platform/upstream/tvm.git
4 years ago[Relay] Conv2d grad (#3636)
Wuwei Lin [Thu, 29 Aug 2019 17:36:06 +0000 (13:36 -0400)]
[Relay] Conv2d grad (#3636)

* [Relay] Conv2d grad

* Fix test

* Fix first order gradient

4 years agoAdd build_create_shared_func to tvm/contrib/cc.py (#3840)
Alexander Pivovarov [Thu, 29 Aug 2019 16:59:40 +0000 (09:59 -0700)]
Add build_create_shared_func to tvm/contrib/cc.py (#3840)

4 years agoImprovements in conda recipe (#3791)
Marcelo Duarte Trevisani [Thu, 29 Aug 2019 03:14:04 +0000 (04:14 +0100)]
Improvements in conda recipe (#3791)

4 years ago[TEST] Not assuming HOME in tvm/download.py (#3803)
Neo Chien [Thu, 29 Aug 2019 03:12:28 +0000 (11:12 +0800)]
[TEST] Not assuming HOME in tvm/download.py (#3803)

* Not assuming HOME in tvm/download.py

* Trigger notification

4 years ago[runtime] reduce set_input and set_input_zero_copy overhead (#3805)
hlu1 [Thu, 29 Aug 2019 03:08:21 +0000 (20:08 -0700)]
[runtime] reduce set_input and set_input_zero_copy overhead (#3805)

4 years ago[TensorFlow] Fix limitation that depth_mult can only be 1 for DepthwiseConv2dNative...
lixiaoquan [Thu, 29 Aug 2019 02:59:06 +0000 (10:59 +0800)]
[TensorFlow] Fix limitation that depth_mult can only be 1 for DepthwiseConv2dNative (#3676)

* [TensorFlow] Fix limitation that depth_mult can only be 1 for DepthwiseConv2dNative

* Improve code readability

4 years agoSupport MKL on Windows (#3837)
Jon Soifer [Thu, 29 Aug 2019 02:44:43 +0000 (19:44 -0700)]
Support MKL on Windows (#3837)

4 years ago[AutoTVM] Fix database APIs (#3821)
Cody Hao Yu [Wed, 28 Aug 2019 17:04:12 +0000 (10:04 -0700)]
[AutoTVM] Fix database APIs (#3821)

* [AutoTVM] Fix database APIs

* Refactor the byte conversion

4 years ago[Relay][Keras] Dot (#3668)
Yong Wu [Wed, 28 Aug 2019 06:16:48 +0000 (23:16 -0700)]
[Relay][Keras] Dot (#3668)

* [Relay][Keras] Dot

* fix reshape

* fix comments

4 years ago[Bugfix][Keras] axis of softmax (#3834)
Yong Wu [Wed, 28 Aug 2019 02:15:51 +0000 (19:15 -0700)]
[Bugfix][Keras] axis of softmax (#3834)

4 years ago[VTA] Parameterization and bug fix in TensorLoad module (#3841)
Liangfu Chen [Tue, 27 Aug 2019 06:13:18 +0000 (14:13 +0800)]
[VTA] Parameterization and bug fix in TensorLoad module (#3841)

4 years agoupdate docs for installation for CUDA (#3832)
Yixing Jiang [Mon, 26 Aug 2019 18:41:27 +0000 (11:41 -0700)]
update docs for installation for CUDA (#3832)

4 years agoFix inconsistent python/cpp API behavior for if_then_else, power (#3829)
Xingjian Shi [Mon, 26 Aug 2019 18:31:10 +0000 (11:31 -0700)]
Fix inconsistent python/cpp API behavior for if_then_else, power (#3829)

* fix inconsistent python/cpp APIs for if_then_else

* fix error message

* fix power consistency

* fix

* fix bug

* add test

4 years ago[VTA][TSIM] Introduce Virtual Memory for TSIM Driver (#3686)
Liangfu Chen [Mon, 26 Aug 2019 16:36:23 +0000 (00:36 +0800)]
[VTA][TSIM] Introduce Virtual Memory for TSIM Driver (#3686)

* initial virtual memory;

* initial integration;

* include the header file in cmake;

* implement allocation with virtual to logical address mapping;

* virtual memory for tsim_driver;

* implement the missing memory release function;

* readability improvement;

* readability improvement;

* address review comments;

* improved robustness in virtual memory allocation;

* remove VTA_TSIM_USE_VIRTUAL_MEMORY macro and use virtual memory for tsim by default;

* link tvm against vta library;

* merge with master

* build virtual memory system without linking tvm against vta;

* minor change;

* reuse VTA_PAGE_BYTES;

* using DRAM class from sim_driver as VirtualMemoryManager;

