You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by ar...@apache.org on 2022/01/11 20:42:05 UTC
[tvm] branch ci-docker-staging updated (5c4a6fa -> d7b0cce)
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
omit 5c4a6fa blank
omit d97bd25 Combine unit and integration test steps into one stage
add aa86dc0 [CUTLASS] Support conv2d activation fusion (#9746)
add 405fa23 [TIR][Schedule] Add Annotate/Unannotate primitive (#9742)
add b08e8e4 [MetaSchedule] Add the missing HasWorkload interface to the Database (#9756)
add 5c2855e [TVMScript][FIX] Fix number of arguments for T.Buffer[...] (#9758)
add 217204c Move Compute library to 21.11 (#9754)
add bd61d18 [Relay] s/SEScope/VirtualDevice/g (#9759)
add a374cdd [Runtime][Pipeline Executor] Add the map logic of global input and subgraph input. (#9751)
add e1255c9 [MetaSchedule] Random Feature Extractor (#9760)
add 89b1676 [Relay] Fix invalid shape function for "copy" operator (#9749)
add bad5861 Remove CMake string REPEAT (#9771)
add 115919b [MetaSchedule] Misc improvement of the Measurer (#9757)
add 9ee0007 [M3c][MetaScheduler] Add ScheduleRule class & PostOrderApply space generator. (#9761)
add 7b9538f [community] @lunderberg -> Committer (#9773)
add 7fac08b Clarify error message for missing libraries (#9710)
add 8352f2f [TE][TensorIR] fix tensor attr in create_prim_func (#9764)
add 5cb5c5b Fix GLOBAL_SCOPE Shallow copy bug (#9718)
add f4af81c [TIRScript] fix parse StringImm value in for loop annotations (#9755)
add 72ff7c8 Include \0 terminating character in strncpy (#9775)
add 0274b95 fix int set analysis on negative scale (#9776)
add 7456b1a [microNPU] Added checks for out of range shifts (#9707)
add f93b0c2 [Hexagon] Account for objects being smaller than the allocated space (#9769)
add 5aea9bc [microNPU] Fix incorrect comparison in schedulers (#9706)
add 124813f [microNPU] Upgrade to 21.11 version of Arm(R) Ethos(TM)-U55 NPU driver (#9777)
add 5a06d55 [Bugfix] fix the bug that occurs when the test_pass_ctx_exception() is (#9774)
add 541f7d0 Improve the frontend tflite _test_abs test to support tflite 2.6 (#9783)
add 8fa5464 [AMP] Disallow converting layer norm to fp16 (#9782)
add 4e0bf23 [Autoscheduler] Task Extraction Raises Exception on Lowering (#9750)
add d026d06 [CodeGen] avoid crash if an exception is raised during llvm cpu codegen (#9786)
add b35fc83 [M3c][MetaScheduler] Add More Measure Callbacks. (#9780)
add b29a443 [Docker] Update to Torch 1.10.1 (#9781)
add 1afcf36 [CUTLASS] Conv2d activation fusion, part 2: Sigmoid fp16, SiLU and HardSwish (#9795)
add 0b8bb96 Update README.md (#9798)
add 85e27c1 [microNPU] Re-enable LayoutOptimizer pass (#9793)
add 0c1422a Redundant batch_flatten removed for 2D input matrix in Dense layer. (#9792)
add 4af2a66 [Target] Fix device mask issue and typos (#9768)
add d486e21 [CMAKE] Automatically detect newly added source files (#9611)
add 066b417 [TE] Support varargs in te.compute (#9796)
add e2dcba2 [TIR] Affine utility support iter lowerbound and diagnostics (#9699)
add 218d291 Update CONTRIBUTORS.md (#9804)
add 2c654b57 [BugFix][TensorIR] Non-positive constant input factors for `split` (#9805)
add 0f3441a fix a bug of instance norm. (#9806)
add 7448eab [Topi] fix get_pad_tuple3d bug, the conv3d kernel layout should be DHW. (#9788)
add ce108c1 [Frontend] Add Span filling for frontends to Relay (#9723)
add ba15197 [TVM Basic] Extend generic func with get_packed_func() interface (#9784)
add d56ca35 disable signal capture in unit test of paddle frontend (#9809)
add 75cd670 DNNL-BYOC enhancement (#9797)
add 654a687 [TensorIR] fix region cover check (#9810)
add 6d35f0b [CUTLASS] Refactor cutlass kernel generation and selection (#9800)
add 0d7e2ec [TIR] For-kind inheritance in decompose-reduction (#9814)
add a5ac362 [Target][BugFix] Convert dict and str to TVM object (#9807)
add 1c7d36f [M3c][MetaScheduler] Update TuneContext, TaskScheduler & Search Strategy Design (#9789)
add 11379f7 Fix reduce NCHWc infer layout (do not keep reduced inner c when keepdims=false) (#9821)
add e7f3648 [CUTLASS] Residual connection fusion (#9820)
add 77ba3cd Fix zephyr/test_zephyr_armv7m (#9684)
add 4c47676 [CI][Caffe Frontend] Change the caffe deps into SSD distribution (#9060)
add 9cc1df6 [AMP][Pass][Typing] Add faster type inference (#9735)
