colin
/
onnx-mlir
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
46 Commits 1 Branch 0 Tags 2.6 MiB
Commit Graph

46 Commits

Author SHA1 Message Date
TUNG LEDUC 5ed79083d5 [MLIR] Add support for Max, Min, Sum, Elu, Selu, LeakyRelu, HardSigmoid (#395) 
* Lower ONNXSumOp

* Add inferShapes() and test cases

* Load the first operand to the result

* Update SharingWork.md

* Update SharingWork.md

* Update SharingWork.md

* Add support for Max, Min

* Pass operation instead of location to mapToLowerScalarOp

* Add support for Elu, Selu, LeakyRelu, HardSigmoid

* Add test cases

* Update SharingWork.md

* Rewrite the part of lowering variadic ops and use it for binary ops

* Use two diffenrent templates for Unary and Variadic Ops

* Revise the code
 2019-12-21 02:02:09 -05:00
Alexandre E Eichenberger fb1b43f842 Create SharingWork.md (#394) 
Add tables to keep track of the work, initially with a section on ONNX to KRNL work. Add more sections as you see fit
 2019-12-21 02:01:47 -05:00
TONG CHEN c8d591fb28 [MLIR] import attribute of onnx node (#383) 
* add attributes as NamedAttribute

* support list value for attribute

* use std::tie to avoid c++17 feature
 2019-12-21 02:00:58 -05:00
TUNG LEDUC 45608282e0 [MLIR] Add support for Relu (#392) 
* Add support for Relu

* Add comments
 2019-12-21 01:38:16 -05:00
Tian Jin 82f5bfec9f Update lower_frontend_to_krnl.cpp (#391) 2019-12-21 01:37:50 -05:00
TUNG LEDUC 1c3176bf9f [MLIR] Lower ONNX element-wise unary ops: Exp, Tanh, Sinh, Cosh, Sigmoid (#389) 
* Lower ExpOp

* Lower ONNXTanhOp

* Lower Exp Tanh, Sinh, and Cosh

* Lower ONNX Sigmoid op

* Merge

* Specialize template lowerScalarOp

* Unify ONNXEWUnaryOpLowering and ONNXEWBinaryOpLowering

* Support multiple types

* Reformat the code

* Add test cases

* Reformat the code

* Change names

* Apply clang-format

* Update variable names
 2019-12-21 01:37:29 -05:00
Tian Jin 0048f2fd86 clean up 2019-12-21 01:36:03 -05:00
TUNG LEDUC c3ef1d93ae [MLIR] Lower ONNX element-wise binary ops: Mul, Div, Sub, And, Or, Xor (#388) 
* Lower ONNX element-wise binary ops: Mul, Div, Sub, And, Or, Xor

* Edit gen_doc.py to avoid changes about AnyTypeOf<[AnyMemRef, AnyTensor]>

* Miss a space

* Add tests

* Shorten ONNXElementWiseBinaryOpLowering into ONNXEWBinaryOpLowering

* Move lowering patterns into runOnModule()

* Redundant space
 2019-12-21 01:35:31 -05:00
TUNG LEDUC 05e16dafae Use template to support lowering all binary onnx ops to kernel ir (#387) 2019-12-21 01:35:17 -05:00
GHEORGHE-TEOD BERCEA 7fb2f80dce [MLIR] Add support for dealloc insertion (#386) 
* Add support for dealloc op.

* Check dealloc for returned result not present.
 2019-12-21 01:34:48 -05:00
Tian Jin b2a1103915 [MLIR] Refactor Krnl Dialect and Krnl Dialect Lowering (#375) 
* Store bounds as affine map attributes & check in test cases with generic printer

* Upgrading MLIR

MLIR is outdated on Buildbot, rebuilding a newer version.

* work with new version of mlir

* check-in parser tests

* custom printer

* nit

* bug fix

* enable custom asm printer test

* enable custom asm printer test

* more consistent variable naming

* test max/min

* variable naming scheme change to MLIR style

* can lower krnl to llvm

* kernel -> llvm

* comments

* bug fix

* try fixing ci

* fix ci

* deactivate model test

* fix lit test

* nit

* fix z buildbot
 2019-12-21 01:34:14 -05:00
GHEORGHE-TEOD BERCEA 652ce4b7d4 Add test for checking lowering of Add op to KRNL IR (#385) 
* Add test for checking lowering of Add op to KRNL IR.

