matmul_block

void ckernel::matmul_block_init(uint32_t in0_cb_id, uint32_t in1_cb_id, const uint32_t transpose = 0, uint32_t ct_dim = 1, uint32_t rt_dim = 1, uint32_t kt_dim = 1, uint32_t call_line = __builtin_LINE())

Short init for matmul_block. Configures the unpacker and math engine to matmul mode.

Must be called before matmul_block. The one-time HW configuration must already have been performed via compute_kernel_hw_startup<SrcOrder::Reverse>(in0, in1, out) at the start of MAIN. Matmul maps in0 -> SrcB and in1 -> SrcA (the reverse of other ops), which is why compute_kernel_hw_startup must use SrcOrder::Reverse.

NOTE (known gap, #46769): if a preceding op left SrcA/SrcB with asymmetric tile sizes (i.e. different data formats per source) and the following matmul uses the same formats, matmul_block_init cannot fix the per-source tile sizes on its own. It does not re-program the tile descriptor, and a reconfig_data_format is inappropriate when the data formats did not change. No current kernel hits this; tracked in #46769.

Return value: None

Argument	Description	Type	Valid Range	Required
in0_cb_id	The identifier of the first input circular buffer (CB)	uint32_t	0 to 31	True
in1_cb_id	The identifier of the second input circular buffer (CB)	uint32_t	0 to 31	True
transpose	The transpose flag for performing transpose operation on B	uint32_t	Any positive value will indicate transpose is set	False
ct_dim	The column dimension for the output block.	uint32_t	Must be equal to block B column dimension; 1 to 8 in half-sync mode, 1 to 16 in full-sync mode	False
rt_dim	The row dimension for the output block.	uint32_t	Must be equal to block A row dimension; 1 to 8 in half-sync mode, 1 to 16 in full-sync mode	False
kt_dim	The inner dimension.	uint32_t	Must be equal to block A column dimension	False

void ckernel::matmul_block(uint32_t in0_cb_id, uint32_t in1_cb_id, uint32_t in0_tile_index, uint32_t in1_tile_index, uint32_t idst, const uint32_t transpose, uint32_t ct_dim, uint32_t rt_dim, uint32_t kt_dim, uint32_t call_line = __builtin_LINE())

Performs block-sized matrix multiplication C=A*B between the blocks in two different input CBs and accumulates the result to DST (DST += C). The DST register buffer must be in acquired state via acquire_dst call. This call is blocking and is only available on the compute engine.

A block is a rectangle of tiles: A is rt_dim x kt_dim tiles, B is kt_dim x ct_dim tiles, and the output C is rt_dim x ct_dim tiles. So a block is just ct_dim * rt_dim output tiles produced in one call (with kt_dim tiles along the shared inner dimension). The output must fit in DST, so the block size is limited by DST size and sync mode (see matmul_block_init for the valid ct_dim/rt_dim ranges).

Return value: None

Argument	Description	Type	Valid Range	Required
in0_cb_id	The identifier of the first input circular buffer (CB)	uint32_t	0 to 31	True
in1_cb_id	The identifier of the second input circular buffer (CB)	uint32_t	0 to 31	True
in0_tile_index	The index of the tile in block A from the first input CB	uint32_t	Must be less than the size of the CB	True
in1_tile_index	The index of the tile in block B from the second input CB	uint32_t	Must be less than the size of the CB	True
idst	The index of the tile in DST REG to which the result C will be written.	uint32_t	Must be less than the acquired size of DST REG	True
transpose	The transpose flag for performing transpose operation on tiles in B.	bool	Must be true or false	True
ct_dim	The column dimension for the output block.	uint32_t	Must be equal to block B column dimension	True
rt_dim	The row dimension for the output block.	uint32_t	Must be equal to block A row dimension	True
kt_dim	The inner dimension.	uint32_t	Must be equal to block A column dimension	True

See also compute_kernel_hw_startup, which must be called once with SrcOrder::Reverse before matmul_block_init.