platform/upstream/tvm.git
4 years agoWindows Support for cpp_rpc (#4857)
jmorrill [Wed, 15 Apr 2020 08:49:15 +0000 (01:49 -0700)]
Windows Support for cpp_rpc (#4857)

* Windows Support for cpp_rpc

* Add missing patches that fix crashes under Windows

* On Windows, use python to untar vs wsl

* remove some CMakeLists.txt stuff

* more minor CMakeLists.txt changes

* Remove items from CMakeLists.txt

* Minor CMakeLists.txt changes

* More minor CMakeLists.txt changes

* Even more minor CMakeLists.txt changes

* Modify readme

4 years ago[Runtime][Relay][Cleanup] Clean up for memory pass to enable heterogenous execution...
Jared Roesch [Wed, 15 Apr 2020 00:10:00 +0000 (17:10 -0700)]
[Runtime][Relay][Cleanup] Clean up for memory pass to enable heterogenous execution support. (#5324)

* Cleanup type pack and unpack for tuples.

* Clean up the memory_pass using common helpers

* Clean up memory.cc

* Refactor pass

* Add doc strings

* Fix CPPlint

* Fix PyLint

* Fix

* Apply suggestions from code review

Co-Authored-By: Zhi <5145158+zhiics@users.noreply.github.com>
* Fix typo

Co-authored-by: Zhi <5145158+zhiics@users.noreply.github.com>
4 years ago[CI] Fix build.sh to propagate --network=host to the docker build command (#5336)
Leandro Nunes [Wed, 15 Apr 2020 00:03:43 +0000 (01:03 +0100)]
[CI] Fix build.sh to propagate --network=host to the docker build command (#5336)

* when passing --net=host to build.sh it needs to be also
   sent as --network=host to "docker build", so that both
   build and run will use the same network configuration

4 years ago[LLVM] Use llvm::FunctionCallee in IRBuilder::CreateCall with LLVM 11+ (#5338)
Krzysztof Parzyszek [Wed, 15 Apr 2020 00:03:31 +0000 (19:03 -0500)]
[LLVM] Use llvm::FunctionCallee in IRBuilder::CreateCall with LLVM 11+ (#5338)

The older variants of CreateCall have been deprecated and were recently
removed from LLVM. This caused compilation failures.

4 years ago[RELAY] Remove re-exports of tvm.transform (#5337)
Tianqi Chen [Wed, 15 Apr 2020 00:03:15 +0000 (17:03 -0700)]
[RELAY] Remove re-exports of tvm.transform (#5337)

4 years ago[TIR] Refactor MakePackedAPI to target dependent stage. (#5326)
Tianqi Chen [Tue, 14 Apr 2020 14:48:14 +0000 (07:48 -0700)]
[TIR] Refactor MakePackedAPI to target dependent stage. (#5326)

Previously MakePackedAPI was in the target independent stage,
but never the less requires the device_type information that will be
binded at a later target dependent stage.

The previous implementation was due to the limitation of LoweredFunc
which can not carry buffer_map info(so they have to be lowered right away).
This is no longer the case after the unified IR refactor.

This PR migrates MakePackedAPI to a target dependent stage
and removes the un-necessary BindDevice pass.

4 years ago[RELAY][PYTORCH]isNan, isinf, isfinite, ceil, clamp, round ops (#5316)
Samuel [Tue, 14 Apr 2020 09:45:02 +0000 (15:15 +0530)]
[RELAY][PYTORCH]isNan, isinf, isfinite, ceil, clamp, round ops (#5316)

* [RELAY][PYTORCH]isNan, isinf, isfinite, ceil, clamp, round ops

* Review comments

4 years ago[TE][BuildModule] Fix import in dump pass ir (#5327)
Wuwei Lin [Tue, 14 Apr 2020 06:47:57 +0000 (02:47 -0400)]
[TE][BuildModule] Fix import in dump pass ir (#5327)

4 years ago[Frontend|MXNet] SwapAxis operator support (#5246)
Mahesh Ambule [Tue, 14 Apr 2020 06:09:21 +0000 (11:39 +0530)]
[Frontend|MXNet] SwapAxis operator support (#5246)

* MXNet swap axis

* MXNet swap axis

* swap axis review comment

* swap axis review comment

4 years ago[CODEGEN][CUDA] Fix vector load (#5226)
LiangLiu [Tue, 14 Apr 2020 03:35:31 +0000 (11:35 +0800)]
[CODEGEN][CUDA] Fix vector load (#5226)

* Fix high-low bit bug in __pack_half2

* Fix vector load

* Add unit8 support for PrintVecElemLoadExpr and BroadcastNode

4 years agoadd memoized expr translator for use by backend codegen (#5325)
masahi [Tue, 14 Apr 2020 01:21:31 +0000 (10:21 +0900)]
add memoized expr translator for use by backend codegen (#5325)

4 years ago[COMMUNITY] @mbaret -> Reviewer (#5322)
Tianqi Chen [Mon, 13 Apr 2020 23:04:32 +0000 (16:04 -0700)]
[COMMUNITY] @mbaret -> Reviewer (#5322)

4 years ago[BYOC] Enhance partitioning and external codegen (#5310)
Zhi [Mon, 13 Apr 2020 21:06:02 +0000 (14:06 -0700)]
[BYOC] Enhance partitioning and external codegen (#5310)

* Remove duplicated output args

* address comment

* fix codegen c

* improve comment

* VisitExprDefault_

* deduce type

4 years ago[RUNTIME][IR] Allow non-nullable ObjectRef, introduce Optional<T>. (#5314)
Tianqi Chen [Mon, 13 Apr 2020 17:49:48 +0000 (10:49 -0700)]
[RUNTIME][IR] Allow non-nullable ObjectRef, introduce Optional<T>. (#5314)

* [RUNTIME] Allow non-nullable ObjectRef, introduce Optional<T>.

We use ObjectRef and their sub-classes extensively throughout our codebase.
Each of ObjectRef's sub-classes are nullable, which means they can hold nullptr
as their values.

