Tianqi Chen [Sun, 16 Feb 2020 23:02:39 +0000 (15:02 -0800)]
[CI] Cleanup logfile before tutorial runs (#4896)
masahi [Sun, 16 Feb 2020 06:43:22 +0000 (15:43 +0900)]
[Relay] Fix VM compiler for while loop with free vars (#4889)
* add additional switch to handle nested call node
* Fix VM compiler for while loop with free var
wpan11nv [Sun, 16 Feb 2020 03:47:36 +0000 (19:47 -0800)]
[CodeGen][CUDA] Fix issues in cuda codegen (#4876)
- Do not emit __shared__ etc. as part of type for casting
- Fix fp16 reduction kernels with compiler errors:
"no operator "+" matches these operands, volatile half + volatile half
This patch inserts casts to remove volatile type qualifier following
volatile loads (fp16 only). CUDA fp16 library headers should add
volatile member functions.
- Update have_fp16 to include compute 6.1 GPUs, which do support fp16,
although their fp16 throughput is low. Updated tests.
Signed-off-by: Wei Pan <weip@nvidia.com>
masahi [Sat, 15 Feb 2020 18:32:58 +0000 (03:32 +0900)]
improve antlr import error message (#4888)
Cody Yu [Sat, 15 Feb 2020 04:15:47 +0000 (20:15 -0800)]
[AutoTVM] Support range in index based tuners (#4870)
* Support range in index based tuners
* Address comments
* Remove __*state__
* trigger CI
masahi [Sat, 15 Feb 2020 01:12:06 +0000 (10:12 +0900)]
[QNN] Add support for per channel weight scale in dense op (#4880)
* add test case for per channel dense
* add unit arg in tflite frontend
* update qnn legalize test
* fix output dim index
masahi [Fri, 14 Feb 2020 04:28:07 +0000 (13:28 +0900)]
[QNN] More doc fix on quantize and convolution (#4874)
* [QNN] Doc fix on quantize and convolution
* update test
wpan11nv [Fri, 14 Feb 2020 04:24:29 +0000 (20:24 -0800)]
[TOPI][CUDA] Enable vectorization on fp16 type (#4867)
- This allows to better utilize the memory bandwidth
- Note that not all cases are vectorized for fp16 datatype. For
instance, when the size is not a multiple of 1024, the inner loop
may be an expression that cannot be vectorized. In this case, a
small inner loop is still benefical for latency hidding.
Signed-off-by: Wei Pan <weip@nvidia.com>
tqchen [Wed, 12 Feb 2020 23:38:39 +0000 (15:38 -0800)]
[REFACTOR][PY] Establish tvm.tir
- Move related files into the corresponding location as in C++
- Keep the top-level TVM API backward compatible to make minimum changes in topi
Zhi [Wed, 12 Feb 2020 16:14:36 +0000 (08:14 -0800)]
Update docs/dev/virtual_machine.rst
Co-Authored-By: Wei Chen <ipondering.weic@gmail.com>
Zhi [Wed, 12 Feb 2020 16:14:27 +0000 (08:14 -0800)]
Update docs/dev/virtual_machine.rst
Co-Authored-By: Wei Chen <ipondering.weic@gmail.com>
Zhi Chen [Tue, 11 Feb 2020 04:52:20 +0000 (04:52 +0000)]
fix vm doc
Alex Gladkov [Thu, 13 Feb 2020 06:38:15 +0000 (22:38 -0800)]
Optimize x86 conv3d_ndhwc using data packing approach. (#4866)
Add tuneable conv3d_ndhwc schedule
mbarrett97 [Thu, 13 Feb 2020 02:07:58 +0000 (02:07 +0000)]
[FRONTEND][TFLITE] Add support for TFLite_Detection_PostProcess (#4543)
* [FRONTEND][TFLITE] Add support for TFLite_Detection_PostProcess
This adds support for the custom operator
TFLite_Detection_PostProcess which is commonly used in
object detection networks such as SSD Mobilenet. It
only adds support for when use_regular_nms = False.
