platform/upstream/tvm.git
4 years ago[Container] Fix NDArray SaveDLTensor declaration and implementation signature differe...
Zhao Wu [Thu, 26 Dec 2019 17:33:03 +0000 (01:33 +0800)]
[Container] Fix NDArray SaveDLTensor declaration and implementation signature different (#4586)

4 years ago[Quantization, Calibrate] Fix context creation when current_target is explicity set...
masahi [Thu, 26 Dec 2019 14:13:38 +0000 (23:13 +0900)]
[Quantization, Calibrate] Fix context creation when current_target is explicity set (#4582)

4 years ago[DOCS]fix typos in autotvm tutorial (#4585)
Wang Yucheng [Thu, 26 Dec 2019 09:45:59 +0000 (17:45 +0800)]
[DOCS]fix typos in autotvm tutorial (#4585)

4 years ago[NEWS] add v0.6 release (#4558)
Yizhi Liu [Thu, 26 Dec 2019 04:31:22 +0000 (20:31 -0800)]
[NEWS] add v0.6 release (#4558)

* [NEWS] add v0.6 release

* remove link prefix

* fix issue number

4 years agoSome Windows and MSVC fixes (#4569)
kice [Wed, 25 Dec 2019 21:42:03 +0000 (16:42 -0500)]
Some Windows and MSVC fixes (#4569)

* fix python exception creation in Windows

* better string conversion for msvc

* fix cpp style issue

4 years ago[RUNTIME] Remove Extension VTable in favor of Unified Object system. (#4578)
Tianqi Chen [Wed, 25 Dec 2019 17:21:01 +0000 (09:21 -0800)]
[RUNTIME] Remove Extension VTable in favor of Unified Object system. (#4578)

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

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

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

4 years ago[DEPRECATION] Cleanup legacy verilog support (#4576)
Tianqi Chen [Tue, 24 Dec 2019 23:14:03 +0000 (15:14 -0800)]
[DEPRECATION] Cleanup legacy verilog support (#4576)

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

4 years ago[DOC] fix doc in api.py (#4580)
Bohan Hou [Tue, 24 Dec 2019 16:51:05 +0000 (00:51 +0800)]
[DOC] fix doc in api.py (#4580)

4 years ago[Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators (#4566)
Josh Fromm [Tue, 24 Dec 2019 05:04:34 +0000 (00:04 -0500)]
[Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators (#4566)

* Added tvm function stencil for subpixel operations to topi.

* Topi subpixel operators added and tested.

* Added subpixel attrs.

* Added depth_to_space relay attributes.

* depth_to_space fully working.

* Fixed NHWC shape bug.

* SpaceToDepth in and all tests passing.

* lint fixes.

* Added string include

* Fixed topi formatting.

* Added DCR/CDR mode to depthtospace operator.

4 years ago[DEPRECATION] Remove NNVM compiler (#4571)
Tianqi Chen [Mon, 23 Dec 2019 19:51:26 +0000 (11:51 -0800)]
[DEPRECATION] Remove NNVM compiler (#4571)

* Remove NNVM compiler

4 years agoFix llvm-enabled build by adding missing intrinsics headers (#4575)
Dmitri Makarov [Mon, 23 Dec 2019 16:50:48 +0000 (17:50 +0100)]
Fix llvm-enabled build by adding missing intrinsics headers (#4575)

4 years agoremove unnecessary cast to int32 (#4573)
masahi [Mon, 23 Dec 2019 16:48:37 +0000 (01:48 +0900)]
remove unnecessary cast to int32 (#4573)

4 years ago[VTA][Chisel] End-to-end Inference with Chisel VTA (#4574)
Liangfu Chen [Mon, 23 Dec 2019 16:43:52 +0000 (00:43 +0800)]
[VTA][Chisel] End-to-end Inference with Chisel VTA (#4574)

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

* Update TensorAlu.scala

4 years agoRemove nnvm (#4565)
Tianqi Chen [Mon, 23 Dec 2019 04:52:33 +0000 (20:52 -0800)]
Remove nnvm (#4565)

4 years ago[Relay] add max_pool3d in relay and TF converter (#4551)
Yong Wu [Mon, 23 Dec 2019 01:43:33 +0000 (17:43 -0800)]
[Relay] add max_pool3d in relay and TF converter (#4551)