While in some places we need nullptr as an alternative value. The implicit support
for nullptr in all ObjectRef creates additional burdens for the developer
to explicitly check defined in many places of the codebase.

Moreover, it is unclear from the API's intentional point of view whether
we want a nullable object or not-null version(many cases we want the later).

Borrowing existing wisdoms from languages like Rust. We propose to
introduce non-nullable ObjectRef, and Optional<T> container that
represents a nullable variant.

To keep backward compatiblity, we will start by allowing most ObjectRef to be nullable.
However, we should start to use Optional<T> as the type in places where
we know nullable is a requirement. Gradually, we will move most of the ObjectRef
to be non-nullable and use Optional<T> in the nullable cases.

Such explicitness in typing can help reduce the potential problems
in our codebase overall.

Changes in this PR:
- Introduce _type_is_nullable attribute to ObjectRef
- Introduce Optional<T>
- Change String to be non-nullable.
- Change the API of function->GetAttr to return Optional<T>

* Address review comments

* Upgrade all compiler flags to c++14

* Update as per review comment

4 years ago[Topi] Tensorcore support for Conv3D (#5284)
Josh Fromm [Mon, 13 Apr 2020 17:49:17 +0000 (10:49 -0700)]
[Topi] Tensorcore support for Conv3D (#5284)

* one weird trick.

* Added schedule knob for different workloads.

* Initial conv3d tensorcore working.

* Added conv3d tensorcore strategy.

* Added layout conversion to tensorcore friendly format for conv2d and conv3d.

* Add target name check.

* Fixed bad names and depthwise check.

* Removed duplicated attribute assignment.

4 years ago[REALY][OP] fix typo (#5315)
windclarion [Mon, 13 Apr 2020 14:55:33 +0000 (22:55 +0800)]
[REALY][OP] fix typo (#5315)

Signed-off-by: windclarion <windclarion@gmail.com>
4 years ago[PYTORCH]Reduce_ops support added (#5308)
Samuel [Mon, 13 Apr 2020 09:50:10 +0000 (15:20 +0530)]
[PYTORCH]Reduce_ops support added (#5308)

* [PYTORCH]Reduce_ops support added

* Review comments updated

* typo bug in qnn test

4 years ago[Torch] Support Python list, more realistic recurrent networks (#5306)
masahi [Mon, 13 Apr 2020 06:11:57 +0000 (15:11 +0900)]
[Torch] Support Python list, more realistic recurrent networks (#5306)

* use funcs from prelude, pass around convert_map

* get relay input type from user ishape

* handle tuple unpack

* experimenting with static tensor array

* use prelude concat instead of cons + rev

* minor clean up

* fix layer norm conversion bug, unwrap tensor array

* add infer shape on tensor array

* pass around prelude for now

* compile worked but runtime error

* fix tensor array wrapping

* begin list dynamic test

* is_list_dynamic first version

* finish dynamic list test

* a few fix

* use shape_of function if Any is found

* improve size conversion

* working on adding free vars to loop block

* fixed inlined inner loop issue

* clean up free var handling

* add support for tensor array concat

* adding ta concat on last axis

* fix concat, but got runtime error

* disable concat on axis -1 for now

* add lstm tests

* revert unrelated change

* fix stacked bidir test

* minor fix to test

* relax tol a bit, revert dnnl change to avoid conflict

* simplify infer type, use input tensor shape rather than concat shape

* more shape fix

4 years ago[Intrinsic] Add log1p, ldexp, atan2, hypot, nextafter, copysign (#5312)
Junru Shao [Sun, 12 Apr 2020 16:32:23 +0000 (09:32 -0700)]
[Intrinsic] Add log1p, ldexp, atan2, hypot, nextafter, copysign (#5312)

* [Intrinsic] Add log1p, ldexp, atan2, hypot, nextafter, copysign

* Lint

4 years ago[Rust][CI] Restore Rust CI (#5137)
Jared Roesch [Sun, 12 Apr 2020 16:30:47 +0000 (09:30 -0700)]
[Rust][CI] Restore Rust CI (#5137)

4 years agoRemove PrimExpr from String (#5311)
Zhi [Sun, 12 Apr 2020 16:12:23 +0000 (09:12 -0700)]
Remove PrimExpr from String (#5311)

4 years ago[Requantize] Cleanup and Optimize Lowering (#5286)
Animesh Jain [Sun, 12 Apr 2020 06:10:52 +0000 (23:10 -0700)]
[Requantize] Cleanup and Optimize Lowering (#5286)

* Adding Cast back to Int32 in FixedPointMultiply.

* Removing extra clip.

* Fix space.

* Retrigger.

* Retrigger.

4 years ago[IR][TRANSFORM] Enable CopyOnWrite for passes. (#5309)
Tianqi Chen [Sun, 12 Apr 2020 00:42:42 +0000 (17:42 -0700)]
[IR][TRANSFORM] Enable CopyOnWrite for passes. (#5309)

This PR enables the copy on write optimizations passes:
- Enable COW for IRModule both TIR and relay passes.
- Enabled COW for PrimFunc in TIR passes.

Need more thoughts into whether/how to enable COW
for relay::Function, due to some function passes depend
on the presence of IRModule for context information,
and the std::move of the related function to nullptr
might affect the related behavior.

4 years ago[PYTORCH]Abs, Arange, Softplus ops (#5295)
Samuel [Sat, 11 Apr 2020 05:02:58 +0000 (10:32 +0530)]
[PYTORCH]Abs, Arange, Softplus ops (#5295)

* [PYTHON]Abs, Arange, Softplus ops

* Review comments updated

4 years ago[LLVM] Fix generation of LLVM intrinsics (#5282)
Krzysztof Parzyszek [Sat, 11 Apr 2020 04:19:03 +0000 (23:19 -0500)]
[LLVM] Fix generation of LLVM intrinsics (#5282)

* [LLVM] Fix generation of LLVM intrinsics

The type list in the call to llvm::Intrinsic::getDeclaration is not
the intrinsic's signature, it's the list of overloaded types. Without
this fix, the updated unit test would cause the following error:

TVMError: LLVM module verification failed with the following errors:
Intrinsic name not mangled correctly for type arguments! Should be:
llvm.ctlz.i32
i32 (i32, i1)* @llvm.ctlz.i32.i1

Special handling for llvm.prefetch, sig matching for overloaded ints only

The prefetch intrinsic returns void in LLVM, while it returns i32 in TVM.
This case needs to be handled specially, because rule-based intrinsic
translation would cause invalid LLVM type to be created.

