multiply_transpose

const kernel_cl< in_buffer, out_buffer, int, int > stan::math::opencl_kernels::multiply_transpose("multiply_transpose", {thread_block_helpers, multiply_transpose_kernel_code}, {{"THREAD_BLOCK_SIZE", 32}, {"WORK_PER_THREAD", 4}})	(	"multiply_transpose"	,
		{thread_block_helpers, multiply_transpose_kernel_code}	,
		{{"THREAD_BLOCK_SIZE", 32}, {"WORK_PER_THREAD", 4}}
	)

See the docs for add() .