[OpPerf] Fix markdown for native profile and add profile param in fun…

…ction desc (apache#17494)

* 5 columns instead of 6 for native profile

* add profiler param in function description

benchmark/opperf/nd_operations/array_rearrange.py

@@ -39,6 +39,8 @@ def run_rearrange_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/binary_operators.py

@@ -48,6 +48,8 @@ def run_mx_binary_broadcast_operators_benchmarks(ctx=mx.cpu(), dtype='float32',
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -75,6 +77,8 @@ def run_mx_binary_element_wise_operators_benchmarks(ctx=mx.cpu(), dtype='float32
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 10
         Number of times to run for warmup
     runs: int, default 50

benchmark/opperf/nd_operations/gemm_operators.py

@@ -44,6 +44,8 @@ def run_gemm_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nativ
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/nn_optimizer_operators.py

@@ -46,6 +46,8 @@ def run_optimizer_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/random_sampling_operators.py

@@ -44,6 +44,8 @@ def run_mx_random_sampling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', p
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/reduction_operators.py

@@ -41,6 +41,8 @@ def run_mx_reduction_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profile
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/sorting_searching_operators.py

@@ -39,6 +39,8 @@ def run_sorting_searching_operators_benchmarks(ctx=mx.cpu(), dtype='float32', pr
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/unary_operators.py

@@ -45,6 +45,8 @@ def run_mx_unary_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='n
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/utils/common_utils.py

@@ -141,10 +141,11 @@ def _prepare_markdown(results, runtime_features=None, profiler='native'):
         results_markdown.append(
             "| Operator | Avg Forward Time (ms) | Avg. Backward Time (ms) | Max Mem Usage (Storage) (Bytes)"
             " | Inputs |")
+        results_markdown.append("| :---: | :---: | :---: | :---: | :---: |")
     elif profiler == 'python':
         results_markdown.append(
             "| Operator | Avg Time (ms) | P50 Time (ms) | P90 Time (ms) | P99 Time (ms) | Inputs |")
-    results_markdown.append("| :---: | :---: | :---: | :---: | :---: | :---: |")
+        results_markdown.append("| :---: | :---: | :---: | :---: | :---: | :---: |")
 
     for op, op_bench_results in sorted(results.items(), key=itemgetter(0)):
         for op_bench_result in op_bench_results: