This is an automated email from the ASF dual-hosted git repository.
leandron pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
discard 5f179ce001 [ACL] Adjust mobilenet test for Keras 2.9
discard 02cb556f74 [CI] Update Docker image tags to 20220822-105603-52f5c155f
discard 16de572c13 Add #12130 PR for testing.
discard 5ea15c2339 Update TensorFlow to release 2.9
add 66a31e97a7 [CI] Add alexnet and googlenet caffe model to request hook
(#12510)
add e5e05feee3 [LLVM] Add "cl-opt" attribute to target_kind "llvm" (#12440)
add 902343a817 [BugFix][UMA] Fix order issue in uma_lower (#12447)
add 1e399fa451 [TIR] Add pass to check for out of bounds memory access
(#12352)
add 8e95bba697 Remove mutable defaults in mlp_model (#12546)
add 3bd168194f check for CMSIS_PATH in project generation (#12547)
add 5cef6bf559 [microTVM] Rework evaluate_model_accuracy into a more
generic helper function (#12539)
add 58f2139ffd [microTVM] Replace static fixtures with parameterization
(#12530)
add e252d7f3ab [docs] Add CI contribution instructions (#12551)
add d26bf809e4 [ACL] Adjust mobilenet test for Keras 2.9 (#12541)
add 3983a472c6 [COMMUNITY] @konturn -> Reviewer (#12543)
add 383bd41931 Fix TFLite 2.9 tests (#12130)
add 52779f1273 [CMSIS-NN] Pad fusion with QNN Conv2D (#12353)
add d271678388 [CI][AArch64] Skip libgomp failures in integration tests
(#12554)
add ff46fa15e0 [ETHOSN] Fix requantize output conversion (#12540)
add dd7ae2d3e5 [Relay] Add Rsqrt to SimplifyExpr (#12363)
add da5836f230 [AutoTVM] Add support for text buffers to ApplyHistoryBest
(#12521)
add 1d71c1b4aa [skip ci][ci] Mark more ethosu tests with xfail (#12560)
add 99b9b74b12 [CI] Remove Vela from ci_cpu (#12533)
add 4d104e5ec6 [ETHOSN] Add support for special indices of Reshape (#12556)
add 8c23469e20 [MicroTVM] add heap-size to project options (#12390)
add 13ebbfb37f Replace std::result_of (deprecated in C++17) with
std::invoke_result, NFC (#12562)
add 8174d082e8 Add using directives for otherwise hidden virtual
functions, NFC (#12561)
add c15cc5ef6d [Target] Remove deprecated parameters from target (#12416)
add 577826182f [PyTorch][Fix] Fix for numerically unstable logsigmoid
(#12563)
add e468dc28ea [microNPU] Force compute_cycles_hint to be interpreted as
an int64 value (#12558)
add 90b2f0d369 [CI][CMSIS-NN] Running tests parallel using pytest-xdist
(#12557)
add 989e5a1128 [ETHOSN] Add support for resize (#12535)
new 95ec5c3c13 Update TensorFlow to release 2.9
new 228dfa9f6b [CI] Update Docker image tags to 20220822-105603-52f5c155f
new 8b309ae15c [CI] Set test python.contrib.test_onnx.test_resize as xfail
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 (5f179ce001)
\
N -- N -- N refs/heads/ci-docker-staging (8b309ae15c)
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 3 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:
CONTRIBUTORS.md | 1 +
apps/hexagon_launcher/README.md | 4 +-
apps/howto_deploy/prepare_test_libs.py | 2 +-
.../template_project/CMakeLists.txt.template | 3 +-
apps/microtvm/zephyr/template_project/boards.json | 3 +-
.../zephyr/template_project/microtvm_api_server.py | 51 +++
.../zephyr/template_project/src/host_driven/main.c | 2 +-
apps/sgx/src/build_model.py | 7 +-
apps/uma/_template/patterns.py | 5 +
.../wasm-graph/tools/build_graph_lib.py | 9 +-
docker/Dockerfile.ci_cpu | 7 -
docs/contribute/ci.rst | 23 ++
.../tune_with_autoscheduler/ci_logs/matmul.json | 2 +-
.../ci_logs/resnet-50-NHWC-B1-llvm.json | 52 +--
.../ci_logs/sparse_dense.json | 2 +-
gallery/how_to/tune_with_autotvm/tune_relay_x86.py | 4 +-
gallery/how_to/work_with_microtvm/micro_tvmc.sh | 4 +-
gallery/tutorial/auto_scheduler_matmul_x86.py | 2 -
include/tvm/script/printer/traced_object.h | 2 +-
include/tvm/tir/analysis.h | 11 +
python/tvm/autotvm/record.py | 31 +-
