onnxruntime/onnxruntime/test
Xavier Dupré 30ec8b038f
Test and fix optimizers LayerNormFusion, BiasSoftmaxFusion, Transpose for opset 18 (#14542)
### Description

Due to the changes introduced in opset 18 on Reduce operators (axes is
an input and not an attribute), the following optimizers are not
catching the pattern they are supposed to optimize. This PR addresses
that.

* layer_norm_fusion.cc: the optimizer was not detecting the pattern it
was suppose to optimize
* bias_softmax_fusion.cc: the optimizer was not detecting the pattern it
was suppose to optimize
* transpose_optimizer.cc: the optimizer was not optimize Reduce
operators other than ReduceSum

### Motivation and Context
Better performance.

---------

Signed-off-by: xadupre <xadupre@microsoft.com>
2023-02-08 14:11:31 -08:00
..
api_tests_without_env
common oneDNN ep bf16 enabling (#13484) 2022-11-04 18:25:09 -07:00
contrib_ops Some kernel changes for TULR (#14517) 2023-02-07 11:51:06 -08:00
custom_op_registration Add ability to register custom ops by specifying a function name (#14177) 2023-01-12 15:11:34 +10:00
debug_node_inputs_outputs Bug Fix - WASM build break (#13699) 2022-11-20 23:30:31 -08:00
eager Switch GSL to MS GSL 4.0.0 (#13416) 2022-10-29 04:15:20 -07:00
framework Add missing semicolon (#14143) 2023-02-02 14:08:33 -08:00
fuzzing Remove previously deprecated API (#12935) 2022-09-14 10:58:03 -07:00
global_thread_pools [oneDNN] Improved thread handling (#13618) 2023-01-31 14:37:13 -08:00
ir to work with onnx 1.13 rc, implement ver 18 reduce and optioanl ops, … (#13765) 2023-01-09 10:26:16 -08:00
mlas Enable parallel output reordering in MlasReorderOutputNchw() (#13643) 2023-02-08 10:02:54 -08:00
onnx [oneDNN] Improved thread handling (#13618) 2023-01-31 14:37:13 -08:00
opaque_api Deprecate APIs returning raw ptrs and provide replacements (#11922) 2022-06-24 09:50:04 -07:00
optimizer Test and fix optimizers LayerNormFusion, BiasSoftmaxFusion, Transpose for opset 18 (#14542) 2023-02-08 14:11:31 -08:00
perftest [oneDNN] Improved thread handling (#13618) 2023-01-31 14:37:13 -08:00
platform Tune test case for hybrid cpu (#14204) 2023-01-10 12:54:02 -08:00
proto
providers [oneDNN] Improved thread handling (#13618) 2023-01-31 14:37:13 -08:00
python Introduce collective ops to ort inference build (#14399) 2023-02-07 13:47:48 -08:00
quantization
shared_lib Fix issue with schema lookup where there are custom ops using the ONNX domain (#14492) 2023-02-03 08:05:18 +10:00
testdata Fix CI failure: temporarily disable real model tests from onnx repo (#14606) 2023-02-07 13:44:04 +08:00
unittest_main
util [oneDNN] Improved thread handling (#13618) 2023-01-31 14:37:13 -08:00
wasm
win_getopt
xctest Add ability to register custom ops by specifying a function name (#14177) 2023-01-12 15:11:34 +10:00