Change-Id: I819b253c0eb6f0fa55da65d2634e09359b888828
* Added a test for the tflite custom op
Change-Id: Ie5baa092deae9a8bcffd2ebd9f6d346b90e58afd
* Removed trailing comma
Change-Id: Ib08f02b5f1a59a883048bfb36e4321152cd2e7f2
* Added spaces between divide
Change-Id: If1171fc03d211a809cedeb800804394972af4060
* Formatted comment
Change-Id: I3ce7e69b8d2c73aec57369c1c64ea1eec07f087b
* Reduced line length in test
Change-Id: I49eaafc3369070f8f3e85fbb965ad20972096c68
* Set random seed for test
Change-Id: I542a787d11422ea83c52147b2cb1144fcef0dd77
* Fixes to style
Change-Id: I2971b8ecebe08c882b2481a99f67cfbe515e0b1f
* Assert for incorrect number of inputs
Change-Id: I393f3b3b62be73e427498d98456fb1d5a214e0af
* Change comparison to pass linting
The linter was updated, so I needed to fix
a small style issue as a result.
Change-Id: Ia3c954565a00de92e7fb1912eae9ed9875d60c7c
tqchen [Wed, 12 Feb 2020 21:39:45 +0000 (13:39 -0800)]
[REFACTOR][PY][API-CHANGE] Establish tvm.target
Move the related target modules into tvm.target.
API change:
- tvm.target.current_target -> tvm.target.Target.current
- tvm.datatype -> tvm.target.datatype
tqchen [Wed, 12 Feb 2020 19:20:23 +0000 (11:20 -0800)]
[JVM] Update the runtime PackedFunc for module
tqchen [Wed, 12 Feb 2020 05:41:47 +0000 (21:41 -0800)]
Fix optimize
tqchen [Wed, 12 Feb 2020 04:36:20 +0000 (20:36 -0800)]
[DOCS][PY] Sphinx docs about tvm.ir
Tianqi Chen [Wed, 12 Feb 2020 04:01:36 +0000 (20:01 -0800)]
[REFACTOR][PY][API-CHANGE] establish tvm.ir, migrate corresponding files (#4862)
* [REFACTOR][PY][API-CHANGE] establish tvm.ir, migrate corresponding relay files.
This PR establishes tvm.ir and migrates the corresponding relay
files into the new folder.
API Change:
- relay.Module -> tvm.IRModule
* Update with ADT
* Migrate transform
* address comments
* Migrate module
* Migrate json_compact
* Migrate attrs
* Move LoweredFunc to stmt temporarily
* temp migrate container
* Finish migrate container
hlu1 [Tue, 11 Feb 2020 22:46:50 +0000 (14:46 -0800)]
[Topi] Missing header (#4865)
kice [Tue, 11 Feb 2020 21:44:48 +0000 (16:44 -0500)]
Fix onnx import bugs (#4750)
* Fix onnx import bugs
Fix onnx attributes of string type incorrect handling
Merge symmetric padding of Conv to symmetric form
* Only merge symmetric padding for conv2d
Zhi [Tue, 11 Feb 2020 20:04:04 +0000 (12:04 -0800)]
[Refactor] move vm.py under runtime and adt to runtime.container.py (#4855)
masahi [Tue, 11 Feb 2020 17:56:14 +0000 (02:56 +0900)]
add resize op converter (#4838)
hlu1 [Tue, 11 Feb 2020 16:52:25 +0000 (08:52 -0800)]
[TVM] const auto p -> const auto &p (#4861)
hlu1 [Tue, 11 Feb 2020 16:45:17 +0000 (08:45 -0800)]
[LLVM] Explicit llvm::StringRef to std::string conversion (#4859)
Lianmin Zheng [Tue, 11 Feb 2020 09:58:36 +0000 (01:58 -0800)]
[RUNTIME] Fix memory leakage of TVMByteArray (#4856)
Animesh Jain [Tue, 11 Feb 2020 02:56:37 +0000 (18:56 -0800)]
[TFLite] Using real image for QNN testing. (#4816)
* [TFLite] Using real image for QNN testing.
* Setting seed for SSD mobilenet for fixed input.
* Support quantized Pad op.
* Remove unnnecessary line.
* Ina comments.