add 796e71a Add Python representation for VirtualDevice (#9812)
add 4b0f18e [TVMC] Split common tvmc file into more specific files (#9529)
add f1c4f21 [CMSIS-NN] Conv2D with equal paddings can be mapped to CMSIS-NN target (#9801)
add 689f263 Update required cmake version in docs. (#9484)
add 9e20da8 [BugFix] shapeOfAttrs should be registered before "vm.shape_of" used (#9669)
add b3314de [Community] Bohan -> Committer (#9833)
add 92eeef6 Calculate CMSIS-NN buffer size with respect to architecture extensions (#9338)
add 72d3efe [microNPU][2a] Add CascaderGraph for cascading analysis (#9469)
add 94552fc [Docker] Pin sphinx version to workaround sphinx-gallery bug (#9822)
add 79cfb79 [M3c][MetaScheduler] Add ReplayFunc Search Strategy. (#9799)
add 0173dc8 Usability fixes to CI runner script (#9752)
add 33724bb Add skip to flaky MacOS RPC test (#9753)
add 818bd48 This patch is to fix some minor typos in project. (#9852)
add 07a46a1 [BugFix] resolve integer 32. ~ 64. mismatch by casting (#9582)
add 65e5ddd [Torch] Better support in-place variant of ops (aten::relu_ etc) (#9851)
add d3a83b5 [M3c][MetaScheduler] Add EvolutionarySearch Search Strategy. (#9836)
add 51803ed Generate compile_commands.json by default (#9763)
add 2493aeb [AMP] Register some new ops (#9849)
add 9258997 [AMP] Fix IsMixedPrecisionType Edge Case (#9856)
add b4c74a9 [TensorRT] Fix pad_value access (removed from PadAttrs) (#9858)
add 256d170 [MetaSchedule] XGB-based Cost Model (#9859)
add 86a9a4b Add Reference System to tvm.ci_qemu (#9853)
add b8851fc Add FreeRTOS dependencies to ci_qemu (#9854)
add 0e0ff4e [TIR]Show meaningful message when input shape size mismatch with expected size. (#9863)
add 6c9c927 Use shallow clone (#9864)
add 47d6eb2 [LLVM] LLVM codegen debug utilities (#9857)
add afc29e6 [microNPU][2b] Create CascaderGraphs from TE graphs (#9471)
add f6f252f [TOPI] Support grouped conv1d (#9832)
add 38f0239 [CI] Update to PyTorch v1.10 in GPU image (#9866)
add ab8a106 [MetaSchedule] Add Per-Store-Feature (#9860)
add 5cea081 Fixed deprecation warning issue for pipeline executor. (#9770)
add f833c8e [FIX] Fix bug in MobileNetV2 quantization (#8243)
add 0f563ac [FQ2I] Support Conv2dTranspose FQ2I (#9347)
add 52039c9 [TESTS] Fix running tests without MICRO (#9867)
add 8c2360e [PROFILING] Add ability to profile a single function_profiling (#9553)
add e97a3f2 [Rust] Update Rust bindings (#9808)
add 5585c94 remove downloaded source code archive (#9879)
add 8fe81b2 Change rust installation profile to minimal (#9878)
add dc1f3c6 [TOPI] Print shape information when the input shape not compatible with (#9876)
add 4babd36 fix convert_pooling in caffe parser (#9828)
add 8c40dfd Remove zephyr installer file after installation (#9883)
add 3b85f7c [VM] Remove undesired arg to load_late_bound_consts (#9870)
add f3661f5 [CMSIS-NN] Fixed the network hash to avoid type inference failure (#9887)
add 7481a29 te_compiler_cache: reduce name length without loss of information (#9787)
add 7a50d52 Add support for aten::dot (#9893)
add e4d0181 Add a JSON converter for 0.7 -> 0.8 and 0.8 -> 0.9 (#9874)
add a29ac5f [Docker] Update onnx to 1.10.2, ORT to 1.9 (#9882)
add 6f9c806 add oneflow dependency in docker file (#9881)
add 31c22c5 Combine unit and integration test steps into one stage (#9733)
add 57af88f [ONNX] Use relay softmax op to convert Softmax if posssible (#9892)
add 46b3fa7 [CMSIS-NN] Support for asymmetric padding in Convolutions (#9886)
add f6b0c38 Update CI to use tlcpack/ci-cpu:v0.80 (#9865)
add d7b0cce Rebase
This update added new revisions after undoing existing revisions.
That is to say, some revisions that were in the old version of the
branch are not in the new version. This situation occurs
when a user --force pushes a change and generates a repository
containing something like this:
* -- * -- B -- O -- O -- O (5c4a6fa)
\
N -- N -- N refs/heads/ci-docker-staging (d7b0cce)
You should already have received notification emails for all of the O
revisions, and so the following emails describe only the N revisions
from the common base, B.
Any revisions marked "omit" are not gone; other references still
refer to them. Any revisions marked "discard" are gone forever.
No new revisions were added by this update.
