Commit Graph

145 Commits

Author SHA1 Message Date
NathanielMcVicar 3491b90b1e
Support LLVM as of 7dcd0042 (#309)
* Update to support LLVM as of 7dcd0042

Fixes for upstream changes to mlir.

- New pass registration method from https://reviews.llvm.org/D85622
- Integer attributes are now C types when possible https://reviews.llvm.org/D86739

Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com>

* Fix for checkclang

* Windows incremental build fix from @max-ku

* Remove MLIRShapeToSCF lib

* Missed a getSExtValue on now c type

* Rebuild prereq docker.

* Bump CircleCI cache version.

* Update hash for Windows build

Signed-off-by: Nathaniel McVicar <namcvica@microsoft.com>

* Bump CircieCI cache version again.

* Rebuild prereq docker.

* Update README.md

* Update README.md

* Undo edits to ONNXOps.td.inc.

* Undo changes to ONNXOps.td.inc.

* Fix cast op TableGen.

* Tweak tablegen definition of Cast.

* Use explicitly signed integer as attributes.

* Move all signless attribute to explicitly signed attribute.

* Import ONNX int attribute as SI64 attribute.

* Make Conv.group attr use SI64 attr.

* Fix conv test.

* Fix DocCheck complaint.

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-22 23:42:50 +07:00
Prashant Kumar 4cc16aceb7
[MLIR] Add SizeOp conversion from ONNX dialect to Krnl dialect (#295)
* [MLIR] Add SizeOp conversion from ONNX dialect to Krnl dialect

Added ONNXSizeOp conversion from ONNX dialect to Krnl dialect. This op is added as a part of --convert-onnx-to-krnl pass.

Signed-off-by: Prashant Kumar <pk5561@gmail.com>

* Add unit tests for Size op.

* Remove unit tests.

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-21 16:55:21 +07:00
Tung D. Le 66074da3ac
Lower ONNXConstantOfShapeOp to Krnl dialect (#296)
* Lower ONNXConstantOfShapeOp to Krnl dialect

* Change a variable name

* Add comments to lit tests

Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
2020-09-19 12:47:39 -04:00
Alexandre Eichenberger 3a5aa7ee31
Gather ONNX to Kernel Lowering (#294)
* Define krnl.permute op.

* Support krnl.permute operation.

* Properly remove loop references.

* Re-push, Github was down.

* Need to debug interpretOp error.

* Fix lowering bug by erasing ops after full krnl IR interpretation is done, and clean up & comment code.

* Introduce permute, unroll operations.

* More debug.

* Remove std::set.

* krnl.terminate fails to be converted.

* Pass all tests, need to add legal ops as well as part of the conversion target.

* Change test format to new permute spec.

* Bug fix for nested iterate op lowering.

* Simplify error reporting.

* Fix compilation error.

* Increase comments coverage.

* Remove unnecessary imports.

* Re-trigger Jenkins

* Add permute/unroll tests.

* Retrigger Jenkins

* initial implementation of gather

* added tests

* format

* remove affine load for second load, as it uses an indirection

* changes suggested by reviewers

* remove backend tests until I can verify them locally

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-09-11 15:36:23 -04:00
chentong319 fa04c32a0c
ShapeInference for SizeOp (#299)
* add shape inference

* Revert "add shape inference"

This reverts commit f9d42f39e68e14b5648abccfc8617fff00244d16.

* shape inference

* test case

* format
2020-09-11 12:47:11 -05:00
chentong319 ac67900baf
Rewrite shape and size OP (#285)
* add shape inference

* Revert "add shape inference"

This reverts commit f9d42f39e68e14b5648abccfc8617fff00244d16.

* add rewrite rules

* test cases

* format

* add constraint

* response to review

* response to review
2020-09-10 14:46:00 -04:00
Tian Jin 5e11429d77
Dropout elimination & Conv Bugfix (#297)
* Dropout elimination.