Leyuan Wang [Mon, 10 Feb 2020 22:13:35 +0000 (14:13 -0800)]
reverse changes in pr #4849 (#4853)
mbarrett97 [Mon, 10 Feb 2020 19:39:20 +0000 (19:39 +0000)]
[Relay] Added Merge Composite pass (#4771)
* [Relay] Added MergeComposite pass
This pass allows for patterns to be wrapped
in a function marked with 'Composite' and a
composite function name. This is intended to be
used with the external codegen for the cases where
an external operator maps to multiple Relay
operators. In that case, the mapping can be expressed
as a pattern and assigned a name.
For more information on this pass and its motivation,
see the RFC:
https://discuss.tvm.ai/t/rfc-external-codegen-defining-composite-relay-operators/5470
Change-Id: Icb1b803a9f0ac57c529143200228f3bb5793afc0
* [Relay] Merge composite tests
Added tests for the merge_composite pass.
Change-Id: I1728b4a05b0c1c36140a40f1afe028fde62185dd
* Merge composite additional test
Change-Id: I9bc7d6053c575e9468ac5abc31214c6ad8507e46
* Support priority order in merge_composite
The order in which the patterns are matched
was currently random as an unordered_map was
used to store the pattern table. This uses
arrays instead so that a distinct priority
order of matching can be defined. Additional
tests have also been added to verify this
behaviour.
Change-Id: Ief347df4262639138d5d9d7c8cee7ef233af7b56
* Improved merge composite docs
Change-Id: Ie3a72045ecc3f13ad3c302fbdf192b7296a306a8
* Removed unused variable
Change-Id: I7814d5fde368ffaf1b3d6d806060c774c7720364
* Remove unnecessary op check
Change-Id: I38e78d2acd5b86cb8e837be72ff9d72cd10bcf33
* Improve styling on composite function creation
Change-Id: I37add1c3134e0b5d5085fe1eb9daf8e06890fa8c
* Comment reword
Change-Id: Ie05872dcbbe0c3e1190b0597083b9a64e6b66c66
* Stylistic changes to avoid std::move
Change-Id: I43a93995bbf10530399900c992aa99dd4ae4575f
* Relax a check in ExtractPattern
Change-Id: I0faef77a66c55f83f09e6e47c561ffaea63dedfa
* Remove new line
Change-Id: Ifdd02c12087a7e1a0a9b54825669bc0de8f13c3d
* Removed MatchPattern from MergeComposite
This is not necessary now that ExtractPattern
can fulfill the same purpose.
Change-Id: I14dc020afa8e50f2df4c0a2efb88a011987f8196
* Removed a new line
Change-Id: I8b50f0c9069aa1bcaccbe68eb421031f01a64842
* Improved docs for merge composite
Change-Id: Ib1959a35c856e7ea5639de2e4ef314a54f44caf5
* Fixed free vars in test
Change-Id: I2b7f273db275964ec0e9820560663f0808adee79
* Handle case where root arg might not be a call
Change-Id: I4eeea3ce723d3ba337d110dcc690377daebe8626
* Removed blank line
Change-Id: I07f5392c0e95cfe3cfa5c333703cc6f82d6034fb
* Change to CHECK_EQ
Change-Id: I5c5d62d3cd57f72508b30b926f72091ae6f0d1cc
* Revised a conditional
Change-Id: I23a7897ca15a7cd076db5039dc653a4b8c27e803
* Improved doc styling
Change-Id: I377f0a1c1ac70f3b8d7584b0c49bddc8c6c134ef
* Fail extraction if vars conflict
Change-Id: I78e36d805e8ed6b55e61d490212a967c857554a4
* Added further merge composite tests
Change-Id: Ib1d800409fca4c1834c7fe0cab5a26ab99a26820
Co-authored-by: lhutton1 <35535092+lhutton1@users.noreply.github.com>
pankratz [Mon, 10 Feb 2020 19:33:51 +0000 (12:33 -0700)]
Fixed bug in ExprOp that caused bitwise operators to fail when a basic python type was on the left hand side of the expression. Added regression test for crashing cases. (#4852)
