Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[RUNTIME] Support standardize runtime module #4532

Merged
merged 1 commit into from
Dec 22, 2019

Conversation

FrozenGene
Copy link
Member

@FrozenGene FrozenGene commented Dec 17, 2019

As RFC https://discuss.tvm.ai/t/standardize-graphruntime-exports-into-a-single-dll/4667 proposed, we want to standardize runtime export.

@FrozenGene FrozenGene force-pushed the standarize_runtime branch 3 times, most recently from 782a066 to f0eac3a Compare December 17, 2019 15:20
python/tvm/module.py Outdated Show resolved Hide resolved
python/tvm/module.py Outdated Show resolved Hide resolved
python/tvm/module.py Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
@tqchen tqchen added the status: need update need update based on feedbacks label Dec 17, 2019
@FrozenGene
Copy link
Member Author

@tqchen I have addressed the comments you mentioned. And I also supply one more test of dso module import another dso module.

@FrozenGene FrozenGene marked this pull request as ready for review December 18, 2019 12:49
@FrozenGene
Copy link
Member Author

FrozenGene commented Dec 18, 2019

@zhiics Would like you could help to review too. Your recent PR #4482 also change the export_library and serialization / deserialization logic. Currently, I test the unit testing of #4482 and could pass.

@FrozenGene FrozenGene changed the title [WIP] Support standardize runtime module Support standardize runtime module Dec 18, 2019
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
@tqchen tqchen changed the title Support standardize runtime module [RUNTIME] Support standardize runtime module Dec 18, 2019
python/tvm/module.py Outdated Show resolved Hide resolved
python/tvm/module.py Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
@FrozenGene
Copy link
Member Author

@tqchen @zhiics Please help to review it again.

python/tvm/module.py Outdated Show resolved Hide resolved
python/tvm/module.py Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/runtime/library_module.cc Show resolved Hide resolved
tests/python/unittest/test_standardize_runtime.py Outdated Show resolved Hide resolved
src/runtime/library_module.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
src/codegen/codegen.cc Outdated Show resolved Hide resolved
@FrozenGene
Copy link
Member Author

@tqchen @zhiics code is updated and help to review it again.

Copy link
Member

@tqchen tqchen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

some final nits, perhaps we need a testcase with a few C modules

python/tvm/module.py Outdated Show resolved Hide resolved
@FrozenGene FrozenGene force-pushed the standarize_runtime branch 3 times, most recently from 84dace4 to 2308047 Compare December 21, 2019 13:00
@FrozenGene
Copy link
Member Author

@tqchen @zhiics please help to review it again.

@FrozenGene FrozenGene force-pushed the standarize_runtime branch 2 times, most recently from 6b7d542 to 7472af7 Compare December 21, 2019 13:31
Copy link
Member

@tqchen tqchen left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

some final nits :)

python/tvm/module.py Outdated Show resolved Hide resolved
python/tvm/module.py Outdated Show resolved Hide resolved
@tqchen
Copy link
Member

tqchen commented Dec 21, 2019

cc @zhiics please also take a look again

@FrozenGene
Copy link
Member Author

@tqchen @zhiics Has updated the code according to the comments. Please help to review it again.

Copy link
Member

@zhiics zhiics left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@tqchen tqchen merged commit f076c83 into apache:master Dec 22, 2019
@tqchen
Copy link
Member

tqchen commented Dec 22, 2019

Thanks @FrozenGene @zhiics this PR is now merged

@tqchen tqchen added status: accepted and removed status: need review status: need update need update based on feedbacks labels Dec 22, 2019
@tqchen
Copy link
Member

tqchen commented Dec 22, 2019

@FrozenGene great job, can you followup with a PR that add developer docs describes the module serialization format standard?

@FrozenGene
Copy link
Member Author

@tqchen, like the table of https://docs.tvm.ai/dev/nnvm_json_spec.html?

@tqchen
Copy link
Member

tqchen commented Dec 22, 2019

yap, just to introduce how do we serialize and package all these modules and how does the Module's API play together.

@FrozenGene
Copy link
Member Author

So, likely to say, the doc should combine your rfc (could cover how do we serialize and package) and the implementation of def export_library / ModuleSerializer::SerializeModule / ProcessModuleBlob (could cover how they work together). Not just the table I mentioned just now.

