This is an automated email from the ASF dual-hosted git repository.
mbrookhart pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
discard c5683d7 disable test until CI update complete
discard f61436f Don't force output shape for conv transpose tests, add 1D and
3D cases
discard e01d807 support convtranspose opset 11 autopadding
discard 017c12a point jenkins at new docker
discard 9227e36 add failing onnx tets
add 3d27ae0 [TIR] Tighten up invariance of CopyOnWrite in recursive stmt
visitor (#8358)
add b803bab Decoupling AOT from graph memory planner (#8096)
add c8f54f9 [Bugfix, CuDNN] fix segfault when cudnnDestroy called with
destroyed cuda context (#8267)
add ae58f2c [Topi][Unittests] Parametrized tests in `test_topi_dense.py`,
split out gpu-independent implementations (#8336)
add aa6fd43 [Build] Add CUDA_VERSION and GIT_COMMIT_TIME (#8372)
add 4284e32 Fix compute library installation on AArch64 (#8371)
add 9ed593e [Unittests] Added a meta-test for tvm.testing.fixture
behavior in case of a broken fixture. (#8343)
add b1a946b [Vulkan][Unittests] Add parametrization to vulkan unit tests.
(#8348)
add faadb7d [FIX] Detect like cores by looking at scaling_max_freq
instead of (#8370)
add 6d1ced0 [Matmul] Add matmul op (#8234)
add 8d4df91 Fix issue with importing models using Tensorflow Lite 2.4.x
schema (#8375)
add 6bf7fd0 add failing onnx tets
add 4e934d9 point jenkins at new docker
add 4bdb558 support convtranspose opset 11 autopadding
add aec720b Don't force output shape for conv transpose tests, add 1D and
3D cases
add 0a3c5ca disable test until CI update complete
add 719ff16 try updating docker images again
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 (c5683d7)
\
N -- N -- N refs/heads/ci-docker-staging (719ff16)
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:
Jenkinsfile | 8 +-
cmake/modules/CUDA.cmake | 2 +-
cmake/modules/Git.cmake | 15 +
cmake/modules/LibInfo.cmake | 8 +
.../ubuntu_download_arm_compute_lib_binaries.sh | 2 +-
include/tvm/relay/attrs/nn.h | 26 ++
include/tvm/tir/stmt_functor.h | 6 +
include/tvm/tir/transform.h | 5 +
python/tvm/relay/frontend/tensorflow.py | 19 +-
python/tvm/relay/frontend/tensorflow_ops.py | 20 +-
python/tvm/relay/frontend/tflite.py | 25 +-
python/tvm/relay/op/_tensor_grad.py | 29 ++
python/tvm/relay/op/nn/_nn.py | 63 +++-
python/tvm/relay/op/nn/nn.py | 44 +++
python/tvm/relay/op/op_attrs.py | 5 +
python/tvm/relay/op/strategy/cuda.py | 51 ++-
python/tvm/relay/op/strategy/generic.py | 36 +++
python/tvm/relay/op/strategy/x86.py | 72 +++++
python/tvm/testing.py | 2 +-
python/tvm/tir/transform/transform.py | 11 +
python/tvm/topi/__init__.py | 1 +
python/tvm/topi/cuda/dense.py | 237 +++-----------
python/tvm/topi/generic/nn.py | 17 +
python/tvm/{contrib/tf_op => topi/gpu}/__init__.py | 6 +-
python/tvm/topi/{cuda => gpu}/dense.py | 199 +++---------
python/tvm/topi/nn/dense.py | 138 ++++++--
python/tvm/topi/x86/dense.py | 119 +++++--
rust/tvm/src/ir/relay/attrs/nn.rs | 12 +
src/relay/backend/aot_executor_codegen.cc | 354 ++++++++++++++-------
src/relay/op/make_op.h | 3 +
src/relay/op/nn/nn.cc | 40 ++-
src/relay/op/nn/nn.h | 72 +++--
src/relay/qnn/op/dense.cc | 2 +-
.../transforms/auto_scheduler_layout_rewrite.cc | 10 +-
src/runtime/contrib/cudnn/cudnn_utils.cc | 6 +-
src/runtime/threading_backend.cc | 2 +-
src/support/libinfo.cc | 10 +
src/target/spirv/codegen_spirv.cc | 28 +-
src/tir/transforms/ir_utils.h | 23 ++
src/tir/transforms/legalize_packed_calls.cc | 121 +++++++
src/tir/transforms/lower_thread_allreduce.cc | 57 +++-
src/tir/transforms/lower_tvm_builtin.cc | 10 -
tests/python/frontend/tensorflow/test_forward.py | 12 +-
tests/python/relay/aot/aot_test_utils.py | 47 ++-
tests/python/relay/aot/test_crt_aot.py | 48 +++
tests/python/relay/test_autotvm_task_extraction.py | 2 +-
tests/python/relay/test_op_grad_level2.py | 17 +
tests/python/relay/test_op_level1.py | 63 +++-
tests/python/topi/python/test_topi_dense.py | 212 ++++++------
tests/python/topi/python/test_topi_matmul.py | 26 ++
.../unittest/test_aot_legalize_packed_call.py | 80 +++++
tests/python/unittest/test_target_codegen_bool.py | 71 ++---
.../python/unittest/test_target_codegen_vulkan.py | 312 +++++++++---------
tests/python/unittest/test_tvm_testing_features.py | 37 ++-
54 files changed, 1928 insertions(+), 915 deletions(-)
copy python/tvm/{contrib/tf_op => topi/gpu}/__init__.py (86%)
copy python/tvm/topi/{cuda => gpu}/dense.py (59%)
create mode 100644 src/tir/transforms/legalize_packed_calls.cc
create mode 100644 tests/python/unittest/test_aot_legalize_packed_call.py