Wang Yucheng [Mon, 10 Feb 2020 17:54:58 +0000 (01:54 +0800)]
[Frontend][TFlite] use qnn helper function in softmax (#4840)
Tianqi Chen [Sun, 9 Feb 2020 17:12:19 +0000 (09:12 -0800)]
[CI][DOCKER] Update ci-lint to pylint2.4.4 (#4851)
Tianqi Chen [Sun, 9 Feb 2020 05:42:36 +0000 (21:42 -0800)]
[CI] Update ci-lint to v0.60 (#4850)
Tianqi Chen [Sun, 9 Feb 2020 03:45:17 +0000 (19:45 -0800)]
[LINT][PY] Fixes for pylint==2.4.4 (#4849)
Tianqi Chen [Sat, 8 Feb 2020 22:05:21 +0000 (14:05 -0800)]
[TEST] test_cuddn flaky (#4846)
Seyyed Hossein Hasanpour [Sat, 8 Feb 2020 18:48:16 +0000 (22:18 +0330)]
Fixed process termination routine in windows (#4844)
* Fixed process termination routine in windows
addresses and Fixes AttributeError: module 'os' has no attribute 'killpg' error in #4821
* Update server.py
Cody Yu [Fri, 7 Feb 2020 22:34:14 +0000 (14:34 -0800)]
[Doc][AutoTVM] Fix bugs that override n_trials (#4842)
ziheng [Fri, 7 Feb 2020 21:41:35 +0000 (13:41 -0800)]
[COMMUNITY] comaniac -> reviewer (#4841)
Tianqi Chen [Fri, 7 Feb 2020 17:15:08 +0000 (09:15 -0800)]
[REFACTOR][PY][API-Change] Polish tvm.runtime, tvm.runtime.module API update (#4837)
* [REFACTOR][PY-API] Polish tvm.runtime, tvm.runtime.module API update
This PR updates the tvm.runtime to use the new FFI style.
- Remove top-level tvm.module to avoid confusion between runtime.Module and IRModule
- API changes wrt to runtime.Module
- tvm.module.load -> tvm.runtime.load_module
- tvm.module.enabled -> tvm.runtime.enabled
- tvm.module.system_lib -> tvm.runtime.system_lib
- Remove dep on api_internal from runtime.
* Update module.load in the latest API
Wang Yucheng [Fri, 7 Feb 2020 11:57:34 +0000 (19:57 +0800)]
[Frontend][TFLite] Add MIRROR_PAD operator (#4822)
Ina Dobreva [Fri, 7 Feb 2020 10:23:55 +0000 (10:23 +0000)]
[Relay][Frontend][TFlite] Add support for quantized LOGISTIC (#4696)
* [Relay][Frontend][TFlite] Add support for quantized LOGISTIC
* add qnn implementation
* add qnn test case for qnn logistic
* Helper functions for quantize and dequantize.
Animesh Jain [Thu, 6 Feb 2020 22:13:08 +0000 (22:13 +0000)]
[Doc] ConvertLayout - Call RemoveUnunsedFunctions.
Tianqi Chen [Fri, 7 Feb 2020 02:12:13 +0000 (18:12 -0800)]
Improve tol to resolve flaky case (#4836)
Josh Fromm [Fri, 7 Feb 2020 02:09:10 +0000 (18:09 -0800)]
[Frontend][ONNX] LSTM Support (#4825)
* Initial version working and passing tests.
* WIP on supporting other activations.
* add support for multiple activation functions in lstm
* All tests working and code cleaned up.
* Undo import swap to avoid conflict with masahi.
* Added new tests and related bug fixes.
Co-authored-by: Matthew Brookhart <mbrookhart@octoml.ai>
Zhao Wu [Fri, 7 Feb 2020 02:03:20 +0000 (10:03 +0800)]
[Doc] Introduction to module serialization (#4564)
Zhi [Fri, 7 Feb 2020 01:38:48 +0000 (17:38 -0800)]
Fix doc after moving to unified IR (#4835)
Tianqi Chen [Thu, 6 Feb 2020 19:58:22 +0000 (11:58 -0800)]
[CI][DOCKER] Update ci-gpu torch1.4 and onnx1.6 (#4826)
Tianqi Chen [Thu, 6 Feb 2020 19:58:11 +0000 (11:58 -0800)]
[CI][DOCKER] Update ci-gpu to v0.60 (#4827)
Just do it [Thu, 6 Feb 2020 17:25:06 +0000 (01:25 +0800)]
It's gpu not cpu. (#4832)
abergeron [Thu, 6 Feb 2020 03:24:42 +0000 (22:24 -0500)]
[TOPI][Relay] Add bitwise ops (#4815)
* Add bitwise ops to topi
* Add the bitwise ops to relay.