* Add test file.
 2019-12-21 01:20:36 -05:00
Tian Jin b46f965715 clean up 2019-12-21 01:13:50 -05:00
GHEORGHE-TEOD BERCEA b02652dd76 [MLIR] Lowering of frontend dialect to KRNL dialect (#382) 
* Partial support for lowering operations to KRNL dialect.

* Attempt to lower to KRNL IR.

* Update file.

* Add lowering.

* Address comments. Fix alloc dynamic dimensions. Correctly link StandardOps.

* Temporarily remove deallocation of locally allocated tensors.
 2019-12-21 01:11:14 -05:00
TUNG LEDUC d61cf35471 [MLIR] Add one more test case for MatMul-Add fusion (#380) 
* Add one more testcase for matmul-add fusion

* Code format for identity elimination testcase
 2019-12-21 00:51:54 -05:00
Tian Jin 004762c13d [MLIR] Remove module from test (#379) 
* Remove module from test

* Update onnx_canonicalization.mlir
 2019-12-21 00:51:23 -05:00
Tian Jin 8ea7e34a60 clean up 2019-12-21 00:51:05 -05:00
Tian Jin 6580b47e25 Exit Bash Script on Error (#381) 
* Update p9.sh

* Update z13.sh

* Update p9.sh

* Update p9.sh

* enable LLVM
 2019-12-21 00:50:30 -05:00
TUNG LEDUC 53ab014a1d [MLIR] Canonicalization pattern for eliminating identity ops (#377) 
* Canonicalization pattern for eliminating identity ops

* Add a test for the identity elimination rule

* Remove frontend from test

* Use CHECK-NEXT instead of CHECK
 2019-12-21 00:47:22 -05:00
GHEORGHE-TEOD BERCEA bee32e2041 Fix rebase errors. (#378) 2019-12-21 00:46:29 -05:00
Tian Jin 6c7ff180f9 Update type parser (#376) 2019-12-21 00:43:33 -05:00
TUNG LEDUC 0c36057404 [MLIR] Add a constraint for the rewriting rule of add_matmult to fullgemm (#374) 
* Add a constraint for the rewriting rule of matmul_add to fullgemm

* Edit comments
 2019-12-21 00:42:19 -05:00
Tian Jin 701c7d7508 clean up 2019-12-21 00:41:40 -05:00
TONG CHEN 3f68c5420d [MLIR] generate op from onnx document (#366) 
* generate op from onnx document

* Restore FullGemm

* update the op attribute for shape inference and canonicalizer

* Update onnx_canonicalization.mlir
 2019-12-21 00:40:40 -05:00
Tian Jin d01ac7732f [MLIR] compartmentalize build script (#369) 
* compartmentalize build script, temporarily remove dependency of onnf_opt on helper.cpp

* fix test includes

* fix op directory include

* compiler -> op

* compiler test depends on boost system

* fix function name

* specify libcompiler dependencies

* let cmake take care of transitive dependencies

* remove unnecessary includes

* use ONNF_SRC_ROOT and ONNF_BIN_ROOT

* allow whole-archive linked libraries to be appended

* [MLIR] Support filecheck (#371)

* support lit+FileCheck

* add lit into build script

* format MLIR.cmake

* format cmake

* [MLIR] Remove input/output ops (#372)

* remove input/output ops

* get output tensor type from symbol table
 2019-12-21 00:34:51 -05:00
GHEORGHE-TEOD BERCEA dc36fd416b [MLIR] Fix shape inference and enable ONNF to read in MLIR files. (#367) 
* Fix inference. Enable ONNF to read in MLIR files.

* Fix input of onnx or mlir models.

* Address comments.
 2019-12-21 00:12:27 -05:00
TUNG LEDUC 0d644fab92 [MLIR] Legalize output tensors' names (#368) 
* [MLIR] legalize output tensor's name

* Update frontend_dialect_transformer.cpp
 2019-12-21 00:08:02 -05:00
GHEORGHE-TEOD BERCEA 63596e723f [MLIR] Add optimization based on TableGen pattern (#363) 
* Define pattern.

* Fix file names.

* Add canonicalizer optimization based on TableGen pattern.

* Remove custom builders.

