Adding docs, changed large_tensor to int64_tensor for clarity

benchmark/opperf/nd_operations/array_rearrange.py

@@ -29,8 +29,8 @@
 """
 
 
-def run_rearrange_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the
+def run_rearrange_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the
     rearrange operators in MXNet.
 
     Parameters
@@ -41,7 +41,7 @@ def run_rearrange_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
-    large_tensor: str, default 'off'
+    int64_tensor: str, default 'off'
         Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
@@ -57,5 +57,5 @@ def run_rearrange_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='
     mx_rearrange_ops = get_all_rearrange_operators()
 
     # Run benchmarks
-    mx_rearrange_op_results = run_op_benchmarks(mx_rearrange_ops, dtype, ctx, profiler, large_tensor, warmup, runs)
+    mx_rearrange_op_results = run_op_benchmarks(mx_rearrange_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_rearrange_op_results

benchmark/opperf/nd_operations/binary_operators.py

@@ -38,8 +38,8 @@
     get_all_elemen_wise_binary_operators, get_all_misc_binary_operators
 
 
-def run_mx_binary_misc_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context and precision (dtype) for all the miscellaneous
+def run_mx_binary_misc_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the miscellaneous
     binary operators in MXNet.
 
     Parameters
@@ -48,6 +48,10 @@ def run_mx_binary_misc_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profi
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -61,12 +65,12 @@ def run_mx_binary_misc_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profi
     # Fetch all Miscellaneous Binary Operators
     mx_binary_misc_ops = get_all_misc_binary_operators()
     # Run benchmarks
-    mx_binary_op_results = run_op_benchmarks(mx_binary_misc_ops, dtype, ctx, profiler, large_tensor, warmup, runs)
+    mx_binary_op_results = run_op_benchmarks(mx_binary_misc_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_binary_op_results
 
 
-def run_mx_binary_broadcast_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the binary
+def run_mx_binary_broadcast_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the binary
     broadcast operators in MXNet.
 
     Parameters
@@ -77,7 +81,7 @@ def run_mx_binary_broadcast_operators_benchmarks(ctx=mx.cpu(), dtype='float32',
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
-    large_tensor: str, default 'off'
+    int64_tensor: str, default 'off'
         Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
@@ -92,12 +96,12 @@ def run_mx_binary_broadcast_operators_benchmarks(ctx=mx.cpu(), dtype='float32',
     # Fetch all Binary Broadcast Operators
     mx_binary_broadcast_ops = get_all_broadcast_binary_operators()
     # Run benchmarks
-    mx_binary_op_results = run_op_benchmarks(mx_binary_broadcast_ops, dtype, ctx, profiler, large_tensor, warmup, runs)
+    mx_binary_op_results = run_op_benchmarks(mx_binary_broadcast_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_binary_op_results
 
 
-def run_mx_binary_element_wise_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the binary
+def run_mx_binary_element_wise_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the binary
     element_wise operators in MXNet.
 
     Parameters
@@ -108,7 +112,7 @@ def run_mx_binary_element_wise_operators_benchmarks(ctx=mx.cpu(), dtype='float32
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
-    large_tensor: str, default 'off'
+    int64_tensor: str, default 'off'
         Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 10
         Number of times to run for warmup
@@ -123,5 +127,5 @@ def run_mx_binary_element_wise_operators_benchmarks(ctx=mx.cpu(), dtype='float32
     # Fetch all Binary Element_wise Operators
     mx_binary_element_wise_ops = get_all_elemen_wise_binary_operators()
     # Run benchmarks
-    mx_binary_op_results = run_op_benchmarks(mx_binary_element_wise_ops, dtype, ctx, profiler, large_tensor, warmup, runs)
+    mx_binary_op_results = run_op_benchmarks(mx_binary_element_wise_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_binary_op_results

benchmark/opperf/nd_operations/gemm_operators.py

@@ -35,8 +35,8 @@
 """
 
 
-def run_gemm_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the GEMM
+def run_gemm_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the GEMM
     operators (dot, batch_dot, khatri_rao) in MXNet.
 
