Skip to content

Commit

Permalink
register signal ops for opset 17 (#11778)
Browse files Browse the repository at this point in the history 
* Register signal ops for op set 17

Note code is mostly being moved, not added. These ops were previously
only registered as Microsoft contrib ops and only built if
`BUILD_MS_EXPERIMENTAL_OPS=1`. They've been added to the ai.onnx
standard op set in version 17.

Main components of this change:

* Move the kernels from the conrib_ops directory to the
  core directory.
* Add function bodies for ms experimental ops. This will allow
  old models that use the contrib ops to continue to function.
  All the function bodies consist of a single op (the
  new standard op), so performance overhead should be minimal.

Minor clean-up also in this change:

* De-duplicate get_scalar_value_from_tensor: put it in a new utils.h.
* Fix some bugs that caused compilation errors with the experimental
  ops. Tested with `build.sh --ms_experimental`
* Fix some spelling errors and lint violations.
* Replace a couple of switch statements with `MLTypeCallDispatcher`.
* Use `InlineVector` instead of `std::vector`.

Unblocks #11640
  • Loading branch information
@garymm @RandySheriffH
garymm authored and RandySheriffH committed Jun 29, 2022
1 parent ef3025e commit f4def27
Show file tree
Hide file tree
Showing 18 changed files with 1,075 additions and 1,980 deletions.
6 changes: 6 additions & 0 deletions docs/OperatorKernels.md
View file
Original file line number Diff line number Diff line change
Expand Up @@ -43,6 +43,7 @@ Do not modify directly.*
|||[9, 13]|**T** = tensor(double), tensor(float)|
|||[7, 8]|**T** = tensor(double), tensor(float)|
|BitShift|*in* X:**T**<br> *in* Y:**T**<br> *out* Z:**T**|11+|**T** = tensor(uint32), tensor(uint64), tensor(uint8)|
|BlackmanWindow|*in* size:**T1**<br> *out* output:**T2**|17+|**T1** = tensor(int32), tensor(int64)<br/> **T2** = tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|Cast|*in* input:**T1**<br> *out* output:**T2**|13+|**T1** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|||[6, 12]|**T1** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)<br/> **T2** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|Ceil|*in* X:**T**<br> *out* Y:**T**|13+|**T** = tensor(float)|
Expand All @@ -69,6 +70,7 @@ Do not modify directly.*
|Crop|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float)|
|CumSum|*in* x:**T**<br> *in* axis:**T2**<br> *out* y:**T**|14+|**T** = tensor(double), tensor(float), tensor(int32), tensor(int64)<br/> **T2** = tensor(int32), tensor(int64)|
|||[11, 13]|**T** = tensor(double), tensor(float), tensor(int32), tensor(int64)<br/> **T2** = tensor(int32), tensor(int64)|
|DFT|*in* input:**T1**<br> *in* dft_length:**T2**<br> *out* output:**T1**|17+|**T1** = tensor(double), tensor(float)<br/> **T2** = tensor(int32), tensor(int64)|
|DepthToSpace|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(double), tensor(float)|
|||[11, 12]|**T** = tensor(double), tensor(float)|
|||[1, 10]|**T** = tensor(double), tensor(float)|
Expand Down Expand Up @@ -125,6 +127,8 @@ Do not modify directly.*
|GreaterOrEqual|*in* A:**T**<br> *in* B:**T**<br> *out* C:**T1**|16+|**T** = tensor(double), tensor(float), tensor(int32), tensor(int64)<br/> **T1** = tensor(bool)|
|||[12, 15]|**T** = tensor(double), tensor(float), tensor(int32), tensor(int64)<br/> **T1** = tensor(bool)|
|GridSample|*in* X:**T1**<br> *in* grid:**T1**<br> *out* Y:**T2**|16+|**T1** = tensor(float)<br/> **T2** = tensor(float)|
|HammingWindow|*in* size:**T1**<br> *out* output:**T2**|17+|**T1** = tensor(int32), tensor(int64)<br/> **T2** = tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|HannWindow|*in* size:**T1**<br> *out* output:**T2**|17+|**T1** = tensor(int32), tensor(int64)<br/> **T2** = tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|HardSigmoid|*in* X:**T**<br> *out* Y:**T**|6+|**T** = tensor(float)|
|Hardmax|*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float)|
|||[11, 12]|**T** = tensor(float)|
Expand Down Expand Up @@ -186,6 +190,7 @@ Do not modify directly.*
|MeanVarianceNormalization|*in* X:**T**<br> *out* Y:**T**<br><br>or<br><br>*in* input:**T**<br> *out* output:**T**|13+|**T** = tensor(float)|
