Benchmarks: Microbenchmark - Add data type option for NCCL and RCCL tests (#595)

**Description**
Add data type option for NCCL and RCCL tests.

superbench/benchmarks/micro_benchmarks/cuda_nccl_bw_performance.py

@@ -99,6 +99,12 @@ def add_parser_arguments(self):
             action='store_true',
             help='If specified, collect in-place numbers, else collect out-of-place numbers.',
         )
+        self._parser.add_argument(
+            '--data_type',
+            type=str,
+            default='float',
+            help='Data type used in NCCL operations. Default: float.',
+        )
 
     def _preprocess(self):
         """Preprocess/preparation operations before the benchmarking.
@@ -128,9 +134,10 @@ def _preprocess(self):
                 return False
 
             command = os.path.join(self._args.bin_dir, self._bin_name)
-            command += ' -b {} -e {} -f {} -g {} -c {} -n {} -w {} -G {}'.format(
+            command += ' -b {} -e {} -f {} -g {} -c {} -n {} -w {} -G {} -d {}'.format(
                 self._args.minbytes, self._args.maxbytes, str(self._args.stepfactor), str(self._args.ngpus),
-                str(self._args.check), str(self._args.iters), str(self._args.warmup_iters), str(self._args.graph_iters)
+                str(self._args.check), str(self._args.iters), str(self._args.warmup_iters), str(self._args.graph_iters),
+                self._args.data_type
             )
             self._commands.append(command)
 

tests/benchmarks/micro_benchmarks/test_cuda_nccl_bw_performance.py

@@ -67,6 +67,7 @@ def test_nccl_bw_performance(self, allgather, allreduce, reduce, broadcast, redu
         assert (benchmark._args.warmup_iters == 5)
         assert (benchmark._args.graph_iters == 0)
         assert (benchmark._args.in_place is False)
+        assert (benchmark._args.data_type == 'float')
 
         # Check command list
         bin_names = [
@@ -75,7 +76,7 @@ def test_nccl_bw_performance(self, allgather, allreduce, reduce, broadcast, redu
         ]
 
         command = bin_names[0] + benchmark._commands[0].split(bin_names[0])[1]
-        expected_command = '{} -b 8 -e 8G -f 2 -g 8 -c 0 -n 20 -w 5 -G 0'.format(bin_names[0])
+        expected_command = '{} -b 8 -e 8G -f 2 -g 8 -c 0 -n 20 -w 5 -G 0 -d float'.format(bin_names[0])
         assert (command == expected_command)
 
         # Check results and metrics.