Tianqi Chen [Thu, 6 Feb 2020 02:49:24 +0000 (18:49 -0800)]
[CONTRIB][CC] Enhance cc.cross_compiler (#4817)
* [CONTRIB][CC] Enhance cc.cross_compiler
- Enhance cc.cross_compiler to take str argument.
- Remove cc.build_create_shared_func as it is dupilicated with cross_compiler
- Add examples to cc.cross_compiler
* address review comments
Xingyu Zhou [Wed, 5 Feb 2020 23:33:45 +0000 (07:33 +0800)]
[Relay] Conv2D padding representation (#4787)
* enforce 4-way padding
* add util with get_pad_tuple
* delete unnecessary arguments
* fix lint
* add container.Array case
* fix cudnn conv2d asymmetric padding logic
* rename get_pad_tuple to get_pad_tuple2d
* revert change for topi/python/topi/nn/conv2d.py
* add get_pad_tuple2d for several contrib conv2d ops
* add get_pad_tuple2d for all conv2d ops
Ina Dobreva [Wed, 5 Feb 2020 20:12:44 +0000 (20:12 +0000)]
[Relay][Frontend][TFLite] Add parser support for logical operators (#4642)
* [Relay][Frontend][TFLite] Add parser support for logical operators
* Add parser support for logical_and, logical_or
* Add boolean dtype as a valid tensor type
* BOOLEAN dtype is supported only from tf 1.15
so logical ops work only in that and newer versions
* Logical_not is ommited since tflite can't convert it -->
throws errors for addv2
* Add TFLite vesion check in tests for logical ops
* Check is added because of boolean dtype lack of support
Animesh Jain [Wed, 5 Feb 2020 19:52:18 +0000 (11:52 -0800)]
[QNN] Optimize lowering for requantize and FixedPointMultiply. (#4798)
* [QNN] Optimize lowering for requantize and FixedPointMultiply.
* Add check for requantize scale gt 1.
* Added test case.
Ina Dobreva [Wed, 5 Feb 2020 19:51:59 +0000 (19:51 +0000)]
[Frontend][TFLite] Dynamically calculate input_stats of any fake_quant range (#4789)
* [TFLite] Dynamically calculate input_stats of any fake_quant range
* pass the input range to the convertor and caclulate (mean, scale) there
* change the range of the second tensor in elemwise operations
so that we test inputs with different quant params
* change the possible output range for elemwise ops wrt the updated ranges
* update the comments for (m, s) calculations
* add input range dict to reduce_mean op
* Apply requested changes
* add exception handling for zero division in input_stats
* fix range of the input tensor in elemwsie
Seyyed Hossein Hasanpour [Wed, 5 Feb 2020 18:07:29 +0000 (21:37 +0330)]
Fixed subprocess creation under windows (#4820)
* fixed subprocess creation under windows
this addresses the issue #4819
* Update server.py
Tianqi Chen [Wed, 5 Feb 2020 17:00:03 +0000 (09:00 -0800)]
[REFACTOR][PY] Establish tvm.runtime (#4818)
* [REFACTOR][PY] Establish tvm.runtime
This PR establishes the tvm.runtime namespace that contains the core runtime data structures.
The top-level API are kept inact for now via re-exporting.
We will followup later to cleanup some of the top-level APIs.
* Fix ndarray name
shoubhik [Wed, 5 Feb 2020 13:27:52 +0000 (05:27 -0800)]
Mxnet parser for Qnn dialect (#4714)
* - Additional util methods needed for mxnet frontend for qnn dialect.
* - Fixing call to quantize.