|||[9, 12]|**T** = tensor(float)|
|||[1, 8]|**T** = tensor(float)|
|MelWeightMatrix|*in* num_mel_bins:**T1**<br> *in* dft_length:**T1**<br> *in* sample_rate:**T1**<br> *in* lower_edge_hertz:**T2**<br> *in* upper_edge_hertz:**T2**<br> *out* output:**T3**|17+|**T1** = tensor(int32), tensor(int64)<br/> **T2** = tensor(float)<br/> **T3** = tensor(double), tensor(float), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
|Min|*in* data_0:**T**<br> *out* min:**T**|13+|**T** = tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
|||12|**T** = tensor(double), tensor(float), tensor(float16), tensor(int32), tensor(int64), tensor(uint32), tensor(uint64)|
|||[8, 11]|**T** = tensor(double), tensor(float)|
Expand Down Expand Up @@ -277,6 +282,7 @@ Do not modify directly.*
|RoiAlign|*in* X:**T1**<br> *in* rois:**T1**<br> *in* batch_indices:**T2**<br> *out* Y:**T1**|16+|**T1** = tensor(double), tensor(float)<br/> **T2** = tensor(int64)|
|||[10, 15]|**T1** = tensor(double), tensor(float)<br/> **T2** = tensor(int64)|
|Round|*in* X:**T**<br> *out* Y:**T**|11+|**T** = tensor(double), tensor(float), tensor(float16)|
|STFT|*in* signal:**T1**<br> *in* frame_step:**T2**<br> *in* window:**T1**<br> *in* frame_length:**T2**<br> *out* output:**T1**|17+|**T1** = tensor(double), tensor(float)<br/> **T2** = tensor(int32), tensor(int64)|
|Scale|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float)|
|ScaledTanh|*in* input:**T**<br> *out* output:**T**|1+|**T** = tensor(float)|
|Scan|*in* initial_state_and_scan_inputs:**V**<br> *out* final_state_and_scan_outputs:**V**<br><br>or<br><br>*in* sequence_lens:**I**<br> *in* initial_state_and_scan_inputs:**V**<br> *out* final_state_and_scan_outputs:**V**|16+|**V** = tensor(bfloat16), tensor(bool), tensor(double), tensor(float), tensor(float16), tensor(int16), tensor(int32), tensor(int64), tensor(int8), tensor(string), tensor(uint16), tensor(uint32), tensor(uint64), tensor(uint8)|
Expand Down
20 changes: 0 additions & 20 deletions onnxruntime/contrib_ops/cpu/cpu_contrib_kernels.cc
View file
Original file line number Diff line number Diff line change
Expand Up @@ -41,16 +41,6 @@ class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, FastG
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, NGramRepeatBlock);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, BifurcationDetector);

#ifdef BUILD_MS_EXPERIMENTAL_OPS
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, DFT);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, IDFT);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, HannWindow);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, HammingWindow);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, BlackmanWindow);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, MelWeightMatrix);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, STFT);
#endif

// ******** Start: Quantization ******************* //
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, MatMulInteger16);
class ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, QLinearGlobalAveragePool);
Expand Down Expand Up @@ -224,16 +214,6 @@ Status RegisterCpuContribKernels(KernelRegistry& kernel_registry) {
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, FastGelu)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, NGramRepeatBlock)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSDomain, 1, BifurcationDetector)>,

#ifdef BUILD_MS_EXPERIMENTAL_OPS
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, DFT)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, IDFT)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, HannWindow)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, HammingWindow)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, BlackmanWindow)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, MelWeightMatrix)>,
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kMSExperimentalDomain, 1, STFT)>,
#endif
// These ops were experimental ops in onnx domain which have been removed now. We add them here as
// contrib ops to main backward compatibility
BuildKernelCreateInfo<ONNX_OPERATOR_KERNEL_CLASS_NAME(kCpuExecutionProvider, kOnnxDomain, 1, Affine)>,
Expand Down
Loading

0 comments on commit f4def27

Please sign in to comment.