* [Relay] add max_pool3d in relay and TF converter

* fix comments

4 years ago[TEST] Remove nnvm related code in topi and test script (#4562)
Tianqi Chen [Sun, 22 Dec 2019 17:47:34 +0000 (09:47 -0800)]
[TEST] Remove nnvm related code in topi and test script (#4562)

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

* Remove docs dep

4 years ago[Relay][Frontend][ONNX] Support auto_pad in Conv and ConvTranspose (#4563)
Neo Chien [Sun, 22 Dec 2019 17:03:39 +0000 (01:03 +0800)]
[Relay][Frontend][ONNX] Support auto_pad in Conv and ConvTranspose (#4563)

4 years agoSupport standardize runtime module (#4532)
Zhao Wu [Sun, 22 Dec 2019 04:14:40 +0000 (12:14 +0800)]
Support standardize runtime module (#4532)

4 years ago[REFACTOR][DTYPE] Isolate dtype to runtime (#4560)
Tianqi Chen [Sun, 22 Dec 2019 02:26:21 +0000 (18:26 -0800)]
[REFACTOR][DTYPE] Isolate dtype to runtime (#4560)

dtype.h -> runtime/data_type.h

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

4 years ago[RUNTIME][VULKAN] Fix compiler warning (#4559)
Tianqi Chen [Sun, 22 Dec 2019 02:26:11 +0000 (18:26 -0800)]
[RUNTIME][VULKAN] Fix compiler warning (#4559)

4 years ago[IR] fix style in ir_mutator and ir_visitor (#4561)
Siyuan Feng [Sun, 22 Dec 2019 01:56:18 +0000 (17:56 -0800)]
[IR] fix style in ir_mutator and ir_visitor (#4561)

4 years ago[VTA] improved virtual memory mapping (#4545)
Liangfu Chen [Sat, 21 Dec 2019 22:19:56 +0000 (06:19 +0800)]
[VTA] improved virtual memory mapping (#4545)

* [VTA] improved virtual memory mapping

* Update virtual_memory.cc

4 years ago[COMMUNITY] @cchung100m -> reviewer (#4557)
Tianqi Chen [Fri, 20 Dec 2019 22:42:57 +0000 (14:42 -0800)]
[COMMUNITY] @cchung100m -> reviewer (#4557)

4 years agovm external codegen (#4544)
Zhi [Fri, 20 Dec 2019 22:36:14 +0000 (14:36 -0800)]
vm external codegen (#4544)

4 years ago[PYTHON][FFI] Cythonize NDArray.copyto (#4549)
Tianqi Chen [Fri, 20 Dec 2019 22:21:09 +0000 (14:21 -0800)]
[PYTHON][FFI] Cythonize NDArray.copyto (#4549)

* [PYTHON][FFI] Cythonize NDArray.copyto

* Cythonize the shape property

4 years ago[DOCS] Mention Ninja build system in install/from_source.rst (#4554)
Hideto Ueno [Fri, 20 Dec 2019 09:25:18 +0000 (18:25 +0900)]
[DOCS] Mention Ninja build system in install/from_source.rst (#4554)

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

* Address comments

4 years ago[TOPI] Fixed nms max_output_size loop (#4541)
mbarrett97 [Wed, 18 Dec 2019 21:23:36 +0000 (21:23 +0000)]
[TOPI] Fixed nms max_output_size loop (#4541)

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

Change-Id: I97184f5887f5f028d8ab339fa2808eb7630a4017

4 years ago[TOPI] Allow batch matmul to be fused into injective ops (#4537)
Haichen Shen [Wed, 18 Dec 2019 21:17:18 +0000 (13:17 -0800)]
[TOPI] Allow batch matmul to be fused into injective ops (#4537)

4 years ago[relay][op] add expand op (from ONNX) to relay frontend (#4483)
Takato Yamada [Wed, 18 Dec 2019 17:58:37 +0000 (02:58 +0900)]
[relay][op] add expand op (from ONNX) to relay frontend (#4483)

* Add Expand to onnx.py

* add test function for expand

* Fix a onnx frontend test

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

* Cleaned up some unnecessary modifications.