Summary of changes:
.gitignore | 1 +
3rdparty/cutlass | 2 +-
CMakeLists.txt | 48 +-
CONTRIBUTORS.md | 4 +
Jenkinsfile | 194 +--
apps/microtvm/ethosu/Makefile | 11 +-
apps/microtvm/ethosu/include/ethosu_mod.h | 6 +-
cmake/libs/Libbacktrace.cmake | 2 +-
cmake/modules/CUDA.cmake | 10 +-
cmake/modules/Hexagon.cmake | 12 +-
cmake/modules/HexagonSDK.cmake | 2 +-
cmake/modules/LLVM.cmake | 2 +-
cmake/modules/Metal.cmake | 4 +-
cmake/modules/Micro.cmake | 2 +-
cmake/modules/OpenCL.cmake | 6 +-
cmake/modules/ROCM.cmake | 6 +-
cmake/modules/StandaloneCrt.cmake | 6 +-
cmake/modules/VTA.cmake | 16 +-
cmake/modules/Vulkan.cmake | 4 +-
cmake/modules/contrib/ArmComputeLib.cmake | 6 +-
cmake/modules/contrib/BNNS.cmake | 4 +-
cmake/modules/contrib/CMSISNN.cmake | 3 +-
cmake/modules/contrib/CODEGENC.cmake | 2 +-
cmake/modules/contrib/CUTLASS.cmake | 2 +-
cmake/modules/contrib/CoreML.cmake | 2 +-
cmake/modules/contrib/DNNL.cmake | 8 +-
cmake/modules/contrib/EthosN.cmake | 10 +-
cmake/modules/contrib/EthosU.cmake | 15 +-
cmake/modules/contrib/ExampleTargetHooks.cmake | 2 +-
cmake/modules/contrib/HybridDump.cmake | 2 +-
cmake/modules/contrib/MicroStandaloneRuntime.cmake | 2 +-
cmake/modules/contrib/NNPack.cmake | 2 +-
cmake/modules/contrib/ONNX.cmake | 2 +-
cmake/modules/contrib/PT_TVMDSOOP.cmake | 2 +-
cmake/modules/contrib/Random.cmake | 2 +-
cmake/modules/contrib/Sort.cmake | 2 +-
cmake/modules/contrib/TFLite.cmake | 4 +-
cmake/modules/contrib/TF_TVMDSOOP.cmake | 2 +-
cmake/modules/contrib/TensorRT.cmake | 6 +-
cmake/modules/contrib/Verilator.cmake | 4 +-
cmake/modules/contrib/VitisAI.cmake | 8 +-
cmake/utils/Summary.cmake | 8 +-
cmake/utils/Utils.cmake | 18 +
docker/Dockerfile.ci_gpu | 4 +
docker/Dockerfile.ci_qemu | 15 +
.../ubuntu_download_arm_compute_lib_binaries.sh | 2 +-
docker/install/ubuntu_install_caffe.sh | 39 +-
.../install/ubuntu_install_ethosu_driver_stack.sh | 2 +-
...install_caffe.sh => ubuntu_install_freertos.sh} | 28 +-
..._install_redis.sh => ubuntu_install_oneflow.sh} | 5 +-
docker/install/ubuntu_install_onnx.sh | 6 +-
docker/install/ubuntu_install_redis.sh | 2 +-
docker/install/ubuntu_install_rust.sh | 3 +-
docker/install/ubuntu_install_sphinx.sh | 2 +-
docker/install/ubuntu_install_tflite.sh | 2 +-
docker/install/ubuntu_install_verilator.sh | 1 +
docker/install/ubuntu_install_zephyr.sh | 1 +
docs/arch/inferbound.rst | 8 +-
docs/contribute/committer_guide.rst | 34 +
docs/install/from_source.rst | 2 +-
include/tvm/arith/iter_affine_map.h | 8 +-
include/tvm/ir/expr.h | 15 +-
include/tvm/ir/function.h | 12 +-
include/tvm/meta_schedule/builder.h | 7 +-
include/tvm/meta_schedule/cost_model.h | 182 +++
include/tvm/meta_schedule/database.h | 25 +-
include/tvm/meta_schedule/feature_extractor.h | 121 ++
include/tvm/meta_schedule/measure_callback.h | 146 ++
include/tvm/meta_schedule/mutator.h | 146 ++
include/tvm/meta_schedule/postproc.h | 167 +++
include/tvm/meta_schedule/schedule_rule.h | 195 +++
include/tvm/meta_schedule/search_strategy.h | 52 +-
include/tvm/meta_schedule/space_generator.h | 24 +-
include/tvm/meta_schedule/task_scheduler.h | 41 +-
include/tvm/meta_schedule/tune_context.h | 35 +-
include/tvm/relay/adt.h | 1 +
include/tvm/relay/attrs/device_copy.h | 10 +-
include/tvm/relay/attrs/memory.h | 6 +-
include/tvm/relay/attrs/nn.h | 2 +-
include/tvm/relay/attrs/on_device.h | 29 +-
include/tvm/relay/attrs/transform.h | 4 +-
include/tvm/relay/expr.h | 29 +-
include/tvm/relay/function.h | 3 +-
include/tvm/relay/transform.h | 31 +-
include/tvm/runtime/debug.h | 54 +
include/tvm/runtime/profiling.h | 34 +
include/tvm/support/random_engine.h | 8 +
include/tvm/target/compilation_config.h | 37 +-
include/tvm/target/generic_func.h | 5 +-
.../tvm/target/{se_scope.h => virtual_device.h} | 162 +-
include/tvm/tir/schedule/schedule.h | 48 +-
include/tvm/tir/stmt.h | 6 +-
python/gen_requirements.py | 15 +
python/tvm/_ffi/libinfo.py | 30 +-
python/tvm/_ffi/runtime_ctypes.py | 5 +-
python/tvm/auto_scheduler/relay_integration.py | 13 +-
python/tvm/autotvm/env.py | 11 +-
python/tvm/autotvm/task/topi_integration.py | 7 +-
python/tvm/contrib/cutlass/build.py | 97 +-
python/tvm/contrib/cutlass/conv2d_operation.py | 62 +-
python/tvm/contrib/cutlass/gen_conv2d.py | 216 ++-
python/tvm/contrib/cutlass/gen_gemm.py | 235 +--
python/tvm/contrib/cutlass/gen_tensor_op.py | 18 +
python/tvm/contrib/cutlass/library.py | 10 +-
python/tvm/contrib/ethosu/cascader/__init__.py | 12 +-
python/tvm/contrib/ethosu/cascader/graph.py | 253 ++++
python/tvm/contrib/ethosu/cascader/parts.py | 64 +
python/tvm/contrib/pipeline_executor.py | 144 +-