@tqchen
Copy link
Member

tqchen commented Dec 22, 2019

Hopefully it will also help more people recognize your work :)

@apivovarov
Copy link
Contributor

apivovarov commented Dec 31, 2019

@FrozenGene Is this change backward compatible? Can new TVM runtime load compiled Cuda models compiled before this change?

@FrozenGene
Copy link
Member Author

FrozenGene commented Dec 31, 2019

@FrozenGene Is this change backward compatible? Can new TVM runtime load compiled Cuda models compiled before this change?

Yes. Backward compatible. For example, you compile one compiled cuda model before this change and export to deploy_old.so, you could load deploy_old.so in the new runtime (merged this change). However, if you compile one model using new runtime (merged this change) and export to deploy_new.so, which can not be loaded into old runtime (before this change). Because we will write _lib for LLVM mod / write _import_tree for constructing model import relationship. Your refer issue is to use new runtime to export library, but loaded into old runtime (DLR), so you can not find _lib loader and _import_tree.

zhiics added a commit to neo-ai/tvm that referenced this pull request Jan 9, 2020
* Change upstream url

* Fix bias_add gradient (apache#4516)

* Fix bias_add gradient

A change caused collapse_sum_like to reject implicit dimension
broadcasting for bias_add gradient, so switch to explicit sum reduction
on the non-bias axis dimensions.

* Lint fix

* [Bugfix][Frontend][TFlite] Fix wrong function call in TANH tests (apache#4517)

* Replace sigmoid() with tanh() in tests for TANH

* Fixed extra reshape parameter bug. (apache#4524)

* Use the best tuner possible (apache#4397)

* Use the best tuner possible

* Add comment denoting availability of better tuners

* Fix typos and wording

* [ir] use DataType instead of Type for readability because Type has been deprecated (apache#4513)

* add bfloat16 typeflag support (apache#4525)

* fix empty config caused KeyError (apache#4520)

* fix onnx shape dtype (apache#4528)

* fix crash issue in tsim backend (apache#4527)

* PIL is depreciated and should be replaced with pillow (a fork of PIL) (apache#4533)

Change-Id: If2075df5475505f2da87dae7145af5a7ab83d8a4

* [Relay] External codegen (apache#4482)

* Update legacy places from nnvm to relay. (apache#4535)

* Update legacy places from nnvm to relay.

This PR prepares the current mainline to remove nnvm compiler dep.

* remove legacy stage

* Implement 1d deconvolution (apache#4476)

* [relay][op] add expand op (from ONNX) to relay frontend (apache#4483)

* Add Expand to onnx.py

* add test function for expand

* Fix a onnx frontend test

* Add tests for the value itself instead of shape only on test_expand

* Cleaned up some unnecessary modifications.

* [TOPI] Allow batch matmul to be fused into injective ops (apache#4537)

* [TOPI] Fixed nms max_output_size loop (apache#4541)

One of the loops in hybrid_nms used for
performing the max_output_size reordering
was incorrectly designated as parallel
resulting in incorrect behaviour. This patch
changes that loop to a serial loop.

Change-Id: I97184f5887f5f028d8ab339fa2808eb7630a4017

* [DOCS] Mention Ninja build system in install/from_source.rst (apache#4554)

* [DOCS] Mention Ninja build system in install/from_source.rst

* Address comments

* [PYTHON][FFI] Cythonize NDArray.copyto (apache#4549)

* [PYTHON][FFI] Cythonize NDArray.copyto

* Cythonize the shape property

* vm external codegen (apache#4544)

* [COMMUNITY] @cchung100m -> reviewer (apache#4557)

* [VTA] improved virtual memory mapping (apache#4545)

* [VTA] improved virtual memory mapping

* Update virtual_memory.cc

* [IR] fix style in ir_mutator and ir_visitor (apache#4561)

* [RUNTIME][VULKAN] Fix compiler warning (apache#4559)