4 years agoImplement 1d deconvolution (#4476)
Alex Gladkov [Wed, 18 Dec 2019 17:35:22 +0000 (09:35 -0800)]
Implement 1d deconvolution (#4476)

4 years agoUpdate legacy places from nnvm to relay. (#4535)
Tianqi Chen [Wed, 18 Dec 2019 06:17:51 +0000 (22:17 -0800)]
Update legacy places from nnvm to relay. (#4535)

* Update legacy places from nnvm to relay.

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

* remove legacy stage

4 years ago[Relay] External codegen (#4482)
Zhi [Wed, 18 Dec 2019 03:17:55 +0000 (19:17 -0800)]
[Relay] External codegen (#4482)

4 years agoPIL is depreciated and should be replaced with pillow (a fork of PIL) (#4533)
lhutton1 [Tue, 17 Dec 2019 17:55:32 +0000 (17:55 +0000)]
PIL is depreciated and should be replaced with pillow (a fork of PIL) (#4533)

Change-Id: If2075df5475505f2da87dae7145af5a7ab83d8a4

4 years agofix crash issue in tsim backend (#4527)
Liangfu Chen [Mon, 16 Dec 2019 18:26:54 +0000 (02:26 +0800)]
fix crash issue in tsim backend (#4527)

4 years agofix onnx shape dtype (#4528)
masahi [Mon, 16 Dec 2019 16:11:53 +0000 (01:11 +0900)]
fix onnx shape dtype (#4528)

4 years agofix empty config caused KeyError (#4520)
Cody Yu [Mon, 16 Dec 2019 06:37:43 +0000 (22:37 -0800)]
fix empty config caused KeyError (#4520)

4 years agoadd bfloat16 typeflag support (#4525)
YixinBao [Mon, 16 Dec 2019 05:46:21 +0000 (13:46 +0800)]
add bfloat16 typeflag support (#4525)

4 years ago[ir] use DataType instead of Type for readability because Type has been deprecated...
Liang ZOU [Sun, 15 Dec 2019 23:09:51 +0000 (07:09 +0800)]
[ir] use DataType instead of Type for readability because Type has been deprecated (#4513)

4 years agoUse the best tuner possible (#4397)
miheer vaidya [Sun, 15 Dec 2019 23:09:16 +0000 (16:09 -0700)]
Use the best tuner possible (#4397)

* Use the best tuner possible

* Add comment denoting availability of better tuners

* Fix typos and wording

4 years agoFixed extra reshape parameter bug. (#4524)
Josh Fromm [Sun, 15 Dec 2019 23:08:35 +0000 (15:08 -0800)]
Fixed extra reshape parameter bug. (#4524)

4 years ago[Bugfix][Frontend][TFlite] Fix wrong function call in TANH tests (#4517)
Ina Dobreva [Sat, 14 Dec 2019 05:15:12 +0000 (05:15 +0000)]
[Bugfix][Frontend][TFlite] Fix wrong function call in TANH tests (#4517)

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

4 years agoFix bias_add gradient (#4516)
SWu [Fri, 13 Dec 2019 20:09:56 +0000 (15:09 -0500)]
Fix bias_add gradient (#4516)

* Fix bias_add gradient

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

* Lint fix

4 years agoFix TF resize for dynamic size models (#4510)
Alexander Pivovarov [Fri, 13 Dec 2019 17:42:58 +0000 (09:42 -0800)]
Fix TF resize for dynamic size models (#4510)

4 years ago[CI] Update docker image ci_lint to obtain Python 3.6 from ppa:deadsnakes/ppa (#4505...
Leandro Nunes [Fri, 13 Dec 2019 05:48:29 +0000 (05:48 +0000)]
[CI] Update docker image ci_lint to obtain Python 3.6 from ppa:deadsnakes/ppa (#4505) (#4506)

4 years ago[Quantization] Fix annotation for multiply op (#4458)
masahi [Thu, 12 Dec 2019 22:52:06 +0000 (07:52 +0900)]
[Quantization] Fix annotation for multiply op (#4458)

* fix mul rewrite

* register Realize Rewrite for global avg pool and add test

* remove unnecessary check

* improve the test case

4 years ago[Hybrid][Fix] Fix hybrid script to support array of tensors (#4494)
Haichen Shen [Thu, 12 Dec 2019 22:33:57 +0000 (14:33 -0800)]
[Hybrid][Fix] Fix hybrid script to support array of tensors (#4494)

