Граф коммитов

38 Коммитов

Автор SHA1 Сообщение Дата
Tianqi Chen cffb4fba03
[HEADER] Add Header to Comply with ASF Release Policy (#2982)
* [HEADER] ASF header dir=include

* [HEADER] ASF Header dir=src

* [HEADER] ASF Header -dir=python

* [HEADER] ASF header dir=topi

* [HEADER] ASF Header dir=nnvm

* [HEADER] ASF Header -dir=tutorials

* [HEADER] ASF Header dir=tests

* [HEADER] ASF Header -dir=docker

* fix whitespace

* [HEADER] ASF Header -dir=jvm

* [HEADER] ASF Header -dir=web

* [HEADER] ASF Header --dir=apps

* [HEADER] ASF Header --dir=vta

* [HEADER] ASF Header -dir=go

* temp

* [HEADER] ASF Header --dir=rust

* [HEADER] Add ASF Header --dir=cmake

* [HEADER] ASF Header --dir=docs

* [HEADER] Header for Jenkinsfile

* [HEADER] ASF Header to toml and md

* [HEADER] ASF Header to gradle

* Finalize rat cleanup

* Fix permission

* Fix java test

* temporary remove nnvm onnx test
2019-04-07 21:14:02 -07:00
Tianqi Chen 6d46060675
[EXPR] ir_operator.h->expr_operator.h Centralize const folder logic (#2719) 2019-03-02 19:17:01 -08:00
Salem Derisavi d546bb7797 Defined a common base class for TensorComputeOp and ComputeOp (#2587)
* Defined a common base class for TensorComputeOp and ComputeOp

* Made changes requested by @ZihengJiang

* added a testcase to assert that `tensorize` does not have any effect on TensorComputeOp ops.
2019-03-01 10:46:21 -08:00
Jian Weng ac54577f0b [Hybrid Script] Supporting scheduling hybrid script (#2416)
* on the way to enable hybrid schedule

* I think I am done with imperfect loop split?

* copyright watermark

* loop annotation

* fix lint

* fix lint 1

* shit!

* loop reorder supported

* support bind to add some tests

* fused tested

* imperfect loop testcase

* fix lint

* add bind testcase

* fix doc

* fix online edit typo

* resolve @mercymercy review

* fix indent

* i should convince myself it is not flaky test first

* fix test hybrid

* how many flaky test are you expecting; i ball ball u to let me pass

* rebase halide...
2019-01-15 14:27:15 +08:00
Jian Weng 7a01476a3b [HYBRID FRONTEND] Modify hybrid script to new interface; hybrid op supported; enable compilation_database in CMakeList.txt (#1757) 2018-11-18 22:52:17 -08:00
ziheng b90620ea25 [LANG] Generalize compute to tensor region (#1476) 2018-10-05 21:30:43 -07:00
MORITA Kazutaka b95b595891 Remove leading "./" from include paths (#1640) 2018-08-22 22:11:12 -07:00
Lianmin Zheng 7751a6babc [AUTOTVM] Fix GATuner and improve error message (#1605) 2018-08-15 15:34:05 -07:00
Tianqi Chen 0702d2c04d [OP] Introduces auxiliary attrs into compute (#1293) 2018-06-17 10:23:39 -07:00
tqchen bb2b86201c [DOCS] documentation merge 2018-05-29 08:47:00 -07:00
webberg b1c690bda6 #1159 bug fixed (#1164)
* #1159 bug fixed

* #1159 #1164 fixed
2018-05-18 16:05:27 -07:00
Lianmin Zheng cfdc5119f3 delete init part when keeping trivial loop (#1031) 2018-03-28 14:30:07 -07:00
Lianmin Zheng d56c777af8 support to keep trivial loops with extent of 1 (#877) 2018-02-06 09:23:19 -08:00
alex-weaver f280f23a3d Porting schedules (except convolutions) to C++ (#763)
* Ported injective schedules to C++. Added some elementwise ops.

