This is an automated email from the ASF dual-hosted git repository.
jroesch pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
omit a41c540 retrigger CI
omit d614c0b fix typo
omit e85c94c properly revert pack_lib changes
omit c0f46b6 revert attempt to use globs in pack_libs, switch to building
standalone_crt
omit ae9dcb0 switch to python script for expanding globs
omit 0c94604 include build prefix
omit fa066e6 Put standalone_crt in correct Jenkinsfile stash bundle
omit 0fd91fb Merge remote-tracking branch 'origin/main' into
standalone-crt-build-tree
omit 03e2edc try stashing entire standalone_crt in hopes it will not upset
jenkins
omit 0935452 pylint
omit 4ae8dcb black format
omit 9db961d Build microTVM using standalone_crt in build tree.
add eeec538 Add resource_handle to both TVM_DLL_EXPORT_TYPED_FUNC and
TVM_DLL_EXPORT_PACKED_FUNC macros in packed_func.h. This is a patch PR for
#7388. (#7343)
add 38fa420 [FIX] Don't add $TVM_HOME/.. to the include path when
compiling code. (#7342)
add eae21b0 [PRNG] Add check to PRNG to make sure that unsigned integer
arithmetic is wrapping (#7287)
add 59e0a4a [Torch] Various updates for PyTorch frontend (#7348)
add fd39122 [AutoScheduler] Enable schedule sharing in dispatch context
(#7344)
add 4006bde [Torch] More graph rewrites for Faster RCNN / MaskRCNN (#7346)
add 00257f3 [Autodiff] Deterministic gradient compute (#7321)
add d8efe70 [COMMUNITY] @trevor-m -> reviewer (#7352)
add 913abe0 [Relay][Frontend][Onnx] Robustify Loop Importer (#7353)
add 02fefbc If an expression has two branches, and the pattern ignores
one with a wildcard, allow grouping via dominator analysis (#7355)
add 8b84e33 Fold If when the condition is Constant (#7354)
add cbc035f Update uTVM code to work with the nRF5340DK dev board. (#7331)
add dda8f5d [Frontend][Tensorflow] Sparse dense matmul adjoint option
added (#7267)
add 67acad3 [Relay][PatternLang] Bug fix of rewrite func attr (#7358)
add f17cba7 [RUNTIME] Improve error messages for TypedPackedFunc (#7152)
add b8ad146 [Relay] Type Relation Fixes (#7362)
add ef032b3 Remove MemoryPlan from VM passes (#7361)
add f7275f9 Some docstring fixes. (#7367)
add f7862e7 [Relay][Frontend[Onnx] Add testing for output datatypes and
fix related bugs. (#7364)
add 4f414fd fix grad for zeros and ones (#7357)
add 4142128 [BYOC][Verilator] change runtime registry function name
(#7351)
add 02c764c disable one of rewrite in torch detection test (#7365)
add 44a071a [Refactor][VM] Port memory_alloc to c++ (#7369)
add 3734d5f [CUDA][PASS]Legalize tensorcore (#7147)
add e892619 swap pytorch and tvm import order (#7380)
add 96b0981 disable other rewrite to test CI (#7371)
add 2365c7e fix duplicated symbol bug in external codegen (#7383)
add f1a03cc Jenkinsfile changes for #7333.
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 (a41c540)
\
N -- N -- N refs/heads/ci-docker-staging (f1a03cc)
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:
CONTRIBUTORS.md | 1 +
apps/microtvm/reference-vm/zephyr/pyproject.toml | 3 +
cmake/modules/StandaloneCrt.cmake | 8 +-
include/tvm/relay/transform.h | 12 +
include/tvm/runtime/packed_func.h | 155 +++++--
include/tvm/runtime/registry.h | 10 +-
pyproject.toml | 93 ----
python/tvm/_ffi/libinfo.py | 2 -
python/tvm/auto_scheduler/dispatcher.py | 135 ++++--
python/tvm/auto_scheduler/measure_record.py | 65 +--
python/tvm/auto_scheduler/utils.py | 65 ++-
python/tvm/contrib/graph_runtime.py | 4 +-
python/tvm/micro/__init__.py | 4 +-
python/tvm/micro/build.py | 174 +++-----
python/tvm/micro/compiler.py | 5 +-
python/tvm/micro/contrib/zephyr.py | 23 +-
python/tvm/relay/__init__.py | 1 -
python/tvm/relay/build_module.py | 10 +-
python/tvm/relay/frontend/onnx.py | 19 +-
python/tvm/relay/frontend/pytorch.py | 63 ++-
python/tvm/relay/frontend/pytorch_utils.py | 258 ++++++++++-
python/tvm/relay/frontend/tensorflow.py | 69 ++-
python/tvm/relay/op/_tensor_grad.py | 22 +-
python/tvm/relay/op/nn/_nn.py | 42 ++
python/tvm/relay/transform/__init__.py | 1 -
python/tvm/relay/transform/memory_alloc.py | 389 ----------------
python/tvm/target/target.py | 3 +
python/tvm/topi/cuda/__init__.py | 1 +
python/tvm/topi/cuda/conv2d_alter_op.py | 48 ++
python/tvm/topi/cuda/tensorcore_alter_op.py | 204 +++++++++
python/tvm/topi/nn/batch_matmul.py | 24 +
python/tvm/topi/nn/dense.py | 24 +
python/tvm/topi/random/kernel.py | 62 ++-
python/tvm/topi/x86/injective.py | 27 +-
src/arith/solve_linear_equation.cc | 9 +-
src/arith/solve_linear_inequality.cc | 54 +--
src/relay/backend/compile_engine.cc | 4 +-
src/relay/backend/contrib/verilator/codegen.cc | 2 +-
src/relay/backend/vm/compiler.cc | 13 +-
src/relay/backend/vm/lambda_lift.cc | 1 -
src/relay/ir/dataflow_matcher.cc | 11 +-
src/relay/ir/indexed_graph.h | 22 +
src/relay/op/dyn/tensor/transform.cc | 3 +
src/relay/op/nn/nn.cc | 15 +-
src/relay/op/nn/sparse.cc | 10 +-
src/relay/op/tensor/reduce.cc | 4 +-
src/relay/op/tensor/transform.cc | 4 +-
src/relay/op/type_relations.cc | 12 +-
src/relay/transforms/fold_constant.cc | 12 +
src/relay/transforms/memory_alloc.cc | 494 +++++++++++++++++++++
src/runtime/contrib/verilator/verilator_runtime.cc | 5 +-
src/te/autodiff/ad_simplify.cc | 26 +-
tests/micro/qemu/conftest.py | 9 +
tests/micro/qemu/test_zephyr.py | 36 +-
tests/python/frontend/onnx/test_forward.py | 75 +++-
tests/python/frontend/pytorch/test_forward.py | 101 ++++-
.../frontend/pytorch/test_object_detection.py | 26 +-
tests/python/frontend/tensorflow/test_forward.py | 12 +-
tests/python/relay/test_any.py | 1 -
tests/python/relay/test_dataflow_pattern.py | 94 ++++
tests/python/relay/test_memory_passes.py | 1 -
tests/python/relay/test_op_grad_level3.py | 49 +-
tests/python/relay/test_pass_fold_constant.py | 39 ++
.../python/relay/test_pass_legalize_tensorcore.py | 239 ++++++++++
tests/python/topi/python/test_topi_prng.py | 8 +
.../python/unittest/test_auto_scheduler_measure.py | 18 +-
tests/python/unittest/test_crt.py | 13 +-
tests/python/unittest/test_link_params.py | 13 +-
tutorials/micro/micro_tflite.py | 13 +-
69 files changed, 2494 insertions(+), 980 deletions(-)
delete mode 100644 python/tvm/relay/transform/memory_alloc.py
create mode 100644 python/tvm/topi/cuda/tensorcore_alter_op.py
create mode 100644 src/relay/transforms/memory_alloc.cc
create mode 100644 tests/python/relay/test_pass_legalize_tensorcore.py
