diff --git a/benchmarks/operator_benchmark/benchmark_pytorch.py b/benchmarks/operator_benchmark/benchmark_pytorch.py
index 0371c74b7f2..fe558dc8890 100644
--- a/benchmarks/operator_benchmark/benchmark_pytorch.py
+++ b/benchmarks/operator_benchmark/benchmark_pytorch.py
@@ -94,11 +94,17 @@ class TorchBenchmarkBase(object):
         """ this is a globally unique name which can be used to 
             label a specific test 
         """
+
+        # This is a list of attributes which will not be included
+        # in the test name. 
+        skip_key_list = ['device']
+
         test_name_str = []
         for key in kargs:
             value = kargs[key]
             test_name_str.append(
-                key + str(value if type(value) != bool else int(value)))
+                ('' if key in skip_key_list else key)
+                + str(value if type(value) != bool else int(value)))
         name = (self.module_name() + '_' +
                 '_'.join(test_name_str)).replace(" ", "")
         return name
diff --git a/benchmarks/operator_benchmark/pt/add_test.py b/benchmarks/operator_benchmark/pt/add_test.py
index 3be7fb27749..1e4c5222cb9 100644
--- a/benchmarks/operator_benchmark/pt/add_test.py
+++ b/benchmarks/operator_benchmark/pt/add_test.py
@@ -11,33 +11,49 @@ import torch
 # Configs for PT add operator
 add_long_configs = op_bench.cross_product_configs(
     M=[8, 64, 128],
-    N=range(2, 10, 3),
-    K=[2 ** x for x in range(0, 3)],
+    N=range(2, 128, 64),
+    K=[8 ** x for x in range(0, 3)], 
+    device=['cpu', 'cuda'],
     tags=["long"]
 )
 
 
 add_short_configs = op_bench.config_list(
+    attr_names=["M", "N", "K"], 
     attrs=[
         [64, 64, 64],
         [64, 64, 128],
     ],
-    attr_names=["M", "N", "K"],
-    tags=["short"],
+    cross_product_configs={
+        'device': ['cpu', 'cuda'],
+    },
+    tags=["short"], 
 )
 
 
 class AddBenchmark(op_bench.TorchBenchmarkBase):
-    def init(self, M, N, K):
-        self.input_one = torch.rand(M, N, K)
-        self.input_two = torch.rand(M, N, K)
+    def init(self, M, N, K, device): 
+        self.input_one = torch.rand(M, N, K, device=device, requires_grad=self.auto_set())
+        self.input_two = torch.rand(M, N, K, device=device, requires_grad=self.auto_set())
         self.set_module_name("add")
 
     def forward(self):
         return torch.add(self.input_one, self.input_two)
 
+# The generated test names based on add_short_configs will be in the following pattern: 
+# add_M8_N16_K32_devicecpu
+# add_M8_N16_K32_devicecuda
+# add_M8_N16_K32_devicecpu_bwdall
+# add_M8_N16_K32_devicecpu_bwd1
+# add_M8_N16_K32_devicecpu_bwd2
+# add_M8_N16_K32_devicecuda_bwdall
+# add_M8_N16_K32_devicecuda_bwd1
+# add_M8_N16_K32_devicecuda_bwd2
+# ...
+# Those names can be used to filter tests. 
 
 op_bench.generate_pt_test(add_long_configs + add_short_configs, AddBenchmark)
+op_bench.generate_pt_gradient_test(add_long_configs + add_short_configs, AddBenchmark)
 
 
 if __name__ == "__main__":