Docs - Unify metric and add doc for cublas and cudnn functions (#271)

**Description** Unify metric and add doc for cuBLAS and cuDNN functions.
microsoft · Dec 23, 2021 · 6ecded2 · 6ecded2
1 parent 7462552
commit 6ecded2
Show file tree

Hide file tree

Showing 3 changed files with 36 additions and 6 deletions.
diff --git a/docs/user-tutorial/benchmarks/micro-benchmarks.md b/docs/user-tutorial/benchmarks/micro-benchmarks.md
@@ -60,11 +60,40 @@ Large scale matmul operation using `torch.matmul` with one GPU.
 
 ### `cublas-function`
 
-TODO
+#### Introduction
+
+Measure the performance of most common Nvidia cuBLAS functions with parameters in models training including ResNet, VGG, DenseNet, LSTM, BERT, and GPT-2.
+
+The supported functions for cuBLAS are as follows:
+ - cublasSgemm
+ - cublasSgemmStridedBatched
+ - cublasGemmStridedBatchedEx
+ - cublasGemmEx
+ - cublasCgemm3mStridedBatched
+ - cublasCgemm
+
+#### Metrics
+
+| Name                                                     | Unit      | Description                                                       |
+|----------------------------------------------------------|-----------|-------------------------------------------------------------------|
+| cublas-function/name_${function_name}_${parameters}_time | time (us) | The mean time to execute the cublas function with the parameters. |
 
 ### `cudnn-function`
 
-TODO
+#### Introduction
+
+Measure the performance of most common Nvidia cuDNN functions with parameters in models training including ResNet, VGG, DenseNet, LSTM, BERT, and GPT-2.
+
+The supported functions for cuDNN are as follows:
+ - cudnnConvolutionBackwardFilter
+ - cudnnConvolutionBackwardData
+ - cudnnConvolutionForward
+
+#### Metrics
+
+| Name                                                    | Unit      | Description                                                      |
+|---------------------------------------------------------|-----------|------------------------------------------------------------------|
+| cudnn-function/name_${function_name}_${parameters}_time | time (us) | The mean time to execute the cudnn function with the parameters. |
 
 ### `tensorrt-inference`
 

diff --git a/superbench/benchmarks/micro_benchmarks/cublas_function.py b/superbench/benchmarks/micro_benchmarks/cublas_function.py
@@ -291,8 +291,8 @@ def _process_raw_result(self, cmd_idx, raw_output):
                     raw_data = raw_data.split(',')
                     raw_data.pop()
                     raw_data = [float(item) for item in raw_data]
-                    self._result.add_result(metric, statistics.mean(raw_data))
-                    self._result.add_raw_data(metric, raw_data)
+                    self._result.add_result(metric.lower() + '_time', statistics.mean(raw_data))
+                    self._result.add_raw_data(metric.lower() + '_time', raw_data)
                 if 'Error' in line:
                     error = True
         except BaseException as e:

diff --git a/superbench/benchmarks/micro_benchmarks/cudnn_function.py b/superbench/benchmarks/micro_benchmarks/cudnn_function.py
@@ -6,6 +6,7 @@
 import os
 import json
 import yaml
+import statistics
 
 from superbench.common.utils import logger
 from superbench.benchmarks import Platform, BenchmarkRegistry, ReturnCode
@@ -424,8 +425,8 @@ def _process_raw_result(self, cmd_idx, raw_output):
                     raw_data = raw_data.split(',')
                     raw_data.pop()
                     raw_data = [float(item) for item in raw_data]
-                    self._result.add_result(metric, sum(raw_data) / len(raw_data))
-                    self._result.add_raw_data(metric, raw_data)
+                    self._result.add_result(metric.lower() + '_time', statistics.mean(raw_data) * 1000)
+                    self._result.add_raw_data(metric.lower() + '_time', raw_data)
                 if 'Error' in line:
                     error = True
         except BaseException as e: