This is an automated email from the ASF dual-hosted git repository.
masahi pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 491738649a [CI] Set test python.contrib.test_onnx.test_resize as xfail
discard 228dfa9f6b [CI] Update Docker image tags to 20220822-105603-52f5c155f
discard 95ec5c3c13 Update TensorFlow to release 2.9
add 1ec2c36912 [TIR][CompactBufferAllocation] Improve upperbound
estimation of buffer compaction (#12527)
add 592148abf6 [Target] Replace IsaAnalyzer with Target Features (#12322)
add 6e79f64108 [CI] Set test python.contrib.test_onnx.test_resize as xfail
(#12568)
add a0fe74b3c3 [ETHOSN] Support multiply conversion to depthwise (#12403)
add 038523e5a2 [TIR] Expose Vector-related API in Python (#12571)
add bf65b396c1 [Hexagon] Add support to run on multiple devices (#12504)
add f53ee0cecf [Hexagon] Fix missing pytest import (#12565)
add 1afd059395 [TOPI][Hexagon] Implement quantized avgpool (#12340)
add 17989e8ab5 [microTVM] Fix `build` directory exists error (#12575)
add b8fbfe26ae [MicroTVM] fix compile error when the compiler implements
char as unsigned (#12519)
add cd8fd9121d [TIR] Expose `shift_left` and `shift_right` to Python
(#12584)
add 9aac161a46 [MetaSchedule] Add software pipeline in CUDA tensor core
auto tensorization (#12544)
add b38738434b [TIR] Expose WMMA-related TensorCore builtins (#12589)
add 40bdea8d7a [PyTorch] Add aten::new_empty (#12591)
add fb7cf97fbc [CI] Install xgboost in Hexagon image (#12592)
add cc19cdd711 [microTVM][Zephyr] Add recommended heap size for NRF and
qemu_x86 (#12585)
add 56b7c8ae96 [CI] Assert some unittests are not skipped in CI (#12436)
add 61c034ae27 [DOC] fix code-block error in debuggging TVM part (#12597)
add b547106fde [CI] github_cc_reviewers: Catch all exceptions so all
reviewers can be processed (#12578)
add 399f2e9b70 [microNPU] Remove xfail from tests relating to #12511
(#12570)
add f7c143608f [ETHOSN] Support conversion of add to depthwise (#12531)
add 21db1eb586 [F2QI] Fix a rounding error on AvgPool when input and
output affine scales differ (#12577)
add bb00a15c26 [CUDA][CodeGen] Fix cuda codegen's fp16 inf literal (#12581)
add 01fcdfcf5f [ci] Default to n=2 for test parallelism (#12414)
add 8d60b3cbbc [Runtime] Change default alignment to 64 bytes. (#12586)
add 5db38ba899 [COMMUNITY] @cconvey -> Reviewer (#12598)
new f4f550f0cc testing new hexagon image
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 (491738649a)
\
N -- N -- N refs/heads/ci-docker-staging (f4f550f0cc)
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.
The 1 revisions listed above as "new" are entirely new to this
repository and will be described in separate emails. The revisions
listed as "add" were already present in the repository and have only
been added to this reference.
Summary of changes:
.github/workflows/{docs_bot.yml => tests_bot.yml} | 11 +-
CONTRIBUTORS.md | 1 +
Jenkinsfile | 80 ++++-
apps/microtvm/zephyr/template_project/boards.json | 8 +-
.../zephyr/template_project/microtvm_api_server.py | 2 +
ci/jenkins/Jenkinsfile.j2 | 22 +-
ci/jenkins/macros.j2 | 3 +
cmake/modules/contrib/TFLite.cmake | 2 -
docker/Dockerfile.ci_cortexm | 3 -
docker/Dockerfile.ci_cpu | 7 -
docker/Dockerfile.ci_gpu | 3 -
docker/Dockerfile.ci_hexagon | 4 +
docker/Dockerfile.ci_riscv | 3 -
docker/install/ubuntu_install_cmake_source.sh | 4 +-
docker/install/ubuntu_install_python_package.sh | 2 +-
docker/install/ubuntu_install_tensorflow.sh | 5 +-
.../install/ubuntu_install_tensorflow_aarch64.sh | 23 +-
docker/install/ubuntu_install_tflite.sh | 13 +-
docker/install/ubuntu_install_vela.sh | 2 +-
docs/dev/how_to/debugging_tvm.rst | 2 +-
include/tvm/arith/int_set.h | 39 ++-
include/tvm/meta_schedule/schedule_rule.h | 3 +-
include/tvm/runtime/device_api.h | 4 +-
python/tvm/arith/__init__.py | 8 +-
python/tvm/arith/int_set.py | 48 +++
python/tvm/contrib/hexagon/pytest_plugin.py | 60 +++-
python/tvm/meta_schedule/default_config.py | 1 +
.../schedule_rule/multi_level_tiling.py | 4 +
python/tvm/meta_schedule/testing/schedule_rule.py | 2 +
python/tvm/relay/frontend/pytorch.py | 16 +
python/tvm/relay/op/contrib/_ethosn.py | 1 +
python/tvm/relay/op/contrib/ethosn.py | 121 +++++--
python/tvm/relay/op/strategy/arm_cpu.py | 17 +-
.../transform/fake_quantization_to_integer.py | 64 +++-
