Duplicated streaming commands cause synthesis error

[chhzh123]

Errors may occur when careless programmers type the same streaming command several times, like the following example, where B->C is done twice. (Actually, this will easily happen when there're lots of stages to be streamed.)

def test_duplicated():
    A = hcl.placeholder((10,), "A")

    def kernel(A):
        B = hcl.compute(A.shape, 
                lambda i: A[i] + 1, "B")
        C = hcl.compute(B.shape,
                lambda i: B[i] + 1, "C")
        return C

    target = hcl.platform.zc706
    target.config(compile="vivado_hls", mode="csyn")
    s = hcl.create_schedule([A], kernel)
    s.to([A], target.xcel)
    s.to(kernel.C, target.host)
    s.to(kernel.B, s[kernel.C])
    s.to(kernel.B, s[kernel.C]) # duplicated streaming
    f = hcl.build(s, target)
    np_A = np.zeros((10,))
    np_C = np.zeros((10,))
    hcl_A = hcl.asarray(np_A)
    hcl_C = hcl.asarray(np_C)
    f(hcl_A, hcl_C)

The compiler should detect this duplication and allocate the streaming buffer only once. However, the generated code redundantly allocates a B_pipe_1 buffer causing synthesis error.

void test(bit32 A[10], bit32 C[10]) {
    bit32 B[10];
    bit32 B_pipe_1[10];
    #pragma HLS stream variable=B_pipe_1 depth=1
    #pragma HLS dataflow
    bit32 B_pipe_2[10];
    #pragma HLS stream variable=B_pipe_2 depth=2
    B_i: for (bit32 i = 0; i < 10; ++i) {
      bit32 B_temp;
      B_temp = (A[i] + 1);
      B_pipe_2[i] = B_temp;
      B_pipe_1[i] = B_temp;
      B[i] = B_temp;
    }
    C_i1: for (bit32 i1 = 0; i1 < 10; ++i1) {
      bit32 B_temp1;
      B_temp1 = B_pipe_2[i1];
      C[i1] = (B_temp1 + 1);
    }
  }

INFO: [XFORM 203-712] Applying dataflow to function 'test', detected/extracted 2 process function(s): 
         'Loop_B_i_proc7'
         'Loop_C_i1_proc'.
ERROR: [XFORM 203-123] Cannot stream  'B_pipe_1.V1': a local variable is streamable only if it is in a dataflow region.
ERROR: [HLS 200-70] Pre-synthesis failed.