python/tvm/driver/tvmc/__init__.py | 11 +-
python/tvm/driver/tvmc/arguments.py | 52 +
python/tvm/driver/tvmc/autotuner.py | 21 +-
python/tvm/driver/tvmc/common.py | 799 ----------
python/tvm/driver/tvmc/compiler.py | 21 +-
python/tvm/driver/tvmc/composite_target.py | 4 +-
python/tvm/driver/tvmc/frontends.py | 3 +-
python/tvm/driver/tvmc/main.py | 3 +-
python/tvm/driver/tvmc/micro.py | 6 +-
python/tvm/driver/tvmc/model.py | 3 +-
python/tvm/driver/tvmc/pass_config.py | 122 ++
python/tvm/driver/tvmc/pass_list.py | 54 +
python/tvm/driver/tvmc/project.py | 233 +++
python/tvm/driver/tvmc/registry.py | 2 +-
python/tvm/driver/tvmc/runner.py | 11 +-
python/tvm/driver/tvmc/shape_parser.py | 67 +
python/tvm/driver/tvmc/target.py | 278 ++++
python/tvm/driver/tvmc/tracker.py | 57 +
python/tvm/driver/tvmc/transform.py | 62 +
python/tvm/ir/json_compact.py | 128 +-
python/tvm/ir/op.py | 26 +
python/tvm/meta_schedule/__init__.py | 3 +
python/tvm/meta_schedule/builder/builder.py | 16 +-
python/tvm/meta_schedule/builder/local_builder.py | 37 +-
.../tvm/meta_schedule/cost_model}/__init__.py | 7 +-
python/tvm/meta_schedule/cost_model/cost_model.py | 147 ++
.../tvm/meta_schedule/cost_model/metric.py | 33 +-
.../tvm/meta_schedule/cost_model/random_model.py | 123 ++
python/tvm/meta_schedule/cost_model/xgb_model.py | 683 +++++++++
python/tvm/meta_schedule/database/database.py | 18 +
.../__init__.py | 12 +-
.../feature_extractor/feature_extractor.py | 81 +
.../feature_extractor/per_store_feature.py | 60 +
.../feature_extractor/random_feature_extractor.py | 62 +
.../__init__.py | 12 +-
.../measure_callback/add_to_database.py | 26 +-
.../measure_callback/echo_statistics.py | 26 +-
.../measure_callback/measure_callback.py | 104 ++
.../measure_callback/remove_build_artifact.py | 26 +-
.../measure_callback/update_cost_model.py | 28 +-
.../tvm/meta_schedule/mutator}/__init__.py | 7 +-
python/tvm/meta_schedule/mutator/mutator.py | 88 ++
.../tvm/meta_schedule/postproc}/__init__.py | 3 +-
python/tvm/meta_schedule/postproc/postproc.py | 90 ++
python/tvm/meta_schedule/runner/local_runner.py | 7 +-
python/tvm/meta_schedule/runner/rpc_runner.py | 7 +-
.../tvm/meta_schedule/schedule_rule}/__init__.py | 10 +-
.../meta_schedule/schedule_rule/schedule_rule.py | 96 ++
.../tvm/meta_schedule/search_strategy/__init__.py | 6 +-
.../search_strategy/evolutionary_search.py | 117 ++
.../{replay_trace.py => replay_func.py} | 30 +-
.../meta_schedule/search_strategy/replay_trace.py | 13 +-
.../search_strategy/search_strategy.py | 41 +-
.../tvm/meta_schedule/space_generator/__init__.py | 2 +-
.../space_generator/post_order_apply.py} | 32 +-
.../meta_schedule/space_generator/schedule_fn.py | 4 +-
.../space_generator/space_generator.py | 13 +-
.../meta_schedule/task_scheduler/round_robin.py | 26 +-
.../meta_schedule/task_scheduler/task_scheduler.py | 20 +-
python/tvm/meta_schedule/tune_context.py | 52 +-
python/tvm/meta_schedule/utils.py | 23 +-
python/tvm/relay/backend/contrib/ethosu/codegen.py | 1 +
.../relay/backend/contrib/ethosu/te/__init__.py | 1 +
.../relay/backend/contrib/ethosu/te/convolution.py | 133 +-
python/tvm/relay/backend/contrib/ethosu/te/dma.py | 21 +-
.../tvm/relay/backend/contrib/ethosu/te/inline.py | 71 +
.../relay/backend/contrib/ethosu/tir/scheduler.py | 7 +-
.../tvm/relay/backend/contrib/ethosu/vela_api.py | 10 +-
python/tvm/relay/expr.py | 7 +-
python/tvm/relay/frontend/caffe.py | 4 +-
python/tvm/relay/frontend/common.py | 53 +
python/tvm/relay/frontend/onnx.py | 40 +-
python/tvm/relay/frontend/pytorch.py | 77 +-
python/tvm/relay/frontend/tensorflow.py | 17 +-
python/tvm/relay/frontend/tensorflow2.py | 17 +-
python/tvm/relay/frontend/tflite.py | 16 +-
python/tvm/relay/op/annotation/annotation.py | 12 +-
python/tvm/relay/op/contrib/cmsisnn.py | 2 -
python/tvm/relay/op/contrib/cutlass.py | 133 +-
python/tvm/relay/op/contrib/dnnl.py | 140 +-
python/tvm/relay/op/contrib/tensorrt.py | 7 +-
python/tvm/relay/op/op.py | 6 +-
python/tvm/relay/op/strategy/cuda.py | 42 +-
python/tvm/relay/op/strategy/generic.py | 43 +
python/tvm/relay/op/strategy/x86.py | 43 +-
python/tvm/relay/op/tensor.py | 29 +-
.../transform/fake_quantization_to_integer.py | 19 +
python/tvm/relay/transform/mixed_precision.py | 11 +-
python/tvm/relay/transform/transform.py | 29 +-
python/tvm/runtime/profiling/__init__.py | 50 +
python/tvm/runtime/vm.py | 2 +-
python/tvm/script/tir/scope_handler.py | 10 +-
python/tvm/script/tir/special_stmt.py | 5 +-
python/tvm/script/tir/ty.py | 9 +-
python/tvm/target/__init__.py | 2 +-
python/tvm/target/generic_func.py | 24 +-
python/tvm/target/target.py | 37 +-