     Parameters
@@ -47,7 +47,7 @@ def run_gemm_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nativ
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
-    large_tensor: str, default 'off'
+    int64_tensor: str, default 'off'
         Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
@@ -60,7 +60,7 @@ def run_gemm_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nativ
 
     """
     # Benchmark tests for dot and batch_dot operators
-    if large_tensor == "on":
+    if int64_tensor == "on":
         dot_benchmark_res = run_performance_test(
             [getattr(MX_OP_MODULE, "dot")], run_backward=True,
             dtype=dtype, ctx=ctx,

benchmark/opperf/nd_operations/indexing_routines.py

@@ -35,8 +35,8 @@
 """
 
 
-def run_indexing_routines_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', warmup=25, runs=100):
-    """Runs benchmarks with the given context and precision (dtype) for all the indexing routines
+def run_indexing_routines_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and data size (int64_tensor) for all the indexing routines
     in MXNet.
 
     Parameters
@@ -47,6 +47,8 @@ def run_indexing_routines_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='na
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100

benchmark/opperf/nd_operations/linalg_operators.py

@@ -34,8 +34,8 @@
 from benchmark.opperf.utils.common_utils import merge_map_list
 from benchmark.opperf.rules.default_params import MX_OP_MODULE
 
-def run_linalg_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', warmup=25, runs=100):
-    """Runs benchmarks with the given context and precision (dtype) for all the linear algebra
+def run_linalg_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and data size (int64_tensor) for all the linear algebra
     operators in MXNet.
 
     Parameters
@@ -46,6 +46,8 @@ def run_linalg_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nat
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -74,5 +76,5 @@ def run_linalg_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nat
     # Fetch all Linear Algebra Operators
     mx_linalg_ops = get_all_linalg_operators()
     # Run benchmarks
-    mx_linalg_op_results = run_op_benchmarks(mx_linalg_ops, dtype, ctx, profiler, warmup, runs)
+    mx_linalg_op_results = run_op_benchmarks(mx_linalg_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return merge_map_list(linalg_potrf_benchmark + [mx_linalg_op_results])

benchmark/opperf/nd_operations/nn_activation_operators.py

@@ -43,8 +43,8 @@
 """
 
 
-def run_activation_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the activation
+def run_activation_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the activation
     operators (relu, sigmoid, softmax) in MXNet.
 
     Parameters
@@ -55,7 +55,7 @@ def run_activation_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler=
         Precision to use for benchmarks
     profiler: str, default 'native'
         Module to use for tracking benchmark excecution time
-    large_tensor: str, default 'off'
+    int64_tensor: str, default 'off'
         Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
@@ -72,6 +72,6 @@ def run_activation_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler=
     mx_activation_ops = get_all_nn_activation_operators()
 
     # Run benchmarks
-    mx_activation_op_results = run_op_benchmarks(mx_activation_ops, dtype, ctx, profiler, large_tensor, warmup, runs)
+    mx_activation_op_results = run_op_benchmarks(mx_activation_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_activation_op_results
 

benchmark/opperf/nd_operations/nn_basic_operators.py

@@ -29,8 +29,8 @@
 """
 
 
-def run_nn_basic_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and data size (large_tensor) for all the basic neural network
+def run_nn_basic_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and data size (int64_tensor) for all the basic neural network
     operators in MXNet.
 
     Parameters
@@ -39,8 +39,10 @@ def run_nn_basic_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='n
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
-    large_tensor: str, default 'off'
-        Tensor size to use for tests
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -51,7 +53,7 @@ def run_nn_basic_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='n
     Dictionary of results. Key -> Name of the operator, Value -> Benchmark results.
 
     """
-    if large_tensor == 'on':
+    if int64_tensor == 'on':
         # FullyConnnected operator benchmarks
         fc_benchmark_res = run_performance_test([getattr(MX_OP_MODULE, "FullyConnected")],
                                                 run_backward=True,

benchmark/opperf/nd_operations/nn_conv_operators.py

@@ -52,8 +52,8 @@
 """
 
 
-def run_pooling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the pooling
+def run_pooling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the pooling
     operators in MXNet.
 
