IMPORTANT: To view this page as Markdown, append `.md` to the URL (e.g. /max/get-started.md). For the complete documentation index, see llms.txt.
Skip to main content
For the complete documentation index, see llms.txt. Markdown versions of all pages are available by appending .md to any URL (e.g. /max/get-started.md).

Mojo struct

TMAStoreCoords

struct TMAStoreCoords[epc: EpilogueConfig, c_smem_shape0: Int, stage: Int, batched: Bool = False]

TMA store coordinates and warp election for SM100 epilogue.

When batched=True, includes a batch coordinate for 3D TMA stores.

Fields​

  • ​coord_m (Int):
  • ​coord_n (Int):
  • ​coord_b (Int):
  • ​elect_one_warp (Bool):
  • ​c_smem_coord_m (Int):

Implemented traits​

AnyType, Copyable, ImplicitlyCopyable, ImplicitlyDeletable, Movable, RegisterPassable, TrivialRegisterPassable

comptime members​

BM​

comptime BM = epc.BM

BN​

comptime BN = epc.BN

CG1_TMA_BM​

comptime CG1_TMA_BM = c_smem_shape0

CG2_TMA_BM​

comptime CG2_TMA_BM = c_smem_shape0 if (epc == Int(256)) else epc.BM

cta_group​

comptime cta_group = epc.cta_group

MMA_M​

comptime MMA_M = epc.MMA_M

MMA_N​

comptime MMA_N = epc.MMA_N

stage_n_offset​

comptime stage_n_offset = (stage * epc)

stageN​

comptime stageN = epc.stageN

TMA_BM​

comptime TMA_BM = c_smem_shape0 if (eq epc.MMA_M, 256) else epc.BM if (epc == Int(2)) else TMAStoreCoords[epc, c_smem_shape0, stage, batched].CG1_TMA_BM

Methods​

__init__​

def __init__(c_coord: Tuple[UInt32, UInt32], warp_id: UInt32) -> Self

Compute TMA store coordinates from 2D tile coords and warp ID.

def __init__(c_coord: Tuple[UInt32, UInt32, UInt32], warp_id: UInt32) -> Self

Compute TMA store coordinates from 3D tile coords and warp ID.

Was this page helpful?