.../tvm/target/{se_scope.py => virtual_device.py} | 21 +-
python/tvm/te/operation.py | 29 +-
python/tvm/te/tensor.py | 4 +-
python/tvm/tir/schedule/schedule.py | 127 +-
python/tvm/topi/cuda/conv1d.py | 40 +-
python/tvm/topi/generic/nn.py | 34 +
python/tvm/topi/nn/conv1d.py | 120 +-
python/tvm/topi/nn/conv2d.py | 315 ++--
python/tvm/topi/nn/utils.py | 53 +-
python/tvm/topi/testing/__init__.py | 2 +-
python/tvm/topi/testing/conv1d_ncw_python.py | 14 +
python/tvm/topi/x86/conv1d.py | 8 +
rust/tvm/src/ir/relay/attrs/mod.rs | 1 +
rust/tvm/src/ir/relay/attrs/nn.rs | 62 +
.../tvm/src/ir/relay/attrs/reduce.rs | 45 +-
rust/tvm/src/ir/relay/attrs/transform.rs | 59 +-
rust/tvm/src/ir/relay/mod.rs | 4 +-
src/README.md | 2 +-
src/arith/int_set.cc | 19 +-
src/arith/iter_affine_map.cc | 471 ++++--
src/contrib/ethosu/cascader/common.h | 25 +-
src/contrib/ethosu/cascader/graph.cc | 257 ++++
src/contrib/ethosu/cascader/graph.h | 321 ++++
src/contrib/ethosu/cascader/parts/ethosu.cc | 120 ++
src/contrib/ethosu/cascader/parts/ethosu.h | 99 ++
src/contrib/ethosu/cascader/parts/inline.cc | 66 +
src/contrib/ethosu/cascader/parts/inline.h | 80 +
src/ir/op.cc | 4 +
src/meta_schedule/builder/builder.cc | 9 +-
src/meta_schedule/cost_model/cost_model.cc | 65 +
src/meta_schedule/database/database.cc | 6 +-
src/meta_schedule/database/json_database.cc | 4 +
.../feature_extractor/feature_extractor.cc | 51 +
.../feature_extractor/per_store_feature.cc | 1337 +++++++++++++++++
.../measure_callback/add_to_database.cc | 65 +
.../measure_callback/echo_statistics.cc | 336 +++++
.../measure_callback/measure_callback.cc | 50 +
.../measure_callback/remove_build_artifact.cc | 52 +
.../measure_callback/update_cost_model.cc | 53 +
src/meta_schedule/mutator/mutator.cc | 57 +
src/meta_schedule/postproc/postproc.cc | 53 +
src/meta_schedule/schedule_rule/schedule_rule.cc | 55 +
.../search_strategy/evolutionary_search.cc | 673 +++++++++
.../{replay_trace.cc => replay_func.cc} | 95 +-
src/meta_schedule/search_strategy/replay_trace.cc | 69 +-
.../space_generator/post_order_apply.cc | 155 ++
.../space_generator/space_generator_union.cc | 4 +-
src/meta_schedule/task_scheduler/round_robin.cc | 15 +-
src/meta_schedule/task_scheduler/task_scheduler.cc | 126 +-
src/meta_schedule/tune_context.cc | 46 +-
src/meta_schedule/utils.h | 112 +-
src/printer/relay_text_printer.cc | 33 +-
src/printer/text_printer.h | 2 +-
src/relay/backend/aot_executor_codegen.cc | 30 +-
src/relay/backend/build_module.cc | 2 +-
src/relay/backend/contrib/cmsisnn/buffer_size.cc | 78 +
src/relay/backend/contrib/cmsisnn/buffer_size.h | 94 ++
.../backend/contrib/cmsisnn/compiler_attrs.cc | 75 +
src/relay/backend/contrib/cmsisnn/compiler_attrs.h | 75 +
src/relay/backend/contrib/cmsisnn/relay_to_tir.cc | 33 +-
src/relay/backend/contrib/cutlass/codegen.cc | 149 +-
src/relay/backend/contrib/dnnl/codegen.cc | 18 +
src/relay/backend/graph_executor_codegen.cc | 8 +-
src/relay/backend/graph_plan_memory.cc | 36 +-
src/relay/backend/interpreter.cc | 8 +-
src/relay/backend/te_compiler.cc | 60 +-
src/relay/backend/te_compiler.h | 5 +-
src/relay/backend/te_compiler_cache.cc | 35 +-
src/relay/backend/utils.cc | 26 +-
src/relay/backend/utils.h | 27 +-
src/relay/backend/vm/compiler.cc | 129 +-
src/relay/backend/vm/compiler.h | 8 +-
src/relay/backend/vm/lambda_lift.cc | 9 +-
src/relay/ir/expr.cc | 50 +-
src/relay/ir/expr_functor.cc | 14 +-
src/relay/ir/function.cc | 4 +-
src/relay/op/dyn/tensor/transform.cc | 3 +
src/relay/op/memory/device_copy.cc | 26 +-
src/relay/op/memory/device_copy.h | 29 +-
src/relay/op/memory/memory.cc | 4 +-
src/relay/op/memory/memory.h | 4 +-
src/relay/op/memory/on_device.cc | 74 +-
src/relay/op/memory/on_device.h | 67 +-
src/relay/op/nn/convolution.h | 2 +-
src/relay/op/tensor/reduce.cc | 2 +-
src/relay/op/tensor/transform.cc | 18 +-
src/relay/op/tensor/unary.cc | 2 -
src/relay/op/vm/vm.cc | 4 +
src/relay/quantize/realize.cc | 42 +-
src/relay/transforms/device_aware_visitors.cc | 82 +-
src/relay/transforms/device_aware_visitors.h | 104 +-
src/relay/transforms/device_domains.cc | 130 +-
src/relay/transforms/device_domains.h | 86 +-
src/relay/transforms/device_planner.cc | 343 ++---
src/relay/transforms/fold_constant.cc | 22 +-
src/relay/transforms/memory_alloc.cc | 99 +-
src/relay/transforms/simplify_inference.cc | 2 +-
src/relay/transforms/to_a_normal_form.cc | 16 +-
src/relay/transforms/to_mixed_precision.cc | 32 +-
src/relay/transforms/type_infer.cc | 106 ++
src/runtime/contrib/dnnl/dnnl_json_runtime.cc | 99 +-
src/runtime/debug.cc | 128 ++
.../hexagon/android/sim/driver/CMakeLists.txt | 2 +-