* Test VGG19.

* Add shufflenet.

* Fix grouped convolution bug.

* Fix lit test failure.
2020-09-10 14:47:30 +08:00
Alexandre Eichenberger 8bfde7de4b
Transpose optimization (#280)
* Define krnl.permute op.

* Support krnl.permute operation.

* Properly remove loop references.

* Re-push, Github was down.

* Need to debug interpretOp error.

* Fix lowering bug by erasing ops after full krnl IR interpretation is done, and clean up & comment code.

* Introduce permute, unroll operations.

* More debug.

* Remove std::set.

* krnl.terminate fails to be converted.

* Pass all tests, need to add legal ops as well as part of the conversion target.

* Change test format to new permute spec.

* Bug fix for nested iterate op lowering.

* Simplify error reporting.

* Fix compilation error.

* Increase comments coverage.

* Remove unnecessary imports.

* Re-trigger Jenkins

* Add permute/unroll tests.

* Retrigger Jenkins

* transpose fusion and removal

* format

* fix comments

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-31 10:40:17 -04:00
Aman LaChapelle 24d0a2ac71
Add shape inference and names (#266)
* Add shape inference and names

 - Add shape inference for PRelu
 - Fix shape inference for group conv
   for ConvTranspose
 - Add input and output names for
   graphs (functions)
 - Add support for (u)int8 tensor
   attributes

* Fix format issues

* Revert formatting for gen_onnx_mlir.py

* Pads can have ArrayAttr and DenseElementsAttr so support both

* NumInputs is the number of graph inputs that don't have initializers

* Add test for 2D batchnorm

* Fix typo in define_loops in new 2d BN test

* Change 'name' to 'onnx_node_name'

* Fix Batchnorm for 2D I/O and add lowering test

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-08-27 15:46:27 -04:00
Tung D. Le 7c1e67898d
Fuse convolution and batch normalization (#253)
* Rewriting rule

* Fix formulas

* Reuse op results

* Const propagation for Div and Sqrt

* Explicitly use ONNXConstantOp

* Minor revise

* Const propagation for unsqueeze

* Do const propagationnce all tensors have inferred shapes

* LIT tests for fusion

* Add LIT tests for constant propagation on Div, Sqrt, and Unsqueeze

* Missing dash

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-18 16:41:40 +08:00
Anh Leu 00299910f3
OneHotEncoder Shape Inference (#265)
* move scalerop to decompose

* change clang format

* change clang format

* add shape inference for scaler op

* fixing generated onnxop

* generate onnx.md

* redo get onnx.md and onnxop.td.inc using onnx 1.6

* Add shape inference for scaler op

* add benefit for scaler decompose and simplify scaler shape inference

* add scaler decompose benefit num and simplify shape inference

* add cast builder

* cast rewrite only for float

* add cast op same type rewrite rule

* working on cast lowering

* cast lowering working

* add cast lowering

* fix format

* Delete OpBuildTable.inc

* complete requested changes

Co-authored-by: chentong319 <chentong@us.ibm.com>
2020-08-14 16:13:31 -04:00
Gheorghe-Teodor Bercea 2f41c2bf5b
Assorted fixes for memory pool related passes (#244)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Make mempooling more robust.

* Fix.

* Update MainUtils.cpp

Additional canonicalization not required anymore.
2020-08-11 17:34:59 -04:00
Anh Leu 2ee725d939
Add CastOp lowering (#259)
* move scalerop to decompose

* change clang format

* change clang format

* add shape inference for scaler op

* fixing generated onnxop

* generate onnx.md

* add benefit for scaler decompose and simplify scaler shape inference

* cast rewrite only for float

* add cast op same type rewrite rule

* working on cast lowering

* cast lowering working

* correct onnx version

* update onnx md

* add test for tensor<10xf64>
2020-08-11 16:07:13 -04:00
albertomagni-ms e1386b0689
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
Tian Jin 58ee62fb49
[NFC] Rename passes for stylistic consistency. (#232)
* lower-frontend -> convert-onnx-to-krnl

