Commit Graph

7 Commits

Author SHA1 Message Date
gongsu832 81c774ba5b
Cleanup rtmemref api (#238)
* Detect llvm-project commit change in utils/clone-mlir.sh and rebuild llvm-project
for zLinux Jenkins build bot

* Cleanup RtMemRef API

-  use forward declaration to hide private data fields
-  RtMemRef.h: external user header, C/C++
- _RtMemRef.h: internal user header, C++ only
-  RtMemRef.hpp and RtMemRef.cpp: implementation header and file
-  add external APIs
       OrderedRtMemRefDict *ormrd_create(RtMemRef **rmrs, int n)
       RtMemRef **ormrd_getRmrs(OrderedRtMemRefDict *ormrd)
       int ormrd_getNumOfRmrs(OrderedRtMemRefDict *ormrd)
   for creating and querying OrderedRtMemRefDict with RtMemRef arrays
-  data buffer installed by rmr_setData() will be managed by user
-  unique_ptr<RtMemRef> must use custom deleter <RtMemRef,decltype(&rmr_destroy)>

* See if I have write access.

* Remove test CMake code.

* Use new API.

* Format code.

* Format code & rename variables for readability.

* Remove used API spec.

* Rename OrderedRtMemRefDict -> RtMemRefList, _dataMalloc -> _owningData.

* OrderedRtMemRefDict -> RtMemRefList

* Update KrnlToLLVM.cpp

* Trigger Jenkins

* Restart Jenkins

* OrderedRtMemRefDict -> RtRmrRefList

* More OrderedRtMemRefDict -> RtMemRefList.

* Format jni wrapper.

* Rename API functions to maintain stylistic consistency.

* Bug fix.

* Bug fix.

* Format code.

* Fix RtMemRefUtils.

* Format code.

* Using llvm function naming scheme.

* Rename runtime api file name to project name (onnx-mlir) as per convention.

* Include the new runtime header file.

* Reflect api header file name change in build script.

* Bug fix.

* Remove C++ code.

* Revert "Remove C++ code."

This reverts commit b217dfabae99e42db30721600cb5507866d4dc98.

* Clarify memory management responsibility.

* Add constructor to specify name & data ownership.

* Include stdbool.

* Remove dictionary semantics from RtMemRefList

* Bug fix.

* Format code.

* Format code.

* Use macro to define database of metadata.

* Prevent formatter from acting on metadata decl.

* Nit.

* Restore backend unit tests.

* Use spaces instead of tabs for better formatting.

* Use explicit template instantiation.

* Update RtMemRef struct doc.

* Make runtime compilable both in c and c++ mode.
Build two versions of the runtime library, one c version as the user-facing c runtime, and one c++ version as the one used inside this project.

* Bug fix, avoid stack allocation for output rmr list.

* Change _dyn_entry_point_main_graph -> run_main_graph for better memorability.

* Write a complete introductory tutorial on c99 Runtime and a test for it.

* Add onnx installation as dependency.

* Use target_include_directory to avoid installation.

* Format code.

* Fix cmake target_include_directories.

* Address compiler warning.

* First pass of RtMemRef->OMTensor.

* Second pass of RtMemRef -> OMTensor.

* nit, omtList -> omTensorList.

* omt -> omTensor for clarity.

* Rename OnnxMlirInternal.h -> OnnxMlirRuntime.hpp because there's no internal/external API, only C/C++ API.

* Format code.

* Restructure Runtime source code and move header -> /include and test -> /test/unit.

* Bugfix.

* Format code.

* Add unit test for OMTensor ctor.

* Update JNI CMake include directory.

* Bugfix.

* No need to re-declare ONNX types.

* Disable runtime doc test on non-x86 platforms.

* Rename OMTensor fields to be more sensible.

* Fix data type mismatch.

* size_t -> int64_t, prefer fixed width integers.

* Use consistent header guard style.

* Further tweak OMTensor API.

* Bugfix.

* Bugfix.

* Format code.

* Add doxygen config file.

* Tweak OMTensor API.

* Tweak API doc, hide OMTensorList implementation.

* Format code.

* Add new documentation item for Runtime API.

* Hide internal use only API declarations, move their comments to their implementations.

* Clarify ownership semantics in relevant API documentations.

* Fix PyRuntime.

* Remove alignment concerns from public API and include explaination of alignment issue in struct OMTensor definition.

* Print out unsupported numpy dtype.

* Use preferred way of type comparison in pybind11.

* Debug s390x issue.

* Remove debug code.

* Clarify semantics of strides/shape setter/getter, use \brief to include short description of API function.