* [REFACTOR][DTYPE] Isolate dtype to runtime (apache#4560)

dtype.h -> runtime/data_type.h

Changes:
- Rename all old reference of tvm::Type to DataType
- ExprNode.type -> ExprNode.dtype
- Expr.type() -> Expr.dtype()
- Change Expr related functions to expr_operator.
  - DataType::min() -> min_value(DataType)
  - DataType::max() -> max_value(DataType)
- Move type constructor Int, UInt, Float, Handle, Bool into DataType.
  - Int(bits) -> DataType::Int(bits)
  - UInt(bits) -> DataType::UInt(bits)

* Support standardize runtime module (apache#4532)

* [Relay][Frontend][ONNX] Support auto_pad in Conv and ConvTranspose (apache#4563)

* [TEST] Remove nnvm related code in topi and test script (apache#4562)

* [TEST] Remove nnvm related code in topi and test script

* Remove docs dep

* [Relay] add max_pool3d in relay and TF converter (apache#4551)

* [Relay] add max_pool3d in relay and TF converter

* fix comments

* Remove nnvm (apache#4565)

* [VTA][Chisel] End-to-end Inference with Chisel VTA (apache#4574)

* [VTA][Chisel] End-to-end Inference with Chisel VTA

* Update TensorAlu.scala

* remove unnecessary cast to int32 (apache#4573)

* Fix llvm-enabled build by adding missing intrinsics headers (apache#4575)

* [DEPRECATION] Remove NNVM compiler (apache#4571)

* Remove NNVM compiler

* [Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators (apache#4566)

* Added tvm function stencil for subpixel operations to topi.

* Topi subpixel operators added and tested.

* Added subpixel attrs.

* Added depth_to_space relay attributes.

* depth_to_space fully working.

* Fixed NHWC shape bug.

* SpaceToDepth in and all tests passing.

* lint fixes.

* Added string include

* Fixed topi formatting.

* Added DCR/CDR mode to depthtospace operator.

* [DOC] fix doc in api.py (apache#4580)

* [DEPRECATION] Cleanup legacy verilog support (apache#4576)

This PR cleans up the left over code for legacy verilog support which was experimental.
The new hardware backend path is now support by VTA via TSIM.

* [RUNTIME] Remove Extension VTable in favor of Unified Object system. (apache#4578)

Before the unified object protocol, we support pass
additional extension objects around by declaring a type as an extension type.
The old extension mechanism requires the types to register their
constructor and deleter to a VTable and does not enjoy the benefit of the
self-contained deletion property of the new Object system.

This PR upgrades the extension example to make use of the new object system
and removed the old Extension VTable.

Note that the register_extension funtion in the python side continues to work
when the passed argument does not require explicit container copy/deletion,
which covers the current usecases of the extension mechanism.

* Some Windows and MSVC fixes (apache#4569)

* fix python exception creation in Windows

* better string conversion for msvc

* fix cpp style issue

* [NEWS] add v0.6 release (apache#4558)

* [NEWS] add v0.6 release

* remove link prefix

* fix issue number

* [DOCS]fix typos in autotvm tutorial (apache#4585)

* [Quantization, Calibrate] Fix context creation when current_target is explicity set (apache#4582)

* [Container] Fix NDArray SaveDLTensor declaration and implementation signature different (apache#4586)

* [TOPI][AutoTVM] NHWC conv2d templates for ARM (apache#3859)

* [AutoTVM][TOPI] NHWC conv2d templates (spatial pack) for ARM

As some frontends (tflite for example) are using NHWC as the default
layout, we are enabling NHWC schedule templates in TOPI and AutoTVM.

* some comments fix

* [FIX][TOPI][X86] schedule dense pack (apache#4539)

* [Relay] Convert Layout Pass. (apache#4335)

* [Relay][AlterLayout] Broadcast with scalar shape (apache#4577)

* [TOPI] add 3D upsampling Op. (apache#4584)

* [TOPI] add 3D upsampling Op.