* satisfy linter;

* add comments in code;

* undo changes to Makefile

* undo changes to Makefile

* retrigger ci;

* retrigger ci;

* directly call into VirtualMemoryManager::Global()

4 years agoFix code comment of operators (#3830)
Neo Chien [Sat, 24 Aug 2019 20:32:55 +0000 (04:32 +0800)]
Fix code comment of operators (#3830)

4 years agoFixed repo change for llvm-9 to resolve missing dependency issue when building images...
tristan-arm [Fri, 23 Aug 2019 13:06:54 +0000 (14:06 +0100)]
Fixed repo change for llvm-9 to resolve missing dependency issue when building images with llvm enabled (#3826)

4 years agoUpdate hybrid_script.rst (#3799)
Haibin Lin [Fri, 23 Aug 2019 04:50:59 +0000 (21:50 -0700)]
Update hybrid_script.rst (#3799)

4 years ago[Legalize][QNN] Pass out_types to Legalize. Update QNN requantize to read from out_ty...
Animesh Jain [Fri, 23 Aug 2019 04:50:00 +0000 (21:50 -0700)]
[Legalize][QNN] Pass out_types to Legalize. Update QNN requantize to read from out_types. (#3782)

4 years ago[CODE] Halide attributions (#3824)
Tianqi Chen [Fri, 23 Aug 2019 04:21:49 +0000 (12:21 +0800)]
[CODE] Halide attributions (#3824)

4 years ago[Relay] Fix typo in parser (#3785)
雾雨魔理沙 [Fri, 23 Aug 2019 03:16:15 +0000 (20:16 -0700)]
[Relay] Fix typo in parser (#3785)

4 years ago[TVM] Fix warnings (#3817)
lixiaoquan [Thu, 22 Aug 2019 23:05:35 +0000 (07:05 +0800)]
[TVM] Fix warnings (#3817)

transform.h:118:3: warning: 'const' type qualifier on return type has no
effect
attrs.h:68:3: note: expanded from macro 'TVM_DECLARE_ATTRS'
node.h:244:3: note: expanded from macro 'TVM_DECLARE_NODE_TYPE_INFO'

transform.h:95:3: warning: extra ';' after member function definition
attrs.h:68:62: note: expanded from macro 'TVM_DECLARE_ATTRS'

4 years ago[TOPI][Relay][TensorFlow] Add OneHot operator (#3781)
Jon Soifer [Thu, 22 Aug 2019 20:45:45 +0000 (13:45 -0700)]
[TOPI][Relay][TensorFlow] Add OneHot operator (#3781)

* Add one-hot to Relay

* topi implementation

* Working

* add topi test

* Add TF test

* Fix check

* fix linting issues

* fix documentation

* Fix documentation

* Add support for on_value, off_value, axis, dtype

* Add full support for axis

* Fix compute and update test_forward

* Move on_value and off_value to inputs

* Add topi test

* Update tests

* Update docs

* Fix style

* re-enable tests

* Add one_hot to mxnet converter

4 years agoChanged topi cc resize to python implementation with new features. (#3788)
Josh Fromm [Thu, 22 Aug 2019 03:39:09 +0000 (20:39 -0700)]
Changed topi cc resize to python implementation with new features. (#3788)

4 years ago[TOPI] Use cblas for dense and batch_matmul when "cblas" is in the target libraries...
Jon Soifer [Wed, 21 Aug 2019 05:24:10 +0000 (22:24 -0700)]
[TOPI] Use cblas for dense and batch_matmul when "cblas" is in the target libraries (#3787)

* Support cblas library in dense

* start to add support for generic batch_matmul compute

* Add x86 override for batch_matmul

* Fix linting

* reset file

* Fix typos

* dummy change to re-trigger CI

4 years ago[Relay][VM]VM Profiler (#3727)
Wei Chen [Wed, 21 Aug 2019 04:28:05 +0000 (21:28 -0700)]
[Relay][VM]VM Profiler (#3727)

* [Relay][VM]VM debugger

* Report mean/min/max for op duration

* Typos

* Lint

* Lint

* Lint

* Support build debug VM in CMake

* Lint

* Enable VM debug in unit test

* Disable debug vm test until new docker image is built

* Add device sync code

* Fix qnn unit test

* Disable vm debug by default

* Rename files

* Rename classes

* Fix comment

* Fix comment

4 years agoadd gfx906 bc (#3808)
Peter Yeh [Wed, 21 Aug 2019 01:57:01 +0000 (18:57 -0700)]
add gfx906 bc (#3808)

