diff --git a/README.md b/README.md
index 707344f..20a46f8 100644
--- a/README.md
+++ b/README.md
@@ -11,25 +11,26 @@ under `src/` directory. The following routines are currently supported:
 
 ## Sort an array of custom defined class objects (uses `O(N)` space)
 ``` cpp
-template <typename T, typename Func>
-void x86simdsort::object_qsort(T *arr, uint32_t arrsize, Func key_func)
+template <typename T, typename U, typename Func>
+void x86simdsort::object_qsort(T *arr, U arrsize, Func key_func)
 ```
 `T` is any user defined struct or class and `arr` is a pointer to the first
-element in the array of objects of type `T`. `Func` is a lambda function that
-computes the `key` value for each object which is the metric used to sort the
-objects. `Func` needs to have the following signature:
+element in the array of objects of type `T`. The `arrsize` parameter can be any
+32-bit or 64-bit integer type. `Func` is a lambda function that computes the
+`key` value for each object which is the metric used to sort the objects.
+`Func` needs to have the following signature:
 
 ```cpp
 [] (T obj) -> key_t { key_t key; /* compute key for obj */ return key; }
 ```
 
-Note that the return type of the key `key_t` needs to be one of the following
-: `[float, uint32_t, int32_t, double, uint64_t, int64_t]`. `object_qsort` has a
-space complexity of `O(N)`. Specifically, it requires `arrsize *
-sizeof(key_t)` bytes to store a vector with all the keys and an additional
-`arrsize * sizeof(uint32_t)` bytes to store the indexes of the object array.
-For performance reasons, we support `object_qsort` only when the array size is
-less than or equal to `UINT32_MAX`.  An example usage of `object_qsort` is
+Note that the return type of the key `key_t` needs to be one of the following :
+`[float, uint32_t, int32_t, double, uint64_t, int64_t]`. `object_qsort` has a
+space complexity of `O(N)`. Specifically, it requires `arrsize * sizeof(key_t)`
+bytes to store a vector with all the keys and an additional `arrsize *
+sizeof(uint32_t)` bytes to store the indexes of the object array.  For
+performance reasons, we recommend using `object_qsort` when the array size
+is less than or equal to `UINT32_MAX`. An example usage of `object_qsort` is
 provided in the [examples](#Sort-an-array-of-Points-using-object_qsort)
 section.  Refer to [section](#Performance-of-object_qsort) to get a sense of
 how fast this is relative to `std::sort`.
diff --git a/lib/x86simdsort.h b/lib/x86simdsort.h
index c79f264..2e47b6a 100644
--- a/lib/x86simdsort.h
+++ b/lib/x86simdsort.h
@@ -70,29 +70,32 @@ XSS_EXPORT_SYMBOL void keyvalue_partial_sort(T1 *key,
                                              bool descending = false);
 
 // sort an object
-template <typename T, typename Func>
-XSS_EXPORT_SYMBOL void object_qsort(T *arr, uint32_t arrsize, Func key_func)
+template <typename T, typename U, typename Func>
+XSS_EXPORT_SYMBOL void object_qsort(T *arr, U arrsize, Func key_func)
 {
-    /* (1) Create a vector a keys */
-    using return_type_of =
-            typename decltype(std::function {key_func})::result_type;
+    static_assert(std::is_integral<U>::value, "arrsize must be an integral type");
+    static_assert(sizeof(U) == sizeof(int32_t) || sizeof(U) == sizeof(int64_t),
+                  "arrsize must be 32 or 64 bits");
+    using return_type_of = typename decltype(std::function{key_func})::result_type;
+    static_assert(sizeof(return_type_of) == sizeof(int32_t) || sizeof(return_type_of) == sizeof(int64_t),
+                  "key_func return type must be 32 or 64 bits");
     std::vector<return_type_of> keys(arrsize);
-    for (size_t ii = 0; ii < arrsize; ++ii) {
+    for (U ii = 0; ii < arrsize; ++ii) {
         keys[ii] = key_func(arr[ii]);
     }
 
     /* (2) Call arg based on keys using the keyvalue sort */
-    std::vector<uint32_t> arg(arrsize);
+    std::vector<U> arg(arrsize);
     std::iota(arg.begin(), arg.end(), 0);
     x86simdsort::keyvalue_qsort(keys.data(), arg.data(), arrsize);
 
     /* (3) Permute obj array in-place */
     std::vector<bool> done(arrsize);
-    for (size_t i = 0; i < arrsize; ++i) {
+    for (U i = 0; i < arrsize; ++i) {
         if (done[i]) { continue; }
         done[i] = true;
-        size_t prev_j = i;
-        size_t j = arg[i];
+        U prev_j = i;
+        U j = arg[i];
         while (i != j) {
             std::swap(arr[prev_j], arr[j]);
             done[j] = true;