Do the signature matching only for overloaded intrinsics. It's not needed
for non-overloaded ones, so this can save a bit of compile-time.

* Include intrinsic name in the error message

* Fix number of arguments for llvm.fmuladd and llvm.pow

4 years ago[BYOC] Add example of Composite + Annotate for DNNL fused op (#5272)
masahi [Sat, 11 Apr 2020 03:29:20 +0000 (12:29 +0900)]
[BYOC] Add example of Composite + Annotate for DNNL fused op (#5272)

* merge change from dev branch

* fix string issue

* bring comanic's change back

4 years ago[Frontend][TensorFlow]Improve TensorFlow Static Shape Tensor Array (#5243)
Yao Wang [Sat, 11 Apr 2020 01:43:23 +0000 (18:43 -0700)]
[Frontend][TensorFlow]Improve TensorFlow Static Shape Tensor Array (#5243)

* Support TF Frontend Static TensorArray

* Fix pylint

* Fix lint

* Move get_tensor_array_shape into prelude

* Fix lint

* Fix common

4 years ago[RUNTIME] Introduce RValue reference(move) support to TypedPackedFunc (#5271)
Tianqi Chen [Sat, 11 Apr 2020 00:07:20 +0000 (17:07 -0700)]
[RUNTIME] Introduce RValue reference(move) support to TypedPackedFunc (#5271)

* [RUNTIME] Introduce RValue reference(move) support to TypedPackedFunc

This PR introduces RValue reference support the PackedFunc calling convention to address the above issue.
Specifically, when an argument is a r-value reference, we will use a assign a different type code(`kObjectRValueRefArg`),
and pass `Object**`  (the address to the Object pointer) instead through the values array.
The callee can choose to move out this Object pointer and set the original Object pointer from the caller side to be nullptr.

We also add an experimental move support to the python side(marked as _move so to indicate the dev nature).
This enhancement will enable copy on write optimizations through out the TVM stack.

* Address review comments

* fix compilation

4 years ago[RELAY][FRONTEND][CAFFE2] add Mul and ConvTranspose operator (#5302)
Huacong Yang [Fri, 10 Apr 2020 21:46:03 +0000 (05:46 +0800)]
[RELAY][FRONTEND][CAFFE2] add Mul and ConvTranspose operator (#5302)

4 years ago[BYOC] Refine AnnotateTarget and MergeCompilerRegion Passes (#5277)
Cody Yu [Fri, 10 Apr 2020 21:32:56 +0000 (14:32 -0700)]
[BYOC] Refine AnnotateTarget and MergeCompilerRegion Passes (#5277)

* add target to region

* refactor annotate_target

* Make all unit test working

* quick fix

* enable BN, unit test failed

* Fix vm test, unit test. Refactor annotate_target a bit.

* quick fix fusion

* revert fusion change

* style fix

* Refactor merge region pass

* format

* minor fix

* Skip e2e test

* lint

* support AnnotateTarget multiple runs

* Add HasAttr and revert DNNL codegen

* address comment

Co-authored-by: Zhi Chen <chzhi@amazon.com>
4 years ago[CI] Fix the hexagon string (#5304)
Tianqi Chen [Fri, 10 Apr 2020 17:58:59 +0000 (10:58 -0700)]
[CI] Fix the hexagon string (#5304)

4 years ago[Arith] linear system and equation solver (#5171)
Yizhi Liu [Fri, 10 Apr 2020 15:11:21 +0000 (08:11 -0700)]
[Arith] linear system and equation solver (#5171)

* [arith] linear system and equation solver

Co-authored-by: Sergei Grechanik <sergei.grechanik+h@gmail.com>
* avoid constructing analyzer every time

* generate random test cases and address comments

Co-authored-by: Sergei Grechanik <sergei.grechanik@gmail.com>
* rename linear_system to int_constraints

* add comments and use random seed

* message for reporting failure with seed

* add SEqualReduce to IntConstraints; allow variables & ranges to be None

Co-authored-by: Sergei Grechanik <sergei.grechanik+h@gmail.com>
Co-authored-by: Sergei Grechanik <sergei.grechanik@gmail.com>
4 years ago[PYTORCH]Repeat, Reciprocal & Reshape Op support (#5280)
Samuel [Fri, 10 Apr 2020 15:08:56 +0000 (20:38 +0530)]
[PYTORCH]Repeat, Reciprocal & Reshape Op support (#5280)

4 years ago[FRONTEND][TENSORFLOW] Fix gather_nd indices (#5279)
MORITA Kazutaka [Fri, 10 Apr 2020 14:47:53 +0000 (23:47 +0900)]
[FRONTEND][TENSORFLOW] Fix gather_nd indices (#5279)

* [FRONTEND][TENSORFLOW] Fix gather_nd indices

* retrigger CI

4 years agoUpdate device_annotation.cc (#5291)
weiliangweiliang [Fri, 10 Apr 2020 14:47:19 +0000 (22:47 +0800)]
Update device_annotation.cc (#5291)

4 years ago[REFACTOR][IR] Move to runtime::String (#5276)
Zhi [Fri, 10 Apr 2020 14:46:23 +0000 (07:46 -0700)]
[REFACTOR][IR] Move to runtime::String (#5276)

* Use runtime::String

* move string to tvm namespace

* add const char* constructor

* implicit cast from std::string

4 years ago[NDArray] Set shape_ in NDArray::FromDLPack (#5301)
hlu1 [Fri, 10 Apr 2020 14:42:54 +0000 (07:42 -0700)]
[NDArray] Set shape_ in NDArray::FromDLPack (#5301)

4 years ago[RUNTIME] Initial implementation of Hexagon runtime support (#5252)
Krzysztof Parzyszek [Fri, 10 Apr 2020 13:47:59 +0000 (08:47 -0500)]
[RUNTIME] Initial implementation of Hexagon runtime support (#5252)

* [RUNTIME] Initial implementation of Hexagon runtime support

This is only the TVM runtime. The FastRPC libraries, simulator driver,
etc. will be provided in subsequent commits.