src/runtime/hexagon/hexagon/hexagon_buffer.cc | 66 +-
src/runtime/hexagon/hexagon/hexagon_buffer.h | 6 +-
.../hexagon/hexagon/hexagon_device_api_v2.cc | 2 +-
src/runtime/object.cc | 2 +-
src/runtime/pipeline/pipeline_executor.cc | 25 +-
src/runtime/pipeline/pipeline_executor.h | 48 +-
src/runtime/pipeline/pipeline_scheduler.cc | 2 +-
src/runtime/pipeline/pipeline_scheduler.h | 3 +-
src/runtime/pipeline/pipeline_struct.h | 181 ++-
src/runtime/profiling.cc | 57 +
src/runtime/vm/executable.cc | 19 +-
src/runtime/vm/vm.cc | 62 +-
src/target/compilation_config.cc | 95 +-
src/target/generic_func.cc | 19 +
src/target/llvm/codegen_cpu.cc | 54 +-
src/target/llvm/codegen_cpu.h | 5 +-
src/target/llvm/codegen_llvm.cc | 61 +-
src/target/llvm/codegen_llvm.h | 20 +
src/target/target_kind.cc | 12 +-
src/target/{se_scope.cc => virtual_device.cc} | 54 +-
src/te/operation/create_primfunc.cc | 23 +-
src/tir/analysis/device_constraint_utils.cc | 107 +-
src/tir/analysis/device_constraint_utils.h | 28 +-
src/tir/ir/data_layout.cc | 12 +-
src/tir/schedule/analysis/analysis.cc | 4 +-
src/tir/schedule/concrete_schedule.cc | 82 +-
src/tir/schedule/concrete_schedule.h | 26 +
src/tir/schedule/primitive.h | 34 +
src/tir/schedule/primitive/annotate.cc | 170 +++
src/tir/schedule/primitive/reduction.cc | 2 +-
src/tir/schedule/primitive/sampling.cc | 30 +-
src/tir/schedule/schedule.cc | 26 +
src/tir/schedule/state.cc | 4 +-
src/tir/schedule/traced_schedule.cc | 40 +-
src/tir/schedule/traced_schedule.h | 4 +
src/tir/schedule/utils.h | 64 +-
src/tir/transforms/flatten_buffer.cc | 26 +-
src/tir/transforms/unify_thread_binding.cc | 13 +-
.../backend/contrib/cmsisnn/buffer_size_test.cc | 206 +++
.../backend/contrib/cmsisnn/compiler_attrs_test.cc | 157 ++
tests/cpp/relay/op/memory/on_device_test.cc | 28 +-
tests/cpp/relay/transforms/device_domains_test.cc | 12 +-
tests/cpp/runtime/hexagon_buffer.cc | 51 +-
tests/cpp/target/compilation_config_test.cc | 66 +-
tests/cpp/target/se_scope_test.cc | 119 --
tests/cpp/target/virtual_device_test.cc | 121 ++
tests/micro/zephyr/test_utils.py | 97 +-
tests/micro/zephyr/test_zephyr_aot.py | 76 +-
tests/micro/zephyr/test_zephyr_armv7m.py | 89 +-
tests/python/contrib/test_cmsisnn/test_conv2d.py | 21 +-
tests/python/contrib/test_cmsisnn/test_networks.py | 2 +-
tests/python/contrib/test_cmsisnn/utils.py | 8 +-
tests/python/contrib/test_cutlass.py | 175 ++-
tests/python/contrib/test_dnnl.py | 350 +++++
.../contrib/test_ethosu/cascader/__init__.py | 2 +-
.../contrib/test_ethosu/cascader/conftest.py | 73 +
.../python/contrib/test_ethosu/cascader/infra.py | 11 +-
.../cascader/test_ethosu_conv2d_matcher.py | 163 ++
.../cascader/test_ethosu_inline_matcher.py} | 35 +-
.../test_ethosu/cascader/test_ethosu_part.py} | 32 +-
.../contrib/test_ethosu/cascader/test_graph.py | 179 +++
.../test_ethosu/reference_system/ethosu_mod.h | 18 +-
tests/python/contrib/test_ethosu/test_codegen.py | 35 +
tests/python/contrib/test_ethosu/test_scheduler.py | 62 +-
tests/python/contrib/test_rpc_server_device.py | 3 +
tests/python/driver/tvmc/test_autotuner.py | 2 +-
tests/python/driver/tvmc/test_compiler.py | 6 +-
tests/python/driver/tvmc/test_composite_target.py | 2 +-
tests/python/driver/tvmc/test_frontends.py | 13 +-
tests/python/driver/tvmc/test_pass_config.py | 16 +-
tests/python/driver/tvmc/test_pass_list.py | 8 +-
tests/python/driver/tvmc/test_registry_options.py | 2 +-
tests/python/driver/tvmc/test_runner.py | 2 +-
tests/python/driver/tvmc/test_shape_parser.py | 22 +-
tests/python/driver/tvmc/test_target.py | 43 +-
tests/python/driver/tvmc/test_target_options.py | 11 +-
tests/python/driver/tvmc/test_tracker.py | 8 +-
tests/python/frontend/paddlepaddle/test_forward.py | 2 +
tests/python/frontend/pytorch/qnn_test.py | 34 +-
tests/python/frontend/pytorch/test_forward.py | 70 +-
tests/python/frontend/tensorflow/test_forward.py | 54 +
.../frontend/tensorflow2/test_sequential_models.py | 24 +-
tests/python/frontend/tflite/test_forward.py | 63 +-
.../quantization/test_quantization_accuracy.py | 43 +-
.../test_quantization_accuracy_for_vit.py | 14 +-
tests/python/relay/aot/aot_test_utils.py | 7 +
tests/python/relay/dyn/test_dynamic_op_level3.py | 66 +-
.../python/relay/op/annotation/test_annotation.py | 22 +-
tests/python/relay/op/test_tensor.py | 20 +-
tests/python/relay/test_build_module.py | 26 +-
tests/python/relay/test_json_compact.py | 62 +
tests/python/relay/test_pass_alter_op_layout.py | 19 +
tests/python/relay/test_pass_auto_quantize.py | 44 +-
.../relay/test_pass_dead_code_elimination.py | 12 +-
.../test_pass_fake_quantization_to_integer.py | 22 +
