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)
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
Tianqi Chen [Tue, 3 Dec 2019 20:34:15 +0000 (12:34 -0800)]
[MEMORY] Fix gcc 4.8 compact (#4461)
Jammy Zhou [Tue, 3 Dec 2019 18:18:52 +0000 (02:18 +0800)]
Fix the Makefile for howto_deploy (#4457)
jmorrill [Tue, 3 Dec 2019 17:52:00 +0000 (09:52 -0800)]
Fix MSVC build error with container.h (#4455)
abergeron [Tue, 3 Dec 2019 17:39:13 +0000 (12:39 -0500)]
[TOPI][Relay][OP] Add a strided_set operation. (#4303)
Yong Wu [Mon, 2 Dec 2019 21:41:44 +0000 (13:41 -0800)]
[Relay] shape func for zeros, zeros_like, ones, ones_like (#4448)
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
Logan Weber [Mon, 2 Dec 2019 18:38:12 +0000 (10:38 -0800)]
[µTVM] Enable AutoTVM for ARM STM32F746XX Boards (#4274)
HarryWu [Mon, 2 Dec 2019 17:09:38 +0000 (01:09 +0800)]
a tiny typo (#4452)
Alexander Pivovarov [Sun, 1 Dec 2019 15:41:50 +0000 (07:41 -0800)]
[TFLite] Add transpose_conv to TFLite parser (#4440)
Wei Chen [Sun, 1 Dec 2019 15:41:00 +0000 (07:41 -0800)]
[Runtime] Make ADTObject POD container type (#4346)
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
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.
Thierry Moreau [Thu, 28 Nov 2019 18:12:49 +0000 (10:12 -0800)]
rpi4b target (#4445)
Liangfu Chen [Thu, 28 Nov 2019 06:45:58 +0000 (14:45 +0800)]
fix multiple transfer issue in loaduop (#4442)
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
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
Thomas Viehmann [Wed, 27 Nov 2019 15:15:37 +0000 (16:15 +0100)]
add DeviceName to ROCm api (#4437)
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
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
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)
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
Junru Shao [Tue, 26 Nov 2019 22:33:44 +0000 (14:33 -0800)]
Allow Array/Map store objects that are not NodeRef (#4430)
Haichen Shen [Tue, 26 Nov 2019 19:06:47 +0000 (11:06 -0800)]
Tweak debugger result (#4426)
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
Neo Chien [Tue, 26 Nov 2019 17:48:24 +0000 (01:48 +0800)]
[SETUP] Add optional dependencies to extras_require (#4428)
Haichen Shen [Tue, 26 Nov 2019 01:11:15 +0000 (17:11 -0800)]
[Fix][Relay] Remove schedule register for nonexisting log1p op (#4425)
Thierry Moreau [Tue, 26 Nov 2019 00:18:10 +0000 (16:18 -0800)]
removing nnvm dep from VTA sources (#4419)
Thomas Viehmann [Mon, 25 Nov 2019 15:37:52 +0000 (16:37 +0100)]
add rocm codegen unittest for cross thread reduction (#4423)
Siyuan Feng [Mon, 25 Nov 2019 06:01:55 +0000 (22:01 -0800)]
[Perf] Enhance cudnn and cublas backend and enable TensorCore (#4353)
* add half and mix precision support to cublas backend
* add TensorCore support in CuDNN
* enhance CuDNN support
* address comments and fix lint
* fix
* add fp16 test
Tianqi Chen [Sun, 24 Nov 2019 22:34:17 +0000 (14:34 -0800)]
[RUNTIME] rename allocator.make -> allocator.make_object for term consistency (#4416)
Philip Hyunsu Cho [Sun, 24 Nov 2019 22:16:29 +0000 (14:16 -0800)]
Fix compilaton of bfloat16 on Windows (#4415)
Tianqi Chen [Sun, 24 Nov 2019 19:43:21 +0000 (11:43 -0800)]
[LICENSE] clarify the blockingqueue license, update version to 0.6.0 (#4414)
Yizhi Liu [Sun, 24 Nov 2019 17:44:38 +0000 (09:44 -0800)]
[License] move cma_api to 3rdparty. separate BSD 2-clause and 3-clause (#4410)
* [License] move cma_api to 3rdparty. separate BSD 2-clause and 3-clause
* add zlib license for blockingconcurrentqueue.h
Tianqi Chen [Sun, 24 Nov 2019 08:22:55 +0000 (00:22 -0800)]
[LINT] Remove unnecessary copyright message for files with ASF header (#4409)
* [LINT] Improve the check tool to handle ASF copyright message.
* [LINT] Remove unnecessary copyright message as per ASF requirement.
* Fix codegen hybrid
* [LINT] Broaden license checks to include html, xml
* [LINT] Fix rest of the files
* Fix notice
* [LINT] Improve check file type error message
Yizhi Liu [Sun, 24 Nov 2019 03:39:25 +0000 (19:39 -0800)]
[Release] resolve license issues (#4408)
Alexander Pivovarov [Sat, 23 Nov 2019 05:59:15 +0000 (21:59 -0800)]
[Relay][Legalize] Legalize conv2d_transpose for NHWC (#4399)
Tianqi Chen [Sat, 23 Nov 2019 04:32:20 +0000 (20:32 -0800)]
[RUNTIME] Move module export to the function level. (#4405)
Zhi [Fri, 22 Nov 2019 23:31:50 +0000 (15:31 -0800)]
[TVM][RUNTIME] A minimum example to generate external library wrappers for DSOModule (#4280)
Yizhi Liu [Fri, 22 Nov 2019 22:37:25 +0000 (14:37 -0800)]
[LICENSE] add 3rdparty licenses (#4402)
* [LICENSE] add 3rdparty licenses
* rename license files to .txt
tristan-arm [Fri, 22 Nov 2019 21:34:40 +0000 (21:34 +0000)]
Added tflite frontend support for quantized mean. (#4339)
Tianqi Chen [Fri, 22 Nov 2019 18:28:43 +0000 (10:28 -0800)]
[DOCS] Mention incubating in readme (#4401)
Neo Chien [Fri, 22 Nov 2019 05:52:24 +0000 (13:52 +0800)]
[Golang][Doc] improve the samples and doc (#4385)
* [Golang][Doc] improve the samples and doc
* [Golang][Doc] add asf header
* [Golang][Doc] Improve the end to end example
* [Golang][Doc] Improve the end to end example
tripley [Fri, 22 Nov 2019 03:12:05 +0000 (19:12 -0800)]
update_document_after_repository_renamed (#4398)
Cody Yu [Fri, 22 Nov 2019 00:45:47 +0000 (16:45 -0800)]
Update Jenkinsfile for external runtime (#4396)
Haichen Shen [Fri, 22 Nov 2019 00:01:01 +0000 (16:01 -0800)]
[Relay][VM] Clean up the VM and VM profiler code (#4391)
* [VM] add a few more API to vm
* [VM][Fix] fix vm convert args
* [VM] a few fixes
* rename fields
* update
* update vm profiler
* x
* add doc
* lint
* fix test
* address comments
Yizhi Liu [Thu, 21 Nov 2019 23:39:40 +0000 (15:39 -0800)]
[TOPI] Fix flaky testcase for floor div (#4382)
* [TOPI] Fix flaky testcase for floor div
* avoid check at 0.0
Haichen Shen [Thu, 21 Nov 2019 20:46:41 +0000 (12:46 -0800)]
Add Logan to reviewer (#4390)
Huang, Guangtai [Thu, 21 Nov 2019 20:46:00 +0000 (04:46 +0800)]
Update compile_engine.py (#4393)
Siyuan Li [Thu, 21 Nov 2019 18:53:37 +0000 (02:53 +0800)]
[Relay][Frontend][TF] Fix slice when begin or size is not Const (#4372)
* fix slice bug when input is param
* use _infer_value rather than _infer_value_simulated
Thomas Viehmann [Thu, 21 Nov 2019 14:40:29 +0000 (15:40 +0100)]
add GPU checking before compilation for rocm (#4394)
Previously, we would rely on the later phases to error out
(often for using too much shared memory). This enables the
checks on the IR that already exist for CUDA and OpenCL also
for ROCm.