* lower-all-llvm -> convert-krnl-to-llvm

* lower-krnl -> convert-krnl-to-affine

* Name fix.
2020-07-31 21:37:35 +08:00
chentong319 b4228fd288
Seq type (#199)
* base implementation

* add example

* change table gen

* docs

* small change for review

Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-31 20:05:59 +08:00
Gheorghe-Teodor Bercea 029fb5eb67
Add support for emitting individual memory pools with dynamic sizes (#211)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Emit memory pools with dynamic sizes.

* Reformat.
2020-07-30 12:24:07 -04:00
Anh Leu a611c145f4
Add Rewrite rule to eliminate CastOp when input element type is the same as expected output element type (#237)
* move scalerop to decompose

* change clang format

* change clang format

* add shape inference for scaler op

* fixing generated onnxop

* generate onnx.md

* add benefit for scaler decompose and simplify scaler shape inference

* cast rewrite only for float

* add cast op same type rewrite rule

* fix format

Co-authored-by: chentong319 <chentong@us.ibm.com>
2020-07-27 12:49:14 -04:00
Anh Leu e631283c71
ScalerOp support non-float input using CastOp (#231)
* move scalerop to decompose

* change clang format

* change clang format

* add shape inference for scaler op

* fixing generated onnxop

* generate onnx.md

* redo get onnx.md and onnxop.td.inc using onnx 1.6

* Add shape inference for scaler op

* add benefit for scaler decompose and simplify scaler shape inference

* add scaler decompose benefit num and simplify shape inference

* add cast builder

Co-authored-by: chentong319 <chentong@us.ibm.com>
2020-07-24 10:57:52 -04:00
Anh Leu c9e3ba2d64
Add shape inference for ScalerOp (#228)
* move scalerop to decompose

* change clang format

* change clang format

* add shape inference for scaler op

* fixing generated onnxop

* generate onnx.md

* Add shape inference for scaler op

* add benefit for scaler decompose and simplify scaler shape inference
2020-07-23 13:05:19 -04:00
Tung D. Le 034f98c00c
Shape inference for some ops in RNN models (#207)
* Shape inference for ShapeOp

* Shape inference for TileOp

* Fix check-doc

* Fix onnx-mlir-doc

* Shape inference for GatherOp

* Check validity of GatherOp's indices tensor

* Shape inference for Slice

* Tests for SliceOp

* Fix importing none inputs

* Type inference for constantofshape

* Empty tensor in case of ConstantOfShape

* Remove unrelated changes

Co-authored-by: chentong319 <chentong@us.ibm.com>
2020-07-22 10:15:56 -04:00
Gheorghe-Teodor Bercea a58594ec81
Revert "Emit allocs at the top of functions (#222)" (#226)
This reverts commit b27e57cc4f.
2020-07-21 18:30:39 -04:00
Gheorghe-Teodor Bercea b27e57cc4f
Emit allocs at the top of functions (#222)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Add support for moving dynamic alloca instructions to top of functions.

* Fix memory pooling tests.

* Various fixes.

* Fix lit tests.

* More test fixes.

* Reformat.

* Reformat some more.

* Fix issue with TestConv and split-input-file.

* Use smart pointers.

* Remove redundant pointer.

* Reformat.

* Add initMap description.

* Clean up tests.
2020-07-20 19:24:17 -04:00
Anh Leu 4b33c312d6
Add ONNXScalerOp pattern (#220)
* add ONNXScalerOp pattern

* move ScalerOp rewrite rule to Rewrite.cpp .td

* attempt to fix format issue

* fixing format issue

* fixing format issue2

* add ONNXScalerOp pattern

* move ScalerOp rewrite rule to Rewrite.cpp .td

* attempt to fix format issue

* fixing format issue

* fixing format issue2
2020-07-17 11:01:30 -04:00
Gheorghe-Teodor Bercea 100bfc81b4
Bundle individual memory pools into a single memory pool (#183)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Add memory pooling for constant sized arrays.