* [QNN] MxNet-MKLDNN parser support for QNN
* [QNN] Relax conv check.
* - Merge from origin
* [QNN] Channel wise changes
* [QNN] Dense changes
* Dense fix for QNN ops.
* - Removed non-mkl code from utils.
- Small refactoring
- Remove "with_sum" from conv
- Simplified code
* - Fixing ring buffer name.
* - Fixing pylint issues.
* - Fixing lint
- Removing redundant commented code.
* - Adding test cases
- Removing unused methods.
* [WIP] end to end test case for mxnet qnn parser
* Changes to parse large CV models.
* Pylint issues.
* Fix Conv2D with sum and quantized pooling.
* Reverting the changes made for mxnet-mkldnn test cases. Because of #4753, mxnet could not be updated to mxnet-mkldnn.
Co-authored-by: Animesh Jain <anijain@umich.edu>
Haichen Shen [Wed, 5 Feb 2020 06:04:41 +0000 (22:04 -0800)]
allow customize mkldnn library location (#4814)
Tianqi Chen [Wed, 5 Feb 2020 01:01:01 +0000 (17:01 -0800)]
[REFACTOR][PY] tvm._ffi (#4813)
* [REFACTOR][PY] tvm._ffi
- Remove from __future__ import absolute_import in the related files as they are no longer needed if the code only runs in python3
- Remove reverse dependency of _ctypes _cython to object_generic.
- function.py -> packed_func.py
- Function -> PackedFunc
- all registry related logics goes to tvm._ffi.registry
- Use absolute references for FFI related calls.
- tvm._ffi.register_object
- tvm._ffi.register_func
- tvm._ffi.get_global_func
* Move get global func to the ffi side
Animesh Jain [Tue, 4 Feb 2020 23:25:46 +0000 (15:25 -0800)]
[TOPI][x86] Injective schedule improvement (#4786)
* [TOPI][x86] Injective Schedule Improvement.
* Add tiling.
* Vectorize when there is an axis.
Haichen Shen [Tue, 4 Feb 2020 21:14:15 +0000 (13:14 -0800)]
fix memory leak (#4811)
Animesh Jain [Tue, 4 Feb 2020 17:32:45 +0000 (09:32 -0800)]
[AutoTVM] Minor bug fixes in AutoTVM for QNN graphs (#4797)
* [AutoTVM] Minor bug fixes in AutoTVM for QNN graphs.
* Bring back strided_slice.
* Replace tvm.nd change.
Tianqi Chen [Tue, 4 Feb 2020 17:21:51 +0000 (09:21 -0800)]
[DOCS] Fix vta tutorial (#4809)
Tianqi Chen [Tue, 4 Feb 2020 04:47:51 +0000 (20:47 -0800)]
[LINT] Fix -Wextra (#4804)
* [LINT] Fix -Wextra
* Fix virtual-dtor
Hua Jiang [Mon, 3 Feb 2020 19:36:53 +0000 (11:36 -0800)]
[TOPI] upsample operator 'NCHWinic' format support. (#4791)
* [TOPI] upsample operator 'NCHWinic' format support.
some hardware accelerator ask packed format data like NCHWinic to fit the
hardware resource, here add upsample NCHWinic format support to help
such requirement.
* address review comments, add assert for 'else must be NCHWxc' logic.
mbarrett97 [Mon, 3 Feb 2020 17:55:43 +0000 (17:55 +0000)]
[TIR] Create a StringImm reference type (#4806)
This is motivated by the want to send an
array of strings across the python/C++
boundary. Arrays only support ObjectRef types
and so can't carry StringImmNodes. This creates
a string reference type, StringImm, which can
be used with tvm::Arrays.
