platform/upstream/tvm.git
3 years agoTVMC - a command line driver for TVM (#6112)
Leandro Nunes [Sun, 16 Aug 2020 17:45:44 +0000 (18:45 +0100)]
TVMC - a command line driver for TVM (#6112)

* Introduce a command line driver to compile, run and tune models, using TVM graph runtime
 * Include tvmc tests and integrate tvmc with linting, testing and CI
 * RFC: https://discuss.tvm.ai/t/rfc-a-tvm-command-line-interface/5165

Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <Matthew.Barrett@arm.com>
Co-authored-by: Dmitriy Smirnov <dmitriy.smirnov@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Co-authored-by: Matthew Barrett <matthew.barrett@arm.com>
Co-authored-by: Elen Kalda <elen.kalda@arm.com>
Co-authored-by: Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>
Co-authored-by: Jeremy Johnson <jeremy.johnson@arm.com>
Co-authored-by: Ina Dobreva <Ina.Dobreva@arm.com>
Co-authored-by: Marcus Shawcroft <marcus.shawcroft@arm.com>
Co-authored-by: Matthew Barrett <Matthew.Barrett@arm.com>
Co-authored-by: Dmitriy Smirnov <dmitriy.smirnov@arm.com>
Co-authored-by: Luke Hutton <luke.hutton@arm.com>
Co-authored-by: Giuseppe Rossini <giuseppe.rossini@arm.com>
Co-authored-by: Elen Kalda <elen.kalda@arm.com>
Co-authored-by: Ramana Radhakrishnan <ramana.radhakrishnan@arm.com>
Co-authored-by: Jeremy Johnson <jeremy.johnson@arm.com>
Co-authored-by: Ina Dobreva <Ina.Dobreva@arm.com>
3 years agoAdd Quantize/Dequantize Partitioning (#5940)
Logan Weber [Sat, 15 Aug 2020 21:48:24 +0000 (14:48 -0700)]
Add Quantize/Dequantize Partitioning (#5940)

* Implement quant/dequant partitioning

on our way

get clooooooser

clean up (part 1)

clean up (part 2)

clean up (part 3)

clean up (part 4)

clean clean

cleaanaannanaaananaananaananaan

clkjsdflkjlfsjdflkj

revert parser changes

add docs

roll lint

roll lint

* add option to toggle fully integral check

* convert dtype collector to C++

* remove need for `with_dtype`

* remove unused imports

* roll lint

* partially address feedback

* roll lint

* upgrade to new parser

* retrigger CI

* roll the dice again

3 years ago[Build] Reflect Compile-Time CMake Options into libtvm.so (#6280)
Junru Shao [Sat, 15 Aug 2020 14:05:40 +0000 (07:05 -0700)]
[Build] Reflect Compile-Time CMake Options into libtvm.so (#6280)

* Initial comit

* Address comments from @tqchen

3 years ago[CI] Update ci-cpu to the latest (#6283)
Tianqi Chen [Sat, 15 Aug 2020 03:41:30 +0000 (20:41 -0700)]
[CI] Update ci-cpu to the latest (#6283)

3 years agoImprove error messages for memory verifier and gpu memory verifier (#6281)
Tristan Konolige [Sat, 15 Aug 2020 03:06:24 +0000 (20:06 -0700)]
Improve error messages for memory verifier and gpu memory verifier (#6281)

* [FIX] Print exactly what issues the GPU memory verifier encountered.

* [FIX] Print exactly why memory verifier failed.

3 years ago[Target] Creating Target from JSON-like Configuration (#6218)
Junru Shao [Sat, 15 Aug 2020 01:33:37 +0000 (18:33 -0700)]
[Target] Creating Target from JSON-like Configuration (#6218)

* [Target] Creating Target from JSON-like Configuration

* Address comments from Cody

* fix unittest

* More testcases as suggested by @comaniac

3 years agoAdded support for tflite quantized maximum and minimum (#6018)
Dmitriy Smirnov [Fri, 14 Aug 2020 18:54:29 +0000 (19:54 +0100)]
Added support for tflite quantized maximum and minimum (#6018)

* Added support for tflite quantized maximum and minimum

* Unit test simplified

Bugfix in unit test. Unit test slightly simplified

* re-trigger CI

* renamed use_real_qnn to ignore_qnn_params

3 years agoUpdate precision in the ONNX strided_slice, update precision of ToScalar (#6272)
Matthew Brookhart [Fri, 14 Aug 2020 17:27:20 +0000 (10:27 -0700)]
Update precision in the ONNX strided_slice, update precision of ToScalar (#6272)

* Update precision in the ONNX strided_slice, update precision of ToScalar

* fix tests

3 years ago[TESTS] Decrease test times by introducing testing model (#6235)
Tristan Konolige [Fri, 14 Aug 2020 16:15:00 +0000 (09:15 -0700)]
[TESTS] Decrease test times by introducing testing model (#6235)

Adds a new testing model `tvm.relay.testing.synthetic` which is a small,
but representative model. Replaces resnet with this model in many tests.

3 years ago[Parser] Add support for parsing the any dimension. (#6277)
Jared Roesch [Fri, 14 Aug 2020 16:13:42 +0000 (09:13 -0700)]
[Parser] Add support for parsing the any dimension.  (#6277)

* Add case for any dimensions

* Fix second test case

3 years agoadd dilation in x86 NCHWc depthwise conv support (#4962) (#6267)
wjliu [Fri, 14 Aug 2020 05:17:38 +0000 (13:17 +0800)]
add dilation in x86 NCHWc depthwise conv support (#4962) (#6267)

3 years ago[BYOC][ACL] Add support for dense (fully connected) layer (#6254)
lhutton1 [Thu, 13 Aug 2020 16:21:35 +0000 (17:21 +0100)]
[BYOC][ACL] Add support for dense (fully connected) layer (#6254)

* [BYOC][ACL] Add support for dense (fully connected) layer

This patch adds the ability to offload dense (or fully connected) operators to ACL.

For fp32 a single dense layer can be offloaded, or the composite variant: nn.dense, nn.bias_add? (ACL does not currently offer fused activation).
For uint8: qnn.dense, nn.bias_add?, qnn.requantize

Change-Id: I83ea00b2aa6bdc5d9ef5cd6d54bbf981e523bd14

* Don't offload dense layer with unsupported datatype

Change-Id: I856eb2298499fdf22c172ba7f85d21033d3cc920

3 years ago[Relay][Dyn] Dynamic full operator (#6260)
Lily Orth-Smith [Thu, 13 Aug 2020 16:08:34 +0000 (09:08 -0700)]
[Relay][Dyn] Dynamic full operator (#6260)

* moved full from other branch

* fixed some typos

* fix lint

* add final newline

* fix int64 test

3 years agofix cuda half math function is undefined: hpow, htanh (#6253)
cloud-mxd [Thu, 13 Aug 2020 15:36:59 +0000 (23:36 +0800)]
fix cuda half math function is undefined: hpow, htanh (#6253)

3 years agoTrivial fix, up the rodata section for the discovery board to 512 bytes. (#6259)
Tom Gall [Thu, 13 Aug 2020 15:34:34 +0000 (10:34 -0500)]
Trivial fix, up the rodata section for the discovery board to 512 bytes. (#6259)

This is more reasonable as the trivial tflite example module needs 208 bytes.

Signed-off-by: Tom Gall <tom.gall@linaro.org>
3 years ago[LINT] Fix clang-format (#6264)
Tianqi Chen [Thu, 13 Aug 2020 15:34:04 +0000 (08:34 -0700)]
[LINT] Fix clang-format (#6264)

3 years agoImprove NHWC depthwise convolution for AArch64 (#6095)
Giuseppe Rossini [Thu, 13 Aug 2020 14:41:45 +0000 (15:41 +0100)]
Improve NHWC depthwise convolution for AArch64 (#6095)

* Improve NHWC depthwise convolution for aarch64

We created a default schedule (no auto-tuning or tensorization) named
depthwise_conv2d_nhwc which does a decent job at optimizing depthwise
for NHWC layouts (on aarch64).

Change-Id: I01e32903f6c1950623f33eae18484e70244fe0af

* Add tuning knobs in depthwise schedule

Change-Id: I15080e7f12b16e6c6aba99a04e42023845eeabf1

* Introduce padding policy

Change-Id: If12a6d05dce9153861550ddef1ee5216809dd1e1

* Vectorize padding

Change-Id: I7e2062a40358bf111c0366a449945eb077fb2e30

* Legalize depthwise convolution (2x improvement) and fix tuning issue

Change-Id: I4b82c58b167e40b0b7747d28293bbb488c505dd9

* Adding assert on padding

Change-Id: Idf8eeaaface5eb7799109cd00f437e404778b9cd

* Fix python linting

Change-Id: Iac16a8daea1268f0eb331fe4ec18a62408106cf9

* Removing commented code

Change-Id: I1412f22ad9864273d77a7bf38a6768694339b7f0

* Revert test file to make CI pass

Change-Id: Ica3eff8f9f0fd4c6f32f7ae80adc922f8b16cec9

* Enabling only arm_cpu tests

Change-Id: Icbaafcb39e892a5d1a4685133c1699e4d1a8e07e

* Rebasing

Change-Id: Ibb23f1d4e0d0107e4e3b3571437161cdc2ee2909

3 years agoupdate tutorial to new TARGET as micro_dev is no more (#6262)
Tom Gall [Thu, 13 Aug 2020 03:18:37 +0000 (22:18 -0500)]
update tutorial to new TARGET as micro_dev is no more (#6262)

Signed-off-by: Tom Gall <tom.gall@linaro.org>
3 years ago[CI] Add apt repository for clang-11 and llvm-11 (#6256)
Leandro Nunes [Wed, 12 Aug 2020 21:18:36 +0000 (22:18 +0100)]
[CI] Add apt repository for clang-11 and llvm-11 (#6256)

- Add specific apt repositories to install clang-11 and llvm-11
 - Fix #6255

3 years ago[Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models (#6190)
Lianmin Zheng [Wed, 12 Aug 2020 21:00:49 +0000 (14:00 -0700)]
[Ansor][AutoTVM v2.0] Phase 1: feature extraction for cost models (#6190)

* [AutoScheduler] add feature extraction

* fix lint

* fix gpu test

* address comments

* improve flop estimation

* rebase

* refactor with group

* fix

* Apply suggestions from code review

3 years agoSupport mxnet _contrib_SyncBatchNorm (#6245)
Trevor Morris [Wed, 12 Aug 2020 16:00:55 +0000 (09:00 -0700)]
Support mxnet _contrib_SyncBatchNorm (#6245)

3 years ago[COREML]Reduceops support added to frontend (#6252)
Siju Samuel [Wed, 12 Aug 2020 15:50:42 +0000 (21:20 +0530)]
[COREML]Reduceops support added to frontend (#6252)

3 years agoFix newer GCC compiler warnings. (#6257)
Balint Cristian [Wed, 12 Aug 2020 15:50:16 +0000 (18:50 +0300)]
Fix newer GCC compiler warnings. (#6257)

3 years ago[TOPI] Fix reduction (#6250)
Zhi [Wed, 12 Aug 2020 08:12:56 +0000 (01:12 -0700)]
[TOPI] Fix reduction (#6250)

3 years agoRevert "fix cuda half math function is undefined: hpow, htanh (#6225)" (#6249)
Tianqi Chen [Wed, 12 Aug 2020 00:32:57 +0000 (17:32 -0700)]
Revert "fix cuda half math function is undefined: hpow, htanh (#6225)" (#6249)

This reverts commit ed04cdd35f1990959ec788be0131b1388fd11d31.

3 years ago[Parser] Parser 2.0 part 2 (#6162)
Jared Roesch [Tue, 11 Aug 2020 23:31:03 +0000 (16:31 -0700)]
[Parser] Parser 2.0 part 2  (#6162)

* Add code from livestream with JK

* Fix errors parsing ResNet

* Parse metadata section efficiently and do most of plumbing to resolve metadata section references.

* WIP

* Change meta reference to an operator

* Meta references now work

* MetaReference expansion now works

* Start working on source map and move diagnostic context

* Convert tokenizer and parser to use new machinery

* Kill to_json

* Fix comment in type_infer.cc

* Remove old parser

* Rename parser tests and remove old ones

* Record span end information

* Convert to using spans everywhere

* Add span fields back to all Relay constructors

* Start passing spans

* Pass spans around visitors

* Format

* Fix

* Fix

* disable reference lint from string helpers

* Fix tokenizer

* Fix issue with empty metadata section

* Document new span fields and small tweaks

* Formatting

* Add span doc fields

* Add format tweak

* Improve errors and fix the semantic version tags in Prelude

* Update gradient.rly

* Clean up broken spans

* Clean up parser tests and turn on previously skipped tests

* Update errors to handle skipped cases

* Tweak

* Tweak

* Format

* Fix some minor issues with ADT tests

* Format

* Fix path

* WIP

* WIP

* Fix ir_text_printer

* format

* Formatted

* More formatting

* Repair test cases

* Fix CI

* Retrigger CI

3 years ago[Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy (#6184)
Chenfan [Tue, 11 Aug 2020 20:53:00 +0000 (04:53 +0800)]
[Ansor][AutoTVM v2.0] Phase 2: Basic CPU Sketch Search Policy (#6184)

* Init commit to pass the compile

* First commit to pass the test

* Update

* Add UTs for sketch generation

* Update

* Add ASF to new UT file.

* Update rule for winograd

* Update

* File renamed

* Lint fix

3 years ago[JVM] Support overriding RPCWatchdog termination behavior on Android and other platfo...
Chris Sullivan [Tue, 11 Aug 2020 20:04:26 +0000 (13:04 -0700)]
[JVM] Support overriding RPCWatchdog termination behavior on Android and other platforms (#6216)

* Instead of performing a system exit and leaving unhandled items on
the activity stack, finish the RPCActivity and return cleanly to the
MainActivity where the RPCActivity can be restarted automatically.

* Update doc. string for checkstyle.

3 years agoFix division range estimation error in simplifier (#6244)
Krzysztof Parzyszek [Tue, 11 Aug 2020 15:35:06 +0000 (10:35 -0500)]
Fix division range estimation error in simplifier (#6244)

Division a/b assumes maximum values when b is close to 0. Account
for that when estimating the range for a/b when 0 belongs to the
estimated range for b.

Assume that a division by zero cannot happen in a valid program,
so in such cases treat the range for b as a union
  [b.min_value, -1] u [1, b.max_value]

3 years ago[TFLite] Implemented EXPAND_DIMS Operator for TFLite. (#6243)
Rishabh Jain [Tue, 11 Aug 2020 08:05:55 +0000 (13:35 +0530)]
[TFLite] Implemented EXPAND_DIMS Operator for TFLite. (#6243)

3 years ago[RPC] Update build support for cross compiling apps/cpp_rpc with OpenCL (#6229)
Chris Sullivan [Tue, 11 Aug 2020 07:47:01 +0000 (00:47 -0700)]
[RPC] Update build support for cross compiling apps/cpp_rpc with OpenCL (#6229)

* Standardize support for building and cross compiling apps/cpp_rpc.
* Add cmake coverage for building the C++ RPC server binary
  and update documentation.
* Add support for linking against custom OpenCL SDK employing
  a custom find_opencl macro. This can be useful when cross
  compiling with a custom OpenCL device driver.

* Update OpenCL related documentation.

* Add embedded linux build instructions to apps/cpp_rpc/README.md and
ensure pthread is linked against when OS=Linux is defined. Remove
outdated apps/cpp_rpc/Makefile.

3 years ago[Topi,x86] Split MKL from BLAS. (#6182)
Tristan Konolige [Tue, 11 Aug 2020 02:16:41 +0000 (19:16 -0700)]
[Topi,x86] Split MKL from BLAS. (#6182)

Make cblas and mkl seperate entities in cmake and topi, allowing users
to use both a BLAS library and MKL. In the future, MKL specific
functions can be added easily. MKLDNN is also split off from MKL and
BLAS for the same reasons.

Other improvements:
  - cblas and mkl strategies are now only applied when they are viable.
  - compile_engine will log which implementation it has chosen and why.

3 years agofix cuda half math function is undefined: hpow, htanh (#6225)
cloud-mxd [Mon, 10 Aug 2020 21:53:15 +0000 (05:53 +0800)]
fix cuda half math function is undefined: hpow, htanh (#6225)

3 years ago[Relay]Refine tensorflow frontend 1.x & 2.x compatibility (#6240)
Tianming Xu [Mon, 10 Aug 2020 16:00:53 +0000 (00:00 +0800)]
[Relay]Refine tensorflow frontend 1.x & 2.x compatibility (#6240)

* [Relay]Refine tensorflow frontend 1.x & 2.x compatibility

* fix lint error

* revert gpu related changes

3 years ago[BYOC][ACL] Improve installation tutorial (#6170)
lhutton1 [Mon, 10 Aug 2020 15:56:09 +0000 (16:56 +0100)]
[BYOC][ACL] Improve installation tutorial (#6170)

* [BYOC][ACL] Improve installation tutorial

Improves installation script so that ACL can be built natively and improves tutorial to give clearer information on how ACL can be installed using two different methods.

Change-Id: I6cec98b4b0a7dc2b151b36583d3d28f2b85f8702

* Address comments

Change-Id: I88db6d9d539a8f06e2dfe1b9a0a3ac7a4b46cece

3 years ago[TOPI, Cuda] Fix conv2d_transpose output padding (#6236)
Wuwei Lin [Mon, 10 Aug 2020 15:37:09 +0000 (11:37 -0400)]
[TOPI, Cuda] Fix conv2d_transpose output padding (#6236)

3 years ago[TIR][Hybrid] Hybrid Script Support for TIR (#6227)
Bohan Hou [Mon, 10 Aug 2020 15:25:01 +0000 (23:25 +0800)]
[TIR][Hybrid] Hybrid Script Support for TIR (#6227)

3 years ago[TFLite] Implemented ONE_HOT Operator for TFLite (#6223)
Rishabh Jain [Mon, 10 Aug 2020 12:21:20 +0000 (17:51 +0530)]
[TFLite] Implemented ONE_HOT Operator for TFLite (#6223)

3 years ago[COMMUNITY] jcf94 -> Reviewer (#6241)
Tianqi Chen [Mon, 10 Aug 2020 09:09:32 +0000 (02:09 -0700)]
[COMMUNITY] jcf94 -> Reviewer (#6241)

3 years ago[Relay][Op] Add unbiased variance op and corresponding support in pytorch frontend...
shiwenloong [Mon, 10 Aug 2020 06:07:43 +0000 (14:07 +0800)]
[Relay][Op] Add unbiased variance op and corresponding support in pytorch frontend (#6232)

3 years ago[uTVM] fix crt building and running error (#6231)
windclarion [Sun, 9 Aug 2020 14:00:53 +0000 (22:00 +0800)]
[uTVM] fix crt building and running error (#6231)

Signed-off-by: windclarion <windclarion@gmail.com>
3 years ago[BYOC][JSON] json_node.h should include data_type.h (#6224)
lhutton1 [Sun, 9 Aug 2020 01:27:03 +0000 (02:27 +0100)]
[BYOC][JSON] json_node.h should include data_type.h (#6224)

Fixes compilation issue after #6214.

Change-Id: I07e25356bbfe4a7bd0950f2672441ce1c338dc3f

3 years ago[FIX] Verify that tensor reshape is valid. (#6215)
Tristan Konolige [Sun, 9 Aug 2020 01:26:36 +0000 (18:26 -0700)]
[FIX] Verify that tensor reshape is valid. (#6215)

3 years ago[Relay][Dynamic] Add Dynamic Resize Op (#6198)
Matthew Brookhart [Sat, 8 Aug 2020 00:08:52 +0000 (17:08 -0700)]
[Relay][Dynamic] Add Dynamic Resize Op (#6198)

* WIP

* optionally remove output shape inference from topi

* fix resize

* add resize to dynamic_to_static pass

add resize to dynamic_to_static pass

* fix clang-format

* fix bad rebase

* add argument to dynamic resize doc string

* fix i386 test

* fix lint

3 years ago[runtime][cublas] fix typo (#6230)
cloud-mxd [Fri, 7 Aug 2020 11:38:11 +0000 (19:38 +0800)]
[runtime][cublas] fix typo (#6230)

3 years ago[Relay][Pass] Support combine multiple dense op just into dense (#6062)
wrongtest [Fri, 7 Aug 2020 07:29:37 +0000 (15:29 +0800)]
[Relay][Pass] Support combine multiple dense op just into dense (#6062)

* feat: Support combine multiple matmuls to flat matmul

* fix: Change to_batch -> to_batch_matmul and enrich docstring

* feat: Add wrapped batching ops pass for python

3 years ago[C++ RPC] fix typo to keep same with source code (#6220)
windclarion [Fri, 7 Aug 2020 04:23:39 +0000 (12:23 +0800)]
[C++ RPC] fix typo to keep same with source code (#6220)

Signed-off-by: windclarion <windclarion@gmail.com>
3 years agoReshape with dynamic shape arg (#6208)
Dmitriy Smirnov [Fri, 7 Aug 2020 03:08:35 +0000 (04:08 +0100)]
Reshape with dynamic shape arg (#6208)

Reshape operation updated to take shape from second operand.
In case if shape is provided using second operand it
can be a tensor now.

3 years ago[ONNX]Mod operator, bug fix (#6160)
Siju Samuel [Fri, 7 Aug 2020 00:57:20 +0000 (06:27 +0530)]
[ONNX]Mod operator, bug fix (#6160)

* Onnx mod, bug fix

* Added comment for the mod/floor_mod behaviour difference between numpy & relay

3 years ago[PYTORCH]Std op without specified dimensions support (#6226)
shiwenloong [Fri, 7 Aug 2020 00:55:46 +0000 (08:55 +0800)]
[PYTORCH]Std op without specified dimensions support (#6226)

3 years ago[µTVM] Add --runtime=c, remove micro_dev target, enable LLVM backend (#6145)
Andrew Reusch [Thu, 6 Aug 2020 23:08:19 +0000 (16:08 -0700)]
[µTVM] Add --runtime=c, remove micro_dev target, enable LLVM backend (#6145)

* need to fill address of globals in tvmfuncregistry

* llvm func registry generator works!

* lint fixes

* rm hexdump include

* bring bundle_deploy back to life and add to CI

* revert gcda additions

* git-clang-format

* fix check for --system-lib and test_runtime_micro target

* fixup compile flags for bundle_deploy CRT and improve robustness

* git-clang-format

* add debugging info

* git-clang-format

* initialize ret_values in PackedFunc_Call.

* retrigger CI

* fix log messages

* git-clang-format

* remove default for --runtime target opt

* put backtrace behind a flag and enable it

* simpify ReadString(), fixing bad instruction exception on os x.

* git-clang-format

* uncomment tests

* reorder backtrace ldflags for linux gcc

3 years ago[Relay][Dynamic] OneHot operation (#6209)
Matthew Brookhart [Thu, 6 Aug 2020 15:46:58 +0000 (08:46 -0700)]
[Relay][Dynamic] OneHot operation (#6209)

* Dynamic OneHot Op

* refactor dynamic_to_static

* add onehot to dynamic_to_static pass

3 years ago[Ansor][AutoTVM v2.0] Phase 1: The base class for cost models (#6187)
Lianmin Zheng [Thu, 6 Aug 2020 10:46:12 +0000 (03:46 -0700)]
[Ansor][AutoTVM v2.0] Phase 1: The base class for cost models (#6187)

* add the base class for cost models

* address comments

* Update tests/python/unittest/test_auto_scheduler_cost_model.py

Disable test if user doesn't have llvm

Co-authored-by: Zhao Wu <zhaowu@apache.org>
3 years ago[DOCS] Update pass infra tutorial (#6193)
Zhi [Thu, 6 Aug 2020 03:36:01 +0000 (20:36 -0700)]
[DOCS] Update pass infra tutorial (#6193)

* [DOCS] Update pass infra tutorial

* update tutorial

3 years ago[RUNTIME] Enable auto conversion String->DLDataType (#6214)
Tianqi Chen [Thu, 6 Aug 2020 01:57:25 +0000 (18:57 -0700)]
[RUNTIME] Enable auto conversion String->DLDataType (#6214)

3 years agomatch pytorch 1.6 googlenet pretrained model (#6201) (#6212)
wjliu [Wed, 5 Aug 2020 20:02:36 +0000 (04:02 +0800)]
match pytorch 1.6 googlenet pretrained model (#6201) (#6212)

3 years ago[Relay] pytorch frontend support conv1d (#6203)
Tianming Xu [Wed, 5 Aug 2020 20:01:27 +0000 (04:01 +0800)]
[Relay] pytorch frontend support conv1d (#6203)

* [Relay] pytorch frontend support conv1d

* add tests for conv1d

Co-authored-by: xutianming.xtm <xutianming.xtm@bytedance.com>
3 years agofix compilation error with cuda 11 (#6213)
Jamie Zhuang [Wed, 5 Aug 2020 17:04:24 +0000 (01:04 +0800)]
fix compilation error with cuda 11 (#6213)

3 years agoPass mfloat-abi to LLVMModule::Init (#6150)
Trevor Morris [Wed, 5 Aug 2020 17:04:08 +0000 (10:04 -0700)]
Pass mfloat-abi to LLVMModule::Init (#6150)

Fix lint

3 years ago[Target] 64-bit RPi4b target (#6211)
Thierry Moreau [Wed, 5 Aug 2020 15:15:31 +0000 (08:15 -0700)]
[Target] 64-bit RPi4b target (#6211)

3 years agoFix compile warnings. (#6204)
Balint Cristian [Wed, 5 Aug 2020 15:13:15 +0000 (18:13 +0300)]
Fix compile warnings. (#6204)

3 years agoChange the meaning of conv3d_transpose output_padding to match conv{1,2}d_transpose...
abergeron [Wed, 5 Aug 2020 05:15:21 +0000 (01:15 -0400)]
Change the meaning of conv3d_transpose output_padding to match conv{1,2}d_transpose (#6065)

* Change the meaning of output_padding to correspond to conv{1,2}d_transpose

* Fix long lines

* Fix the relay test

* Add missing doc.

* fix size ordering problem

3 years ago [Rust] fix #6205 (#6207)
韩朴宇 [Wed, 5 Aug 2020 02:32:26 +0000 (10:32 +0800)]
 [Rust] fix #6205 (#6207)

3 years ago[COREML]Unary ops support added in frontend (#6196)
Siju Samuel [Tue, 4 Aug 2020 13:48:05 +0000 (19:18 +0530)]
[COREML]Unary ops support added in frontend (#6196)

* [COREML]Unary ops support added in frontend

* Used coreml enums

3 years ago[RELAY] Basic block normal form (#6152)
Haibin Lin [Tue, 4 Aug 2020 04:38:51 +0000 (21:38 -0700)]
[RELAY] Basic block normal form (#6152)

* initial commit

* refactor utils

* add util

* revert anf test

* update test

* fix logging

* fix scope bug

* complete tests

* remove logging

* revert refactoring

* add one more test case

* fix missing var binding

* fix test

* fix lint

* fix lint

* fix clang-format

* fix lint

* fix lint

* commit missing code

* add analysis api

* fix lint

* fix lint

* lint

* add test for func

* address CR

* fix typo

* fix return type

* fix lint

* refactor classes

* fix lint

* remove prints

* address comments

Co-authored-by: Ubuntu <ubuntu@ip-172-31-42-138.ec2.internal>
3 years ago[TFLite] Implemented PADV2 Operator for TFLite and added support for constant values...
Rishabh Jain [Tue, 4 Aug 2020 02:08:13 +0000 (07:38 +0530)]
[TFLite] Implemented PADV2 Operator for TFLite and added support for constant values in PAD. (#6167)

3 years ago[CI][ETHOSN] Enable CI for Ethos-N (#6171)
mbaret [Tue, 4 Aug 2020 02:04:16 +0000 (03:04 +0100)]
[CI][ETHOSN] Enable CI for Ethos-N (#6171)

This introduces the necessary changes to docker to
support building the Ethos-N driver stack. This is
required for subsequent patches which introduce
the Ethos-N integration into TVM.

Co-authored-by: Leo Blonk <Leo.Blonk@arm.com>
Co-authored-by: Leandro Nunes <leandro.nunes@arm.com>
# Please enter the commit message for your changes. Lines starting
# with '#' will be kept; you may remove them yourself if you want to.
# An empty message aborts the commit.
#
# Date:      Mon Jul 27 15:43:41 2020 +0100
#
# On branch ethosn-ci
# Changes to be committed:
# modified:   docker/Dockerfile.ci_cpu
# new file:   docker/install/ubuntu_install_ethosn_driver_stack.sh
#
# Untracked files:
# CombinedMemoryMap.hex
# OutputModel.hex
# config.txt
# docker/install/ethosn_cap/
# docker/install/ethosn_driver_dev-20.05-dbg-20200612-141030.tar.gz
# ssd.npy
# tests/python/integration/test_tir_gemm.py
# tests/python/relay/test_pattern_annotate.py
# tests/python/unittest/failure.py
#

3 years ago[DOCS] Added casting to hybrid script doc and fixed pass infra doc (#6174)
Lily Orth-Smith [Tue, 4 Aug 2020 01:51:25 +0000 (18:51 -0700)]
[DOCS] Added casting to hybrid script doc and fixed pass infra doc (#6174)

* updated hybridscript docs and pass infra docs

* forgot uint16

3 years ago[AutoScheduler] Fix alignment of note (#6181)
LiangLiu [Tue, 4 Aug 2020 01:51:03 +0000 (09:51 +0800)]
[AutoScheduler] Fix alignment of note (#6181)

* Fix alignment of note

* trigger CI

Co-authored-by: Lianmin Zheng <lianminzheng@gmail.com>
3 years ago[Target] Rename target_id => target_kind (#6199)
Junru Shao [Tue, 4 Aug 2020 01:50:32 +0000 (18:50 -0700)]
[Target] Rename target_id => target_kind (#6199)

3 years ago[TIR][Transform] HoistIfThenElse added (#6066)
ANSHUMAN TRIPATHY [Mon, 3 Aug 2020 20:50:11 +0000 (02:20 +0530)]
[TIR][Transform] HoistIfThenElse added (#6066)

* [TIR][Transform] HoistIfThenElse added

* lint error resolved

* Pass position changed

* pylint error resolved

* CI issues resolved

* Frontend tflite test case failure resolved

* [1] Review comment handled

* [2] Review comment handled

* [3] Review comment handled

* Lint error resolved

3 years ago[TIR] Enhance VerifyGPUCode (#6194)
Lianmin Zheng [Mon, 3 Aug 2020 20:23:07 +0000 (13:23 -0700)]
[TIR] Enhance VerifyGPUCode (#6194)

3 years ago[Fix] avoid unexpected throw in AttrInitEntry (#6128)
qiuhan [Mon, 3 Aug 2020 19:29:55 +0000 (03:29 +0800)]
[Fix] avoid unexpected throw in AttrInitEntry (#6128)

3 years ago[FoldConstant] Create Interpreter for each constant subgraph (#6195)
Animesh Jain [Mon, 3 Aug 2020 16:36:41 +0000 (09:36 -0700)]
[FoldConstant] Create Interpreter for each constant subgraph (#6195)

3 years ago[BUILD] Remove libtopi from the build (#6189)
Tianqi Chen [Sun, 2 Aug 2020 23:51:22 +0000 (16:51 -0700)]
[BUILD] Remove libtopi from the build (#6189)

3 years ago[CI] Remove topi from the CI cache (#6188)
Tianqi Chen [Sun, 2 Aug 2020 20:39:50 +0000 (13:39 -0700)]
[CI] Remove topi from the CI cache (#6188)

3 years ago[REFACTOR] topi -> tvm/topi (#6186)
Tianqi Chen [Sun, 2 Aug 2020 16:29:29 +0000 (09:29 -0700)]
[REFACTOR] topi -> tvm/topi (#6186)

This PR migrates the topi library as a sub namespace of tvm.

3 years ago[TEST] Temporary disable conv2d grad strided flaky test (#6183)
Tianqi Chen [Sat, 1 Aug 2020 03:24:29 +0000 (20:24 -0700)]
[TEST] Temporary disable conv2d grad strided flaky test (#6183)

3 years ago[FIX] Fixes #6096 (#6131)
Tristan Konolige [Fri, 31 Jul 2020 19:50:16 +0000 (12:50 -0700)]
[FIX] Fixes #6096 (#6131)

Clear the compile cache between module builds so that schedule changes
will have an effect. Also, clear the warning cache so that schedule
changes properly list untuned ops.

3 years ago[DOCS] Improve the docs build instructions (#6173)
Tianqi Chen [Fri, 31 Jul 2020 19:49:27 +0000 (12:49 -0700)]
[DOCS] Improve the docs build instructions (#6173)

3 years ago[Relay] Fix bug in transpose_shape_func (#6180)
lixiaoquan [Fri, 31 Jul 2020 15:06:37 +0000 (23:06 +0800)]
[Relay] Fix bug in transpose_shape_func (#6180)

3 years agoFix incorrect function signature in header (#6172)
Wuwei Lin [Thu, 30 Jul 2020 23:21:19 +0000 (19:21 -0400)]
Fix incorrect function signature in header (#6172)

3 years ago[BYOC] Retire the example json runtime (#6177)
Zhi [Thu, 30 Jul 2020 20:16:36 +0000 (13:16 -0700)]
[BYOC] Retire the example json runtime (#6177)

3 years agoBuffer logger assert removed (#6147)
ANSHUMAN TRIPATHY [Thu, 30 Jul 2020 16:58:23 +0000 (22:28 +0530)]
Buffer logger assert removed (#6147)

3 years ago[AutoScheduler] Improve doc string (#6176)
Lianmin Zheng [Thu, 30 Jul 2020 16:35:29 +0000 (09:35 -0700)]
[AutoScheduler] Improve doc string (#6176)

3 years ago[TF] Fix some shape mismatches between TF and Relay (#6166)
lixiaoquan [Wed, 29 Jul 2020 17:34:32 +0000 (01:34 +0800)]
[TF] Fix some shape mismatches between TF and Relay (#6166)

Make ndarray_size output scalar
  Make gather_nd output scalar if needed

3 years agofix bug when converting constant nodes with types of int64 or float64 (#6159)
sleepwalker2017 [Wed, 29 Jul 2020 17:30:03 +0000 (01:30 +0800)]
fix bug when converting constant nodes with types of int64 or float64 (#6159)

Co-authored-by: yuweilong <yuweilong03@meituan.com>
3 years ago[BYOC][ACL] Support asymmetric per-layer quantized operators (#6109)
lhutton1 [Wed, 29 Jul 2020 16:18:57 +0000 (17:18 +0100)]
[BYOC][ACL] Support asymmetric per-layer quantized operators (#6109)

* [BYOC][ACL] Support asymmetric per-layer quantization

Adds support for asymmetric per-layer quantization in the ACL runtime. This includes support for qnn.conv2d, nn.maxpool2d and reshape. Reflected these changes in codegen and runtime tests.

Change-Id: I8f610bd37af1e3740fd48c2d502bcc4727d9d712

* Address comments

Change-Id: I4f9e3e7dbf6053066927cf07c4c19ecc88572e9d

* Fix tutorial

Change-Id: I4371e9d97a120fb7776db40ffcde60f46927af4d

* Improve test infrastructure

* Doc-string for generate trials
* Output params on error

Change-Id: Ib2e2b1fcdf05cdc77f7f4fb4b46395f28c129957

3 years ago[Parser] Typo in mod creation (#6165)
Animesh Jain [Wed, 29 Jul 2020 15:56:23 +0000 (08:56 -0700)]
[Parser] Typo in mod creation (#6165)

3 years ago[CI] Update ci-cpu to the latest (#6164)
Tianqi Chen [Wed, 29 Jul 2020 15:34:38 +0000 (08:34 -0700)]
[CI] Update ci-cpu to the latest (#6164)

3 years ago[Ansor][AutoTVM v2.0] Phase 1: Add pragma/storage_align/rfactor steps (#6141)
Chenfan [Wed, 29 Jul 2020 06:39:21 +0000 (14:39 +0800)]
[Ansor][AutoTVM v2.0] Phase 1: Add pragma/storage_align/rfactor steps (#6141)

* Add pragma/storage_align/rfactor step

* Update

* Update

* Update UT

* Update

4 years agoImprove error messages in graph tuner, graph runtime, and module loader. (#6148)
Tristan Konolige [Wed, 29 Jul 2020 03:04:19 +0000 (20:04 -0700)]
Improve error messages in graph tuner, graph runtime, and module loader. (#6148)

* Raise error if no operators are found in GraphTuner

* Raise error if key cannot be found in graph runtime inputs

* Detailed error message when module loader is not found

4 years ago[Relay] Handle ndarray_size in FoldConstant (#6156)
lixiaoquan [Tue, 28 Jul 2020 22:49:21 +0000 (06:49 +0800)]
[Relay] Handle ndarray_size in FoldConstant (#6156)

* [Relay] Handle ndarray_size in FoldConstant

* Use Optional

4 years ago[Topi, x86] Using MKL blas for quantized dense (#6115)
Animesh Jain [Tue, 28 Jul 2020 20:32:00 +0000 (13:32 -0700)]
[Topi, x86] Using MKL blas for quantized dense (#6115)

* [Topi, x86] Using MKL blas for quantized dense

* Typo

* CBLAS_OFFSET only available for MKL

* Skipping tests as GPU CI uses Openblas

* Retrigger

Co-authored-by: Ubuntu <ubuntu@ip-172-31-0-202.us-west-2.compute.internal>
4 years agoCorrect runtime.load_module (#6161)
Tianqi Chen [Tue, 28 Jul 2020 20:18:14 +0000 (13:18 -0700)]
Correct runtime.load_module (#6161)

4 years ago[TIR][Bugfix] Improved massive build times caused by tir.floormod and tir.floordiv...
dprankratz [Tue, 28 Jul 2020 16:06:06 +0000 (10:06 -0600)]
[TIR][Bugfix] Improved massive build times caused by tir.floormod and tir.floordiv. Fixed Topi testcase. (#5666)

* Improved uncommon case of floormod and floordiv. Removed dependence on np floor_div and fmod.

* Fixed clang-format complaints

* Streamlined floormod and floordiv lowering logic

* Improved build times by expressing int64 case of tir FloorMod and FloorDiv using let nodes

* Updated use-def analysis and llvm codegen to support duplicated letnodes.

* Corrected misuse of var_map_ in llvm codegen

* Updated backends that support LetNode

* Changed floormod and div lowering logic to avoid using FP on systems that don't support it.

* Fixed formatting

Co-authored-by: pankratz <pankratz@ualberta.ca>
4 years ago[CI][Caffe Frontend] add caffe environment (#6023)
FernChen [Tue, 28 Jul 2020 15:58:26 +0000 (23:58 +0800)]
[CI][Caffe Frontend] add caffe environment (#6023)

* [CI][Caffe Frontend] add caffe environment

* [CI][Caffe Frontend] change the caffe deps into BVLC distribution.

* [CI][Caffe Fronted] simplify configuration while installing tzdata for precompiled caffe.

* [CI][Caffe Frontend] add more information about tzdata.

* [CI][CaffeFrontend]remove the ci for gpu env and change to pip3 env

Co-authored-by: fernchen <zifeng.cf@alibaba-inc.com>
4 years ago[Ansor][AutoTVM v2.0] Phase 1: Add follow_split and follow_fused_split steps (#6142)
jiuqi-yang [Tue, 28 Jul 2020 14:49:05 +0000 (22:49 +0800)]
[Ansor][AutoTVM v2.0] Phase 1: Add follow_split and follow_fused_split steps (#6142)

* Add cache_read/cache_write step

* Update

* Add follow split and follow fused split

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
Conflicts:
src/auto_scheduler/compute_dag.cc
src/auto_scheduler/transform_step.cc
src/auto_scheduler/transform_step.h
tests/python/unittest/test_auto_scheduler_loop_state.py

* add loop_state.py

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

* Update

* Update state->current_compute_dag to Optional

* Add some doc strings for Follow_Split and Follow_fused_split

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Check code using c-lint

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add more doc strings and change the order for follow split.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add record test for follow_split and follow_fused_split

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add record test for follow_split

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add record test for follow_fused_split.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add test record for follow_fused_split
1. delete a comment
2. add "fuse" between follow_split and follow_fused_split

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add doc strings for some functions and variables

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Fix the code format in src/auto_scheduler/transform_step.h

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

* Update doc

* Update

* Update

* Fix follow_split and follow_fused_split record test.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Doc update

* Update some doc strings

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Fix code style and some function definitions.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add comments on parameters.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Add more doc strings and fix some.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
* Update.

Signed-off-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
Co-authored-by: chengfan.jcf <chengfan.jcf@alibaba-inc.com>
Co-authored-by: jingbang.yjb <jingbang.yjb@alibaba-inc.com>
4 years agoAdding t-vi as a reviewer (#6149)
Thierry Moreau [Tue, 28 Jul 2020 14:36:34 +0000 (07:36 -0700)]
Adding t-vi as a reviewer (#6149)

4 years ago[DOCS][REFACTOR] Clarify Docs Categorization (#6155)
Tianqi Chen [Tue, 28 Jul 2020 14:27:01 +0000 (07:27 -0700)]
[DOCS][REFACTOR] Clarify Docs Categorization (#6155)

This PR categorizes the docs into a few categories:
- How To
- Tutorials
- References
- Deep Dive
- MISC

Co-authored-by: Chris Hoge <chris@hogepodge.com>
Co-authored-by: Chris Hoge <chris@hogepodge.com>