* Fix pylint complaints

* Fix some more pylint complaints

* Add link to the Hexagon SDK website

* Extract VTCM marker into a common variable

* Implement device->device memory copy

* Disable unsigned PDs by default

* Ensure that --hvx_length is present in sim_args if HVX is enabled

* Remove the line about clang from README.md

Apparently things work with libstdc++.

* Mention to set USE_RPC=OFF when building libtvm_runtime.so for Hexagon

* Remember to use codegen_hvx in validate_hvx_length

* Add a line about minimum version of LLVM

4 years ago[BYOC] Refine DNNL Codegen (#5288)
Cody Yu [Fri, 10 Apr 2020 07:29:39 +0000 (00:29 -0700)]
[BYOC] Refine DNNL Codegen (#5288)

* Improve DNNL

* Add bind params

* trigger ci

4 years agoAdding support for TFLite QnnSub operator. (#5230)
shoubhik [Fri, 10 Apr 2020 05:32:28 +0000 (22:32 -0700)]
Adding support for TFLite QnnSub operator. (#5230)

4 years ago[NODE] General serialzation of leaf objects into bytes. (#5299)
Tianqi Chen [Fri, 10 Apr 2020 05:04:08 +0000 (22:04 -0700)]
[NODE] General serialzation of leaf objects into bytes. (#5299)

This PR refactors the serialization mechanism to support general
serialization of leaf objects into bytes.

The new feature superceded the original GetGlobalKey feature for singletons.
Added serialization support for runtime::String.

4 years agoLegalize - Use Non-recursive Rewriter. (#5296)
Animesh Jain [Fri, 10 Apr 2020 04:01:35 +0000 (21:01 -0700)]
Legalize - Use Non-recursive Rewriter. (#5296)

* Legalize - Use Non-recursive Rewriter.

* Cleanup.

4 years ago[Node] Provide guide to user who has difficulty register SEqualReduce (#5300)
Yizhi Liu [Fri, 10 Apr 2020 03:58:43 +0000 (20:58 -0700)]
[Node] Provide guide to user who has difficulty register SEqualReduce (#5300)

4 years ago[TENSORFLOW]reduce ops updated (#5180)
Samuel [Fri, 10 Apr 2020 01:56:47 +0000 (07:26 +0530)]
[TENSORFLOW]reduce ops updated (#5180)

4 years agoCreate loops according to storage scope and thread hierarchies (#5190)
yongfeng-nv [Fri, 10 Apr 2020 01:49:37 +0000 (21:49 -0400)]
Create loops according to storage scope and thread hierarchies (#5190)

* Set IterVar index to 0 for local thread bound IterVars.

* Lint fix

* Use rank instead of scope name to predicate.  Add tests.

* Handle cases other than local/threadIdx.

* Turn warp to the old behavior.

* Modify test to cover global/blockIdx.

* Fix a typo.

* Update test_te_schedule_ops.py with more testing coverage in test_local_stage_predicate; remove test_schedule_schedule_ops.py which was added by mistake.

4 years ago[CI] Temporary disable CRT test (#5297)
Tianqi Chen [Fri, 10 Apr 2020 00:55:20 +0000 (17:55 -0700)]
[CI] Temporary disable CRT test (#5297)

4 years ago[BUGFIX] Fix CRT static test bug (#5293)
Tianqi Chen [Thu, 9 Apr 2020 19:48:51 +0000 (12:48 -0700)]
[BUGFIX] Fix CRT static test bug (#5293)

* [CI][DOCS] Make sure to refresh the cython part

* [BUGFIX] Fix CRT static test bug

* Fix demo_static

* resolve review comment

4 years ago[BUGFIX][IR] Fix String SEqual (#5275)
Zhi [Wed, 8 Apr 2020 21:20:16 +0000 (14:20 -0700)]
[BUGFIX][IR] Fix String SEqual (#5275)

* fix String SEqual

* retrigger ci

4 years agoupdate compiler version in docs (#5281)
Luis Vega [Wed, 8 Apr 2020 20:46:52 +0000 (13:46 -0700)]
update compiler version in docs (#5281)

4 years ago[LINT] Remove scalalint from lint deps (#5269)
Haichen Shen [Wed, 8 Apr 2020 03:55:48 +0000 (20:55 -0700)]
[LINT] Remove scalalint from lint deps (#5269)

4 years ago[LLVM] Include Support/Host.h for declaration of getDefaultTargetTriple (#5268)
Krzysztof Parzyszek [Wed, 8 Apr 2020 03:53:25 +0000 (22:53 -0500)]
[LLVM] Include Support/Host.h for declaration of getDefaultTargetTriple (#5268)

In newer versions of LLVM, this header is no longer included by one of
the already included headers in llvm_common.h, so include it explicitly.

4 years ago[PYTORCH]celu, gelu, selu activations (#5263)
Samuel [Wed, 8 Apr 2020 03:45:41 +0000 (09:15 +0530)]
[PYTORCH]celu, gelu, selu activations (#5263)

4 years ago[RELAY][BYOC] Add support for composite functions in BYOC (#5261)
mbaret [Wed, 8 Apr 2020 03:12:15 +0000 (04:12 +0100)]
[RELAY][BYOC] Add support for composite functions in BYOC (#5261)

* [RELAY] Add 'check' functions to MergeComposite

Currently, MergeComposite can only perform structural
matches. This patch introduces the ability to specify
a 'check' function alongside the pattern which can include
custom logic to determine whether an extracted pattern
should be merged.

For example, if you only want to merge 'NHWC' convolutions,
you can specify a 'check' function which queries the
data_layout value of the extracted pattern (see the test).