Change-Id: I598a44536c156b97dbfe3e9518e0a1f705da850c
Zhao Wu [Mon, 3 Feb 2020 17:53:13 +0000 (01:53 +0800)]
[ThreadPool] Solve ARM BIG.LITTLE heterogeneous multicores (#4747)
vizero1 [Mon, 3 Feb 2020 04:03:57 +0000 (05:03 +0100)]
Change color channel from BGR to RGB for darknet preprocessing (#4794)
Animesh Jain [Mon, 3 Feb 2020 02:56:45 +0000 (18:56 -0800)]
[QNN] Conv2D with dilation support. (#4796)
masahi [Mon, 3 Feb 2020 02:53:41 +0000 (11:53 +0900)]
[QNN] Doc fix on convolution and dequantize (#4799)
* QNN doc fix on conv and dequantize
* fix param name in tflite frontend
* make different fix
kshitij12345 [Sun, 2 Feb 2020 18:57:12 +0000 (00:27 +0530)]
fix #4670: add bias for fc layer (#4801)
masahi [Sun, 2 Feb 2020 02:04:44 +0000 (11:04 +0900)]
[Relay] Expose vm OptimizeModule to Python (#4800)
* Expose VM OptimizeModule to python
* added missing imports
* fix import
Alex Gladkov [Sat, 1 Feb 2020 01:43:27 +0000 (17:43 -0800)]
Add schedule for conv3d NDHWC layout (#4775)
Animesh Jain [Fri, 31 Jan 2020 22:29:08 +0000 (14:29 -0800)]
[Relay][Topi] Use SimplifyInference for L2 Normazlization. (#4795)
masahi [Thu, 30 Jan 2020 19:09:48 +0000 (04:09 +0900)]
Dedup BindParamByName function in VM compiler (#4793)
jmorrill [Thu, 30 Jan 2020 16:43:16 +0000 (08:43 -0800)]
Fix parsing of different exception string formats (#4785)
Ina Dobreva [Thu, 30 Jan 2020 14:10:52 +0000 (14:10 +0000)]
[Relay][Frontend][TFlite] Add add parser support for relational ops (#4695)
Add support for: greater_equal, less, less_equal, equal, not_equal
Add tests for the elemwise relational ops
abergeron [Thu, 30 Jan 2020 02:33:39 +0000 (21:33 -0500)]
Make sure to visit the arguments of inlined functions (#4783)
wpan11nv [Wed, 29 Jan 2020 03:40:39 +0000 (19:40 -0800)]
[AUTOTVM] Fix a bug in generating the search space (#4779)
- Do not use numpy.prod which ignores integer (64 bits) overflows.
This leads to an incorrect number of points in the search space.
hlu1 [Wed, 29 Jan 2020 01:58:36 +0000 (17:58 -0800)]
[Python] Replace os.path.exists with try...except...else (#4784)
Jared Roesch [Tue, 28 Jan 2020 11:25:52 +0000 (03:25 -0800)]
[PassManager] Implement pass manager tracing API (#4782)
* Implement pass tracing API
* Set is_before correctly
* Add docs for trace function
* Fix lint
* Remove PDB
* Ensure trace_func is set before calling
* Fix conditional
Cody Yu [Tue, 28 Jan 2020 00:10:35 +0000 (16:10 -0800)]
Safe remove tmpdir (#4781)
Jon Soifer [Mon, 27 Jan 2020 23:40:25 +0000 (17:40 -0600)]
[Relay][Frontend][ONNX] Broadcast condition, x, and y for Where op (#4774)
* ONNX frontend broadcast condition
* fix
* fix style
Co-authored-by: Jon Soifer <jonso@microsoft.com>
Jon Soifer [Mon, 27 Jan 2020 22:58:11 +0000 (16:58 -0600)]
properly extract error type from windows error message (#4780)
Co-authored-by: Jon Soifer <jonso@microsoft.com>
Jon Soifer [Mon, 27 Jan 2020 22:27:55 +0000 (16:27 -0600)]
[Build] Explicitly link to cublasLt if it exists (#4776)
* Explicitly link to cublasLt
* Only link cublasLt if it's found
Co-authored-by: Jon Soifer <jonso@microsoft.com>
Kaiyan Chang [Mon, 27 Jan 2020 00:41:46 +0000 (08:41 +0800)]
Update tune_simple_template.py (#4778)
fixed a spelling mistake.
