colin
/
onnx-mlir
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
onnx-mlir/SharingWork.md

196 lines
12 KiB
Markdown
Raw Normal View History

Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
# Please keep up to date.
- As you start working on a new operation, move it from the lower table to the top table,
- write your name under 'person working on it,'
- once you have pushed the functionality in the master branch, mark it as complete.
# ONNX to KRNL work.
Update as you push code to the master branch.
| ONNX Operation | Person working on it | ONNX Def | Shape Inference | ONNX to KRNL | Optimized |Extended Functionality |
|----------------|-----------------|----|---|---|----|-------|
| Abs | | v | v | v | | |
| Add | | v | v | v | | M |
| And | | v | v | v | | M |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| AveragePool | | v | v | v | | P |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| BatchNorm | | v | v | v | | |
| Constant | | v | v | v | | |
| Conv | | v | v | v | | nP |
Concat doc (#84) * concat done in sharing * create how to to add new ops in ONNX * update link * add step in doc * text fixes
2020-04-14 20:45:00 +08:00
| Concat | | v | v | v | | V |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Cos | | v | v | v | | |
| Cosh | | v | v | v | | |
| Div | | v | v | v | | M |
Add shape inference for Ops used by BERT (#249) * Add shape inference for Ops used by BERT * Erf * Pow * ReduceMean * Dropout * Expand https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand Deduce the value of the shape operand by looking at the producer of the operand. Currently supported producers are: onnx.Constant and onnx.Shape. * Add corresponding tests for each op. * Sort the list of ops with shape inference in gen_onnx_mlir.py in alphabetic order for clarity. * Restart CI Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
| Dropout | | v | v | | | |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Elu | | v | v | v | | |
Add shape inference for Ops used by BERT (#249) * Add shape inference for Ops used by BERT * Erf * Pow * ReduceMean * Dropout * Expand https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand Deduce the value of the shape operand by looking at the producer of the operand. Currently supported producers are: onnx.Constant and onnx.Shape. * Add corresponding tests for each op. * Sort the list of ops with shape inference in gen_onnx_mlir.py in alphabetic order for clarity. * Restart CI Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
| Erf | | v | v | | | |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Exp | | v | v | v | | |
Add shape inference for Ops used by BERT (#249) * Add shape inference for Ops used by BERT * Erf * Pow * ReduceMean * Dropout * Expand https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand Deduce the value of the shape operand by looking at the producer of the operand. Currently supported producers are: onnx.Constant and onnx.Shape. * Add corresponding tests for each op. * Sort the list of ops with shape inference in gen_onnx_mlir.py in alphabetic order for clarity. * Restart CI Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
| Expand | | v | v | | | |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Gemm | | v | v | v | | U |
| HardSigmoid | | v | v | v | | |
| Identity | | v | v | v | | |
| LeakyRelu | | v | v | v | | |
| Log | | v | v | v | | |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| MatMul | | v | v | v | | M |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Max | | v | v | v | | M V |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| MaxPool | | v | v | v | | P |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Min | | v | v | v | | M V |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| Mul | | v | v | v | | M |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Or | | v | v | v | | M |
| Pad | | v | V | v | | const only |
Add shape inference for Ops used by BERT (#249) * Add shape inference for Ops used by BERT * Erf * Pow * ReduceMean * Dropout * Expand https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand Deduce the value of the shape operand by looking at the producer of the operand. Currently supported producers are: onnx.Constant and onnx.Shape. * Add corresponding tests for each op. * Sort the list of ops with shape inference in gen_onnx_mlir.py in alphabetic order for clarity. * Restart CI Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
| Pow | | v | v | | | M |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Reciprocal | | v | v | v | | |
| ReduceMax | | v | v | v | | |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| ReduceL1 | | v | | | | be decomposed into ReduceSum and Abs |
| ReduceL2 | | v | | | | be decomposed into ReduceSumSquare and Sqrt |
| ReduceLogSum | | v | | | | be decomposed into ReduceSum and Log |
| ReduceLogSumExp| | v | | | | be decomposed into ReduceLogSum and Exp |
Add shape inference for Ops used by BERT (#249) * Add shape inference for Ops used by BERT * Erf * Pow * ReduceMean * Dropout * Expand https://github.com/onnx/onnx/blob/master/docs/Operators.md#expand Deduce the value of the shape operand by looking at the producer of the operand. Currently supported producers are: onnx.Constant and onnx.Shape. * Add corresponding tests for each op. * Sort the list of ops with shape inference in gen_onnx_mlir.py in alphabetic order for clarity. * Restart CI Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-07 13:08:00 +08:00
| ReduceMean | | v | v | | | |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| ReduceMin | | v | v | v | | |
| ReduceProd | | v | v | v | | |
| ReduceSum | | v | v | v | | |
Update SharingWork.md (#92)
2020-04-20 22:25:46 +08:00
| ReduceSumSquare| | v | | | | be decomposed into ReduceSum and Mul |
Update progress in SharingWork.md (#61) * sharing work migrated to issue * url * updated shared work Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-07 06:13:28 +08:00
