diff --git a/contrib/exhaustive_search.py b/contrib/exhaustive_search.py
index 808453e6c1..257427777d 100644
--- a/contrib/exhaustive_search.py
+++ b/contrib/exhaustive_search.py
@@ -11,7 +11,7 @@
 
 LOG = logging.getLogger(__name__)
 
-def knn_ground_truth(xq, db_iterator, k, metric_type=faiss.METRIC_L2):
+def knn_ground_truth(xq, db_iterator, k, metric_type=faiss.METRIC_L2, shard=False, ngpu=-1):
     """Computes the exact KNN search results for a dataset that possibly
     does not fit in RAM but for which we have an iterator that
     returns it block by block.
@@ -23,9 +23,14 @@ def knn_ground_truth(xq, db_iterator, k, metric_type=faiss.METRIC_L2):
     rh = faiss.ResultHeap(nq, k, keep_max=keep_max)
 
     index = faiss.IndexFlat(d, metric_type)
-    if faiss.get_num_gpus():
-        LOG.info('running on %d GPUs' % faiss.get_num_gpus())
-        index = faiss.index_cpu_to_all_gpus(index)
+    if ngpu == -1:
+        ngpu = faiss.get_num_gpus()
+
+    if ngpu:
+        LOG.info('running on %d GPUs' % ngpu)
+        co = faiss.GpuMultipleClonerOptions()
+        co.shard = shard
+        index = faiss.index_cpu_to_all_gpus(index, co=co, ngpu=ngpu)
 
     # compute ground-truth by blocks, and add to heaps
     i0 = 0
diff --git a/tests/test_contrib.py b/tests/test_contrib.py
index ba185f92b2..ca5d2bcca7 100644
--- a/tests/test_contrib.py
+++ b/tests/test_contrib.py
@@ -35,7 +35,7 @@
 
 class TestComputeGT(unittest.TestCase):
 
-    def do_test_compute_GT(self, metric=faiss.METRIC_L2):
+    def do_test_compute_GT(self, metric=faiss.METRIC_L2, ngpu=0):
         d = 64
         xt, xb, xq = get_dataset_2(d, 0, 10000, 100)
 
@@ -50,7 +50,7 @@ def matrix_iterator(xb, bs):
                 yield xb[i0:i0 + bs]
 
         Dnew, Inew = knn_ground_truth(
-            xq, matrix_iterator(xb, 1000), 10, metric)
+            xq, matrix_iterator(xb, 1000), 10, metric, ngpu=ngpu)
 
         np.testing.assert_array_equal(Iref, Inew)
         # decimal = 4 required when run on GPU
@@ -62,6 +62,12 @@ def test_compute_GT(self):
     def test_compute_GT_ip(self):
         self.do_test_compute_GT(faiss.METRIC_INNER_PRODUCT)
 
+    def test_compute_GT_gpu(self):
+        self.do_test_compute_GT(ngpu=-1)
+
+    def test_compute_GT_ip_gpu(self):
+        self.do_test_compute_GT(faiss.METRIC_INNER_PRODUCT, ngpu=-1)
+
 
 class TestDatasets(unittest.TestCase):
     """here we test only the synthetic dataset. Datasets that require