     Parameters
@@ -62,8 +62,10 @@ def run_pooling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='na
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
-    large_tensor: str, default 'off'
-        Tensor size to use for tests
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -82,7 +84,7 @@ def run_pooling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='na
     pool2d_benchmark_res = []
     for pool_type in pool_types:
         for global_pool in global_pool_types:
-            if large_tensor == 'on':
+            if int64_tensor == 'on':
                 for pool1d_data in [(1, 1, 2**32), (2**31, 1, 3)]:
                     pool1d_benchmark_res += run_performance_test([getattr(MX_OP_MODULE, "Pooling")],
                                                                  run_backward=True,
@@ -179,8 +181,8 @@ def run_pooling_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='na
     return mx_pooling_op_results
 
 
-def run_convolution_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', large_tensor='off', warmup=25, runs=100):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the convolution
+def run_convolution_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the convolution
     operators in MXNet.
 
     Parameters
@@ -189,8 +191,10 @@ def run_convolution_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
-    large_tensor: str, default 'off'
-        Tensor size to use for tests
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -203,7 +207,7 @@ def run_convolution_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler
     """
     conv1d_benchmark_res = []
     conv2d_benchmark_res = []
-    if large_tensor == 'on':
+    if int64_tensor == 'on':
         # Conv1D Benchmarks
         for conv_data in [(2**30, 1, 4), (2**31, 1, 3)]:
             conv1d_benchmark_res += run_performance_test([getattr(MX_OP_MODULE, "Convolution")],
@@ -286,8 +290,8 @@ def run_convolution_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler
     return mx_conv_op_results
 
 
-def run_transpose_convolution_operators_benchmarks(ctx=mx.cpu(), profiler='native', large_tensor='off', dtype='float32', warmup=10, runs=50):
-    """Runs benchmarks with the given context, precision (dtype), and input data size (large_tensor) for all the transpose convolution
+def run_transpose_convolution_operators_benchmarks(ctx=mx.cpu(), profiler='native', int64_tensor='off', dtype='float32', warmup=10, runs=50):
+    """Runs benchmarks with the given context, precision (dtype), and input data size (int64_tensor) for all the transpose convolution
     operators in MXNet.
 
     Parameters
@@ -296,8 +300,10 @@ def run_transpose_convolution_operators_benchmarks(ctx=mx.cpu(), profiler='nativ
         Context to run benchmarks
     dtype: str, default 'float32'
         Precision to use for benchmarks
-    large_tensor: str, default 'off'
-        Tensor size to use for tests
+    profiler: str, default 'native'
+        Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -310,7 +316,7 @@ def run_transpose_convolution_operators_benchmarks(ctx=mx.cpu(), profiler='nativ
     """
     # Conv1DTranspose Benchmarks
     conv1d_transpose_benchmark_res = []
-    if large_tensor == 'on':
+    if int64_tensor == 'on':
         for conv_data in [(2**30, 1, 4), (2**31, 1, 3)]:
             conv1d_transpose_benchmark_res += run_performance_test([getattr(MX_OP_MODULE, "Deconvolution")],
                                                                    run_backward=True,

benchmark/opperf/nd_operations/nn_loss_operators.py

@@ -28,8 +28,8 @@
 """
 
 
-def run_loss_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', warmup=25, runs=100):
-    """Runs benchmarks with the given context and precision (dtype) for all the
+def run_loss_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='native', int64_tensor='off', warmup=25, runs=100):
+    """Runs benchmarks with the given context, precision (dtype), and data size (int64_tensor) for all the
     Neural Network loss operators in MXNet.
 
     Parameters
@@ -40,6 +40,8 @@ def run_loss_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nativ
         Precision to use for benchmarks
     profiler: str, default 'native'
         Type of Profiler to use (native/python)
+    int64_tensor: str, default 'off'
+        Input tensor size to use for tests (if on, dimensions >= 2**32)
     warmup: int, default 25
         Number of times to run for warmup
     runs: int, default 100
@@ -54,5 +56,5 @@ def run_loss_operators_benchmarks(ctx=mx.cpu(), dtype='float32', profiler='nativ
     mx_loss_ops = get_all_loss_operators()
 
     # Run benchmarks
-    mx_loss_op_results = run_op_benchmarks(mx_loss_ops, dtype, ctx, profiler, warmup, runs)
+    mx_loss_op_results = run_op_benchmarks(mx_loss_ops, dtype, ctx, profiler, int64_tensor, warmup, runs)
     return mx_loss_op_results