typo in comment

[wzhcz8902]

cutlass/include/cutlass/gemm/warp/mma_tensor_op.h

Lines 140 to 168 in 5c447dd

	/// Structure to compute the matrix product targeting CUDA cores and SIMT math instructions.
	template <
	/// Size of the Gemm problem - concept: gemm::GemmShape<>
	typename Shape_,
	/// Data type of A elements
	typename ElementA_,
	/// Layout of A matrix (concept: MatrixLayout)
	typename LayoutA_,
	/// Data type of B elements
	typename ElementB_,
	/// Layout of B matrix (concept: MatrixLayout)
	typename LayoutB_,
	/// Element type of C matrix
	typename ElementC_,
	/// Layout of C matrix (concept: MatrixLayout)
	typename LayoutC_,
	/// Policy describing warp-level MmaTensorOp (concept: MmaTensorOp policy)
	typename Policy_,
	/// Number of partitions along K dimension
	int PartitionsK_ = 1,
	/// Store the accumulators in row major or column major. Row major is used
	/// when output layout is interleaved.
	bool AccumulatorsInRowMajor = false,
	/// Used for partial specialization
	typename Enable = bool
	>
	class MmaTensorOp {
	public:

As a newbie to cutlass, I think this struct is targeted for tensor cores, not cuda cores as the comment claims.

[hwu36]

yes, you are correct. copy and paste error. thanks for reporting it.