HUAN-PING SU [Sat, 25 Jan 2020 22:55:55 +0000 (06:55 +0800)]
Bump prebuilt-image version in demo dockerfile (#4770)
Ina Dobreva [Fri, 24 Jan 2020 06:41:56 +0000 (06:41 +0000)]
[Bugfix][Frontend][TF] Fix incorrect calculations in tf SLICE (#4518)
* fix formula for calculating end indices when size[i] == -1
* add a test case for size[i] == -1
* discard expanding dimension of begin_value & end_value since
it is needed only if you pass them as scalars not as tensors.
* discard 'slice_tensor' variable so that implementation matches
the tf parser pattern
masahi [Fri, 24 Jan 2020 05:01:47 +0000 (14:01 +0900)]
add missing nullptr check (#4773)
masahi [Fri, 24 Jan 2020 03:19:48 +0000 (12:19 +0900)]
[TOPI] Remove cpp upsampling and resize op (#4769)
* remove cpp upsampling
* remove cpp resize
Alex Gladkov [Fri, 24 Jan 2020 03:17:45 +0000 (19:17 -0800)]
Fix Tensorflow conv3d pad bug, add non-cubic data and kernel tests (#4772)
hlu1 [Fri, 24 Jan 2020 00:48:25 +0000 (16:48 -0800)]
[Doc] TVM_REGISTER_API -> TVM_REGISTER_GLOBAL (#4768)
Hua Jiang [Thu, 23 Jan 2020 22:05:07 +0000 (14:05 -0800)]
[VTA] Support network which have no unique operator as start/stop name for graph pack. (#4703)
* [VTA] Support network which have no unique operator as start/stop name
for graph pack.
[Issue]
Current vta use 'start' and 'stop' name to define the pack start point
and end point, but this method not work for these network which have
no 2 unique operator as start point and stop point.
[Solution]
In this solution we give 2 addtional parameters start_name_indx and
stop_name_indx to make vta pack logic work with the said network,
for exampl for following networks which have no unique operator,
%0 = nn.add
%1 = nn.conv2d
%2 = nn.batch_norm
%3 = nn.leaky_relu
%4 = nn.add
%5 = nn.conv2d
%6 = nn.batch_norm
%7 = nn.leaky_relu
%8 = nn.add
with this solution we can use following parameter format to make
vta work on it.
relay_prog = graph_pack(
//....
start_name="nn.add",
stop_name="nn.add",
start_name_idx=0,
stop_name_idx=4)
to apply on new network, by printing the network we can get index information like following.
print(mod.astext(show_meta_data=False))
relay_prog = graph_pack(mod
...
start_name="nn.add",
stop_name="nn.add",
start_name_idx=0,
stop_name_idx=4)
* address review comments and fix index count bug
issue:
when do print(mod), the output not only the Call is also have other type
like Var, need add logic to count all except meta.
solution:
add related logic
* address review comments.
* address review comments
* add more detail comments.
Alexander Pivovarov [Thu, 23 Jan 2020 00:47:15 +0000 (16:47 -0800)]
pooling.cc improvements (#4767)
Alex Gladkov [Wed, 22 Jan 2020 13:41:46 +0000 (05:41 -0800)]
Improve CUDA conv2d_transpose_nchw (#4762)
- combine pad and dilate;
- fix for the issue https://discuss.tvm.ai/t/compile-error-for-cuda-target/4164
- fix for the issue https://github.com/apache/incubator-tvm/pull/4472
Alexander Pivovarov [Wed, 22 Jan 2020 06:30:02 +0000 (22:30 -0800)]
Remove run_infer_type duplicates (#4766)
Alexander Pivovarov [Wed, 22 Jan 2020 02:21:10 +0000 (18:21 -0800)]
Fix padding in pooling op (#4738)
Tianqi Chen [Wed, 22 Jan 2020 00:51:07 +0000 (16:51 -0800)]
[REFACTOR] driver.h -> driver_api.h (#4760)
"driver" normally refers to the "main" function.
Rationale: the header exposes set of APIs to drive compilation
and should be named as driver api to best reflect its usage.
Cody Yu [Tue, 21 Jan 2020 21:50:20 +0000 (13:50 -0800)]
[Docs] Bring Your Own Codegen Guide -- Part 2 (#4718)
* BYOC Tutorial -- part 2
* Fix comments
* Address comments