You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by le...@apache.org on 2022/02/04 11:01:30 UTC
[tvm] branch ci-docker-staging updated (89bc502 -> 89aa4fe)
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 89bc502 Upgrade tensorflow to version to 2.6.x
add d576f3d [CMSIS-NN] Moved test_cnn_small to the latest version (#9962)
add 9ef374f [CUDA] Support float16 erf,tan,atan (#10122)
add 339f888 [USMP] Add performance characteristics to PoolInfo (#10005)
add 72b22f8 [Relay][VM] Fix loading late bound consts when none exist (#10087)
add a1f51aa [CUTLASS] Conv2d dgrad (#10110)
add 780f88a [FIX,AUTOTVM] Add backtraces to tuning errors (#9901)
add faf63f9 Update ethos-u-vela for demo app (#10129)
add ac4815c [AutoScheduler] Allow device specification for AutoScheduler Runners. (#10123)
add efe662f [Relay][Pass] Add a relay pass to extract fake quantized ops (#10089)
add 565e6b4 Add more logging information to ReshapeLikeRel (#10125)
add cb3d7e2 [CMSIS-NN] Convert scalar constants to tensor constants (#10100)
add ded4065 [Misc] typo and nit fixes (#10145)
add 8727c60 [onnx] fix onnx where broadcast (#10106)
add a91b518 Add bot to ping reviewers after no activity (#9973)
add 8ce1b6c [skip ci] Fix for ping_reviewers wait time (#10149)
add e53cbe4 Fix LayoutRewriter (#10118)
add 95e466e [BugFix] Linker: undefined reference to kTargetPoolReadWriteAccess (#10147)
add 2e6702c [microNPU] Add support for transpose convolution (#9855)
add a45aa3e [CMSIS-NN] Moved all asserts in tests under a single utils function (#10148)
add d436a10 fix corner case when relay return empty tuple (#10128)
add 506bc3c [microTVM][Zephyr] Update RVM to Zephyr 2.7 (#10138)
add f929b0f [Runtime][PackedFunc] Bring `PackedFunc` into TVM Object System (#10032)
add 9518b7e Remove javah support (#10104)
add f2b7e82 [microNPU][3] Plan generation for the cascader (#9890)
add 455c02a [TVMScript] Support T.buffer_decl using data pointer from Let/Allocate (#10099)
add 8736593 [CI] Update ci_arm and ci_lint (#10146)
add a8741e2 [microNPU] Fix layout assignment in layout optimizer pass (#10143)
add 96416c4 [TIR][Schedule] Update compact_dataflow constraint (#10158)
add cfc8db0 remove async tst (#10160)
add 0482cdc OpenCL debug runtime timer handler added. (#10140)
add bec72f1 [microNPU] Enable network tests for U65 256 mac variant (#10159)
add e94e83d [ETHOSN] Drop back to Ethos(TM)-N release 21.08 (#10157)
add cbf6468 [Relay] Align strided slice shape functions (#10155)
new 89aa4fe Upgrade tensorflow to version to 2.6.x
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 (89bc502)
\
N -- N -- N refs/heads/ci-docker-staging (89aa4fe)
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/ping_reviewers.yml | 21 +
CMakeLists.txt | 1 +
Jenkinsfile | 4 +-
apps/android_camera/app/src/main/jni/build.sh | 3 +-
apps/android_deploy/app/src/main/jni/build.sh | 3 +-
apps/android_rpc/app/src/main/jni/build.sh | 3 +-
apps/extension/src/tvm_ext.cc | 2 +-
apps/microtvm/ethosu/requirements.txt | 4 +-
apps/microtvm/reference-vm/base-box-tool.py | 11 +-
apps/microtvm/reference-vm/zephyr/Vagrantfile | 2 +-
.../zephyr/base-box/base_box_provision.sh | 6 +-
.../reference-vm/zephyr/base-box/base_box_setup.sh | 11 +-
.../reference-vm/zephyr/base-box/base_box_test.sh | 7 +-
.../zephyr/template_project/microtvm_api_server.py | 9 +-
docker/Dockerfile.ci_qemu | 1 +
docker/install/ubuntu_init_zephyr_project.sh | 51 +-