Change-Id: I9337ce39f10997051a286d888be38ed0d410d340

* [RELAY] Reformat merge_composite.cc

Run clang-format on merge_composite.cc

Change-Id: I1736bff798cc6d93e57519b08ab3362869098779

* [RELAY][BYOC] Support composite functions in AnnotateTarget

This patch introduces support to annotate composite functions
in the AnnotateTarget pass. In order for a composite function
to be annotated, you should name it according to the style:

{codegen}.{name}
eg. dnnl.add_relu

Change-Id: I74d6c0b506153d866f6d1feb203b32dad59f2871

4 years ago[RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime (#4459)
tobe [Tue, 7 Apr 2020 23:59:32 +0000 (07:59 +0800)]
[RUNTIME] Implement TVMDSOOp(TensorFlow custom op) for TVM runtime (#4459)

* Add implementation of TVMDSOOp

* feat: Update cmake script to work with c++11 and in-repo build

* feat: Use libtvm as oplib dependency

* fix: Add missing link dependency to libtvm

* feat: Update tf tvmdso op by review comments

* fix: Update with pr comments

* fix: Fix lint

* feat: Add test script and fix gpu shape

* feat: Add test script and fix gpu shape

* fix: Conditional build tftvm op for gpu

* fix: Conditional build tftvm op for gpu

* fix: Fix pylint of tf_op module.py

* fix: Fix pylint of tf_op module.py

* feat: Conditional enable gpu test for tftvm op

* feat: Conditional enable gpu test for tftvm op

* feat: Add tf_tvmdsoop test script as an app test

* fix: Fix gpu/cpu enabled check on tvm in test script

* fix: Make tf tvmdso op test script runnable with pytest

* remove unused test script test_tfop_module.py

* fix: Remove pushd & popd in tfdsoop test script

* fix: Upgrade tftvmop use python3 to find TensorFlow

* fix: Upgrade tftvmop use python3 to find TensorFlow

* fix: Change target_link_options to target_link_libraries

* fix: Add tftvmop build script's c++ option

* fix: Add tvm library path to tf op test library path

* fix: Debug ci build for tftvm dso op

* fix: Fix cmake error and skip tfop test

* fix: Fix typo and indentation issues

* feat: Use TF list input op def

* fix: Fix style and unexpected changes

Co-authored-by: baoxinqi <baoxinqi@4paradigm.com>
Co-authored-by: Chen Dihao <chendihao@4paradigm.com>
Co-authored-by: wrongtest <wrongtest@4paradigm.com>
4 years ago[LLVM] Do not use x86_vcvtph2ps_256 intrinsic with LLVM 11+ (#5267)
Krzysztof Parzyszek [Tue, 7 Apr 2020 23:58:33 +0000 (18:58 -0500)]
[LLVM] Do not use x86_vcvtph2ps_256 intrinsic with LLVM 11+ (#5267)

This intrinsic was removed in LLVM 11.

4 years ago[RUNTIME] Quick fix PackedFunc String passing (#5266)
Tianqi Chen [Tue, 7 Apr 2020 23:33:12 +0000 (16:33 -0700)]
[RUNTIME] Quick fix PackedFunc String passing (#5266)

4 years ago[LLVM] Use llvm::ElementCount with LLVM 11+ when creating vectors (#5265)
Krzysztof Parzyszek [Tue, 7 Apr 2020 22:49:07 +0000 (17:49 -0500)]
[LLVM] Use llvm::ElementCount with LLVM 11+ when creating vectors (#5265)

LLVM 11 added support for scalable vectors, and now the number of
elements in a vector is represented by a llvm::ElementCount class,
not just a number.

4 years ago[LLVM] Use llvm::Align with LLVM 11+ to avoid warnings (#5264)
Krzysztof Parzyszek [Tue, 7 Apr 2020 22:48:59 +0000 (17:48 -0500)]
[LLVM] Use llvm::Align with LLVM 11+ to avoid warnings (#5264)

LLVM 11 is introducing a separate class to represent alignment.
The functions in IRBuilder that create aligned loads and stores,
and which accept the alignment as an unsigned value have been
deprecated (and now cause warnings to be emitted).

4 years ago[uTVM][Runtime] Introduce Virtual Memory Allocator to CRT (#5124)
Liangfu Chen [Tue, 7 Apr 2020 21:33:05 +0000 (05:33 +0800)]
[uTVM][Runtime] Introduce Virtual Memory Allocator to CRT (#5124)

* initial crt_memory and memory leak fix in graph_runtime

Change-Id: I0f79f909a04d1c677aabb80f202f0612c5ce7f2a

* fix memory leak

Change-Id: I37104c09e28112b1974fa2b064c809d0a8d686c3

* clean up

Change-Id: I039b12015a1d56c8f4120867cd5a5292da34f3e3

* implement vrealloc

Change-Id: I35800470bcbfcf96652494f359711cb4c2d34398

* allocate from stack memory for most of the variables

Change-Id: I72071289843fff4031c0df8796868a0b9fbc57ee

* allocate from stack memory for all of the variables

Change-Id: I32dba85ac1660c77f51c2d0d8ab6436ed0c01c74

* lint

Change-Id: If12cd240685d7791fc60bc0cfb66389cdc186b73

* lint

Change-Id: I7c9d90c11b60b8edda2427ebd189ebe535af2100

* facilitate the growth of TVM_CRT_MAX_NDIM

Change-Id: I939fa43027a5c7529c5c7c6bd8d6e6beb91b7581

* extend test coverage of vmalloc

Change-Id: Ie4ff6b64fdfe6810836cf8fd44dace82a20c4581

* lint

Change-Id: Ibf3c06619ef296df5c49f3945cb6428777781d69

* move logging.h to src

* fix an error in macOS

* remove logging.h

* use cflags for gcc

* fix compilation error

4 years ago[Relay][OP] Add fast_erf implementation (#5241)
Haichen Shen [Tue, 7 Apr 2020 19:05:33 +0000 (12:05 -0700)]
[Relay][OP] Add fast_erf implementation (#5241)

