Commit Graph

39 Commits

Author SHA1 Message Date
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
Tian Jin cde1157d62
Rapid check test (#141)
* Call llc, ld from within onnx-mlir.

* Rename EmitLLVMBC -> EmitLib., reorder header files

* Edit comment.

* Checkpoint, debug.py works.

* Automatically generate inputs in debug.py.

* Use float.

* initial support for rapidcheck tests.

* Convolution test case works.

* Format code.

* Link library with MainUtils.

* Fix CMake script error.

* Fast implementation of array assertion, more detailed error analysis.

* More utility for DynMemRef.

* Fix linking issue.

* Uncomment unit test.

* Refactor to separate C++/Python ExecutionSession, enable unit test.

* format code.

* Verbose build.

* Enable PIC option for ExecusionSession.

* Fix cmake error.

* Build all targets.

* Fix doc to build all targets.

* Clean up.

* Clean up, debug.

* Use type alias consistently.

* Move definitions to DynMemRef.cpp.

* include algorithm.

* pyruntime -> PyRuntime

* Format code.

* Free memory.

* Add comments.

* Copyright notice.

* Improve stylistic consistency.

* Add comment.

* Revert irrelevant changes.

* Disambiguate.

* Refator test case generator out from test case implementation, implement example exhaustive test driver.

* Add documentation for testing.
2020-06-08 10:18:55 +08:00
Tian Jin 4cdc0873ca
Call llc, ld from within onnx-mlir. (#127)
* Call llc, ld from within onnx-mlir.

* Rename EmitLLVMBC -> EmitLib., reorder header files

* Edit comment.

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-05-19 10:15:48 +08:00
Tian Jin adc08fb93e
Specify in linking stage, where runtime shared library is located. (#120)
* Specify in linking stage, where runtime shared library is located.

* Cite & make comment a full sentence.

* Fix error communicating runtime dir to ld.
2020-05-14 09:04:16 +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
Gheorghe-Teodor Bercea f5f336db08
Fix running backend tests triggered by preloading cruntime dynamic library (#104)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Fix preloading of runtime shared library for backend tests.

* Update library name.

* Only add libstdc++ library if it exists.
2020-05-04 08:37:58 -04:00
Tian Jin fad2ad7d03
Make onnx-mlir work with latest mlir. (#93)
* Make onnx-mlir work with latest mlir.

* Bump CircleCI cache version.

* Fix missing passes in onnx-mlir-opt.

* Fix backend test failure.

* Fix doc.

* Fix doc and exclude the generated _site directory from DocCheck.

* Remove debug code.

* Do not hard code target name, on Mac shared lib can end with .dylib.

* FunctionPass -> PassWrapper.
2020-04-27 17:03:56 +08:00
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
gongsu832 72de6eb004
Fix check-onnx-backend build on x86 Linux. (#91) 2020-04-16 14:38:52 +08:00
Alexandre Eichenberger fa8962753c
Concat lower (#82)
* implement shape inference for concat

* better checking of axis being concatenated: constant values only

* lowering of Concat with lit and backend tests

* fixes

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-04-13 11:40:39 -04:00
Tung D. Le f4fefcf713
Re-add tanh lowering (#75)
* Re-add tanh lowering

* Make the emission deterministic
2020-04-09 14:22:36 +08:00
Alexandre Eichenberger 844dcd8b1f
Name change for tests, to be check-onnx-(lit | backend) (#62) 2020-03-31 10:06:14 -04:00
Tung D. Le 2814ea3898
Support dilations and enable the remaining e2e tests for MaxPoolSingleOut (#31)
* 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

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-03-18 09:55:50 -04:00
Tung D. Le 4763e8a8bc
Lower ONNXAbsOp to Krnl dialect and enable e2e tests for ONNXReduceL1 (#18)
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-03-17 11:12:45 -04:00
Gheorghe-Teodor Bercea 1622b9f161
[NFC] Change ONNF based names to ONNX-MLIR (#32)
* Rename onnf to onnx-mlir.