4 years ago[dep] psutil (#3780)
Bing Xu [Tue, 20 Aug 2019 21:45:18 +0000 (14:45 -0700)]
[dep] psutil (#3780)

4 years ago[CI] Temporary disable rust test (#3809)
Tianqi Chen [Tue, 20 Aug 2019 21:44:23 +0000 (05:44 +0800)]
[CI] Temporary disable rust test (#3809)

4 years ago[CI] Solve occasional CI issue when pad value is all 0 (#3801)
Zhao Wu [Mon, 19 Aug 2019 21:50:49 +0000 (05:50 +0800)]
[CI] Solve occasional CI issue when pad value is all 0 (#3801)

4 years ago[Relay][Frontend][TFLite] transpose implementation for tflite.py (#3705)
Neo Chien [Mon, 19 Aug 2019 17:20:38 +0000 (01:20 +0800)]
[Relay][Frontend][TFLite] transpose implementation for tflite.py (#3705)

* transpose implementation for tflite.py

* add TRANSPOSE to convert_map

* Fix Unexpected keyword argument 'axis' in function call

* add test for transpose oprator

* Add the parameter 'axes' handling

* add test for transpose oprator

* solve conflict within CONTRIBUTORS.md

* Improve the if condition for empty tuple

* Add one unit test to cover empty tuple

* solve conflict within CONTRIBUTORS.md

4 years agoFixed onnx test failures when run on a cpu backend (#3764)
tristan-arm [Mon, 19 Aug 2019 16:33:43 +0000 (17:33 +0100)]
Fixed onnx test failures when run on a cpu backend (#3764)

* Fixed onnx test failures when run on a cpu backend

* Updated check_torch_conversion function to include output comparison

4 years ago[CoreML] Solve CoreML frontend issue of image scaler and padding so that Mobilenet...
Zhao Wu [Mon, 19 Aug 2019 06:05:41 +0000 (14:05 +0800)]
[CoreML] Solve CoreML frontend issue of image scaler and padding so that Mobilenet mlmodel can work correctly. (#3800)

4 years ago[TOPI, CUDA] Improve conv2d_transpose schedule template (#3796)
Wuwei Lin [Mon, 19 Aug 2019 05:58:09 +0000 (01:58 -0400)]
[TOPI, CUDA] Improve conv2d_transpose schedule template (#3796)

4 years ago[VTA][TSIM] parallel TSIM hardware compilation with macOS and debug support (#3797)
Liangfu Chen [Sun, 18 Aug 2019 23:19:22 +0000 (07:19 +0800)]
[VTA][TSIM] parallel TSIM hardware compilation with macOS and debug support (#3797)

* [VTA][TSIM] parallel hardware compilation with macOS and debug support

* simplify

4 years ago[Community] Hao Lu -> Committer (#3789)
ziheng [Sat, 17 Aug 2019 07:51:42 +0000 (00:51 -0700)]
[Community] Hao Lu -> Committer (#3789)

4 years agoFix ArgBinder assert order (#3794)
Wuwei Lin [Sat, 17 Aug 2019 03:28:46 +0000 (20:28 -0700)]
Fix ArgBinder assert order (#3794)

4 years ago[BUGFIX] Fix for NoneType Target (#3792)
ziheng [Fri, 16 Aug 2019 20:14:29 +0000 (13:14 -0700)]
[BUGFIX] Fix for NoneType Target (#3792)

4 years ago[Relay][Quantization] Fix out-of-date realize (#3790)
Wuwei Lin [Fri, 16 Aug 2019 06:23:08 +0000 (23:23 -0700)]
[Relay][Quantization] Fix out-of-date realize (#3790)

4 years agoQNN quantize and dequantize operators. (#3745)
shoubhik [Fri, 16 Aug 2019 03:29:34 +0000 (20:29 -0700)]
QNN quantize and dequantize operators. (#3745)

* QNN quantize and dequantize operators.

* addressing review comments.

* addressing review comments.

* Adding new line at the end of the file.

* Adhering to styling guidelines.

* Adding name to contributors.

* Fixing lint issue.

* Fixing file name.

* Removing unnecessary code.

4 years ago[Relay][Frontend][ONNX] Add Sign and Equal operators to ONNX frontend (#3760)
Jon Soifer [Thu, 15 Aug 2019 18:41:54 +0000 (11:41 -0700)]
[Relay][Frontend][ONNX] Add Sign and Equal operators to ONNX frontend (#3760)

* [Relay][Frontend][ONNX] Add Sign and Equal operators to ONNX frontend

* Dummy change to retrigger integration test

4 years ago[QUANTIZE] Refactor quantization codebase and fix model accuracy (#3543)
ziheng [Thu, 15 Aug 2019 09:31:30 +0000 (02:31 -0700)]
[QUANTIZE] Refactor quantization codebase and fix model accuracy (#3543)

* Refactor.