* [Fix][Hybrid] Fix hybrid script to support array of tensors

* add test case

* clean up

* trigger ci

4 years agoFix build for llvm newer than 9.0 (#4515)
Dmitri Makarov [Thu, 12 Dec 2019 16:00:32 +0000 (17:00 +0100)]
Fix build for llvm newer than 9.0 (#4515)

4 years ago[TOPI] implement pool3d op (#4478)
optima2005 [Thu, 12 Dec 2019 06:06:20 +0000 (14:06 +0800)]
[TOPI] implement pool3d op (#4478)

* [TOPI] implement pool3d op

* use PoolInferCorrectLayout for both 2d and 3d pooling

* unify MakeMaxPool and MakeAvgPool

4 years ago[NODE][Serialization]fix serialization precision loss in float (#4503)
LaiyuanGong [Thu, 12 Dec 2019 01:47:50 +0000 (19:47 -0600)]
[NODE][Serialization]fix serialization precision loss in float (#4503)

* fix serialization precision loss in float

When we want to serialize a tvm.tensor object(like pickle), we will get a precision loss cause by std::to_string()。
For example, a2.value will be 0.0 while a.value=0.00000001 in the following:
    import tvm
    import pickle
    a = tvm.const(0.00000001, 'float32')
    a2 = pickle.loads(pickle.dumps(a))

* remove line end spaces

4 years agoadd rocm schedules to topi C++ (#4507)
Thomas Viehmann [Thu, 12 Dec 2019 01:23:00 +0000 (02:23 +0100)]
add rocm schedules to topi C++ (#4507)

This imports the CUDA schedules to rocm.

4 years agoAdd AMD codeGen unit tests (#4509)
Peter Yeh [Thu, 12 Dec 2019 01:19:42 +0000 (17:19 -0800)]
Add AMD codeGen unit tests (#4509)

4 years agoRefactor bilinear and neighbour implementation in Tensorflow frontend (#4504)
Ramana Radhakrishnan [Wed, 11 Dec 2019 18:42:15 +0000 (18:42 +0000)]
Refactor bilinear and neighbour implementation in Tensorflow frontend (#4504)

There is significant duplication between functions.

Spotted while looking to move the tensorflow and tflite framework support to later than
1.13.1. The tests barf around resize_nearest_neighbour not ignoring the attribute
'helpful_pixel_centers'.

That upgrade is a separate discussion while this can go in
independently.

Thanks,
Ramana

4 years ago[codegen][Build] it's more readable to move the if condition out of the loop (#4501)
Liang ZOU [Wed, 11 Dec 2019 17:33:08 +0000 (01:33 +0800)]
[codegen][Build] it's more readable to move the if condition out of the loop (#4501)

4 years ago[RUNTIME] Fix compile errors of OpenCL FPGA backend (#4492)
MORITA Kazutaka [Wed, 11 Dec 2019 16:39:06 +0000 (08:39 -0800)]
[RUNTIME] Fix compile errors of OpenCL FPGA backend (#4492)

4 years agoupdate rocm intrin rule (#4499)
Peter Yeh [Wed, 11 Dec 2019 09:14:36 +0000 (01:14 -0800)]
update rocm intrin rule (#4499)

4 years ago[VTA] Speedup TSIM by Multi-threading (#4491)
Liangfu Chen [Wed, 11 Dec 2019 00:53:53 +0000 (08:53 +0800)]
[VTA] Speedup TSIM by Multi-threading (#4491)

This PR tries to increase TSIM performance by introducing multi-threading support.

4 years agoAdd __float2half_rn for cuda compute capabilities less than 53 (#4489)
reminisce [Tue, 10 Dec 2019 22:05:52 +0000 (14:05 -0800)]
Add __float2half_rn for cuda compute capabilities less than 53 (#4489)

* Fix

* clean up

4 years ago[Relay][Fix] Fix alter op layout when calling a global var (#4454)
Haichen Shen [Tue, 10 Dec 2019 19:09:23 +0000 (11:09 -0800)]
[Relay][Fix] Fix alter op layout when calling a global var (#4454)

* [Relay][Fix] Fix alter op layout when calling a global var

* add test case

4 years ago[Team] Jared Roesch -> PPMC (#4488)
Yizhi Liu [Tue, 10 Dec 2019 18:35:12 +0000 (10:35 -0800)]
[Team] Jared Roesch -> PPMC (#4488)