* Fix lint errors

* Added reduction ops and schedules

* Fix lint errors

* Fix lint errors

* Fix lint errors

* Added transform ops

* Fix lint errors

* Fix lint errors

* Added softmax, log_softmax, leaky_relu and flatten ops.
Fixed issue where TVM_DECLARE_INTRIN_UNARY used the PureExtern flag
instead of PureIntrinsic.
Added softmax CUDA schedule.

* Fix lint

* Fix lint

* Added binary_dense, batch_norm_inference, dense, dilate, scale_shift_*,
global_pool and pool ops.
Extended pad to allow specifying pad_value.
Fixed issue where pad would throw if padding was zero in all dimensions.

* Fix lint

* Fix lint

* Added CUDA schedules for dense, pool and global_pool

* Added extern schedules for generic and CUDA

* Fix lint

* Added x86 binary schedules

* Fix lint

* Added rocm dense schedule. Added rocBLAS and cuBLAS support to dense ops

* Added pow ops. Added x86 default and injective schedules

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix lint

* Fix indent

* Removed schedules directory

* Changed left_shift, right_shift to operators. Changed pad_value in pad() to remove pointer usage

* Fixed usage of pad in nn/pooling.h. Fixed declaration of operator>>

* Fixed comments for shift operators

* Added comments to utility functions

* Added TOPI C++ library, exporting broadcast_add op

* Fix lint

* Share libinfo.py with TVM

* Fix lint

* Add other broadcast ops

* Fix lint

* Fix imports in topi

* Fix lib names

* Fixed build issue where windows builds don't apply correct definitions

* Removed TVM_EXPORTS from topi library

* Attempted CI build fix

* Add topi lib to tvm_multilib

* Fix Jenkinsfile

* Added TOPI build target to Makefile

* Fix nn op namespaces.

* Fix lint

* Renamed TOPI lib to libtvm_topi

* Removed _ffi/base.py

* Remove _ffi from topi, now shared with tvm.

* Make libtvm_topi loading optional

* Fix compiler warnings

* Fix lint

* Fix lint

* Fix lint

* Fix build error by making new libs argument to Target optional

* Added C++ Target type interop. Added registration of remaining C++ ops and schedules. Added test of broadcast ops

* Fix lint

* Fix lint

* Fix compile error

* Fix compiler warnings

* Fix compiler warnings

* Fixed int vector interop. Fixed argmin incorrectly invoking argmax. Fixed corner case in default schedules of attempting to fuse 0 length axes. Added tests for reduce ops.

* Refactored reduce builders

* Fixed typos in topi.cc. Added basic test.

* Fixed padding size error. Added dense, dilate, pooling tests

* Fixed issue where clip would output a different dtype to the input. Added split_sections op to cover the other mode of the python split op. Added tests.

* Changed extension type numbers to avoid clash with NNVM

* Fix lint

* Fix compiler warnings

* Removed use of std::vector from the public TOPI API

* Fix lint

* Add TOPI C++ tests to CI

* Fixed detail namespacing. Improved comments.
2018-01-27 21:57:13 -08:00
Tianqi Chen 4865f95830 [BUILD] Windows support of DLL exports (#522) 2017-10-08 15:28:36 -07:00
Tianqi Chen 8ef266063f [SCHEDULE][PASS] support storage_align of certain axis (#400)
* [SCHEDULE][PASS] support storage_align of certain axis

* fix lint
2017-08-30 13:11:18 -07:00
ziheng c9da7254ba [TAG] Add tvm.tag module for tagging operator (#217)
* [TAG] Add op_tag module for tagging operator

* Fix accroading to comments

* Add example

* Add into doc

* Add --fix-missing for docker
2017-07-04 22:27:48 -07:00
Tianqi Chen 34d2aae351 [BUFFER/REFACTOR] Buffer byte_offset-> elem_offset, add buffer_bind_scope (#209) 2017-07-03 14:13:52 -04:00
Tianqi Chen 3cad2478f1 [OP] Initial Stucture of Op Library (#198)
* [OP] Initial start of op library