* add fast erf

* doc

* lint

* fix

* fix indent

4 years ago[TIR] Fix perf regression of tir refactor (#5258)
Tianqi Chen [Tue, 7 Apr 2020 17:24:55 +0000 (10:24 -0700)]
[TIR] Fix perf regression of tir refactor (#5258)

4 years agoFixed typo and type mismatch (#5259)
Adrian Muresan [Tue, 7 Apr 2020 15:21:23 +0000 (17:21 +0200)]
Fixed typo and type mismatch (#5259)

Co-authored-by: Adrian Muresan <muresan.adrian.bn@gmail.com>
4 years ago[Pytorch]layernorm bug fix and testcase updated (#5257)
Samuel [Tue, 7 Apr 2020 10:13:45 +0000 (15:43 +0530)]
[Pytorch]layernorm bug fix and testcase updated (#5257)

4 years ago[TFLITE]Hard Swish & MobilnetV3 model testing (#5239)
Samuel [Tue, 7 Apr 2020 08:14:02 +0000 (13:44 +0530)]
[TFLITE]Hard Swish & MobilnetV3 model testing (#5239)

* [TFLITE]Hard Swish & MobilnetV3 model testing

* CI Failure addressed

4 years ago[TE] Minor bugfix in message_passing.cc (#5254)
Pratik Fegade [Tue, 7 Apr 2020 02:04:20 +0000 (22:04 -0400)]
[TE] Minor bugfix in message_passing.cc (#5254)

4 years ago[Topi] Breakdown topi.cc into smaller files (#5253)
Haichen Shen [Mon, 6 Apr 2020 21:30:53 +0000 (14:30 -0700)]
[Topi] Breakdown topi.cc into smaller files (#5253)

* [Topi] Breakdown topi.cc into smaller files

* add missing file

4 years ago[PYTORCH]LayerNorm support added (#5249)
Samuel [Mon, 6 Apr 2020 20:31:19 +0000 (02:01 +0530)]
[PYTORCH]LayerNorm support added (#5249)

4 years ago[RUNTIME] Enable auto conversion from str to runtime::String in PackedFunc, move...
Tianqi Chen [Mon, 6 Apr 2020 20:25:00 +0000 (13:25 -0700)]
[RUNTIME] Enable auto conversion from str to runtime::String in PackedFunc, move dtype related handling to data_type.h (#5251)

4 years agofix lower_warp_memory (#5247)
Tang, Shizhi [Mon, 6 Apr 2020 15:43:38 +0000 (23:43 +0800)]
fix lower_warp_memory (#5247)

4 years agofix to skip node not in graph. (#5238)
chinakook [Mon, 6 Apr 2020 15:42:01 +0000 (23:42 +0800)]
fix to skip node not in graph. (#5238)

fix to skip node not in graph because some network cannot be hybridized with some var unused.

4 years ago[CI] Update MxNet to 1.6.0 with MKL (#5240)
Haichen Shen [Mon, 6 Apr 2020 06:38:24 +0000 (23:38 -0700)]
[CI] Update MxNet to 1.6.0 with MKL (#5240)

4 years ago[Runtime][Contrib] Support cudnn softmax (#5214)
Haichen Shen [Mon, 6 Apr 2020 03:53:59 +0000 (20:53 -0700)]
[Runtime][Contrib] Support cudnn softmax (#5214)

4 years ago[Relay][Topi][AutoTVM] Winograd support for Conv3D (#5186)
Josh Fromm [Sun, 5 Apr 2020 21:59:38 +0000 (14:59 -0700)]
[Relay][Topi][AutoTVM] Winograd support for Conv3D (#5186)

* Functional conv3d winograd working.

* Formatted python code.

* registered conv3d winograd compute and started adding relay without_weight_transform operator.

* Add topi testing for conv3d winograd.

* Format file.

* small tweak to unrolling to prevent build sticking.

* Refactoring convolution ops in relay.

* Refactored relay convolutions.

* Bug fixes.

* Fixed static bug in convolution.

* Added conv3d alter op layout and related support.

* Bug fixes and testing done.

* Fix a few autotvm bugs.

* Drop silly debug print.

* Removed debug_skip_region.

* Add variant of conv3d_winograd that doesn't transform depth.

* initial infrastructure done for depthless conv.

* Fix no_depth schedule bugs.

* automatic topi switching between depth and depthless winograd.

* Fixed bug in schedule.

* lint fixes.

* Removed indents in convolution.cc

* missed a few indents oops.

* fixed flop count.

* One more small tweak.

* Change kernel pack inner axes order.

* Style changes.

* Comment fixes.

4 years ago[Fix][VM] Fix copy constructor (#5237)
ga [Sun, 5 Apr 2020 20:45:43 +0000 (16:45 -0400)]
[Fix][VM] Fix copy constructor (#5237)

4 years ago[Relay][ADT]Static Tensor Array (#5103)
Yao Wang [Sun, 5 Apr 2020 20:42:28 +0000 (13:42 -0700)]
[Relay][ADT]Static Tensor Array (#5103)

* Add other static tensor array ops

* Add tensor array get data

* Minor refactor

* Fix pylint

* Update docstring

* Make get data more generic

* Improve test

* Improve split test

* Improve get data

* Minor fix

* Further improvement for static shape

* Improve shape parsing

* Unify get_static_name

4 years ago[REFACTOR][TIR] Migrate all low-level passes to the Pass Manager. (#5233)
Tianqi Chen [Sun, 5 Apr 2020 00:36:49 +0000 (17:36 -0700)]
[REFACTOR][TIR] Migrate all low-level passes to the Pass Manager. (#5233)

* [REFACTOR][TIR] Migrate all low-level passes to the Pass Manager.

This PR migrates the tvm.lower to return IRModule of PrimFuncs
instead of the LoweredFuncs.

* Remove LoweredFunc.