* update

* update

* update

* update

* update

* update

4 years ago[QNN] InferType changes that missed CI. (#3779)
Animesh Jain [Thu, 15 Aug 2019 06:35:15 +0000 (23:35 -0700)]
[QNN] InferType changes that missed CI. (#3779)

4 years ago[QNN] Concatenate operator (#3730)
Animesh Jain [Wed, 14 Aug 2019 23:56:58 +0000 (16:56 -0700)]
[QNN] Concatenate operator (#3730)

4 years ago[Relay][Legalize][ARM_CPU] Handling NHWC layout for arm_cpu. (#3754)
Animesh Jain [Wed, 14 Aug 2019 23:44:13 +0000 (16:44 -0700)]
[Relay][Legalize][ARM_CPU] Handling NHWC layout for arm_cpu. (#3754)

4 years ago[VTA][Chisel] scale dram base address in hardware instead of runtime (#3772)
Luis Vega [Wed, 14 Aug 2019 17:42:59 +0000 (10:42 -0700)]
[VTA][Chisel] scale dram base address in hardware instead of runtime (#3772)

* [VTA][Chisel] scale dram base address in hardware instead of runtime

* remove trailing spaces

4 years agofix dense tuning (#3768)
Thierry Moreau [Wed, 14 Aug 2019 07:17:19 +0000 (00:17 -0700)]
fix dense tuning (#3768)

4 years agofix (#3769)
雾雨魔理沙 [Wed, 14 Aug 2019 05:31:18 +0000 (22:31 -0700)]
fix (#3769)

4 years ago[Relay][Frontend][TensorFlow] Support BatchMatMul with input dimensions larger than...
Jon Soifer [Wed, 14 Aug 2019 00:15:45 +0000 (17:15 -0700)]
[Relay][Frontend][TensorFlow] Support BatchMatMul with input dimensions larger than 3 (#3732)

* Support BatchMatMul with shapes greater than length 3

* Fixes

* Add tests

* Remove dependency on Python3

* Clean up

* Merge with master

* Resolve comments

4 years agosyntax fix (#3765)
Benjamin Tu [Tue, 13 Aug 2019 23:03:13 +0000 (16:03 -0700)]
syntax fix (#3765)

4 years ago[VTA][Chisel] run all unittests by default (#3766)
Luis Vega [Tue, 13 Aug 2019 23:02:48 +0000 (16:02 -0700)]
[VTA][Chisel] run all unittests by default (#3766)

* [VTA][Chisel] run all unittests by default

* better naming

* add generated unittest folder to clean rule

4 years agofix some pass docs (#3767)
Zhi [Tue, 13 Aug 2019 22:23:50 +0000 (15:23 -0700)]
fix some pass docs (#3767)

4 years ago[VTA][TSIM][Build] Towards TSIM CI testing (#3704)
Thierry Moreau [Tue, 13 Aug 2019 21:01:46 +0000 (14:01 -0700)]
[VTA][TSIM][Build] Towards TSIM CI testing (#3704)

* building TSIM specific library along with fast simulator to quickly switch between dlls

* cmake controlled TSIM libraries

* always build tsim driver in either simulation modes

* build DLLs based on CMAKE flags

* updating the jenkinsfile

* small restructuring

* reducing the cmake flags

* update instructions

* reverting to 3 flags

* update Jenkinsfile

* adding new line

* enabling TSIM unit and integration tests

* fix description

* temporarily disabling task_python_vta tests in CPU Build stage

* move CPU tests in unit test stage

* stage  reorg

* better make

* disabling TSIM tests for now

* reverting some restructuring

* fix

4 years ago[VTA] [Chisel] Improved Data Gen, Added ALU Test (#3743)
Benjamin Tu [Tue, 13 Aug 2019 16:58:32 +0000 (09:58 -0700)]
[VTA] [Chisel] Improved Data Gen, Added ALU Test (#3743)

* added alutest

* fix indent

* name change for cycle

* improved data gen and infra

* added alutest

* fix indent

* name change for cycle

* improved data gen and infra

* fix space

* fix indent

* fixes

* aluRef

* fix randomarary

* add

* Revert "add"

This reverts commit 87077daebbe055dee11f80e37da3a6291138e0f0.

* Revert "fix randomarary"

This reverts commit df386c1e660eb6ebcff1a1f905610573676f1589.

* Revert "aluRef"

This reverts commit 8665f0d4a7b12b796b2cb1ca6bf9cfe5613ee389.