* Clean code.

* Clean code.

* Clean code.

* Add simple bundling test.

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-08 12:35:31 -04:00
Tian Jin 01a4977c74
Remove optimize_loops/return_loops op. (#200)
* Remove optimize_loops/return_loops op in elementwise ops lowering and fix tests in onnx_lowering.mlir.

* Fix all tests.

* Remove all occurences of def_loops/return_loops.

* Fix test.

* Fix comments for defineLoops & emitKrnlLoopsAndIterationForOperand function.

* Remove emitOptimizedLoops.

* Allow not specifying optimizedLoops when creating KrnlIterateOperandPack.

* Fix style.

* Make BuildKernelLoop helper not emit optimize/return_loop operations & retire emitKrnlLoopsAndIterationForOperand by replacing it with BuildKernelLoop.

* DefineLoops -> DefineLoopsEx, remove redundant emitKrnlLoopsAndIterationForOperand function.

* BuildKrnlLoop API name update.

* Tweak comments.

* Remove unused withEmptyOptimization flag.

* Better comment for BuildKrnlLoop.

* Fully remove krnl.return_loops/optimize_loops op.

* Trigger Windows Build

* Bump windows ci python version.
2020-07-08 12:49:15 +08:00
Aaron Smith 8e6642b2bc
Update llvm version (#187)
* Update llvm version

* Update git hash for llvm-project

* Update option handling

* Update LLVM version

* Update tests

* Update git hash

* Update docs

* clang-format

* Fix operand adaptor

* Fix dim with constant

* Update LSTM.cpp

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-07 21:26:00 +08:00
Tung D. Le 7e05f371de
Replace std.load/std.store by affine.load/affine.store (#180)
* Move to more recent LLVM ID (May 15)

* clang-format

* Bump cache version up

* Update readme

* Fix doc check

* Move to a newer commit id

* Update LoopToStandard -> SCFToStandard

* Change MLIRSideEffects to MLIRSideEffectInterfaces

* Add AffineScope trait to KrnlIterateOp

* [ElementWise] Load/Store op to AffineLoad/AffineStore op

* [Gemm, MatMul, Reduction, Softmax] Load/Store op to AffineLoad/AffineStore op

* [Concat] Load/Store op to AffineLoad/AffineStore op

* [Pad, PadConstantValuePad, Reshape, Transpose] Load/Store op to AffineLoad/AffineStore op

* [LSTM] Load/Store op to AffineLoad/AffineStore op

* [Conv, Norm, Pooling] Load/Store op to AffineLoad/AffineStore op

* Add affine-loop-fusion pass

* Use Load/Store for scalar

* Use Load/Store for scalar

* Fix lit tests

* Unknown dimensions for broadcasting ops

* Affine Load/Store for scalar memref

* clang-format

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-05 16:20:21 +08:00
Tung D. Le 2c8f5701bd
Lower SqueezeOp to Krnl dialect (#164)
* Lower Squeeze op to Krnl dialect

* Emit tensor size as a single constant; add a lit test for unknown dimensions

* Code style

* Speical case where the input is only used by this squeeze op

* Remove squeeze-in-place optimization

* Update ConvertONNXToKrnl.cpp

Twek to re-run tests.

* Trigger buildbot re-run.

