3X3 Matrix Multiplication

module matrix3x3(a, b, y);

  input [8:0] a, b; // 8x8 input matrices (1-bit elements)
  output reg [17:0] y; // 8x8 output matrix (2-bit elements)

  reg [2:0] a1[0:2][0:2];
  reg [2:0] b1[0:2][0:2];
  reg [2:0] y1[0:2][0:2];

  integer i, j, k;

  always @(a or b)
  begin
    // Unpack the 1-bit input matrices a and b into 3-bit matrices a1 and b1
    for (i = 0; i < 3; i=i+1) begin
      for (j = 0; j < 3; j=j+1) begin
        a1[i][j] = a[i*3 + j];
        b1[i][j] = b[i*3 + j];
      end
    end

    // Matrix multiplication
    for (i = 0; i < 3; i=i+1) begin
      for (j = 0; j < 3; j=j+1) begin
        y1[i][j] = 3'b000; // Initialize each element in the output matrix to 0
        for (k = 0; k < 3; k=k+1) begin
          y1[i][j] = y1[i][j] + (a1[i][k] * b1[k][j]);
        end
      end
    end

    // Pack the 2-bit output matrix y1 into the 128-bit output y
    for (i = 0; i < 3; i=i+1) begin
      for (j = 0; j < 3; j=j+1) begin
        y[i*6+ j*2 +: 2] = y1[i][j];
      end
    end
  end

endmodule