* should fix dlmc-core

4 years agofix mistype (#3763)
pzq [Tue, 13 Aug 2019 16:37:50 +0000 (00:37 +0800)]
fix mistype (#3763)

4 years ago [ARITH] Simplify casts of constants 0 and 1 (#3758)
Sergei Grechanik [Tue, 13 Aug 2019 15:28:28 +0000 (18:28 +0300)]
 [ARITH] Simplify casts of constants 0 and 1 (#3758)

* [ARITH] Simplify casts of constants 0 and 1

* [EXPR] is_const_value to check whether non-ints are consts

* Revert "[EXPR] is_const_value to check whether non-ints are consts"

This reverts commit 7e1b3462e3f74fd0afb1541d72978107cfa23c30.

* Use tvm::cast

4 years ago[Relay] SpaceToDepth and MirrorPad Operators (#3718)
Josh Fromm [Tue, 13 Aug 2019 00:48:10 +0000 (17:48 -0700)]
[Relay] SpaceToDepth and MirrorPad Operators (#3718)

* Added relay and topi mirror_pad operator.

* Added mirror_padding to tensorflow frontend.

* Added mirrorpad testing in tensorflow frontent.

* Added space_to_depth in tf frontend.

* Added tests for spacetodepth.

* spacetodepth bug fix.

* Lint fix

* Added mirror pad python attrs.

* Pad code formatting.

* Syntax improvement

* Hopefully last lint fix

4 years agoDon't replace reduction init axis with new axis if bound to a thread. (#3408)
Christian Sarofeen [Mon, 12 Aug 2019 21:11:11 +0000 (17:11 -0400)]
Don't replace reduction init axis with new axis if bound to a thread. (#3408)

* Don't replace reduction init axis with new axis if bound to a thread.

* Linter.

* Reduce bind test case.

* Guard test on CUDA support.

* [CUDA TE TESTS] Add rfactor predicate test, add global bx and tx.

* [CUDA TE TESTS] Add loop partition test for simple rfactor case.

4 years ago[Bugfix] tvm.scan follow by tvm.compute segfault (#3723)
Yizhi Liu [Mon, 12 Aug 2019 16:04:48 +0000 (00:04 +0800)]
[Bugfix] tvm.scan follow by tvm.compute segfault (#3723)

* [bugfix] tvm.scan follow by tvm.compute segfault

* more strict bound condition check

* access k + 1 -> k

* fix scan test

4 years agoFix the potential index overflow (#3751)
Neo Chien [Mon, 12 Aug 2019 15:54:18 +0000 (23:54 +0800)]
Fix the potential index overflow (#3751)

4 years agoRevert compile_cmd kwarg name change (#3746)
Logan Weber [Mon, 12 Aug 2019 15:52:19 +0000 (08:52 -0700)]
Revert compile_cmd kwarg name change (#3746)

* Revert compile_cmd kwarg name change

* Fix binutil tests

4 years agoadd reviewer (#3755)
Haichen Shen [Mon, 12 Aug 2019 15:52:10 +0000 (08:52 -0700)]
add reviewer (#3755)

4 years agoImprove graph tuner dealing with Tuple (#3649)
Yao Wang [Sun, 11 Aug 2019 16:36:13 +0000 (09:36 -0700)]
Improve graph tuner dealing with Tuple (#3649)

* Improve graph tuner dealing with Tuple

* Add test case

* Move some data out of _base.py

* Fix lint

4 years ago[TOPI] Update tophub according to the fix in schedule (opencl and rocm) (#3752)
Lianmin Zheng [Sun, 11 Aug 2019 13:59:09 +0000 (21:59 +0800)]
[TOPI] Update tophub according to the fix in schedule (opencl and rocm) (#3752)

4 years ago[Relay] Fix Partial Evaluator, Add stricter checking for CheckWellFormed (#3749)
雾雨魔理沙 [Sun, 11 Aug 2019 01:23:23 +0000 (18:23 -0700)]
[Relay] Fix Partial Evaluator, Add stricter checking for CheckWellFormed (#3749)

* aot

* save

* save

* fix test

* remove vta changes

* lint

4 years agouse pip3 for python3 (#3742)
Henry [Fri, 9 Aug 2019 21:24:12 +0000 (14:24 -0700)]
use pip3 for python3 (#3742)

* use pip3 for python3

* make python3 as default

4 years ago[Relay] [Training] Fix ad for concatenate (#3729)
雾雨魔理沙 [Fri, 9 Aug 2019 19:40:16 +0000 (12:40 -0700)]
[Relay] [Training] Fix ad for concatenate (#3729)

