diff --git a/flang-rt/lib/cuda/memory.cpp b/flang-rt/lib/cuda/memory.cpp
index 1ebe5059b9411..adc24ff223729 100644
--- a/flang-rt/lib/cuda/memory.cpp
+++ b/flang-rt/lib/cuda/memory.cpp
@@ -8,6 +8,7 @@
 
 #include "flang/Runtime/CUDA/memory.h"
 #include "flang-rt/runtime/assign-impl.h"
+#include "flang-rt/runtime/descriptor.h"
 #include "flang-rt/runtime/terminator.h"
 #include "flang/Runtime/CUDA/common.h"
 #include "flang/Runtime/CUDA/descriptor.h"
@@ -98,8 +99,21 @@ void RTDECL(CUFDataTransferDescDesc)(Descriptor *dstDesc, Descriptor *srcDesc,
   } else {
     terminator.Crash("host to host copy not supported");
   }
-  Fortran::runtime::Assign(
-      *dstDesc, *srcDesc, terminator, MaybeReallocate, memmoveFct);
+  if ((srcDesc->rank() > 0) && (dstDesc->Elements() < srcDesc->Elements())) {
+    // Special case when rhs is bigger than lhs and both are contiguous arrays.
+    // In this case we do a simple ptr to ptr transfer with the size of lhs.
+    // This is be allowed in the reference compiler and it avoids error
+    // triggered in the Assign runtime function used for the main case below.
+    if (!srcDesc->IsContiguous() || !dstDesc->IsContiguous())
+      terminator.Crash("Unsupported data transfer: mismatching element counts "
+                       "with non-contiguous arrays");
+    RTNAME(CUFDataTransferPtrPtr)(dstDesc->raw().base_addr,
+        srcDesc->raw().base_addr, dstDesc->Elements() * dstDesc->ElementBytes(),
+        mode, sourceFile, sourceLine);
+  } else {
+    Fortran::runtime::Assign(
+        *dstDesc, *srcDesc, terminator, MaybeReallocate, memmoveFct);
+  }
 }
 
 void RTDECL(CUFDataTransferCstDesc)(Descriptor *dstDesc, Descriptor *srcDesc,