* add gtest
2017-06-23 17:34:12 -07:00
ziheng f467f66e32 Support for Tuple Inputs of Reducer and ComputeOp (#175)
* Support for batch ComputeOp

* Support for batch ComputeOp

* Fix CrossThreadReduction

* Fix lint

* Add UpdateArray, remove support for batch reduce

* Tuple input support for reduce

* rfactor works with multiple reducer; support multiple reducers with different types

* Small fix

* Small fix

* Change return type of rfactor to Array<Expr>

* Fix lint

* Improve

* Add tutorial

* Improve tutorial

* Improve tutorial
2017-06-10 23:28:52 -07:00
Tianqi Chen 8f51c5fd79 [SCHEDULE] Add group, refactor thread bind api. (#82)
* [SCHEDULE] Add group, refactor thread bind api.

* fix doc

* fix g++-4.8

* More testscase

* Remove graph context from fix pt analysis
2017-04-08 23:31:52 -07:00
Tianqi Chen 2548cedcb8 [OP/LANG] Support Extern Call, more regression tests (#69)
* [OP/LANG] Support Extern Call, more regression tests

* [TEST] Include pylintrc
2017-03-12 11:34:04 -07:00
Tianqi Chen 3fb8579695 [REFACTOR] Add Types to IterVar, Isolate Operator (#62)
* [IterVar/REFACTOR] Add types to IterVar

* [ARITH/REFACTOR] Move IntSet to include

* [REFACTOR/OP] Move Op detail to seperate folder.

* fix test
2017-03-05 12:45:02 -08:00
Tianqi Chen 8f240ee76d [CODEGEN/LLVM] Initial support for codegen LLVM. (#49)
* [LLVM] Initial support for codegen LLVM.

* Fix the naming issue of codegen
2017-02-22 10:47:54 -08:00
Tianqi Chen c8ec41118d [SCAN/Refactor] Refactor scan interface, enable fix point analysis. (#47) 2017-02-20 13:09:23 -08:00
Tianqi Chen d114dfc96e [SCHEDULE] Mutate dataflow in schedule, refactor Stage (#44) 2017-02-16 19:08:50 -08:00
Tianqi Chen 820a85975f [LANG] Introduce Scan, Bugfix Canonical (#43) 2017-02-13 16:39:07 -08:00
Tianqi Chen a2c8a29b21 [SCHEDULE] Improve bound inference, support reduce codegen. (#30) 2017-02-02 08:41:19 -08:00
Tianqi Chen 78ea652d61 [PASS] Schedule Ops init working version (#6)
* [PASS] Schedule Ops init working version

* bugfix in PassUp
2017-01-10 11:18:57 -08:00
tqchen 302c2e644f Make Tensor comparator and hash to be aware of same op and index, init checkin of the ir generation 2017-01-08 22:41:30 -08:00
tqchen 57a74936db Rename dim_var to axis, update testcases 2017-01-06 15:08:36 -08:00
tqchen 357ad592ac Fix Schedule structure, refactor compute to all rely on iter var 2016-12-02 14:03:22 -08:00
tqchen 5445a93697 Refactor to use iterVar 2016-12-01 22:15:40 -08:00
tqchen 70d9302891 Keep up with changes of NodeRef 2016-11-29 12:08:45 -08:00
tqchen 2887653020 Add AttrStmt 2016-11-28 21:02:39 -08:00
tqchen 61de73b428 Finalize tensor and operation 2016-11-27 23:21:57 -08:00
tqchen 605813e4f4 schedule over operation 2016-11-27 22:39:40 -08:00
tqchen 2fafa93577 Add Operation class 2016-11-25 12:12:37 -08:00