* reproduce error

* fix

* lint

* lint

4 years ago Fix typo in ir_pass.h (#3741)
雾雨魔理沙 [Fri, 9 Aug 2019 08:51:20 +0000 (01:51 -0700)]
 Fix typo in ir_pass.h  (#3741)

4 years ago[VTA] [Chisel] Bug fix for VME Shell (#3737)
Benjamin Tu [Thu, 8 Aug 2019 20:53:27 +0000 (13:53 -0700)]
[VTA] [Chisel] Bug fix for VME Shell (#3737)

* fix

* fixes

4 years ago[CI] Update docker image ci_cpu,i386 to include verilator (#3738)
Tianqi Chen [Thu, 8 Aug 2019 20:10:23 +0000 (13:10 -0700)]
[CI] Update docker image ci_cpu,i386 to include verilator (#3738)

4 years ago[QNN] Requantize operator (#3531)
Animesh Jain [Thu, 8 Aug 2019 18:41:24 +0000 (11:41 -0700)]
[QNN] Requantize operator (#3531)

* [Relay] [Quantization] WIP - Common files for the qauntization work.

* [Relay] [Quantization] WIP - Prototyping requantize op.

* Requantize operator implementation.

Requantize converts one quantized tensor representation to another quantized
representation. The PR has following implementation features

- Requantize operator defined in qnn namespace - relay.qnn.requantize
- Lowering of the requantize to exisiting Relay operators
- Integer fixed point implementation of requantize
    - Two rounding modes - FE_UPWARDS (round towards infinity) and
    FE_AWAY_FROM_ZERO (std::round behavior)
- Floating point implementation as well, that can act as reference or can be
used for devices when FP32 computation is not used.
- Unit test cases

Relevant Issue - https://github.com/dmlc/tvm/issues/2351

Credit to TFLite and GemmLowp to provide reference implementations.

* Typo and lint fixes.

* Doc fix.

* Uncommenting the lint script (fixing mistake).

* Modifying the unit tests.

* Moving C++ files into src/relay/qnn

* Moving python files to python/tvm/relay/qnn. Some minor fixes.

* Moving the attrs.h inside the include directory.

* Pushing files that I forgot earlier. Changing util location.

* Incorporating comments. API change. Lint fixes.

* Modifying the GetFixedPointMultiplierShift API as per comments.

* Forgot the dialect change.

* Changing rewrite to qnn_lower.

* Renaming Quantize to Qnn for clarity.

* Remove use_int_domain.

* Incorportaing review comments.

* Adding API doc for QNN dialect.

* Move the qnn_lower pass to transform namespace.

* Moving from expr to module. Adding namespace in C++.

* Minor sentence rewrites. Added qnn namespace.

* Added the API doc.

* Chanding default out_dtype to int8. Adding a test with in/out_dtype as uint8.

* Style fixes. Better error messages.

* Adding documentation.

* More documentation fixes.

* Adding out dtype check for requantize.

* Adding corner case for FP32 to fixed point conversion.

* Adding extra line.

* Documentation fix.

* Adding static inline.

* Incorporating jackwish comment. Removed idtype from requantize lowering.

* Removing Quantize/Dequantize code. Restricting Requantize to (u)int8/int32.

* Style fixes.

* Fix the docs.

* Move to Legalize API.

4 years ago[DOCKER] Fix missing apt https transport support (#3735)
Marcus Shawcroft [Thu, 8 Aug 2019 17:36:36 +0000 (18:36 +0100)]
[DOCKER] Fix missing apt https transport support (#3735)

* [DOCKER] Fix missing apt https transport support

* [DOCKER] Drop superflous explicit sudo's

4 years agoRemove sccache from Rust install (#3728)
Nick Hynes [Wed, 7 Aug 2019 19:51:48 +0000 (12:51 -0700)]
Remove sccache from Rust install (#3728)

4 years agoTutorial: Build a Graph Convolutional Network on TVM (#3681)
Yulun Yao [Wed, 7 Aug 2019 16:59:00 +0000 (09:59 -0700)]
Tutorial: Build a Graph Convolutional Network on TVM (#3681)

* add build gcn tutorial

* add dgl to docker file

* add dgl to docker file

* Apply suggestions from code review

Co-Authored-By: 雾雨魔理沙 <lolisa@marisa.moe>
* add dgl to docker file

* rerun checks

* Revert "add build gcn tutorial"

This reverts commit dbe8b5f0e02a13fdd586a9faa58fd1326653afb0.