tests/python/relay/test_pass_instrument.py | 2 +-
tests/python/relay/test_pass_partition_graph.py | 67 +-
tests/python/relay/test_pass_plan_devices.py | 442 +++---
tests/python/relay/test_pipeline_executor.py | 16 +-
tests/python/relay/test_to_mixed_precision.py | 29 +
tests/python/relay/test_type_infer.py | 27 +-
tests/python/relay/test_type_solver.py | 24 +
tests/python/relay/test_vm.py | 74 +-
tests/python/relay/utils/external_codegen.py | 1 -
.../{test_se_scope.py => test_virtual_device.py} | 33 +-
tests/python/topi/python/test_topi_conv1d.py | 73 +
tests/python/topi/python/test_topi_conv3d_ncdhw.py | 66 +-
.../python/test_topi_conv3d_transpose_ncdhw.py | 12 +
tests/python/unittest/test_arith_intset.py | 108 ++
.../python/unittest/test_arith_iter_affine_map.py | 200 +++
tests/python/unittest/test_ci.py | 132 ++
.../python/unittest/test_meta_schedule_builder.py | 4 +-
.../unittest/test_meta_schedule_cost_model.py | 218 +++
.../python/unittest/test_meta_schedule_database.py | 20 +-
.../test_meta_schedule_feature_extractor.py | 58 +
...schedule_feature_extractor_per_store_feature.py | 1555 ++++++++++++++++++++
.../test_meta_schedule_measure_callback.py | 132 ++
.../test_meta_schedule_post_order_apply.py | 342 +++++
.../unittest/test_meta_schedule_search_strategy.py | 235 ++-
.../unittest/test_meta_schedule_task_scheduler.py | 78 +-
tests/python/unittest/test_runtime_profiling.py | 47 +
tests/python/unittest/test_target_codegen_llvm.py | 18 +
tests/python/unittest/test_target_target.py | 104 ++
tests/python/unittest/test_te_create_primfunc.py | 16 +
.../python/unittest/test_tir_schedule_reduction.py | 39 +
tests/python/unittest/test_tir_schedule_reorder.py | 5 +-
tests/python/unittest/test_tir_schedule_rfactor.py | 8 +-
.../unittest/test_tir_schedule_split_fuse.py | 12 +
.../test_tir_schedule_state_cached_flags.py | 78 +
.../python/unittest/test_tir_schedule_utilities.py | 66 +
.../unittest/test_tir_transform_flatten_buffer.py | 22 +
.../python/unittest/test_tvmscript_syntax_sugar.py | 12 +
tests/scripts/ci.py | 150 +-
tests/scripts/git_skip_ci.py | 110 ++
tests/scripts/task_config_build_gpu.sh | 3 +-
tests/scripts/task_python_integration.sh | 3 +
tests/scripts/task_sphinx_precheck.sh | 2 +-
version.py | 2 +-
446 files changed, 21524 insertions(+), 4698 deletions(-)
copy docker/install/{ubuntu_install_caffe.sh => ubuntu_install_freertos.sh} (57%)
mode change 100644 => 100755
copy docker/install/{ubuntu_install_redis.sh => ubuntu_install_oneflow.sh} (89%)
mode change 100755 => 100644
create mode 100644 include/tvm/meta_schedule/cost_model.h
create mode 100644 include/tvm/meta_schedule/feature_extractor.h
create mode 100644 include/tvm/meta_schedule/measure_callback.h
create mode 100644 include/tvm/meta_schedule/mutator.h
create mode 100644 include/tvm/meta_schedule/postproc.h
create mode 100644 include/tvm/meta_schedule/schedule_rule.h
create mode 100644 include/tvm/runtime/debug.h
rename include/tvm/target/{se_scope.h => virtual_device.h} (65%)
create mode 100644 python/tvm/contrib/ethosu/cascader/graph.py
create mode 100644 python/tvm/contrib/ethosu/cascader/parts.py
create mode 100644 python/tvm/driver/tvmc/arguments.py
delete mode 100644 python/tvm/driver/tvmc/common.py
create mode 100644 python/tvm/driver/tvmc/pass_config.py
create mode 100644 python/tvm/driver/tvmc/pass_list.py
create mode 100644 python/tvm/driver/tvmc/project.py
create mode 100644 python/tvm/driver/tvmc/shape_parser.py
create mode 100644 python/tvm/driver/tvmc/tracker.py
create mode 100644 python/tvm/driver/tvmc/transform.py
copy {tests/python/contrib/test_ethosu/cascader => python/tvm/meta_schedule/cost_model}/__init__.py (82%)
create mode 100644 python/tvm/meta_schedule/cost_model/cost_model.py
copy docker/install/ubuntu_install_caffe.sh => python/tvm/meta_schedule/cost_model/metric.py (59%)
create mode 100644 python/tvm/meta_schedule/cost_model/random_model.py
create mode 100644 python/tvm/meta_schedule/cost_model/xgb_model.py
copy python/tvm/meta_schedule/{search_strategy => feature_extractor}/__init__.py (70%)
create mode 100644 python/tvm/meta_schedule/feature_extractor/feature_extractor.py
create mode 100644 python/tvm/meta_schedule/feature_extractor/per_store_feature.py
create mode 100644 python/tvm/meta_schedule/feature_extractor/random_feature_extractor.py
copy python/tvm/meta_schedule/{search_strategy => measure_callback}/__init__.py (72%)
copy docker/install/ubuntu_install_caffe.sh => python/tvm/meta_schedule/measure_callback/add_to_database.py (60%)
copy docker/install/ubuntu_install_caffe.sh => python/tvm/meta_schedule/measure_callback/echo_statistics.py (59%)