| Relu | | v | v | v | | |
| Reshape | | v | v | v | | const only |
| Selu | | v | v | v | | |
| Sigmoid | | v | v | v | | |
| Sign | | v | v | v | | |
| Sinh | | v | v | v | | |
| Softmax | | v | v | v | | |
| Softplus | | v | v | v | | |
| Softsign | | v | v | v | | |
| Sqrt | | v | v | v | | |
| Sub | | v | v | v | | M |
| Sum | | v | v | v | | M V |
| Tanh | | v | v | v | | |
| Transpose | | v | v | v | | |
| Unsqueeze | | v | v | v | | |
| Xor | | v | v | v | | M |
### Extended functionality info (noXXX: additional work is needed).
* M / noM: multi-broadcast imlemented / not implemented
* U / noU: unidir-broadcast implemented / not implemented
* P / noP: padding implemented / not implemented
* V / noV: variadic input implemented / non implemented
# Operation not supported yet.
Please pick new operations to work on, and make sure you utilize current code to minimize additional work needed to support new functionality.
Typical sequence of work.
1. Ensure the operation is properly parsed from ONNX and MLIR input.
2. Perform shape inference.
3. Lower to KRNL dialect.
And add literal tests at each step, and end to end tests once completed.
| ONNX Operation | Person working on it | ONNX Def | Shape Inference | ONNX to KRNL | Basic Functionality | Extended functionality |
|----------------|-----------------|----|---|---|----|-------|
| ACos | | | | | | |
| ACosh | | | | | | |
| ArgMax | | | | | | |
| ArgMin | | | | | | |
| ASin | | | | | | |
| ASinh | | | | | | |
| ATan | | | | | | |
| ATanh | | | | | | |
| BitShift | | | | | | M |
| Ceil | | | | | | |
| Celu | | | | | | |
| Clip | | | | | | |
| Compress | | | | | | |
| ConcatFromSeq | | | | | | |
| ConstOfShape | | | | | | |
| ConvInt | | | | | | P |
| ConvTrans | | | | | | P |
| CumSum | | | | | | |
| DepthToSpace | | | | | | |
| DequantizeLin | | | | | | |
| Det | | | | | | |
| DynQuantizeLin | | | | | | |
| Einsum | | | | | | V |
| Equal | | | | | | M |
| EyeLike | | | | | | |
| Flatten | | | | | | |
| Floor | | | | | | |
| GRU | | | | | | |
| GatherElements | | | | | | |
| GatherND | | | | | | |
| GlobalAvgPool | | | | | | |
| GlobalLpPool | | | | | | |
| GlobalMaxPool | | | | | | |
| Greater | | | | | | M |
| GreaterOrEq | | | | | | M |
| HardMax | | | | | | |
| If | | | | | | V |
| InstanceNorm | | | | | | |
| Inverse | | | | | | |
| IsInf | | | | | | |
| IsNaN | | | | | | |
| Less | | | | | | M |
| LessOrEq | | | | | | M |
| LSTM | | | | | | |
| LSTM | | | | | | |
| LSTM | | | | | | |
| LogSoftmax | | | | | | |
| Loop | | | | | | V |
| LpNorm | | | | | | |
| LpPool | | | | | | |
| MatMulInteger | | | | | | U |
| MaxRoiPool | | | | | | |
| MaxUnpool | | | | | | |
| Mean | | | | | | M V |
| MeanSquareDist | | | | | | M |
| MeanVarNorm | | | | | | |
| Mod | | | | | | M |
| Multinomial | | | | | | |
| Neg | | | | | | |
| NegLogLikeLoss | | | | | | |
| NonMaxSupress | | | | | | |
| NonZero | | | | | | |
| Not | | | | | | |
| OneHot | | | | | | |
| PRelu | | | | | | U |
| QLinearConv | | | | | | P |
| QLinearMatMul | | | | | | M |
| QuantizeLinear | | | | | | |
| RNN | | | | | | |
| RandomNormal | | | | | | |
| RandNormalLike | | | | | | |
| RandUniform | | | | | | |
| RandUniformLike| | | | | | |
| Range | | | | | | |
| Resize | | | | | | |
| ReverseSequence| | | | | | |
| RoiAlign | | | | | | |
| Round | | | | | | |
| Scan | | | | | | V |
| Scatter | | | | | | deprecated for Scatter Element |
| ScatterElem | | | | | | |
| ScatterND | | | | | | |
| SequenceAt | | | | | | |
| SeqConstruct | | | | | | V |
| SequenceErase | | | | | | |
| SequenceInsert | | | | | | |
| SequenceLength | | | | | | |
| Shape | | | | | | |
| Shrink | | | | | | |
| Slice | | | | | | |
| SoftMaxCross | | | | | | |
| SpaceToDepth | | | | | | |
| Split | | | | | | V |
| SplitToSequence| | | | | | |
| Squeeze | | | | | | |
| StringNorm | | | | | | |
| Tan | | | | | | |
| TfldfVect | | | | | | |
| ThresholdRelu | | | | | | |
| Tile | | | | | | |
| TopK | | | | | | |
| UnfoldToDepth | | | | | | |
| Unique | | | | | | |
| Upsample | | | | | | deprecated |
| Where | | | | | | M |