* Enable canonicalization in ONNF and ONNF-OPT.
 2019-12-21 00:04:51 -05:00
Tian Jin 780e6f0aa0 [MLIR] Krnl Dialect Definition (#357) 
* a complete, roud-trippable Krnl dialect operation definition

* remove old dialect definition files, edit build files

* register dialect

* check in src for onnf_opt and dimension handler types

* re-trigger jenkins

* fix build

* clarify operation semantics

* add verifier for krnl.iterate

* refactor to make things clear

* do not hard code types

* nit and add comments

* fix rebase

* update op implementation

* fix merge

* update kernel dialect definition

* more comment on how to use the builder for krnl.iterate operation

* ammend the comment

* can parse krnl.iterate

* can parse and print if bounds are not SSA values

* address comments

* better error handling

* Update CMakeLists.txt

* update comment

* reflow comments
 2019-12-20 11:37:09 -05:00
GHEORGHE-TEOD BERCEA 03be41f7df [MLIR] Add shape inference pass (#361) 
* Add shape inference pass.

* Format code.

* Enable shape inference pass.

* Rename new files to use ONNF convention.

* Use include path from src folder.

* Replace guards with pragma once.

* Format variable names. Shuffle headers.

* Fix comment.

* Fix comments.
 2019-12-19 20:14:07 -05:00
Doru Bercea a6cca3cbb7 Code clean-up. 2019-12-19 19:51:01 -05:00
GHEORGHE-TEOD BERCEA a9960f6e44 [MLIR] Add conversion to MLIR types. (#360) 
* Add conversion of tensor proto types to MLIR types.

* Fix integer type conversion. Use new type conversion for ouput type.
 2019-12-19 19:48:31 -05:00
Doru Bercea 626552f4a0 Remove files. 2019-12-19 19:35:19 -05:00
Tian Jin 02e1e8720f [MLIR] Add onnf-opt Support (#359) 
* support onnf-opt, register standard dialect

* use onnf native assertions

* fix build

* nit
 2019-12-19 19:31:48 -05:00
GHEORGHE-TEOD BERCEA 958a2fbffc ONNX Dialect creation and registration with MLIR (#358) 
* Create and register ONNX Dialect with one Add operation.

* Fix file formatting.

* Change name from ONNX to SGIR.

* Use ONNX dialect. Change SGIR to frontend placeholder dialect.

* Add comments.

* Type clean-up.
 2019-12-19 16:56:30 -05:00
Doru Bercea b5a35c9138 Update buildbot scripts. 2019-12-19 16:28:53 -05:00
Tian Jin f086948347 Mlir check in build script (#356) 
* bug fixes

* better format

* check in build script on z13

* fix cmake syntax
 2019-12-19 16:20:04 -05:00
GHEORGHE-TEOD BERCEA 45a5a8499c Fix MLIR-enabled build. (#354) 
* Add new build paths. Add Ranker or Unracked tensor types.

* Remove path to LLVM root folder, it is not needed anymore.

* Code clean-up.

* Clean-up code.

* update LLVM_PROJECT_SRC

* Update p9.sh

* Update MLIR.cmake
 2019-12-19 16:16:06 -05:00
Tian Jin 00aee2e0b6 Use TableGen (#347) 
* use table gen

* fix name of the dialect

* add old compilation path

* add some doc

* fix bug, sgir importer imports every op twice

* knl.visit -> knl.iterate
 2019-12-19 15:18:35 -05:00
Tian Jin cc39a92802 fix code format (#348) 2019-12-19 14:53:18 -05:00
Doru Bercea e1f6ae1336 Fix name legalization. 2019-12-19 14:46:18 -05:00
TONG CHEN 50ac6e7bce emit SGIR based on onnx model, following the toy/Ch2 example (#345) 
* emit SGIR based on onnx model, following the toy/Ch2 example

* fix 1) code style 2) multiple output of a node

* Update sgir.cpp
 2019-12-19 14:37:20 -05:00
Doru Bercea 63427030ca Enable building of first commit. 2019-12-19 14:24:37 -05:00
Doru Bercea b6a2a50dd8 Add header. Clean-up file. Add CMake file. 2019-12-18 16:45:05 -05:00
TONG CHEN f3207be963 add MLIR: compile/link/run (#342) 
* add MLIR: compile/link/run

* change LLVMPROJECT to LLVM_PROJECT and do not allow linking with system LLVM libraries
 2019-12-18 15:43:35 -05:00
Gheorghe-Teodor Bercea 85bf198681
Initial commit 2019-12-18 10:18:14 -05:00