4 years ago[docs] typos in include/tvm/ir.h (#4493)
Liang ZOU [Tue, 10 Dec 2019 17:54:22 +0000 (01:54 +0800)]
[docs] typos in include/tvm/ir.h (#4493)

4 years ago[REFACTOR][RUNTIME] Add LibraryModule that merges systemlib and dso. (#4481)
Tianqi Chen [Mon, 9 Dec 2019 21:22:31 +0000 (13:22 -0800)]
[REFACTOR][RUNTIME] Add LibraryModule that merges systemlib and dso. (#4481)

Historically we have two variations of modules(DSOModule and SystemLibModule)
that both exposes module via symbols.

This PR creates a common implementation for both, and introduce a Library
base class that allows us to have different implementations of GetSymbol.

It paves ways for future library related module enhancements.

4 years ago[Relay][Frontend][TFlite] Add parses support for UNPACK tflite operator (#4447)
Ina Dobreva [Mon, 9 Dec 2019 17:20:55 +0000 (17:20 +0000)]
[Relay][Frontend][TFlite] Add parses support for UNPACK tflite operator (#4447)

* use SPLIT & SQUEEZE = UNPACK as implemented in tensorflow parser
  Relay doesn't support UNPACK
* tflite 1.13: UNPACK doesn't work as exepcted -> copies the values from
  1st unpacked tensor to the other unpacks
* tflite 1.13: doesn't accept negative axis

4 years ago[VTA] Bringing group convolution support (#4421)
Thierry Moreau [Mon, 9 Dec 2019 06:08:21 +0000 (22:08 -0800)]
[VTA] Bringing group convolution support  (#4421)

* group conv operator support for VTA

* autotvm tuning script for group conv2d

* lint fix

* lint fix

* lint fix

* addressing comments

4 years agoCheck function attr for alpha equal (#4479)
Zhi [Sun, 8 Dec 2019 19:57:25 +0000 (11:57 -0800)]
Check function attr for alpha equal (#4479)

4 years ago[Codegen] fix bug on LLVM 10.0 (#4480)
Yuanqiang Liu [Sun, 8 Dec 2019 19:56:40 +0000 (03:56 +0800)]
[Codegen] fix bug on LLVM 10.0 (#4480)

4 years agoWorkaround to make conv2d_transpose compilation for CUDA work (#4472)
Alexander Pivovarov [Sun, 8 Dec 2019 00:29:55 +0000 (16:29 -0800)]
Workaround to make conv2d_transpose compilation for CUDA work (#4472)

4 years agoFix typo in travserse (#4469)
Alexander Pivovarov [Fri, 6 Dec 2019 08:35:20 +0000 (00:35 -0800)]
Fix typo in travserse (#4469)

4 years ago[relay][op] Add shape func to tile (#4441)
Zhi [Thu, 5 Dec 2019 06:16:37 +0000 (22:16 -0800)]
[relay][op] Add shape func to tile (#4441)

* [relay][op] Add shape func to tile

* retrigger ci

* check dynamic axes

* retrigger ci

4 years ago[BUGFIX] Fix search path for libtvm_topi.so (#4467)
Junru Shao [Wed, 4 Dec 2019 23:08:28 +0000 (15:08 -0800)]
[BUGFIX] Fix search path for libtvm_topi.so (#4467)

4 years ago[CONTRIB] TFLite Runtime (#4439)
ziheng [Wed, 4 Dec 2019 18:09:31 +0000 (10:09 -0800)]
[CONTRIB] TFLite Runtime (#4439)

4 years agolldb pretty printers for relay (#4453)
Leo-arm [Wed, 4 Dec 2019 17:45:42 +0000 (17:45 +0000)]
lldb pretty printers for relay (#4453)

* lldb pretty printers for relay

A set of lldb debugger pretty printers that use the relay
PrettyPrinter functionality to display data structures in
the lldb debugger.