* resolve git issue

* resolve git issue

* resolve git issue

* apply marisa's comment

4 years ago[VTA][Dockerfile] Chisel dependencies for TSIM CI (#3721)
Thierry Moreau [Wed, 7 Aug 2019 15:53:41 +0000 (08:53 -0700)]
[VTA][Dockerfile] Chisel dependencies for TSIM CI (#3721)

4 years agoTake zero extent loops as NoOp and remove it and add unittest for the same (#3724)
Umang Yadav [Wed, 7 Aug 2019 15:51:18 +0000 (11:51 -0400)]
Take zero extent loops as NoOp and remove it and add unittest for the same (#3724)

4 years ago[Relay/TOPI][Op] Add variance and layer norm op (#3700)
Haichen Shen [Wed, 7 Aug 2019 11:34:53 +0000 (04:34 -0700)]
[Relay/TOPI][Op] Add variance and layer norm op (#3700)

* Add LayerNorm op

* update

* fix

* Add mean_std and mean_variance

* add std and update doc

* add license

* x

* lint

* x

* fix

* fix doc

4 years ago[Frontend][MXNet] Fix mxnet converter for hybridblock and add div_sqrt_dim (#3701)
Haichen Shen [Wed, 7 Aug 2019 04:27:06 +0000 (21:27 -0700)]
[Frontend][MXNet] Fix mxnet converter for hybridblock and add div_sqrt_dim (#3701)

* Fix mxnet converter for hybrid block

* tweak

* fix rebase

* fix

* add test

4 years agofix name (#3719)
雾雨魔理沙 [Wed, 7 Aug 2019 02:39:09 +0000 (19:39 -0700)]
fix name (#3719)

4 years ago[Relay] Legalize pass (#3672)
Animesh Jain [Tue, 6 Aug 2019 22:23:41 +0000 (15:23 -0700)]
[Relay] Legalize pass (#3672)

* [Relay] Rewrite pass.

This pass transforms an expression to other expression.

This pass has many usecases
 * Replace a expr to another expr, if the other expr has faster performance.
 * For ASICs, we might want to modify the inputs to adapt to the HW support.
 * Alter op layout can work in conjunction with this pass.

The supporting usecase is the Intel i8 x i8 conv. Intel HW supports u8 x i8 conv
in HW. Using this pass, we can replace an i8 x i8 conv to a sequence of
operators where one of the operators is now u8 x i8 conv. This will also help
automatic quantizaion performance.

* Better API name.

* Removing the conv2d legalization for x86. Will send a separate PR.

* Test name changes.

* Registering one funtion to register FTVMLegalize.

* Better comments.

4 years agoFix (2/2) [TOPI] conv2d schedule code (#3648) (#3717)
mingwayzhang [Tue, 6 Aug 2019 22:20:08 +0000 (15:20 -0700)]
Fix (2/2) [TOPI] conv2d schedule code (#3648) (#3717)

* Fix the tile_rx and tile_ry issue.

    Note that this patch depends on pull request #9 in tvm-distro.

4 years agoUpdate dmlc-core to the latest commit (#3716)
Krzysztof Parzyszek [Tue, 6 Aug 2019 21:58:24 +0000 (16:58 -0500)]
Update dmlc-core to the latest commit (#3716)

This includes changes to build TVM runtime for Hexagon.

4 years ago[relay][frontend] clean up tf frontend (#3710)
Zhi [Tue, 6 Aug 2019 21:05:06 +0000 (14:05 -0700)]
[relay][frontend] clean up tf frontend (#3710)

* clean up tf frontend

* fix get_relay_op

4 years agosafe to remove thread related headers? (#3713)
Liangfu Chen [Tue, 6 Aug 2019 20:58:38 +0000 (04:58 +0800)]
safe to remove thread related headers? (#3713)

4 years ago[Bugfix] Fix the issue that function pass modifies original module (#3712)
Haichen Shen [Tue, 6 Aug 2019 19:25:59 +0000 (12:25 -0700)]
[Bugfix] Fix the issue that function pass modifies original module (#3712)

* fix

* fix interpreter

4 years ago[Relay] [TOPI] `{relay,topi}.nn.sparse_transpose` for **Square** CSR matrices (#3707)
Yulun Yao [Tue, 6 Aug 2019 01:13:22 +0000 (18:13 -0700)]
[Relay] [TOPI] `{relay,topi}.nn.sparse_transpose` for **Square** CSR matrices (#3707)

* add build gcn tutorial

* add transpose operator for square sparse matrices

* remove extra files

* change loop tag

* comply with lint

* comply with lint -- line too long

* comply with lint

* lint check

* lint check

* lint check

* apply marisa and theirry's reviews

4 years agoExport tvm::relay::OpRegistry::OpRegistry (#3711)
Junru Shao [Mon, 5 Aug 2019 22:16:14 +0000 (15:16 -0700)]
Export tvm::relay::OpRegistry::OpRegistry (#3711)