* fix lint issues

* change align_corners to coordinate_transformation_mode

* fix resize3d half_pixel

* make a simple function and clean up trilinear_resize3d_python

* fix doc

* [Runtime] add necessary const qualifier for NDArray container of parameters (apache#4590)

* [autotvm] fix typos in comment (apache#4591)

* fix tf.compat.v1 issue for tf verison <=1.12 (apache#4593)

* [FRONTEND][TF] conv2d_transpose 'SAME' support kernel more than 1x1 (apache#4484)

* [FRONTEND][TF] conv3d_transpose 'SAME' support kernel more than 1x1

* revised per as review comments

* add more fallback wolkaround to make all tests pass

* [GraphRuntime] Support parameter out in the graph runtime debug (apache#4598)

* [GraphRuntime] Support parameter out in the graph runtime debug

* Dummy commit to trigger build

* [Perf] Add CublasLt extern support for better Igemm performance (apache#4550)

* cublaslt added

* fix lint

* address comments

* address more comments

* Trigger CI

* Trigger CI

* fix codegenc (apache#4597)

* [REFACTOR][RUNTIME] Update NDArray use the Unified Object System (apache#4581)

* [REFACTOR][RUNTIME] Move NDArray to Object System.

Previously NDArray has its own object reference counting mechanism.
This PR migrates NDArray to the unified object protocol.

The calling convention of NDArray remained intact.
That means NDArray still has its own type_code and
its handle is still DLTensor compatible.

In order to do so, this PR added a few minimum runtime type
detection in TVMArgValue and RetValue only when the corresponding
type is a base type(ObjectRef) that could also refer to NDArray.

This means that even if we return a base reference object ObjectRef
which refers to the NDArray. The type_code will still be translated
correctly as kNDArrayContainer.
If we assign a non-base type(say Expr) that we know is not compatible
with NDArray during compile time, no runtime type detection will be performed.

This PR also adopts the object protocol for NDArray sub-classing and
removed the legacy NDArray subclass protocol.
Examples in apps/extension are now updated to reflect that.

Making NDArray as an Object brings all the benefits of the object system.
For example, we can now use the Array container to store NDArrays.

* Address review comments

* [Relay][Convert Layout] Handling batch norm layout change. (apache#4600)

* [relay][refactor] Cache Op::Get in passes to reduce lookup overhead (apache#4594)

* Refactor to use IsOp utility

* retrigger CI

* Update dmlc_tvm_commit_id.txt

* disable one test_batch_norm unit test for now to check CI

* enable test_batch_norm

Co-authored-by: SWu <[email protected]>
Co-authored-by: Ina Dobreva <[email protected]>
Co-authored-by: Josh Fromm <[email protected]>
Co-authored-by: miheer vaidya <[email protected]>
Co-authored-by: Liang ZOU <[email protected]>
Co-authored-by: YixinBao <[email protected]>
Co-authored-by: Cody Yu <[email protected]>
Co-authored-by: masahi <[email protected]>
Co-authored-by: Liangfu Chen <[email protected]>
Co-authored-by: lhutton1 <[email protected]>
Co-authored-by: Tianqi Chen <[email protected]>
Co-authored-by: Alex Gladkov <[email protected]>
Co-authored-by: Takato Yamada <[email protected]>
Co-authored-by: Haichen Shen <[email protected]>
Co-authored-by: mbarrett97 <[email protected]>
Co-authored-by: Hideto Ueno <[email protected]>
Co-authored-by: Siyuan Feng <[email protected]>
Co-authored-by: Zhao Wu <[email protected]>
Co-authored-by: Neo Chien <[email protected]>
Co-authored-by: Yong Wu <[email protected]>
Co-authored-by: Dmitri Makarov <[email protected]>
Co-authored-by: Bohan Hou <[email protected]>
Co-authored-by: kice <[email protected]>
Co-authored-by: Yizhi Liu <[email protected]>
Co-authored-by: Wang Yucheng <[email protected]>
Co-authored-by: 王振华(Zhenhua WANG) <[email protected]>
Co-authored-by: deepIgnorance <[email protected]>
Co-authored-by: Animesh Jain <[email protected]>
Co-authored-by: optima2005 <[email protected]>
Co-authored-by: zhuochen <[email protected]>
Co-authored-by: Leyuan Wang <[email protected]>
zhiics pushed a commit to neo-ai/tvm that referenced this pull request Jan 11, 2020
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Projects
None yet
Development

Successfully merging this pull request may close these issues.

4 participants