* lldb pretty printers for relay

A set of lldb debugger pretty printers that use the relay
PrettyPrinter functionality to display data structures in
the lldb debugger.
- Put the dot.lldbinit file in your home directory as .lldbinit.
- Update the file to point to the pretty printer script tvm.py
- Restart lldb

4 years ago[doc] fix typo (#4463)
Liang ZOU [Wed, 4 Dec 2019 08:46:59 +0000 (16:46 +0800)]
[doc] fix typo (#4463)

4 years agoimplement conv3d op (#4400)
optima2005 [Wed, 4 Dec 2019 08:44:07 +0000 (16:44 +0800)]
implement conv3d op (#4400)

* implement conv3d op

* add back missed conv2d_output_shape by mistake

* fix typo and docs, add topi test

* rebase to master and merge 2d/3d unification

* use cudnn.conv_forward

4 years ago[RUNTIME][RPC] Update RPC runtime to allow remote module as arg (#4462)
Tianqi Chen [Tue, 3 Dec 2019 23:14:07 +0000 (15:14 -0800)]
[RUNTIME][RPC] Update RPC runtime to allow remote module as arg (#4462)

4 years ago[RUNTIME] Add cudnn conv3d (#4418)
optima2005 [Tue, 3 Dec 2019 21:18:19 +0000 (05:18 +0800)]
[RUNTIME] Add cudnn conv3d (#4418)

* [RUNTIME] Add cudnn conv3d

* add output checking to test_cudnn.verify()

* fix tests failure

* revised per as review comments

* unify conv_output_shape, conv_find_algo and conv_forward

* convert python list to tvm.array in conv_forward

* revise per as comments

* 'pass as reference' for vector args

* add back con2d/3d seperated implementation

* remove unused included header

* remove extra std::vectors

* remove unused header

4 years ago[MEMORY] Fix gcc 4.8 compact (#4461)
Tianqi Chen [Tue, 3 Dec 2019 20:34:15 +0000 (12:34 -0800)]
[MEMORY] Fix gcc 4.8 compact (#4461)

4 years agoFix the Makefile for howto_deploy (#4457)
Jammy Zhou [Tue, 3 Dec 2019 18:18:52 +0000 (02:18 +0800)]
Fix the Makefile for howto_deploy (#4457)

4 years agoFix MSVC build error with container.h (#4455)
jmorrill [Tue, 3 Dec 2019 17:52:00 +0000 (09:52 -0800)]
Fix MSVC build error with container.h (#4455)

4 years ago[TOPI][Relay][OP] Add a strided_set operation. (#4303)
abergeron [Tue, 3 Dec 2019 17:39:13 +0000 (12:39 -0500)]
[TOPI][Relay][OP] Add a strided_set operation. (#4303)

4 years ago[Relay] shape func for zeros, zeros_like, ones, ones_like (#4448)
Yong Wu [Mon, 2 Dec 2019 21:41:44 +0000 (13:41 -0800)]
[Relay] shape func for zeros, zeros_like, ones, ones_like (#4448)

4 years ago[DOCS] add benchmark log format doc (#4366)
anwang2009 [Mon, 2 Dec 2019 18:40:10 +0000 (10:40 -0800)]
[DOCS] add benchmark log format doc (#4366)

* add benchmark log format doc

* code review changes

* remove runtime_config, add md5 field

* schema edits

4 years ago[µTVM] Enable AutoTVM for ARM STM32F746XX Boards (#4274)
Logan Weber [Mon, 2 Dec 2019 18:38:12 +0000 (10:38 -0800)]
[µTVM] Enable AutoTVM for ARM STM32F746XX Boards (#4274)

4 years agoa tiny typo (#4452)
HarryWu [Mon, 2 Dec 2019 17:09:38 +0000 (01:09 +0800)]
a tiny typo (#4452)

4 years ago[TFLite] Add transpose_conv to TFLite parser (#4440)
Alexander Pivovarov [Sun, 1 Dec 2019 15:41:50 +0000 (07:41 -0800)]
[TFLite] Add transpose_conv to TFLite parser (#4440)

4 years ago[Runtime] Make ADTObject POD container type (#4346)
Wei Chen [Sun, 1 Dec 2019 15:41:00 +0000 (07:41 -0800)]
[Runtime] Make ADTObject POD container type (#4346)

4 years ago[Relay][Pass] Fix lambda lift pass for recursive call (#4432)
Haichen Shen [Sun, 1 Dec 2019 00:27:15 +0000 (16:27 -0800)]
[Relay][Pass] Fix lambda lift pass for recursive call (#4432)

* Fix lambda lift

* clean up

* lint

* fix

* remove unused import

4 years ago[Relay][Frontend][TFlite] Add test for qnn_mul operator (#4395)
Ina Dobreva [Sun, 1 Dec 2019 00:16:44 +0000 (00:16 +0000)]
[Relay][Frontend][TFlite] Add test for qnn_mul operator (#4395)

* Add a function to set the qnn output range wrt each elemwise operation.
* Add comments warning for nonsense clamped output in the tflite/tvm results comparison.