* Improve documentation.

* Single out unpolished C++ API declarations.

* Clarify OMTensorList API.

* Bugfix.

* Bugfix.

* Assert after malloc.

* Handle malloc failures.

* Nit.

* Tweak legal notices.

* Format code.

* Remove doxygen generated files.

* Tweak legal notice format.

* Upgrade Cython

Numpy installation depends on Cython.

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-10-10 10:32:09 -04:00
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
Tian Jin dbc41d2330
Update llvm commit ID to 1d01fc1 (#292)
* Fix for LLVM revision D85495

* Fix for LLVM revision DD86121

* Fix for LLVM revision D85622 (f9dc2b7)
TODO: Change preloadDialectsInContext to false

Memo for previous fixes: D86121 (250f43d), D85495 (575b22b)

* clang-format

* Update llvm commit ID of README and clone-mlir.sh

* Updated llvm commit ID of README.md

* Fix for passing backend tests

* Removed the commented code

* Empty commit for triggering rebuild

* Test multi-stage travis build

* Specify stage order.

* Empty commit for triggering rebuild

* Update prereq.s390x.Dockerfile

Make it possible to execute s390x prereq docker multiple times.

* Build prereq for each arch

* Fix multi-arch prereq build.

* timeout at 40m

* Update .travis.yml

* add ppc64le prereq builder

* Run ppc docker prereq build multiple times

* Do not test branch update unless it's mater.

* Fix dockerfile.

* Fix typo in travis.yml.

* Fix ppc64 docker file

* Update .travis.yml

* turn off metacopy on ppc64le

* Update .travis.yml

* Turn off metacopy.

* Turn off metacopy inside Dockerfile in ppc64.

* No sudo in Docker.

* Remove metacopy config from Dockerfile.

* Change base image to be bionic.

* Using newer linux distro for ppc64.

* Turn off metacopy in before_install.

* Fix sudo permission issue.

* Run docker info.

* Allow amd64 docker file to be built multiple times

* Support building amd64 prereq.

* Fix amd64 docker file typo.

* fix ppc64le dockerfile typo.

* timeout from 40m -> 30m

* 40m->30m

* 40m->30m

* fix bug preventing incremental build.

* fix bug preventing incremental build.

* Bump CircleCI cache version.

* Push to production prereq container repository and condition prereq docker rebuild on commit message.

* Rebuild prereq docker.

* Move default script to top-level.

* Python not properly installed.

* amd64 -> x86

* Rebuild prereq docker.

* Rebuild prereq docker.

* Rebuild prereq docker.

* Restart all CI.

* Disallow cache on Jenkins docker build.

* Restart zJenkins.

* Restart zJenkins.

Co-authored-by: Haruki Imai <imaihal@jp.ibm.com>
Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
2020-09-09 23:12:01 +08:00
gongsu832 d235f248e4
Add emitjni target (#204)
* Detect llvm-project commit change in utils/clone-mlir.sh and rebuild llvm-project
for zLinux Jenkins build bot

* Add --EmitJNI target (tested working with mnist and resnet50)
- MainUtils
  * first shot at refactoring compileModuleToSharedLibrary
  * add setExecPath call to allow resolving runtime directory from onnx-mlir
    executable path when ONNX_MLIR_RUNTIME_DIR is not set. This allows
    tests to run without having to install onnx-mlir or to explicitly set
    ONNX_MLIR_RUNTIME_DIR
- RtMemRef
  * add getDataSize for C (equivalent of size() for C++).
  * fix setStrides bug (setting sizes, not strides)
- TestConv
  * _main_graph-*.so were filling up /tmp. Change to use fixed shared library
    in build directory

* Fix clang-format-lint complaints

* - getRuntimeDir checks lib64
- install targets for javaruntime and jniruntime
- remove ONNX_MLIR_LD_PRELOAD_onnx-mlir and ONNX_MLIR_LD_PRELOAD_onnx-mlir-opt

* See what happens when `kExecPath` decl is dropped.

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-11 13:23:13 +08:00
Tian Jin e902506ee5
Support encoding data type infomration as part of the DMR struct. (#178)
* Support encoding data type infomration as part of the DMR struct.

* Support full range of np types.

* Report error when encountering unsupported type.

* Add gerRank method API.

* Add missing API declarations.

* DynMemRef -> RtMemRef

* Format code.

* Missed DynMemRef -> RtMemRef conversion.

* More comments for RMR, and rename variable names from dmr -> rmr.

* DynMemRef -> RtMemRef.

* Format code.
2020-06-30 10:58:21 +08:00
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
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