4 years ago[ONNX]Pool3d & upsample3d op support (#5135)
Samuel [Sat, 4 Apr 2020 09:33:43 +0000 (15:03 +0530)]
[ONNX]Pool3d & upsample3d op support (#5135)

* [ONNX]Pool3d and Upsample3d op updated

* Pool3d and Upsample3d testcase

* Review comments fixed

* Review comments

4 years agoFix intel conv2d auto tune (#5200)
Yao Wang [Sat, 4 Apr 2020 03:46:32 +0000 (20:46 -0700)]
Fix intel conv2d auto tune (#5200)

* Fix x86 conv2d and depthwise conv2d auto tuning

* Fix depthwise conv2d infer layout

* Use random data instead of empty data for autotvm

* Fix pylint

* Keep empty array for now for autotvm

4 years ago[TE] Support mixing normal and cross-thread reduction (#5193)
Tang, Shizhi [Sat, 4 Apr 2020 01:49:56 +0000 (09:49 +0800)]
[TE] Support mixing normal and cross-thread reduction (#5193)

* Support mixing normal and cross-thread reduction

* minor improvements

4 years ago[REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager. (#5225)
Tianqi Chen [Fri, 3 Apr 2020 22:50:11 +0000 (15:50 -0700)]
[REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager. (#5225)

* [REFACTOR][TIR] Migrate most of low-level build to use the Pass Manager.

- SplitHostDevice
- ThreadSync
- BindDevice
- LowerThreadAllreduce
- Provide a temp fix for printing IRModule with PrimFunc before the formal text printer.

* Address comments, fix tests.

* Fix relay tests

* Explicit move

4 years ago[PYTHON] Make IntImm more like an integer (#5232)
Tianqi Chen [Fri, 3 Apr 2020 22:24:19 +0000 (15:24 -0700)]
[PYTHON] Make IntImm more like an integer (#5232)

4 years ago[RELAY] Non-recursive Graph Vistor and Rewriter (#4886)
Matthew Brookhart [Fri, 3 Apr 2020 21:35:55 +0000 (14:35 -0700)]
[RELAY] Non-recursive Graph Vistor and Rewriter (#4886)

* First pass a defining a non-recursive Graph Vistor and Rewriter

autoformat

remove a currently empty test until testing is solidfied

* Make CalcDep from Dead Code Elimination non-recursive

* Partially working, not passing all tests yet

passes tests when disabling GetExprRefCount, I think I have a bug in visit counting

fix GetExprRefCount

Fix a subtle bug with nested recursive/non-recursive scopes

* Refactor

* improve comments

* respond to review comments on comments

* Fix a problem with default recursion for dataflow nodes

mark DataflowVisitor methods as override

* implement ScopeMutator

* convert forward_rewrite to ScopeMutator, remove DataflowMutator

* rewrite ExprRewriter and convert fast_math to use it

* switch BiasAddSimplifier to ExprRewriter

fix a clang warning

fix cpp lint

fix doc param error

* respond to review comments

* fix a typo in the iterative looping

* add a regression test for GetExprRefCount issue

* Normalize naming

* fix lint

* First pass a defining a non-recursive Graph Vistor and Rewriter

autoformat

remove a currently empty test until testing is solidfied

* Make CalcDep from Dead Code Elimination non-recursive

* Partially working, not passing all tests yet

passes tests when disabling GetExprRefCount, I think I have a bug in visit counting

fix GetExprRefCount

Fix a subtle bug with nested recursive/non-recursive scopes

* Refactor

* improve comments

* respond to review comments on comments

* Fix a problem with default recursion for dataflow nodes

mark DataflowVisitor methods as override

* implement ScopeMutator

* convert forward_rewrite to ScopeMutator, remove DataflowMutator

* rewrite ExprRewriter and convert fast_math to use it

* switch BiasAddSimplifier to ExprRewriter

fix a clang warning

fix cpp lint

fix doc param error

* respond to review comments

* fix a typo in the iterative looping

* add a regression test for GetExprRefCount issue

* Normalize naming

* fix lint

* respond to review comments

4 years ago[TOPI x86] Adding unroll_kw config option for depthwise conv2d. (#5197)
Animesh Jain [Fri, 3 Apr 2020 19:11:32 +0000 (12:11 -0700)]
[TOPI x86] Adding unroll_kw config option for depthwise conv2d. (#5197)

4 years ago[RELAY][FIX] Fix hang in MergeCompilerRegions (#5227)
mbaret [Fri, 3 Apr 2020 16:33:15 +0000 (17:33 +0100)]
[RELAY][FIX] Fix hang in MergeCompilerRegions (#5227)

For certain network topologies, MCR could hang.
This patch fixes that case.

Change-Id: I3edd8a8a6b452b2b838b777720adea22a3b995b4

4 years ago[KERAS]Upsample3d & ZeroPadding3d op (#5125)
Samuel [Fri, 3 Apr 2020 16:04:41 +0000 (21:34 +0530)]
[KERAS]Upsample3d & ZeroPadding3d op (#5125)

* [KERAS]upsampling3d and zeropadding3d op

* [KERAS]upsampling3d and zeropadding3d test case

* Review comments updated

4 years ago[DOCSTRING]missing function parameters updated (#5228)
Samuel [Fri, 3 Apr 2020 13:41:28 +0000 (19:11 +0530)]
[DOCSTRING]missing function parameters updated (#5228)

4 years ago[CodeGen][CUDA] Fix bugs (#5209)
Wei Pan [Fri, 3 Apr 2020 06:57:40 +0000 (23:57 -0700)]
[CodeGen][CUDA] Fix bugs (#5209)

- Support vectorized casts

- It is incorrect to extract elements from int8x4 with

   0x000000ff & (x >> i * 8)

  as this value is of type int in C/C++. If this expression
  is used for sign extensions, the sign bit will be wrong.
  Simply use C style casts instead and sign bits will just work.

Signed-off-by: Wei Pan <weip@nvidia.com>
4 years ago[REFACTOR] tvm.hybrid -> te.hybrid (#5223)
Tianqi Chen [Thu, 2 Apr 2020 23:56:24 +0000 (16:56 -0700)]
[REFACTOR] tvm.hybrid -> te.hybrid (#5223)

Rationale: The current hybrid module is more aligned with the te part.
We might consider add a new varient of hybrid script that support the unified IR later.
This refactor paves for the potential later changes.