4 years agorpi4b target (#4445)
Thierry Moreau [Thu, 28 Nov 2019 18:12:49 +0000 (10:12 -0800)]
rpi4b target (#4445)

4 years agofix multiple transfer issue in loaduop (#4442)
Liangfu Chen [Thu, 28 Nov 2019 06:45:58 +0000 (14:45 +0800)]
fix multiple transfer issue in loaduop (#4442)

4 years ago[Doc] Fix broken link (#4438)
Neo Chien [Wed, 27 Nov 2019 18:42:54 +0000 (02:42 +0800)]
[Doc] Fix broken link (#4438)

* [Doc] Fix broken link

* [Doc] Fix broken link

* [Doc] Fix broken link

4 years ago[VTA] Enable streamlined GEMM execution (#4392)
Liangfu Chen [Wed, 27 Nov 2019 17:04:19 +0000 (01:04 +0800)]
[VTA] Enable streamlined GEMM execution (#4392)

* disable pipelined adder and enable streamlined gemm execution

* pipeline first layer of adder

* explain difference between pipeadder and adder

* add comment for explaining the hard-coded latency

4 years agoadd DeviceName to ROCm api (#4437)
Thomas Viehmann [Wed, 27 Nov 2019 15:15:37 +0000 (16:15 +0100)]
add DeviceName to ROCm api (#4437)

4 years ago[ARM CPU] Fix infer shape error of depthwise (#4384)
Zhao Wu [Wed, 27 Nov 2019 06:42:20 +0000 (14:42 +0800)]
[ARM CPU] Fix infer shape error of depthwise (#4384)

* [ARM CPU] Fix contrib_spatial_pack error

* PyLint error fix

* diable no-else-return as other files

* Change the test case split OC not be 1 to cover 5D weight layout

4 years ago[VTA][HotFix] Relay->VTA quantization fix (#4433)
Thierry Moreau [Wed, 27 Nov 2019 03:21:56 +0000 (19:21 -0800)]
[VTA][HotFix] Relay->VTA quantization fix (#4433)

* relay -> vta fix

* setting optlevel to 3 for quantization to fold batchnorm

4 years ago[RELEASE] Update copyright message, change notice, remove cma kernel module for now...
Tianqi Chen [Tue, 26 Nov 2019 23:58:13 +0000 (15:58 -0800)]
[RELEASE] Update copyright message, change notice, remove cma kernel module for now (#4431)

4 years ago[DOCS] Update main website to tvm.apache.org (#4429)
Tianqi Chen [Tue, 26 Nov 2019 22:40:26 +0000 (14:40 -0800)]
[DOCS] Update main website to tvm.apache.org (#4429)

* [DOCS] Update main website to tvm.apache.org

* Update jvm pom repo loc

* Change the org to asf

* Update ci addr to new one

4 years agoAllow Array/Map store objects that are not NodeRef (#4430)
Junru Shao [Tue, 26 Nov 2019 22:33:44 +0000 (14:33 -0800)]
Allow Array/Map store objects that are not NodeRef (#4430)

4 years agoTweak debugger result (#4426)
Haichen Shen [Tue, 26 Nov 2019 19:06:47 +0000 (11:06 -0800)]
Tweak debugger result (#4426)

4 years ago[AutoTVM] select model with the most tuned schedules (#4404)
Xingyu Zhou [Tue, 26 Nov 2019 18:17:25 +0000 (10:17 -0800)]
[AutoTVM] select model with the most tuned schedules (#4404)

* select model with the most tuned schedules

* change detect empty map method

* modify model description for load_reference_log

4 years ago[SETUP] Add optional dependencies to extras_require (#4428)
Neo Chien [Tue, 26 Nov 2019 17:48:24 +0000 (01:48 +0800)]
[SETUP] Add optional dependencies to extras_require (#4428)