4 years ago[CI] Update GPU docker (#3709)
Tianqi Chen [Mon, 5 Aug 2019 21:55:25 +0000 (14:55 -0700)]
[CI] Update GPU docker (#3709)

4 years agoQuit and clean when TVM is interrupted (#3640)
ghostplant [Mon, 5 Aug 2019 16:31:55 +0000 (00:31 +0800)]
Quit and clean when TVM is interrupted (#3640)

4 years agoMetal reinterpret fix (#3706)
Andrew Tulloch [Mon, 5 Aug 2019 16:31:19 +0000 (09:31 -0700)]
Metal reinterpret fix (#3706)

4 years ago[Relay] Partial Evaluator do concatenate, and has better termination checker for...
雾雨魔理沙 [Mon, 5 Aug 2019 16:23:36 +0000 (09:23 -0700)]
[Relay] Partial Evaluator do concatenate, and has better termination checker for scalar. (#3703)

* save

lint some

lint

lint

add charrnn

save

save

save

remove debug

remove debug

remove space

refactor

save

rewrite dce

* reset files

* join -> meet

* lint

* address review comment

* wordsmith

4 years ago[TOPI] Update softmax compute and CPU schedule (#3680)
Jon Soifer [Mon, 5 Aug 2019 02:46:28 +0000 (19:46 -0700)]
[TOPI] Update softmax compute and CPU schedule (#3680)

* Update Softmax compute and CPU schedule

* Add C++ compute

* Fix schedule

* Update CUDA and OpenGL schedules

* Fix log_softmax

* Fix hls and opengl schedules

* Fix CUDA schedule

4 years agoFix gather_nd in Relay (#3442)
Huilin Qu [Sat, 3 Aug 2019 23:55:22 +0000 (19:55 -0400)]
Fix gather_nd in Relay (#3442)

* Fix gather_nd in Relay

* Add test cases for gather_nd.

4 years ago[VTA] [Chisel] Added Chisel Module Unit Test Infrastructure (#3698)
Benjamin Tu [Sat, 3 Aug 2019 06:04:38 +0000 (23:04 -0700)]
[VTA] [Chisel] Added Chisel Module Unit Test Infrastructure (#3698)

* added wholething

* changed build and makefile

4 years agoAdd an option to build with -pthread (ON by default) (#3671)
abergeron [Sat, 3 Aug 2019 04:09:44 +0000 (00:09 -0400)]
Add an option to build with -pthread (ON by default) (#3671)

4 years ago[Relay] [Error] Fix error in partial evaluator (#3693)
雾雨魔理沙 [Fri, 2 Aug 2019 17:35:27 +0000 (10:35 -0700)]
[Relay] [Error] Fix error in partial evaluator (#3693)

* fix

* lint

4 years ago[AutoTVM] Fix hang/crash issues on feature extraction (#3689)
Lianmin Zheng [Fri, 2 Aug 2019 16:14:27 +0000 (00:14 +0800)]
[AutoTVM] Fix hang/crash issues on feature extraction (#3689)

* [AutoTVM] Fix hang/crash issues on feature extraction

* Update xgboost_cost_model.py

* fix lint

4 years agoAlign the naming rule for OpAttributeUnImplemented (#3695)
Neo Chien [Fri, 2 Aug 2019 15:52:00 +0000 (23:52 +0800)]
Align the naming rule for OpAttributeUnImplemented (#3695)

4 years ago[DOCKER] Add DGL to {ci_gpu, demo_cpu, demo_gpu} docker images (#3692)
Yulun Yao [Fri, 2 Aug 2019 15:51:14 +0000 (08:51 -0700)]
[DOCKER] Add DGL to {ci_gpu, demo_cpu, demo_gpu} docker images (#3692)

* add dgl to docker file

* add dgl to docker file

4 years ago[TOPI] Memoize winograd matrix (#3687)
Lianmin Zheng [Fri, 2 Aug 2019 15:50:33 +0000 (23:50 +0800)]
[TOPI] Memoize winograd matrix (#3687)

* [TOPI] Memoize winograd matrix

* lint

* Fix name

5 years ago[Relay][Quantization] KL-divergence-based per-layer calibration (#3538)
Wuwei Lin [Fri, 2 Aug 2019 03:55:27 +0000 (20:55 -0700)]
[Relay][Quantization] KL-divergence-based per-layer calibration (#3538)

* [Relay][Quantization] Support floating-point scale

* [Relay][Quantization] KL-divergence calibration on dataset

* Fix unhandled LeftShift case in QuantizeRealize

* Fix lint

* drop QBias

* fix lint

* address comments

* address comments

* Update comments

* address comments

* lint

* kQIdentity = 0