Animesh Jain [Thu, 21 Nov 2019 05:22:25 +0000 (21:22 -0800)]
[QNN] Lowering for Depthwise Convolution. (#4351)
Zhi [Thu, 21 Nov 2019 00:50:01 +0000 (16:50 -0800)]
[fix][pass] Save the function when it is used as a call arg (#4389)
Tianqi Chen [Wed, 20 Nov 2019 23:43:54 +0000 (15:43 -0800)]
[CI] Add more info, per exec ws isolation (#4388)
Zhao Wu [Wed, 20 Nov 2019 20:43:20 +0000 (04:43 +0800)]
[ThreadPool] Solve thread transitions issue (#4344)
* [ThreadPool] Solve thread transitions issue
* Use pthread_atfork to avoid master thread affinity be derived by child.
* Code Format
* comment of exclude_worker0_
* set full cpu affinity
* Redundant blank line
* CPPLint
* CPPLint namespace
* CPPLint
* Fix the wrong logic of bind master thread.
Alexander Pivovarov [Wed, 20 Nov 2019 17:36:57 +0000 (09:36 -0800)]
Compare all outputs in TFLite test_forward_ssd_mobilenet_v1 (#4373)
Yizhi Liu [Wed, 20 Nov 2019 17:31:34 +0000 (09:31 -0800)]
[team] add Yizhi's pgp key (#4380)
masahi [Wed, 20 Nov 2019 17:09:29 +0000 (02:09 +0900)]
fix build with llvm trunk (#4386)
Liang ZOU [Wed, 20 Nov 2019 13:05:01 +0000 (21:05 +0800)]
[doc] fix typo, codege to codegen (#4383)
Tianqi Chen [Wed, 20 Nov 2019 06:04:42 +0000 (22:04 -0800)]
[CI] Avoid content-length request in test data download (#4375)
Yizhi Liu [Tue, 19 Nov 2019 23:07:29 +0000 (15:07 -0800)]
[nvcc] enable multiple arch in one fatbin (#4377)
Wuwei Lin [Tue, 19 Nov 2019 22:54:57 +0000 (17:54 -0500)]
[Relay][Quantize] Integrate data-aware calibration into quantization (#4295)
* [Relay][Quantize] Integrate data-aware calibration into quantization
* Update _calibrate.py
* trigger ci
* Address comments
* address comments
Haichen Shen [Tue, 19 Nov 2019 21:56:51 +0000 (13:56 -0800)]
[PERF] Parallelize reduction for CPU (#4158)
* [PERF] parallel reduction in cpu
* fix
* x
* update
* lint
* fix
Yizhi Liu [Tue, 19 Nov 2019 21:51:34 +0000 (13:51 -0800)]
[tutorial][benchmark] nnvm -> relay (#4368)
* [tutorial] nnvm -> relay
* use relay workload
* delete movbilenetv2 option
Alexander Pivovarov [Tue, 19 Nov 2019 17:15:08 +0000 (09:15 -0800)]
Fix TFLite RESHAPE assert (#4320)
Animesh Jain [Tue, 19 Nov 2019 04:18:58 +0000 (20:18 -0800)]
[Relay tests] AlterOpLayout - Temporary attr update (#4357)
miheer vaidya [Tue, 19 Nov 2019 04:03:53 +0000 (21:03 -0700)]
add rule for clean (#4364)
* add rule for clean
* Update clean rule
Seems like lib/ directory is not made by the makefile
So don't delete directory, just the contents of it.
Yizhi Liu [Mon, 18 Nov 2019 23:10:10 +0000 (15:10 -0800)]
reminding message for TVM_REGISTER_NODE_TYPE (#4365)
Cody Hao Yu [Mon, 18 Nov 2019 19:24:39 +0000 (11:24 -0800)]
fix Android and OpenCL docker install (#4363)
Tianqi Chen [Mon, 18 Nov 2019 18:22:25 +0000 (10:22 -0800)]
[SOURCE] Add ASF header to __init__.py files (#4359)
Yao Wang [Mon, 18 Nov 2019 03:54:34 +0000 (19:54 -0800)]
[Frontend]Add TensorFlow FloorMod (#4308)
* Add tf FloorMod
* Add floor_div/mod into topi and relay
* Add to rst
* Fix test
optima2005 [Mon, 18 Nov 2019 01:24:44 +0000 (09:24 +0800)]
[Relay][Frontend][Tensorflow]Add conv2d_transpose (#4300)
* [Relay][Frontend][Tensorflow]Add conv2d_transpose
* add transformation from NHWC to NCHW to compatible with TVM conv2d_transpose implementation
* remove 'dilations' paramater to compitable with TF1.3
miheer vaidya [Mon, 18 Nov 2019 00:39:36 +0000 (17:39 -0700)]
Send list as argument to schedule_conv2d (#4358)
When getting cuda schedule passing single tensor seem to work but after changing target to "llvm" causes assert.
