nn_mm_f32()

void nn_mm_f32	(	Tensor2D_F32 *	y,
		const Tensor2D_F32 *	x1,
		const Tensor2D_F32 *	x2
	)

Performs a matrix multiplication of the matrices x1 and x2.

Parameters

y	The output tensor, shape (n, p)
x1	The first input tensor, shape (n, m)
x2	The second input tensor, shape (m, p)