* Re-run CI

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-03 16:26:41 +08:00
chentong319 2e08b2112c
String type (Ready for Review) (#182)
* string type from tensorflow

* simplify type

* parser and print

* gen StringType for tablegen

* onnx to onnx-mlir type

* add namespace

* allow all integer type

* dialect document

* add test case

* format

* more precise type for ONNXOp

* format

* enable the failed test

* update comment

* update onnx.md

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-06-25 16:34:37 -04:00
chentong319 cc68f77d8d
Merge onnx ml into onnx (#176)
* merge onnx-ml into onnx

* delete onnx ml
2020-06-22 20:01:56 -04:00
chentong319 1fc43fa181
support map and seq in tablegen (#159)
* support map and seq in tablegen

* register MLONNX for testing

* format

* remove the unwanted test

* add a test

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-18 21:49:40 +08:00
Alexandre Eichenberger 82d2caa542
constant folding for transpose of constant tensors (#171)
* added constant folding for transpose of constant tensors

* format

* responding to reviews
2020-06-17 10:42:06 -04:00
Alexandre Eichenberger 742e817722
Constprop2 (#167)
* initial const prop attempt

* added support for broadcast ops

* adde all binary broadcast ops into custom builders with precise type

* added test example

* working

* format

* fixed suggestion by Tung, start woring on unary

* added subtraction and neg the right way, and added elementwise mul too

* formatting changes

* format

* format

* added instructions to add new optimizations

* added propagation rules that always migrate constants toward the root of the expression, using assoc and commutativity

* format comment
2020-06-15 14:56:15 -04:00
Tian Jin e0ae583da0
Compiling Models with Large Constant Arrays (#146)
* PoC works.

* MNist works.

* Clean up.

* Fix test.

* Make Linux work.

* Use consistent symbol name.

* Fix variable name.

* Fix array addr access.

* Bug fix.

* Bug fix.

* install before running e2e tests.

* Fix build config.

* Use sudo when installing.

* Make embeddedDataLoader position independent.

* Enable ResNet50.

* Format code.

* Format MainUtil.

* Try not using sudo to install.

* Supply runtime dir via environment variable.

* Dump problematic operation.

* Dump entire function.

* Debug.

* Dump input.

* Dump constant op.

* Debug.

* Debug.

* Debug.

* Print to stderr.

* take care of endianness.

* Use endianness-aware execution session.

* Fix ZLinux error.

* Include warning when desired output endianness can't be deduced.

* Remove debug code.

* Remove debug code in shape inference.

* Support binary-decoder for testing constants packing.

* Support filename, move-to-file, elision-threshold configurations in constant packing pass for easy testing.

* Add lit test, fix lit test type mismatch.

* Add more consts packing tests.

* Ensure intermediate files are properly cleaned up.

* No need for constant elimination.

* Link with threading libraries.

* Remove debug code.

* Format code.

* More tests.

* test nit.

* Remove debug code.

* Reduce hard-coded constants.

* Use temporary and unique working directory for hosting model parameters.

* Test if it works.

* Try to find objcopy.

* Rename symbols using objcopy.

* Move sanitized name to linux section.

* Use verbose mode for debugging.

* Disambiguate pass constructor.

* Fix symbol name.

* Use Command API to build and execute commands.

* Move linux to use Command API.

* Fix reset args.

* Execute redefine sym.

* Format code.

* Do not use verbose mode for CircleCI.

* Remove debug code.

* Prettify code, add comments.

* getSegmentData -> getEmbeddedConstPool

* vector -> std::vector.

* Make sure we properly clean up intermediate files.

* Fix test cases.

* Add runtime directory.

* Trigger rebuild.

* [Merge with master] fix debug script.

* Diable affine fusion pass for now.

* Support generic fallback const packing mechanism.

* Remove debug code.

* Handle the case where objcopy is not available.

* Fix Windows missing types.

* Support int64.

* Copy packed constant to a local directory for non-Linux/Mac platforms.

* Nit: remove debug code, refactor const pack preprocessing out as a separate function.

* Cannot make preprocessConstPack a standalone function because file removers are stack-allocated, and they are deallocated prematurely when function stack gets popped, deleteing intermediate files too early.

* Don't require executable filename.

* Import ONNX data types directly.

* Fix LIT test.

* Bug fix, use moved string value.