Sending list on other hand makes both cuda and llvm targets happy.
See https://discuss.tvm.ai/t/solved-simple-example-error-attributeerror-tensorslice-object-has-no-attribute-op/2245/3
Philip Hyunsu Cho [Sat, 16 Nov 2019 16:40:38 +0000 (08:40 -0800)]
Fix docstring in topi.nn.fifo_buffer (#4349)
Ramana Radhakrishnan [Sat, 16 Nov 2019 16:39:19 +0000 (16:39 +0000)]
Retain qnn input kernel scales (#4292)
* Add qnn conv2d attributes for input_tensor_scale and
kernel_tensor_scale.
The lowering in the tflite frontend loses the input_tensor_scale
and the kernel_tensor_scale by multiplying it and putting it into
the Requantize operation. This means that any graph partitioning
passes or other passes that need to access this information no longer
have it available in the qnn dialect.
regards
Ramana
* Store input tensor scale and Weight tensor scale for Dense as well
As for conv2d, the tflite frontend drops the input tensor
scale and the weight tensor scale from the relay op. Store
it as separate fields in there.
* Fix unintentional tab
* Rename input_tensor_scale to input_scale and kernel_tensor_scale
to kernel_scale for conv2d.
* input_tensor_scale -> input_scale weight_tensor_scale->weight_scale
* Rework dense testcase
And use input_scale and kernel_scale
* Be consistent in use of input_scale and kernel_scale values
* Fixup qnn conv2d tests for input_scale and kernel_scale
* Make pydoc identical between conv2d and dense for weight_tensor
* Fix up conv2d parameters to be in the same order between C++ and python
* Fix ordering of parameters for dense.
* Add input_scale and output_scale to try and satisfy ci gods
* Delete input_scale and kernel_scale.
nn.conv2d does not contain input_scale and kernel_scale. We need
to delete it when lowering it to nn.conv2d.
* Add input_scale and kernel_scale for qnn.conv2d
Animesh Jain [Sat, 16 Nov 2019 16:38:10 +0000 (08:38 -0800)]
[Debugger] Sorting op-time breakdown for quicker analysis. (#4352)
Peter Yeh [Sat, 16 Nov 2019 06:39:44 +0000 (22:39 -0800)]
proper device query through rocm api (#4305)
Cody Hao Yu [Sat, 16 Nov 2019 06:27:49 +0000 (22:27 -0800)]
fix install script (#4350)
黎明灰烬 [Sat, 16 Nov 2019 00:53:01 +0000 (08:53 +0800)]
AutoTVM: selecting tuning templates when extracting task (#4338)
* AutoTVM: selecting tuning templates when extracting task
Make the procedure of trying new templates easier.
Test: tests/python/relay/test_autotvm_task_extraction.py
* Use dict to match key for topi ops
* fix lint issue
* be more pythonic :)
Thomas Viehmann [Fri, 15 Nov 2019 23:14:56 +0000 (00:14 +0100)]
Add workgroup size attribute to AMDGPU functions in codegen (#4342)
When we did not set the workgroup size, LLVM will use too many registers
for kernel launches with many threads. This resulted in "invalid ISA"
errors. Here we set the maximum workgroup size to the maximum threads
per block from the device API.
Of course, one might look into allowing configurations with fewer
threads at runtime to use more registers.
Kimish Patel [Fri, 15 Nov 2019 22:37:37 +0000 (14:37 -0800)]
[FIX] Fix for a specific case when loop partitioning with indivisble (#4243)
factors and resulting nested loop is broken.