create mode 100644 python/tvm/meta_schedule/measure_callback/measure_callback.py
copy docker/install/ubuntu_install_caffe.sh => python/tvm/meta_schedule/measure_callback/remove_build_artifact.py (59%)
copy docker/install/ubuntu_install_verilator.sh => python/tvm/meta_schedule/measure_callback/update_cost_model.py (61%)
copy {tests/python/contrib/test_ethosu/cascader => python/tvm/meta_schedule/mutator}/__init__.py (82%)
create mode 100644 python/tvm/meta_schedule/mutator/mutator.py
copy {tests/python/contrib/test_ethosu/cascader => python/tvm/meta_schedule/postproc}/__init__.py (89%)
create mode 100644 python/tvm/meta_schedule/postproc/postproc.py
copy {tests/python/contrib/test_ethosu/cascader => python/tvm/meta_schedule/schedule_rule}/__init__.py (72%)
create mode 100644 python/tvm/meta_schedule/schedule_rule/schedule_rule.py
create mode 100644 python/tvm/meta_schedule/search_strategy/evolutionary_search.py
copy python/tvm/meta_schedule/search_strategy/{replay_trace.py => replay_func.py} (64%)
copy python/tvm/{autotvm/env.py => meta_schedule/space_generator/post_order_apply.py} (59%)
create mode 100644 python/tvm/relay/backend/contrib/ethosu/te/inline.py
rename python/tvm/target/{se_scope.py => virtual_device.py} (58%)
copy src/runtime/pipeline/pipeline_scheduler.cc => rust/tvm/src/ir/relay/attrs/reduce.rs (55%)
create mode 100644 src/contrib/ethosu/cascader/graph.cc
create mode 100644 src/contrib/ethosu/cascader/graph.h
create mode 100644 src/contrib/ethosu/cascader/parts/ethosu.cc
create mode 100644 src/contrib/ethosu/cascader/parts/ethosu.h
create mode 100644 src/contrib/ethosu/cascader/parts/inline.cc
create mode 100644 src/contrib/ethosu/cascader/parts/inline.h
create mode 100644 src/meta_schedule/cost_model/cost_model.cc
create mode 100644 src/meta_schedule/feature_extractor/feature_extractor.cc
create mode 100644 src/meta_schedule/feature_extractor/per_store_feature.cc
create mode 100644 src/meta_schedule/measure_callback/add_to_database.cc
create mode 100644 src/meta_schedule/measure_callback/echo_statistics.cc
create mode 100644 src/meta_schedule/measure_callback/measure_callback.cc
create mode 100644 src/meta_schedule/measure_callback/remove_build_artifact.cc
create mode 100644 src/meta_schedule/measure_callback/update_cost_model.cc
create mode 100644 src/meta_schedule/mutator/mutator.cc
create mode 100644 src/meta_schedule/postproc/postproc.cc
create mode 100644 src/meta_schedule/schedule_rule/schedule_rule.cc
create mode 100644 src/meta_schedule/search_strategy/evolutionary_search.cc
copy src/meta_schedule/search_strategy/{replay_trace.cc => replay_func.cc} (53%)
create mode 100644 src/meta_schedule/space_generator/post_order_apply.cc
create mode 100644 src/relay/backend/contrib/cmsisnn/buffer_size.cc
create mode 100644 src/relay/backend/contrib/cmsisnn/buffer_size.h
create mode 100644 src/relay/backend/contrib/cmsisnn/compiler_attrs.cc
create mode 100644 src/relay/backend/contrib/cmsisnn/compiler_attrs.h
create mode 100644 src/runtime/debug.cc
rename src/target/{se_scope.cc => virtual_device.cc} (71%)
create mode 100644 src/tir/schedule/primitive/annotate.cc
create mode 100644 tests/cpp/relay/backend/contrib/cmsisnn/buffer_size_test.cc
create mode 100644 tests/cpp/relay/backend/contrib/cmsisnn/compiler_attrs_test.cc
delete mode 100644 tests/cpp/target/se_scope_test.cc
create mode 100644 tests/cpp/target/virtual_device_test.cc
create mode 100755 tests/python/contrib/test_dnnl.py
create mode 100644 tests/python/contrib/test_ethosu/cascader/conftest.py
copy cmake/modules/contrib/CODEGENC.cmake => tests/python/contrib/test_ethosu/cascader/infra.py (69%)
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_ethosu_conv2d_matcher.py
copy tests/python/{driver/tvmc/test_pass_list.py => contrib/test_ethosu/cascader/test_ethosu_inline_matcher.py} (52%)
copy tests/python/{driver/tvmc/test_pass_list.py => contrib/test_ethosu/cascader/test_ethosu_part.py} (50%)
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_graph.py
rename tests/python/target/{test_se_scope.py => test_virtual_device.py} (55%)
create mode 100644 tests/python/unittest/test_ci.py
create mode 100644 tests/python/unittest/test_meta_schedule_cost_model.py
create mode 100644 tests/python/unittest/test_meta_schedule_feature_extractor.py
create mode 100644 tests/python/unittest/test_meta_schedule_feature_extractor_per_store_feature.py
create mode 100644 tests/python/unittest/test_meta_schedule_measure_callback.py
create mode 100644 tests/python/unittest/test_meta_schedule_post_order_apply.py
create mode 100755 tests/scripts/git_skip_ci.py