* Remove redundant filenames.

* Fix CMake script.

* Embed endianness information as a symbol, and check during runtime.

* More comments, update lit tests.

* Fix lit test on BE machine.

* Copyright notices.
2020-06-12 10:27:05 +08:00
Tung D. Le 8c4d527eea
Lower SplitOp to Krnl dialect (#155)
* Fix importing variadic output

* Lower splitop

* Support unknown dimension and add lit tests

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-11 10:57:20 +08:00
Gheorghe-Teodor Bercea 4ab96fbc6c
Add basic support for memory pool (#161)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Replace internal malloc with memory pool and getref instruction.

* Lower krnl.getref to LLVM.

* Fix formatting issues.

* Add tests.

* Add missing dependency.

* Improve LLVM lowering.

* Add test to show getref is generic.
2020-06-09 16:48:33 -04:00
Aman LaChapelle ca185002f2
Add shape inference for several ops (#163)
* 1. Add shape inference for the following ops:
 - Atan
 - Tan
 - Sin
 - Cast
 - ConvTranspose
 - Flatten
 - DynamicQuantizeLinear
 - QuantizeLinear
 - DequantizeLinear
 - ConvInteger

2. Import attributes for generic nodes
3. Fixes for cases where .cast<> should be .isa<> (ONNXConcat::inferShapes)

* Fix foormatting issues

* Address comments:
 - SmallVector<> * -> SmallVectorImpl<> &
 - switch-case -> helper function
   - Inside helper function, preserve signed-ness
 - add TODOs

* Can't use signed integers yet in convertONNXTypeToMLIRType, add TODO

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-09 14:55:49 +08:00
Alexandre Eichenberger e2af505746
Constprop (#162)
* initial const prop attempt

* added support for broadcast ops

* adde all binary broadcast ops into custom builders with precise type

* added test example

* working

* format

* fixed suggestion by Tung, start woring on unary

* added subtraction and neg the right way, and added elementwise mul too

* formatting changes

* format

* format

* added instructions to add new optimizations
2020-06-08 15:45:32 -04:00
Tung D. Le bb17fa965f
Add AffineScope trait to KrnlIterateOp and enable affine-loop-fusion pass (#140)
* Make KrnlIterate's IVs valid to AffineLoad/AffineStore

* [Unary elementwise op] Load/Store -> AffineLoad/AffineStore

* [Conv] Load/Store -> AffineLoad/AffineStore

* Add affine-loop-fusion pass

* typos

* Mistake when merging branch master

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-06-08 15:36:27 +08:00
Alexandre Eichenberger 20dd6544aa
conv bug fix (#154) 2020-05-28 07:34:58 +08:00
chentong319 6099efd91b
Express some basic features of an Operation in TableGen file (#103)
* change operation definition

* change importer

* default type inference

* file format

* generate types for input/output

* generate the mapping for operation output type

* remove debug message for gen_doc.py

* update the dialect doc

* add support Complex

* format

* update document

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-05-21 22:03:16 -04:00
chentong319 23bea50404
Implement PadOp based on attribute promotion (#71)
* enable promote attr for pad

* use optional arguments for pad

* shape infereance for pad

* Lowering Pad

* format file

* use DenseTensor for the attribute

* use Pad in ONNXRewrite

* fix the merge conflict

* fix the attr given to constantOp

* handle ONNXConstantOp in attribute promotion

* Fix bug when AttributePromotion is called more than once

* update ONNXOps.td.inc with correct version of onnx

* update onnx.md

* responses to review

* fix the build error

* change the implementation of Pad

* delete commented out code

* clang format

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-05-15 13:19:28 +08:00
Tung D. Le 4d8b855c17
Unify codes in shape inference and conversion (#98)
* Use AffineMap

* Shared AffineMap

* AffineMap for Conv/Pooling

* Create helper files

* Remove changes for Relu

* Remove redundant includes

* Use AffineMap for AveragePool's shape inference

* Add MLIR tests for unknown dimension case

* Extract a method AffineMapIntConstant

* Comment stylist and include path

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-05-14 17:31:33 +08:00
Tung D. Le d65a6e72dd
Specialize the op lowering logic for element-wise operations (#118)
* Specialize the op lowering logic for elementwise operations

* Fix clang-format error.

