (a single field, not independent bools): Block is the default (also every CPU tier, where only emit_tile_width/simd_width matter). Scaffolder-internal — a body never reads Context._tier.
Fields
- value (
Int):
Implemented traits
AnyType,
Copyable,
Deinitable,
ImplicitlyCopyable,
Movable,
RegisterPassable,
TrivialRegisterPassable
comptime members
Block
comptime Block = ReduceTier(Int(0))
Block-per-row (or block-per-output) cooperative tier — the default. Also the tag used for every CPU tier.
Serial
comptime Serial = ReduceTier(Int(2))
One thread per row (unused; kept for future scalar-fallback dispatches; GPU only).
Splitk
comptime Splitk = ReduceTier(Int(3))
Multiple blocks cooperate on one row when num_rows < sm_count would otherwise leave SMs idle (GPU only).
Warp
comptime Warp = ReduceTier(Int(1))
Warp-per-row: one warp covers the whole row (GPU only).
Methods
__init__
def __init__(value: Int) -> Self