* Change workspace name.
2020-03-17 09:16:33 -04:00
Gheorghe-Teodor Bercea e4c23da4fd
Lower MaxPoolSingleOutOp to Krnl dialect (#1)
* Lower MaxPoolSingleOutOp to Krnl dialect

* Edit comments

* Update changes according to the new folder structure

* Add MLIR tests

* Support ceil_mode

* Merge the first two krnl loops into one krnl loop; remove attribute checks

* Dynamically allocate memory for the result if the result has unknown dimensions

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-03-04 14:27:21 -05:00
Tung D. Le aea6479ad3
Lower BatchNormalization (test mode) to Krnl dialect (#70)
* Add ONNXBatchNormalizationTestModeOp and its shape inference

* Lower batchnormalization test mode

* re-use scale, bias, mean, and variance

* Add MLIR tests

* Add e2e tests

* fix typos

* Fix a bug in MLIR tests

* Change type from int to int64_t for indices

* Uncomment e2e tests due to segmentation fault

* Uncomment e2e tests due to segmentation fault

* Revise the code

* [Tian] Fix segmentation fault in e2e tests

* Re-generate onnx.md to include BatchNormalizationTestModeOp

* Reverse an unintentional change

* Fix some typos in comments

* Use convertToMemRefType from the master branch

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-02-20 11:45:40 -05:00
Tung D. Le f1d20e368f
Add support of GemmNoBias (#91)
* Add support of GemmNoBias

* Fix a wrong indentation
2020-02-20 10:55:24 -05:00
Tung D. Le b521719587
Lower Matmul operation to Krnl dialect (#57)
* Allocate memory for matmul's result

* Group cases

* Add support of N-D x N-D, N>=2

* Revise createIterateOperandPack

* Add 1-D x 1-D

* Add 1-D x N-D

* Add MLIR tests

* Change variable names

* Change type from int to int64_t for indices

* Change variable names

* Change int64_t back to int

* Change int64_t back to int

* Change int64_t back to int

* Use decltype

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-02-14 10:43:17 -05:00
Tian Jin 937bbec265
Fix scalar entry point parameter lowering issue. (#78)
* Fix scalar entry point parameter lowering issue.

* Enable scalar bias test.

* Nit. Improve comments and remove debug code.

* Make helper function static, move to upfront position.

* Move helper function to top of the file.

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-02-13 13:50:05 +08:00
Tung D. Le e5677bba1f
Add e2e tests related to Reduction Ops (#79) 2020-02-12 16:40:32 +08:00
Gheorghe-Teodor Bercea 094be4f37a
Add support for strides when emitting convolution loop nest. (#76)
* Add support for strides when emitting convolution loop nest.

* Only emit stride multiplication if strides is greater than one.

* Add test.
2020-02-11 11:53:13 -05:00
Tung D. Le adad9e24bd
Add support of negative dimensions (#66)
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-02-11 10:37:47 -05:00
Tung D. Le 2c7046ff5f
Lowering ReductionMax, ReductionMin, ReductionProd and ReductionSum (#31)
* Shape inference for reduction

* Lower ReduceSum

* Support list-like attributes

* Add ReduceMax, ReduceMin, ReduceProd

* Add tests

* Emit errors for unsupported types

* Typos

* Add backend test

* Fix axis computation

* Update the use of attributes

* Use SmallVector

* Address stylistic comments

* Change type from int to int64_t for indices

* Change type from int to int64_t for indices
2020-02-10 21:38:19 +08:00
Gheorghe-Teodor Bercea 0272451521
Lower convolution to KRNL dialect. (#65)
* Ensure data shape is at least 4.

* First version of convolution.

* Simplify code for KRNL lowering.

* Add test without padding or strides.

* Refactor code for lowering frontend operations to KRNL dialect.

* Add test for conv with no bias and no padding.

* Add test with group greater than one.

* Address comment.
2020-02-07 16:51:32 -05:00
Haruki Imai 477227a0ec
Added lowering of SignOp (#21)
* Support lowering of SignOp

* Fixed test code for signop of integer input

* Inserted Sigh and Reciprocal in SharingWork.md (Reciprocal is for past commit 7e3f96e)

* Added test for Sign Op

* Fixed minus_one -> minusOne

* Fixed test for signop
2020-02-04 22:27:17 +08:00
Gheorghe-Teodor Bercea 9fb826ae7e
Lower transpose operation to KRNL dialect (#54)
* Lower transpose operation.

* Fix IndetityOp.

* Add tests.

* Add backend tests.

* Clean-up code.