This is due to the fact that we are creating zero extent loops which
are fixed afterwards. However unroll pass breaks due to the zero extent
loop.
Logan Weber [Fri, 15 Nov 2019 22:12:52 +0000 (14:12 -0800)]
[Relay][VM][Interpreter] Enable first-class constructors in VM and interpreter via eta expansion (#4218)
* Fix constructor pretty printing
* Make Module::HasDef name consistent with API
* Add VM constructor compilation via eta expansion
* Lint
* Fix CI
* Fix failing test
* Address comment
* Retrigger CI
* Retrigger CI
Tianqi Chen [Fri, 15 Nov 2019 22:09:47 +0000 (14:09 -0800)]
[COMMUNITY] Add DISCLAIMER, KEYS for ASF release (#4345)
* [COMMUNITY] Add DISCLAIMER, KEYS for ASF release
* Add file name spec
T.J. Mercier [Fri, 15 Nov 2019 19:15:12 +0000 (11:15 -0800)]
Add check to ensure input file was successfully opened in NNVM deploy code demo (#4315)
Alex Gladkov [Fri, 15 Nov 2019 19:04:00 +0000 (11:04 -0800)]
Bump up CUDA log version in tophub.py (#4347)
Zhao Wu [Fri, 15 Nov 2019 18:05:26 +0000 (02:05 +0800)]
[CodeGen] Add build config option disable_assert to control whether to generate assert (#4340)
ziyu-guo [Fri, 15 Nov 2019 17:59:59 +0000 (09:59 -0800)]
fix inconsistent tag name (#4134)
Liangfu Chen [Fri, 15 Nov 2019 17:59:04 +0000 (01:59 +0800)]
[VTA] Bug fix for padded load with large inputs (#4293)
* bug fix for padded load with large inputs
* Update TensorLoad.scala
* Update test_vta_insn.py
Jian Weng [Fri, 15 Nov 2019 17:13:04 +0000 (09:13 -0800)]
imp module is deprecated (#4275)
Neo Chien [Fri, 15 Nov 2019 16:53:13 +0000 (00:53 +0800)]
[Relay][Frontend][ONNX] operator support: DepthToSpace, SpaceToDepth (#4271)
Wei Chen [Fri, 15 Nov 2019 16:42:58 +0000 (08:42 -0800)]
[Test][Relay][Pass] Add test case for lambda lift (#4317)
Peter Yeh [Fri, 15 Nov 2019 04:43:47 +0000 (20:43 -0800)]
[RUNTIME] Add device query for AMD GcnArch (#4341)
* add gcnArch query
* kGcnArch query for cuda is a no-op
Jon Soifer [Fri, 15 Nov 2019 03:52:40 +0000 (19:52 -0800)]
[Relay][Frontend][TF] Fix transpose when axes is not a param (#4327)
* [Relay][Frontend][TF] Use _infer_value_simulated when axes is not a const to Transpose
* uncomment tests
* dummy change to retrigger ci
Haichen Shen [Fri, 15 Nov 2019 03:45:57 +0000 (19:45 -0800)]
[Contrib] Add MKL DNN option (#4323)
* [Contrib] Add MKL DNN
* update
* update
Yizhi Liu [Fri, 15 Nov 2019 03:45:25 +0000 (19:45 -0800)]
Deprecate NNVM warning msg (#4333)
Zhao Wu [Fri, 15 Nov 2019 03:43:38 +0000 (11:43 +0800)]
Solve custom model of prelu (#4326)
Philip Hyunsu Cho [Fri, 15 Nov 2019 03:42:53 +0000 (19:42 -0800)]
Add topi.nn.fifo_buffer to TVM doc (#4343)
Ina Dobreva [Fri, 15 Nov 2019 03:41:36 +0000 (03:41 +0000)]
Add support for quant. mul operator in tflite frontend (#4283)
A test for qnn_mul has to be added when the qnn elemwise tests (#4282) get merged.
Wei Chen [Fri, 15 Nov 2019 01:52:01 +0000 (17:52 -0800)]
[Relay][Pass] Add pass to remove unused functions in relay module (#4334)
* [Relay][Pass] Add pass to remove unused functions in relay module
* Add tests
* Fix lint
* Fix visit order
* Add pass argument
* Fix