Commit Graph

445 Commits

Author SHA1 Message Date
Tung D. Le 1b42d0b4eb
Update LLVM commit ID to the version that corresponds to MLIR News, 13th edition (8/7/2020) (#248)
* Update LLVM commit ID to include to the new modeling of LLVM type in MLIR

* Fix commit id discrepancy

* Update README.md

* Update MLIR version

* Force rebuild prereq dockers and see what happens.

* Use LLVM commit ID that corresponds to MLIR News, 13th edition (8/7/2020)

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-08-14 12:52:48 +08:00
Lsz c7b5eecc7f
Added builder case for int8 tensors in the dialect (#263) 2020-08-13 09:16:27 -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
Chun-Wei Chen 20686d8f0f
Catch build failure on Windows-CI (Azure Pipelines) (#241)
* catch errors after build command

* remove spaces

* use %ERRORLEVEL% instead

* move modification to CI command only

* add extra nextline to prevent modification
2020-08-06 16:53:59 +08:00
Tung D. Le dbe0d734b5
Call LLVM opt to optimize bitcode (#245)
* Call LLVM opt to optimize bitcode

* Rename variables
2020-08-03 11:46:21 +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
Tian Jin 8e8f894574
Update CMakeLists.txt (#240) 2020-07-31 16:36:03 +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
Masahiro H 4db3edc025
include stdlib.h on macOS (#236)
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-30 16:48:31 +08:00
gongsu832 7a2bb1f2a3
Fix mainutils win32 (#239)
* Detect llvm-project commit change in utils/clone-mlir.sh and rebuild llvm-project
for zLinux Jenkins build bot

* Fix MainUtils.cpp compilation on Windows

* Fix clang-format

* Update comments on Windows not to delete the constant pack object file
2020-07-29 21:31:30 +08:00
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
chentong319 32ceb6968a
Use map when Import onnx node (#230)
* add map

* generate map
2020-07-27 12:25:21 -04:00
Kevin O'Brien 8af5fdeb62
fix comment (#229)
* fix comment

* add the .inc files to the PR
2020-07-24 17:03:08 -04:00
Kevin O'Brien 75716baa2f
use secret instead of token (#233)
I fixed the github action that builds the prereq, but I forgot to fix this one
2020-07-24 13:31:43 -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
Tian Jin 2e8f012195
Support krnl loop permutation (#215)
* 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

* Using a non-trivial example.

* Add more complex example/test case.
2020-07-24 18:19:38 +08:00
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
NathanielMcVicar 1263d01968
Add PIC property to RtMemRefUtils (#225)
Co-authored-by: Gheorghe-Teodor Bercea <gt.bercea@gmail.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-22 14:15:25 +08:00
chentong319 f43f26a79c
modify builder (#214) 2020-07-21 22:05:18 -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
chentong319 13b8591af8
add AnyMemRef (#219) 2020-07-14 11:15:06 -04:00
Tung D. Le 0df421f7ad
Fix importing none inputs (#217) 2020-07-14 10:06:58 -04:00
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
Gheorghe-Teodor Bercea af75b4c75e
Add selected MLIR options (#213)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Add selected MLIR passes.

* Refactor.

* Fix descriptions.

* Refactor.
2020-07-09 18:12:57 -04:00
Kevin O'Brien c557bd3444
remove access toke, use secret instead (#212) 2020-07-09 15:32:06 -04:00
chentong319 8848464a23
changes for mypipeline.onnx (#202)
* changes for mypipeline.onnx

* format

* rm MLOpBuildTable.inc

* copy string without free

* fix the memory issue

* restore change for STRING

* format

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-08 16:52:56 -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
Tung D. Le 0a936edf79
Remove ImportNodeReshape (#208) 2020-07-08 10:27:14 -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
Kevin O'Brien 07757a28ce
Mention how to change LLVM commit level (#210) 2020-07-07 16:43:01 -04:00
Kevin O'Brien 0d375dd75e
allow build of prereq docker image on forks (#209)
* push to GITHUB_ACTOR in Docker Hub

* forcing change to cause rebuild

* ditto

* add docker hub secret

* ditto

* ditto

* ditto

* add comment

* differentiate between master and fork

Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
2020-07-07 12:42:05 -04:00
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 8b6cf7c661
Remove dangling constant op (#205) 2020-07-07 13:47:54 +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
Haruki Imai 4d96247327
Set alignment attribute to AllocOp of insertAllocAndDealloc() (#195)
* Added alignment in AllocOp of insertAllocAndDealloc()

* Added comments

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-02 15:21:01 +08:00
Kevin O'Brien 5c6d85e6f3
README change to add info on using prebuilt Docker images (#201)
* Add description of prebuilt docker images

* example Dockerfile using prebuilt container

* vscode config files for Docker example

* vscode files for Docker example

* vscode files for Docker example

* add Dockerfile info

* typo

* fix bad name for example file

doc check failed because file name was incorrect

Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-02 13:54:38 +08:00
gongsu832 cf96d635cc
Compile cruntime with fpic (#188)
* Detect llvm-project commit change in utils/clone-mlir.sh and rebuild llvm-project
for zLinux Jenkins build bot

* Compile libcruntime.a object with -fPIC to avoid segfault when embedded into model.so

* Enable unit tests on zLinux

Co-authored-by: Alexandre Eichenberger <alexe@us.ibm.com>
Co-authored-by: Tian Jin <tjingrant@gmail.com>
2020-07-01 15:06:55 +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 f9cb113a84
Krnl block (#170)
* Support krnl.block printing/parsing.

* Checkpoing, PoC working.

* Implement krnl.block operation.

* Make tuple -> make pair.

* Bug fix, white list krnl.iterate op while lowering.

* Add return loop op lowering.

* Bug fix.

* Allow using loop refs more than once if they are used by krnl.iterate op.

* More comments and include lit test.

* Make krnl.block definition more restrictive.

* Splitting tests creates modules, making affine_map matching more verbose, prefer not splitting since test cases are small.

* Use verbose mode for LIT test on Z.

* Use verbose build to diagnose.

* Missing libraries linking when building in shared mode.

* Fix whole-archive linkage.

* Try preloading affinetransforms.

* Try put AffineTransforms into LD_LIBRARY_PATH.

* Fix python syntax error.

* No need to link with whole-archive libs, as they are pre-loaded.

* Do not preload any library.

* Link with whole-archive libs.

* Explicitly shared linkage in CMake.

* Fix CMake syntax error.

* Restore test.py

* Update z13.sh

* Update z13.sh

* Provide krnl.block operation description.
2020-06-27 22:35:01 +08:00
Kevin O'Brien fd3ee81bcf
fix wrong tag on docker image (#193)
Was tagging the image with "latest", should be the CPU type
2020-06-26 11:43:32 -04:00
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
Gheorghe-Teodor Bercea f811718144
Add new passes related to Linalg and Affine dialects (#181)
* Reorganize main function.

* Follow review comments.

* Emit constants are globals in Krnl and LLVM dialects.

* Add more passes to onnx-mlir-opt.

* Clean-up.
2020-06-25 13:36:39 -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