* Move transpose code and improve comment.
2020-01-30 11:44:56 -05:00
Tung D. Le 400676e371
Lowering Gemm (#19)
* Initial implementation

* Support transposing inputs

* Revise unidirectional broadcasting and unknown dimensions

* Revise gemm

* Add testcase

* Rename some variables

* Update SharingWork.md

* Change from the use of Value* to Value

* Insert deallocation

* Initilize the output matrix and fix wrong computation

* Add end-to-end testcases

* Edit lowering tests

* Change attribute names

* Use emplace_push for SmallVector

* Use the new way of getting attributes

* Revise the use of attributes

* Check the bias's shape

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-01-29 11:11:49 -05:00
Tung D. Le 9e82d388f0
Add support for Unsqueeze (#50)
* Infer shape for Unsqueeze

* Lower Unsqueeze

* Revise

* Turn off backend tests

* Compute tensorSize for static shape

* Compute tensorSize with unknown dims

* Edit tests

* Update the use of attributes

* Add e2e tests

* Use SmallVector

* Remove return

* Check whether the operand is ranked or not

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-01-29 10:46:02 -05:00
Tung D. Le 5b44169aaa
Support dimension zero in reshape (#55)
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-01-29 10:41:09 -05:00
Tung D. Le 195bf9d15d Add KrnlSqrtOp (#22)
* Initial lowering of KrnlSqrtOp

* Fix errors and add a testcase

* typos

* Add the MLIR example

* Restore doc/doc_check/CMakeLists.txt

* Clean the code

* Edit comments

* Remove redundant parts

* Chang the use of -> to .

* Add a test for f64

* Support ONNXSqrtOp

* Fix indentation

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
2020-01-28 11:10:47 -05:00
Gheorghe-Teodor Bercea f00206cecf
Fix reshape op. (#53) 2020-01-28 10:21:08 -05:00
Tung D. Le 7c889548a7 Allow importing variadic inputs/outputs of onnx operators (#16)
* Allow importing variadic inputs/outputs of onnx operators

* Enable testcases for variadic ops

* Modify gen_doc.py
2020-01-28 21:48:11 +08:00
Yasushi Negishi 383a5c31ac Support Softplus and Softsign operations (#17)
* Support Softplus and Softsign operations

* Add the default shape inference for the transposition operation.

* Fix conflict with master

* Fix conflict with master branch

* Add test for softplus and softsign in test/backend/test.py

* Re-enable Reciprocal tests.

Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-01-23 21:18:38 -07:00
Tian Jin ff0e25fdc9 Re-enable Reciprocal tests. 2020-01-21 19:41:22 -07:00
Tung D. Le e89e51699b Lowering softmax (#14)
* Rebase

* Use max normalization

* Handle axis

* Add tests

* Update SharingWork.md

* Remove redundant spaces

* Format code

* Rebase

* Change from the use of Value* to Value

* Add end-to-end tests

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-01-20 21:57:32 -05:00
Tian Jin 8665ecd998
Enable e2e tests (#29)
* Sync with latest MLIR.

* Enable ONNX backend tests as a means to test ONNF lowering end-to-end.

* Install ONNX using quiet mode.

* Remove debug comments.

* Install ONNX from third_party/onnx.

* Check python version and fix pip command for installing ONNX.

* Using --user install option to prevent permission denied.

* Remove unused imports.

* Try using stock ONNX pip package as there are more tests in them.

* Pip got stuck building wheels, try sudo.

* Use verbose install to debug.

* Invalidate cache to build LLVM tools.

* Fix mlir installation script location.

* Debug to locate ONNF.

* Sanity check.

* Check out ONNF code first.

* Use verbose LIT output.

* 1. Update documentation to always use verbose LIT.
2. Update krnl ops to reflect new affine map attribute syntax.

* See if conda exists

* Install ONNX by manually cloning the repo.

* Install cmake first.

* Using sudo priviledge when installing.

* Limit build parallelism.

* Limit parallelism.

* Larger memory.

* Install onnx package with pip.

* Build MLIR tools.

* Invalidate cache.

* Compile model.so with -fPIC.

* Remove module dump to get concise debug output.

* Print command before executing.

* Use quiet install mode to reduce logging.

* Use -relocation-model=pic to generate position independent code.

* 1. Remove MAKEFLAGS because now buildbot has enough memory.
2. Run DocCheck as a last step.

* 1. Add verbose mode for backtend test.

* When dumping to LLVM bitcode, do not dump module IR, but print a message indicating that bitcode has been written to disk.

* Do not pass MakeFlags to CMake.

* Add more explaination for posible reasons of failing to identify tests.
2020-01-20 12:30:08 -05:00