* Update tests for LSTM since LSTM uses element-wise ops

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-05-14 13:00:15 +08:00
Tung D. Le 24343177b8
Lower LSTMOp to Krnl dialect (#73)
* Support dilations and enable e2e tests

* Fix allocating memory for dynamic shape

* Edit comments

* Do dilation by computing an offset from kernel index

* Correct dilation formula, add an example of out-of-bound, and add a test for dilation

* Import optional outputs as NoneType

* Shape inference for ONNXLSTM

* Edit ONNXLSTM::inferShape()

* Shape inference for ONNXLSTMOp

* Create a common function for inferring shape for RNN ops

* CheckInsertDeallocation for a specific result

* Allocate memory for LSTM

* First round of lowering

* Allocate memory for hidden and cell states

* Test with custom Tanh

* Fix an error in Ct's formula

* Add E2E tests

* Return outputs

* Refactor the code

* Enable E2E tests

* Support reverse and bidirectional directions

* Minor revision

* Return all intermediate hidden states

* Call existing activation functions

* Structs for activation functions

* Call existing activations in ONNX

* Minor revision

* Compare strings ignoring case

* Use memreftype of rank 0 for calling activation functions

* Fix getActivationPack()

* Revise the code

* Add one MLIR test

* Add MLIR tests for reverse and bidirectional modes

* Make the order of emiting instructions deterministic

* Use OperandAdaptor instead of directly use an operand index

* Use literal assignments

* Change some variable names

* Use literal assignments

* Use literal assignments

* Format the code

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-05-13 21:08:06 +08:00
Tung D. Le 9a874007ce
Implement shape inference for SplitOp (#95)
* Implement shape inference for SplitOp

* Change spitOpt to SplitAttribute and check the axis range before updating the axis attribute

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-05-13 18:07:27 +08:00
Tung D. Le 64ed03295f
Fix converting type for functions with no argument (#96)
* Fix converting type for functions with no argument

* Add two tests

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-27 11:01:51 -04:00
Gheorghe-Teodor Bercea 137ce767e6
Rework output to improve readability of intermediate MLIR code. (#87)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Output of non-value constants. Write full source to file.

* Fix e2e tests.

* Output constant free and full code in separate files.

* Emit separate files.

* Move file output management to utils.

* Elide the values of glotbal krnl constants.

* Add dual file output for Basic flag.

* Add tests.

* Add passes to cmake file.
2020-04-24 16:15:36 -04:00
Tung D. Le eac2297624
Lower MaxPooling and AveragePool to Krnl dialect using AffineMap (#38)
* Create a template for pooling and add support for AveragePool

* Edit MLIR tests for MaxPool according to the new lowering template for pooling

* Dealloc temporary variables

* Support count_include_pad for AveragePool

* Add MLIR tests for AveragePool lowering

* Make changes according to Tian's comments

* Push AffineMap as upper bound for KrnlIterateOp

* Test AffineMap to use in Pooling

* Replace the old implementaion by a new one using AffineMap

* Fix the computation when dilations are non-unit

* Clean up the old code

* Remove AveragePool from Canonicalization pass

* Fix computing the end indices of a filter window

* Refactor the code for pooling

* Revise pushAffineMapBound

* Add MLIR tests

* Remove unused functions

* Fix check-onnx-backend build on x86 Linux. (#91)

* Add the split marker to test files (#90)

Co-authored-by: Tian Jin <tjingrant@gmail.com>

Co-authored-by: gongsu832 <gong_su@hotmail.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-04-19 21:39:34 +08:00