update the baseline data for the operator benchmark (pytorch#164789)

update the baseline data for the operator benchmark (pytorch#162693)

According to the results of the last four operator benchmark runs, we found that five models achieved more than a 30% improvement compared to the baseline. Therefore, we will update the operator benchmark baseline data.
We use the average results from the four runs as the new baseline for the five models.

And add a pull request trigger for the operator benchmark workflow

Benchmarking   Framework | Benchmarking   Module Name | Case Name | tag | run_backward | baseline   old | r1 | r2 | r3 | r4 | avg | speedup
-- | -- | -- | -- | -- | -- | -- | -- | -- | -- | -- | --
PyTorch | add | add_M1_N1_K1_cpu | short | FALSE | 3.9497 | 2.57 | 2.54 | 2.38 | 2.31 | 2.45 | 1.61
PyTorch | functional.hardtanh | functional.hardtanh_dims(512	512)_contigFalse_inplaceFalse_dtypetorch.quint8 | short | FALSE | 67.118 | 50.02 | 49.80 | 46.78 | 48.94 | 48.88 | 1.37
PyTorch | relu6 | relu6_dims(512	512)_contigFalse_inplaceFalse_dtypetorch.quint8 | short | FALSE | 68.739 | 51.17 | 51.19 | 48.07 | 50.42 | 50.21 | 1.37
PyTorch | relu6 | relu6_dims(256	1024)_contigFalse_inplaceFalse_dtypetorch.quint8 | short | FALSE | 69.1875 | 51.97 | 52.77 | 50.00 | 51.24 | 51.50 | 1.34
PyTorch | functional.hardtanh | functional.hardtanh_dims(256	1024)_contigFalse_inplaceFalse_dtypetorch.quint8 | short | FALSE | 67.436 | 50.98 | 51.69 | 49.06 | 49.87 | 50.40 | 1.34

@chuanqi129 @huydhn @desertfire @jainapurva

Pull Request resolved: pytorch#162693
Approved by: https://github.com/huydhn

(cherry picked from commit f7ea497)

Co-authored-by: LifengWang <[email protected]>

Author: pytorchbot

.github/workflows/operator_benchmark.yml

@@ -14,6 +14,10 @@ on:
   schedule:
     # Run at 07:00 UTC every Sunday
     - cron: 0 7 * * 0
+  pull_request:
+    paths:
+      - benchmarks/operator_benchmark/**
+      - .github/workflows/operator_benchmark.yml
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.event.pull_request.number || github.sha }}-${{ github.event_name == 'workflow_dispatch' }}

benchmarks/operator_benchmark/expected_ci_operator_benchmark_eager_float32_cpu.csv

@@ -1,5 +1,5 @@
 Benchmarking Framework,Benchmarking Module Name,Case Name,tag,run_backward,Execution Time
-PyTorch,add,add_M1_N1_K1_cpu,short,FALSE,3.9497
+PyTorch,add,add_M1_N1_K1_cpu,short,FALSE,2.459
 PyTorch,add,add_M64_N64_K64_cpu,short,FALSE,14.3181
 PyTorch,add,add_M64_N64_K128_cpu,short,FALSE,14.6826
 PyTorch,add,add_M1_N1_K1_cpu_bwdall_BACKWARD,short,TRUE,58.1449
@@ -376,10 +376,10 @@ PyTorch,relu6,"relu6_dims(3,4,5)_contigFalse_inplaceFalse_dtypetorch.qint32",sho
 PyTorch,relu6,"relu6_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,9.6588
 PyTorch,relu6,"relu6_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,9.5969
 PyTorch,relu6,"relu6_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,9.547
-PyTorch,relu6,"relu6_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,68.739
+PyTorch,relu6,"relu6_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,50.21375
 PyTorch,relu6,"relu6_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,45.14133333
 PyTorch,relu6,"relu6_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,52.6664
-PyTorch,relu6,"relu6_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,69.1875
+PyTorch,relu6,"relu6_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,51.49525
 PyTorch,relu6,"relu6_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,48.3458
 PyTorch,relu6,"relu6_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,62.0719
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(3,4,5)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,7.5728
@@ -388,10 +388,10 @@ PyTorch,functional.hardtanh,"functional.hardtanh_dims(3,4,5)_contigFalse_inplace
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,8.1647
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,8.1768
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(2,3,4,5)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,8.0619
-PyTorch,functional.hardtanh,"functional.hardtanh_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,67.118
+PyTorch,functional.hardtanh,"functional.hardtanh_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,48.88475
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,43.702
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(512,512)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,50.3613
-PyTorch,functional.hardtanh,"functional.hardtanh_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,67.436
+PyTorch,functional.hardtanh,"functional.hardtanh_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,50.3995
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.qint8",short,FALSE,46.9813
 PyTorch,functional.hardtanh,"functional.hardtanh_dims(256,1024)_contigFalse_inplaceFalse_dtypetorch.qint32",short,FALSE,59.2295
 PyTorch,functional.hardsigmoid,"functional.hardsigmoid_dims(3,4,5)_contigFalse_inplaceFalse_dtypetorch.quint8",short,FALSE,6.5189
@@ -1316,4 +1316,4 @@ PyTorch,where,"where_cond_shape(8,16,1)_input_shape(1,)_other_shape(1,)_cpu_dtyp
 PyTorch,where,"where_cond_shape(8,16,1)_input_shape(16,1)_other_shape(8,16,1)_cpu_dtypetorch.float32",short,FALSE,5.763
 PyTorch,where,"where_cond_shape(8,16,1)_input_shape(8,1,1)_other_shape(1,)_cpu_dtypetorch.float32",short,FALSE,5.744666667
 PyTorch,clamp,clamp_M512_N512_cpu,short,FALSE,15.26233333
-PyTorch,gelu,gelu_M512_N512_cpu,short,FALSE,31.33166667
+PyTorch,gelu,gelu_M512_N512_cpu,short,FALSE,31.33166667