.../install/ubuntu_install_ethosn_driver_stack.sh | 2 +-
docker/install/ubuntu_install_tensorflow.sh | 2 +-
docker/install/ubuntu_install_zephyr.sh | 15 +-
...hyr_project.sh => ubuntu_install_zephyr_sdk.sh} | 45 +-
docs/contribute/code_review.rst | 8 +
gallery/how_to/work_with_microtvm/micro_ethosu.py | 2 +-
include/tvm/auto_scheduler/measure.h | 8 +-
include/tvm/runtime/object.h | 2 +
include/tvm/runtime/packed_func.h | 203 +++++---
include/tvm/runtime/registry.h | 7 +-
include/tvm/tir/usmp/utils.h | 88 +++-
jvm/native/linux-x86_64/pom.xml | 65 ++-
jvm/native/osx-x86_64/pom.xml | 64 ++-
.../src/main/native/org_apache_tvm_native_c_api.cc | 2 +-
python/tvm/auto_scheduler/measure.py | 28 +-
python/tvm/autotvm/measure/measure_methods.py | 59 ++-
python/tvm/autotvm/tuner/tuner.py | 6 +-
python/tvm/contrib/cutlass/build.py | 31 +-
python/tvm/contrib/cutlass/conv2d_profiler.py | 18 +-
python/tvm/contrib/cutlass/gen_conv2d.py | 71 ++-
python/tvm/contrib/cutlass/gen_tensor_op.py | 1 +
python/tvm/contrib/cutlass/library.py | 10 +
python/tvm/contrib/ethosu/cascader/__init__.py | 3 +
.../contrib/ethosu/cascader/cascader_options.py | 61 +++
.../tvm/contrib/ethosu/cascader/pareto.py | 39 +-
python/tvm/contrib/ethosu/cascader/plan.py | 167 +++++++
.../tvm/contrib/ethosu/cascader/plan_generator.py | 51 ++
.../tvm/contrib/ethosu/cascader/tensor_config.py | 206 ++++++++
python/tvm/meta_schedule/schedule_rule/__init__.py | 3 +
python/tvm/relay/analysis/analysis.py | 16 +
python/tvm/relay/backend/contrib/ethosu/codegen.py | 139 +++---
.../tvm/relay/backend/contrib/ethosu/legalize.py | 82 ++++
.../relay/backend/contrib/ethosu/te/convolution.py | 9 +-
.../backend/contrib/ethosu/tir/convolution.py | 2 +-
python/tvm/relay/backend/contrib/ethosu/util.py | 14 +
python/tvm/relay/frontend/onnx.py | 23 +-
python/tvm/relay/op/_transform.py | 66 ++-
python/tvm/relay/op/contrib/cmsisnn.py | 19 +-
python/tvm/relay/op/contrib/cutlass.py | 32 +-
python/tvm/relay/op/contrib/ethosu.py | 152 ++++++
python/tvm/relay/op/strategy/cuda.py | 31 +-
python/tvm/relay/op/strategy/generic.py | 4 +-
python/tvm/runtime/object.py | 2 +-
python/tvm/script/parser.py | 32 +-
python/tvm/script/tir/ty.py | 23 +-
python/tvm/tir/usmp/utils.py | 47 +-
python/tvm/topi/cuda/__init__.py | 2 +-
...onv2d_transpose_nchw.py => conv2d_transpose.py} | 14 +-
python/tvm/topi/nn/conv2d_transpose.py | 6 +
src/auto_scheduler/measure.cc | 18 +-
src/contrib/ethosu/cascader/cascader_options.cc | 59 +++
src/contrib/ethosu/cascader/cascader_options.h | 71 +++
src/contrib/ethosu/cascader/pareto.cc | 140 ++++++
src/contrib/ethosu/cascader/pareto.h | 73 +++
src/contrib/ethosu/cascader/plan.cc | 112 +++++
src/contrib/ethosu/cascader/plan.h | 187 ++++++++
src/contrib/ethosu/cascader/plan_generator.cc | 529 +++++++++++++++++++++
src/contrib/ethosu/cascader/plan_generator.h | 108 +++++
src/contrib/ethosu/cascader/tensor_config.cc | 177 +++++++
src/contrib/ethosu/cascader/tensor_config.h | 226 +++++++++
src/ir/op.cc | 8 +-
src/meta_schedule/mutator/mutate_unroll.cc | 1 -
src/meta_schedule/schedule_rule/auto_inline.cc | 5 +-
.../schedule_rule/random_compute_location.cc | 5 +-
src/printer/tvmscript_printer.cc | 126 ++++-
src/relay/analysis/extract_fake_quantized_ops.cc | 80 ++++
.../backend/contrib/cmsisnn/extract_constants.cc | 125 +++--
.../contrib/cmsisnn/scalar_to_tensor_constant.cc | 204 ++++++++
src/relay/backend/contrib/cutlass/codegen.cc | 93 +++-