python/tvm/target/arm_isa.py | 39 ---
python/tvm/testing/plugin.py | 42 +++
python/tvm/tir/__init__.py | 10 +-
python/tvm/tir/op.py | 331 +++++++++++++++++++
python/tvm/tir/tensor_intrin/cuda.py | 54 ++--
python/tvm/topi/hexagon/__init__.py | 1 +
.../tvm/{script => topi/hexagon/qnn}/__init__.py | 5 +-
python/tvm/topi/hexagon/qnn/avg_pool2d.py | 205 ++++++++++++
python/tvm/topi/hexagon/slice_ops/__init__.py | 2 +-
python/tvm/topi/hexagon/slice_ops/avg_pool2d.py | 24 +-
python/tvm/topi/hexagon/utils.py | 136 ++++++++
src/arith/int_set.cc | 131 ++++++--
.../multi_level_tiling_tensor_core.cc | 122 ++++++-
src/printer/tir_text_printer.cc | 2 +-
src/relay/backend/contrib/ethosn/codegen.cc | 8 +-
.../backend/contrib/ethosn/convert_equivalent.cc | 251 +++++++++++++++
src/relay/op/make_op.h | 2 +
src/relay/qnn/utils.h | 4 +
src/relay/transforms/pattern_utils.h | 34 ++
src/runtime/crt/common/crt_runtime_api.c | 2 +-
src/runtime/crt/graph_executor/load_json.c | 2 +-
src/target/source/codegen_cuda.cc | 6 +-
src/tir/schedule/primitive/compute_at.cc | 2 +-
src/tir/schedule/state.cc | 14 +-
src/tir/schedule/utils.h | 18 --
src/tir/transforms/compact_buffer_region.cc | 2 +-
tests/micro/zephyr/test_zephyr.py | 4 +-
tests/python/ci/test_ci.py | 179 +++++++++++
tests/python/contrib/test_dlpack.py | 10 +-
tests/python/contrib/test_ethosn/infrastructure.py | 3 +-
tests/python/contrib/test_ethosn/test_addition.py | 214 ++++++++++---
.../test_ethosn/test_convert_equivalents.py | 177 +++++++++++
tests/python/contrib/test_ethosn/test_multiply.py | 193 +++++++++++
tests/python/contrib/test_ethosn/test_networks.py | 2 +-
tests/python/contrib/test_ethosu/test_codegen.py | 5 -
.../test_ethosu/test_tir_to_cs_translator.py | 68 ++--
tests/python/contrib/test_ethosu/test_vela_api.py | 18 +-
.../python/contrib/test_hexagon/infrastructure.py | 55 +++-
.../test_hexagon/test_fixed_point_conversion.py | 64 ++++
.../test_hexagon/topi/test_avg_pool2d_slice.py | 209 +++++++-----
.../contrib/test_hexagon/topi/test_cast_slice.py | 2 +
tests/python/frontend/pytorch/test_forward.py | 17 +
tests/python/relay/test_op_level3.py | 16 +-
.../test_pass_fake_quantization_to_integer.py | 15 +-
tests/python/unittest/test_arith_intset.py | 354 +++++++++++----------
...ta_schedule_schedule_rule_multi_level_tiling.py | 125 ++++++++
.../test_tir_analysis_calculate_workspace.py | 16 +-
tests/python/unittest/test_tir_intrin.py | 8 +-
tests/python/unittest/test_tir_op_types.py | 83 +++++
.../python/unittest/test_tir_schedule_analysis.py | 6 +-
.../python/unittest/test_tir_schedule_reduction.py | 16 +-
.../unittest/test_tir_schedule_storage_align.py | 18 +-
.../python/unittest/test_tir_schedule_tensorize.py | 30 +-
.../test_tir_transform_compact_buffer_region.py | 100 ++++++
.../test_tir_transform_convert_for_loops_serial.py | 8 +-
.../test_tir_transform_inject_rolling_buffer.py | 12 +-
tests/python/unittest/test_tir_usmp_algo.py | 18 +-
.../test_tir_usmp_analysis_extract_bufferinfo.py | 138 ++++----
...ransform_convert_pool_allocations_to_offsets.py | 36 +--
.../test_tir_usmp_transform_create_io_allocates.py | 48 +--
tests/python/unittest/test_tir_usmp_utils.py | 18 +-
tests/python/unittest/test_tvmscript_complete.py | 18 +-
tests/python/unittest/test_tvmscript_roundtrip.py | 36 +--
.../python/unittest/test_tvmscript_syntax_sugar.py | 12 +-
tests/python/unittest/test_tvmscript_type.py | 6 +-
tests/scripts/github_cc_reviewers.py | 6 +-
tests/scripts/github_skipped_tests_comment.py | 256 +++++++++++++++
tests/scripts/setup-pytest-env.sh | 10 +-
tests/scripts/task_config_build_cpu.sh | 2 +-
tests/scripts/task_python_hexagon.sh | 14 +-
104 files changed, 3809 insertions(+), 873 deletions(-)
copy .github/workflows/{docs_bot.yml => tests_bot.yml} (55%)
delete mode 100644 python/tvm/target/arm_isa.py
copy python/tvm/{script => topi/hexagon/qnn}/__init__.py (85%)
create mode 100644 python/tvm/topi/hexagon/qnn/avg_pool2d.py
create mode 100644 src/relay/backend/contrib/ethosn/convert_equivalent.cc
create mode 100644 tests/python/contrib/test_ethosn/test_convert_equivalents.py
create mode 100644 tests/python/contrib/test_ethosn/test_multiply.py
create mode 100644
tests/python/contrib/test_hexagon/test_fixed_point_conversion.py
create mode 100755 tests/scripts/github_skipped_tests_comment.py