4 years ago[DOCS] Misc docs improvements (#5222)
Tianqi Chen [Thu, 2 Apr 2020 23:56:11 +0000 (16:56 -0700)]
[DOCS] Misc docs improvements (#5222)

- Reduce CI docs task log size.
- Update the relation to halide to the latest state.

4 years ago[PYTORCH]AvgPool3d, MaxPool3d and Squeeze op support (#5220)
Samuel [Thu, 2 Apr 2020 22:20:41 +0000 (03:50 +0530)]
[PYTORCH]AvgPool3d, MaxPool3d and Squeeze op support (#5220)

* [PYTORCH]AvgPool3d, MaxPool3d and Squeeze op support

* Testcases added

* review comments

4 years ago[REFACTOR][TIR] Migrate low-level pass functions to Pass Manager, (#5213)
Tianqi Chen [Thu, 2 Apr 2020 20:22:23 +0000 (13:22 -0700)]
[REFACTOR][TIR] Migrate low-level pass functions to Pass Manager, (#5213)

- Migrate LowerTVMBultin
- Migrate inferFragment, LowerThreadAllreduce
- Migrate ThreadSync
- Refactor target::Build to directly take IRModule.
- Remove un-used legacy functions.

4 years ago[TIR] Introduce BufferLoad/Store (#5205)
Tianqi Chen [Thu, 2 Apr 2020 19:36:55 +0000 (12:36 -0700)]
[TIR] Introduce BufferLoad/Store (#5205)

Co-authored-by: Siyuan Feng <hzfengsy@sjtu.edu.cn>
This PR introduces BufferLoad/Store to TIR. The new nodes will replace
Provide and Call with Tensor arguments in the subsequent refactors.

4 years ago[TIR][PASS] dtype rewrite for indexing variables (#5092)
Haozheng Fan [Thu, 2 Apr 2020 16:04:33 +0000 (00:04 +0800)]
[TIR][PASS] dtype rewrite for indexing variables (#5092)

4 years ago[Runtime][Object] expose runtime::String to Python (#5212)
Zhi [Thu, 2 Apr 2020 15:56:37 +0000 (08:56 -0700)]
[Runtime][Object] expose runtime::String to Python (#5212)

* expose runtime::String to Python

* retrigger ci

4 years ago[REFACTOR][IR] kExternalSymbol -> kGlobalSymbol (#5211)
Zhi [Thu, 2 Apr 2020 15:30:46 +0000 (08:30 -0700)]
[REFACTOR][IR] kExternalSymbol -> kGlobalSymbol (#5211)

* expose runtime::String to Python

* kExternalSymbol -> kGlobalSymbol

4 years ago[Frontend][Torch] Fix up graph input handling (#5204)
Jeremy Johnson [Thu, 2 Apr 2020 15:29:14 +0000 (16:29 +0100)]
[Frontend][Torch] Fix up graph input handling (#5204)

* [Frontend][Torch] Simplify operator input handling

* [Frontend][Torch] Allow user supplied input names to override graph inputs

* Fix pylint issues

* Updates from code review feedback

* Fix tutorial to use shape list input

* Disable intermittent test failure in topi vision test

4 years ago[Debug] Add Dump function for Object type (NFC) (#5207)
Wei Pan [Thu, 2 Apr 2020 02:44:52 +0000 (19:44 -0700)]
[Debug] Add Dump function for Object type (NFC) (#5207)

Signed-off-by: Wei Pan <weip@nvidia.com>
4 years ago[DOCS] Reduce artifcats generated by sphinx gallery (#5208)
Tianqi Chen [Thu, 2 Apr 2020 02:44:42 +0000 (19:44 -0700)]
[DOCS] Reduce artifcats generated by sphinx gallery (#5208)

4 years ago[REFACTOR][TIR] Introduce ExprDeepEqual, Remove IRDeepCompare (#5206)
Tianqi Chen [Thu, 2 Apr 2020 00:14:49 +0000 (17:14 -0700)]
[REFACTOR][TIR] Introduce ExprDeepEqual, Remove IRDeepCompare (#5206)

* [REFACTOR][TIR] Introduce ExprDeepEqual, Remove IRDeepCompare

This PR introduces ExprDeepEqual which reuses the StructuralEqual infra.
We migrated the usecases of ir_pass::Equal to ExprDeepEqual and StructuralEqual.

* Address comments

4 years ago[RELAY] Fixes to MergeCompilerRegions (#5195)
mbaret [Wed, 1 Apr 2020 23:16:31 +0000 (00:16 +0100)]
[RELAY] Fixes to MergeCompilerRegions (#5195)

* [RELAY] Fixed issues with MergeCompilerRegions

This PR addresses a few outstanding issues with
the implementation of MergeCompilerRegions. In
particular, it now handles TupleGetItem nodes properly
and other minor bugs related to region merging have
been fixed.

Change-Id: I07783afc56183a6f798a510209f23b0a5f252255

* Fixed issue using pre-merged regions

Change-Id: I0a844ac59bda1089ae0c67cef52f0b0c7ab2cbd7

* Removed some debugging logic

Change-Id: Ib6f2eede6f38bbb270073eb8d4c4dc19f60832c6

* Remove default annotations

Change-Id: I9b7696a51c95871491cbea33c40f92ec327e417f

* Annotate default 'if's

Change-Id: I0098bd1bf6788dd6366810dcefa84f1ebbffaab0

* Clang format

Change-Id: I944365cd3080a97a9261f643a8f1efa5a63cf82b

* Use src/dest in merge

Change-Id: Ie43113492bda8f1ce63eaf9615cb645bb9e2ee86

* Fixed partition test

Change-Id: I46f9e349b1a813a9140f7e4f8a2241687e2df73b

* Removed comments

Change-Id: I309afdd1951d7e796e41d13788aa487707e0ac4c