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 80f7d82 Merge jenkinsfile
discard 2d5ca7f Add uses_gpu to onnx node tests
discard 75ca940 add onnx to CPU tests
discard 7189a1a See if this fixes CI problem
add 2df0854 [TensorIR][M2a] Fuse, Split (#8467)
add 789ab1f [Relay] Support resize in the ONNX conversion (#8455)
add 18491ea update qemu install (#8518)
add 45497bd [Topi][UnitTests] Parameterize conv2d and depthwise_conv2d
tests (#8433)
add e95f10f [CUDA] Initial support for dynamic shared memory (#8466)
add 59e96e0 [microTVM][Cortex-R5] Add zephyr cortex-r5 board to Zephyr
(#8519)
add 07243a8 [TVMSCRIPT]Fix script printters StructuralEqual check failed
(#8499)
add bce0db5 [PROFILING] Add json output to profiling reports (#8503)
add e664ef0 [PRINTER] Fix the repeatitive cast in scripr printing (#8531)
add 8ab2074 [Frontend, Tensorflow2] Added support for TensorList ops
(#8454)
add 18171e4 [CMake] Split out libinfo.cc into a separate target. (#8520)
add 3445532 [RUNTIME] Fix TypeKey2Index when for root Object (#8547)
add 9c63f4f [TFLite] Mimic the TFLite's 2.4 reader's behaviour (#8538)
add e190b5ca See if this fixes CI problem
add 03178c4 add onnx to CPU tests
add 903c853 Add uses_gpu to onnx node tests
add be5502e Merge jenkinsfile
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 (80f7d82)
\
N -- N -- N refs/heads/ci-docker-staging (be5502e)
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:
CMakeLists.txt | 24 +-
.../boards/qemu_cortex_r5.conf} | 4 +-
.../boards/{qemu_x86.conf => qemu_cortex_r5.conf} | 2 +-
apps/microtvm/zephyr/qemu-hack/qemu-system-arm | 2 +-
...u-system-riscv64 => qemu-system-xilinx-aarch64} | 0
docker/Dockerfile.ci_qemu | 6 +-
docs/dev/codebase_walkthrough.rst | 4 +-
include/tvm/arith/iter_affine_map.h | 12 +
include/tvm/runtime/profiling.h | 33 +
include/tvm/tir/function.h | 11 +-
include/tvm/tir/schedule/schedule.h | 19 +
python/tvm/contrib/target/onnx.py | 91 +++
python/tvm/relay/frontend/tensorflow2.py | 206 ++++-
python/tvm/relay/frontend/tensorflow2_ops.py | 179 +++++
python/tvm/relay/frontend/tensorflow_ops.py | 12 +
python/tvm/relay/frontend/tflite.py | 24 +-
python/tvm/runtime/profiling/__init__.py | 57 ++
python/tvm/script/intrin.py | 26 +-
python/tvm/target/target.py | 1 +
python/tvm/tir/schedule/schedule.py | 138 +++-
python/tvm/topi/nn/conv2d.py | 5 +-
python/tvm/topi/nn/depthwise_conv2d.py | 52 +-
python/tvm/topi/nn/mapping.py | 31 +-
python/tvm/topi/testing/__init__.py | 6 +-
python/tvm/topi/testing/depthwise_conv2d_python.py | 57 ++
python/tvm/topi/x86/group_conv2d.py | 7 +-
src/arith/iter_affine_map.cc | 15 +
src/arith/rewrite_simplify.cc | 4 +
src/runtime/cuda/cuda_module.cc | 14 +-
src/runtime/file_utils.cc | 10 +-
src/runtime/meta_data.h | 5 +-
src/runtime/metal/metal_module.mm | 12 +-
src/runtime/object.cc | 8 +-
src/runtime/opencl/opencl_module.cc | 14 +-
src/runtime/profiling.cc | 68 ++
src/runtime/rocm/rocm_module.cc | 19 +-
src/runtime/thread_storage_scope.h | 33 +-
src/runtime/vulkan/vulkan_wrapped_func.cc | 8 +-
src/runtime/vulkan/vulkan_wrapped_func.h | 7 +-
src/target/build_common.h | 7 +-
src/target/llvm/codegen_amdgpu.cc | 70 +-
src/target/llvm/codegen_llvm.cc | 16 +
src/target/llvm/codegen_llvm.h | 5 +
src/target/llvm/codegen_nvptx.cc | 60 +-
src/target/source/codegen_cuda.cc | 28 +-
src/tir/schedule/concrete_schedule.cc | 87 +++
src/tir/schedule/concrete_schedule.h | 43 +-
src/tir/schedule/primitive.h | 22 +-
src/tir/schedule/primitive/loop_transformation.cc | 389 ++++++++++
src/tir/schedule/schedule.cc | 2 +
.../transforms/lower_device_storage_access_info.cc | 2 +-
src/tir/transforms/split_host_device.cc | 23 +
src/tir/transforms/storage_rewrite.cc | 6 +-
tests/lint/check_file_type.py | 3 +
tests/micro/zephyr/conftest.py | 1 +
tests/python/contrib/test_onnx.py | 45 ++
.../frontend/tensorflow2/test_functional_models.py | 136 ++++
.../frontend/tensorflow2/test_sequential_models.py | 55 ++
tests/python/topi/python/test_topi_conv2d_nchw.py | 476 ++++++------
.../topi/python/test_topi_depthwise_conv2d.py | 858 ++++++++-------------
tests/python/unittest/test_runtime_profiling.py | 22 +
tests/python/unittest/test_tir_base.py | 7 +
tests/python/unittest/test_tir_ir_builder.py | 58 ++
.../unittest/test_tir_schedule_split_fuse.py | 453 +++++++++++
tests/python/unittest/test_tvmscript_roundtrip.py | 15 +
tests/scripts/task_python_vta_tsim.sh | 3 +
web/src/webgpu.ts | 6 +-
67 files changed, 3169 insertions(+), 955 deletions(-)
copy apps/microtvm/zephyr/{host_driven/boards/qemu_x86.conf =>
aot_demo/boards/qemu_cortex_r5.conf} (91%)
copy apps/microtvm/zephyr/host_driven/boards/{qemu_x86.conf =>
qemu_cortex_r5.conf} (93%)
copy apps/microtvm/zephyr/qemu-hack/{qemu-system-riscv64 =>
qemu-system-xilinx-aarch64} (100%)
create mode 100644 python/tvm/relay/frontend/tensorflow2_ops.py
create mode 100644 src/tir/schedule/primitive/loop_transformation.cc
create mode 100644 tests/python/unittest/test_tir_schedule_split_fuse.py
