Returns whether the block assigned this work should compute the epilogue for the corresponding output tile. For the case of stream-K, this should only

Notify the iterator which k-group it is currently pointing to. This does not advance the iterator. Rather, it overrides its internal tracking with co

Transform the mma operands to the required types

Constructs a matrix from a uniform element 1

Overrides the internal iteration index

Functionally required for serial reduction in the epilogue

Releases ownership of the managed object, if any

Number of iterations per output tile

Returns the relative dim3 block rank local to the cluster.

Returns the sum of all elements

CUTLASS helper to get SMEM pointer

Returns the dim3 cluster shape.

Returns true if the current coordinate is within the filter tensor W

Input A: float_e4m3_t ; Input B: float_e5m2_t

Returns a pointer

Issuing the launch_dependents instruction hints a dependent kernel to launch earlier launch_dependents doesn't impact the functionality but the perfor

Loads a fragment from memory with additional logical offset

Stores a fragment to memory at the location pointed to by the iterator

* Find quotient and remainder using device-side intrinsics */

Value

Wait until all TMA descriptor previously issued are safe to be modified after tma_desc_commit_group()

Returns the pointer to referenced data

Accesses raw internal state

Returns a lane index in the warp. The threads in warp may not be convergent

Determine if the source is needed. May return false if

Efficient clear method

Loads a fragment from memory with additional logical offset

Returns the stride of the layout