python/tvm/autotvm/task/dispatcher.py | 87 +++--
python/tvm/contrib/ethosu/cascader/scheduler.py | 6 +-
python/tvm/contrib/hexagon/pytest_plugin.py | 2 +-
python/tvm/meta_schedule/cost_model/mlp_model.py | 37 +-
python/tvm/micro/testing/__init__.py | 2 +-
python/tvm/micro/testing/evaluation.py | 21 +-
python/tvm/micro/testing/pytest_plugin.py | 30 +-
python/tvm/micro/testing/utils.py | 5 +
python/tvm/relay/backend/contrib/uma/api/lower.py | 22 +-
python/tvm/relay/build_module.py | 78 ----
python/tvm/relay/frontend/pytorch.py | 4 +-
python/tvm/relay/op/_tensor.py | 1 +
python/tvm/relay/op/contrib/cmsisnn.py | 50 ++-
python/tvm/relay/op/contrib/dnnl.py | 3 +-
python/tvm/relay/op/contrib/ethosn.py | 15 +
python/tvm/target/target.py | 19 +-
python/tvm/testing/aot.py | 25 +-
python/tvm/tir/analysis/analysis.py | 11 +
src/arith/int_set.cc | 4 +-
src/ir/transform.cc | 2 +-
src/relay/backend/annotate_used_memory.cc | 2 +-
src/relay/backend/contrib/cmsisnn/fuse_pads.cc | 209 ++++++++++
src/relay/backend/contrib/ethosn/codegen.cc | 39 ++
src/relay/backend/contrib/ethosn/codegen_ethosn.h | 1 +
src/relay/backend/contrib/ethosn/ethosn_api.cc | 94 +++--
src/relay/backend/contrib/ethosn/ethosn_api.h | 8 +
src/relay/transforms/annotate_texture_storage.cc | 4 +
src/relay/transforms/compiler_function_utils.cc | 2 +
src/relay/transforms/simplify_expr.cc | 24 ++
src/target/llvm/llvm_instance.cc | 430 ++++++++++++++++++++-
src/target/llvm/llvm_instance.h | 194 ++++++++--
src/target/llvm/llvm_module.cc | 4 +-
src/target/target_kind.cc | 62 ++-
src/tir/analysis/oob_checker.cc | 130 +++++++
src/tir/schedule/error.cc | 4 +-
tests/cpp/c_codegen_test.cc | 10 +-
tests/cpp/target_test.cc | 164 +++++++-
tests/micro/arduino/test_arduino_workflow.py | 13 +-
tests/micro/common/conftest.py | 16 -
tests/micro/common/test_autotune.py | 14 +-
tests/python/contrib/test_cmsisnn/test_conv2d.py | 277 +++++++++++--
.../python/contrib/test_cmsisnn/test_fuse_pads.py | 340 ++++++++++++++++
tests/python/contrib/test_cmsisnn/utils.py | 45 ++-
.../python/contrib/test_ethosn/test_requantize.py | 63 +++
tests/python/contrib/test_ethosn/test_reshape.py | 37 +-
tests/python/contrib/test_ethosn/test_resize.py | 134 +++++++
tests/python/contrib/test_ethosu/test_codegen.py | 17 +-
.../test_hexagon/topi/test_softmax_slice.py | 1 -
tests/python/contrib/test_onnx.py | 3 +
tests/python/contrib/test_uma/test_uma_pipeline.py | 82 ++++
.../test_uma/test_uma_vanilla_accelerator.py | 3 +-
tests/python/driver/tvmc/test_autotuner.py | 9 +
tests/python/driver/tvmc/test_frontends.py | 9 +
tests/python/driver/tvmc/test_model.py | 4 +
tests/python/driver/tvmc/test_target.py | 6 +-
tests/python/driver/tvmc/test_target_options.py | 2 +-
tests/python/frontend/pytorch/test_forward.py | 2 +
tests/python/relay/aot/test_cpp_aot.py | 2 +-
tests/python/relay/aot/test_crt_aot.py | 36 --
tests/python/relay/test_build_module.py | 47 +--
tests/python/relay/test_pass_simplify_expr.py | 19 +
tests/python/unittest/test_arith_intset.py | 2 +-
tests/python/unittest/test_autotvm_record.py | 92 ++++-
tests/python/unittest/test_target_target.py | 7 +
tests/python/unittest/test_tir_analysis_oob.py | 78 ++++
.../test_tir_transform_common_subexpr_elim.py | 2 +-
tests/python/unittest/test_tvmscript_roundtrip.py | 4 +-
tests/scripts/request_hook/request_hook.py | 3 +
tests/scripts/task_python_docs.sh | 2 +-
tests/scripts/task_python_microtvm.sh | 2 +-
91 files changed, 2804 insertions(+), 601 deletions(-)
create mode 100644 src/relay/backend/contrib/cmsisnn/fuse_pads.cc
create mode 100644 src/tir/analysis/oob_checker.cc
create mode 100644 tests/python/contrib/test_cmsisnn/test_fuse_pads.py
create mode 100644 tests/python/contrib/test_ethosn/test_resize.py
create mode 100644 tests/python/unittest/test_tir_analysis_oob.py
