Wrong results for inverse transformation for 2D batches about rocfft HOT 9 CLOSED

--- clients/samples/hipfft/hipfft_planmany_2d_z2z.cpp	2019-12-03 17:33:03.676271591 +0100
+++ clients/samples/hipfft/hipfft_planmany_2d_z2z.cpp	2019-12-03 17:32:05.728933650 +0100
@@ -30,21 +30,21 @@
         << "hipfft 2D double-precision complex-to-complex transform using advanced interface\n";
 
     int rank    = 2;
-    int n[2]    = {4, 5};
-    int howmany = 3;
+    int n[2]    = {4, 4};
+    int howmany = 4;
 
     // array is contiguous in memory
-    int istride = 1;
+    int istride = 4;
     // in-place transforms require istride=ostride
     int ostride = istride;
 
     // we choose to have no padding around our data:
-    int inembed[2] = {istride * n[0], istride * n[1]};
+    int inembed[2] = {n[0], n[1]};
     // in-place transforms require inembed=oneembed:
     int onembed[2] = {inembed[0], inembed[1]};
 
-    int idist = inembed[0] * inembed[1];
-    int odist = onembed[0] * onembed[1];
+    int idist = 1;
+    int odist = 1;
 
     std::cout << "n: " << n[0] << " " << n[1] << "\n"
               << "howmany: " << howmany << "\n"
@@ -54,7 +54,8 @@
               << "idist: " << idist << "\todist: " << odist << "\n"
               << std::endl;
 
-    std::vector<std::complex<double>> data(howmany * idist);
+    std::vector<std::complex<double>> data(4*4*4);
+    std::vector<std::complex<double>> cdata(4*4*4);
     const auto total_bytes = data.size() * sizeof(decltype(data)::value_type);
 
     std::cout << "input:\n";
@@ -96,9 +97,11 @@
     hipMemcpy(d_in_out, (void*)data.data(), total_bytes, hipMemcpyHostToDevice);
 
     result = hipfftExecZ2Z(hipPlan, d_in_out, d_in_out, HIPFFT_FORWARD);
+    result = hipfftExecZ2Z(hipPlan, d_in_out, d_in_out, HIPFFT_BACKWARD);
 
-    hipMemcpy((void*)data.data(), d_in_out, total_bytes, hipMemcpyDeviceToHost);
+    hipMemcpy((void*)cdata.data(), d_in_out, total_bytes, hipMemcpyDeviceToHost);
 
+    const double s = 1.0/(n[0]*n[1]);
     std::cout << "output:\n";
     for(int ibatch = 0; ibatch < howmany; ++ibatch)
     {
@@ -108,7 +111,7 @@
             for(int j = 0; j < onembed[1]; j++)
             {
                 const auto pos = ibatch * odist + i * onembed[1] + j;
-                std::cout << data[pos] << " ";
+                std::cout << s*cdata[pos] << " ";
             }
             std::cout << "\n";
         }
@@ -116,5 +119,16 @@
     }
     std::cout << std::endl;
 
+    double err = 0.0;
+    for (int i = 0; i < data.size(); i++)
+    {
+        double ierr = std::abs(s*cdata[i] - data[i]);
+        if (ierr > err)
+        {
+            err = ierr;
+        }
+    }
+    std::cout << "max error: " << err << std::endl;
+
     hipFree(d_in_out);
 }