src/relay/backend/te_compiler.cc | 2 +-
src/relay/op/contrib/ethosu/convolution.cc | 17 +-
src/relay/op/nn/nn.cc | 12 -
src/relay/op/tensor/transform.cc | 4 +-
.../transforms/fake_quantization_to_integer.cc | 109 ++---
...xpr_subst.cc => fake_quantization_to_integer.h} | 39 +-
src/relay/transforms/transform_layout.h | 37 +-
src/runtime/c_runtime_api.cc | 32 +-
src/runtime/opencl/opencl_common.h | 48 ++
src/runtime/opencl/opencl_device_api.cc | 15 +
src/runtime/opencl/opencl_module.cc | 7 +
src/runtime/registry.cc | 12 +-
src/runtime/rpc/rpc_local_session.cc | 9 +-
src/runtime/vm/executable.cc | 4 +
src/target/generic_func.cc | 18 +-
src/target/source/intrin_rule_cuda.cc | 2 +-
src/target/source/literal/cuda_half_t.h | 67 ++-
src/tir/schedule/analysis.h | 23 +-
src/tir/schedule/analysis/analysis.cc | 85 ++--
src/tir/schedule/concrete_schedule.cc | 4 +-
src/tir/schedule/concrete_schedule.h | 6 +-
src/tir/schedule/instruction_traits.h | 4 +-
src/tir/schedule/primitive.h | 1 +
src/tir/schedule/primitive/blockize_tensorize.cc | 6 +-
src/tir/schedule/primitive/cache_read_write.cc | 6 +-
src/tir/schedule/primitive/compute_at.cc | 7 +-
src/tir/schedule/primitive/compute_inline.cc | 8 +-
src/tir/schedule/primitive/for_kind.cc | 6 +-
src/tir/schedule/primitive/get_block_loop.cc | 6 +-
src/tir/schedule/primitive/reduction.cc | 6 +-
src/tir/schedule/trace.cc | 13 +-
src/tir/schedule/traced_schedule.h | 4 +-
src/tir/usmp/algo/greedy.cc | 2 +-
src/tir/usmp/transform/assign_pool_info.cc | 9 +-
src/tir/usmp/utils.cc | 32 +-
.../python/contrib/test_cmsisnn/test_binary_ops.py | 175 +++++--
tests/python/contrib/test_cmsisnn/test_conv2d.py | 60 +--
.../contrib/test_cmsisnn/test_extract_constants.py | 67 +--
.../contrib/test_cmsisnn/test_fully_connected.py | 26 +-
.../test_cmsisnn/test_generate_constants.py | 1 -
tests/python/contrib/test_cmsisnn/test_networks.py | 9 +-
tests/python/contrib/test_cmsisnn/test_pooling.py | 28 +-
.../test_cmsisnn/test_scalar_to_tensor_constant.py | 187 ++++++++
tests/python/contrib/test_cmsisnn/test_softmax.py | 27 +-
tests/python/contrib/test_cmsisnn/utils.py | 23 +
tests/python/contrib/test_cutlass.py | 238 ++++++---
tests/python/contrib/test_ethosn/test_addition.py | 2 +-
.../contrib/test_ethosn/test_fullyconnected.py | 2 +-
.../contrib/test_ethosu/cascader/conftest.py | 69 +++
tests/python/contrib/test_ethosu/cascader/infra.py | 224 +++++----
.../contrib/test_ethosu/cascader/test_pareto.py | 149 ++++++
.../contrib/test_ethosu/cascader/test_plan.py | 244 ++++++++++
.../test_ethosu/cascader/test_plan_generator.py | 180 +++++++
.../test_ethosu/cascader/test_tensor_config.py | 110 +++++
tests/python/contrib/test_ethosu/infra.py | 3 +-
tests/python/contrib/test_ethosu/test_codegen.py | 39 ++
.../contrib/test_ethosu/test_layout_optimizer.py | 85 ++++
tests/python/contrib/test_ethosu/test_legalize.py | 129 +++++
tests/python/contrib/test_ethosu/test_networks.py | 5 +-
.../contrib/test_ethosu/test_replace_conv2d.py | 363 ++++++++++----
.../contrib/test_ethosu/test_type_inference.py | 26 +
tests/python/contrib/test_popen_pool.py | 18 -
tests/python/frontend/onnx/test_forward.py | 6 +
.../test_analysis_extract_fake_quantized_ops.py | 133 ++++++
tests/python/relay/test_any.py | 56 ++-
tests/python/relay/test_auto_scheduler_tuning.py | 2 +-
tests/python/relay/test_backend_graph_executor.py | 8 +
tests/python/relay/test_op_level1.py | 30 +-
tests/python/relay/test_op_level2.py | 38 +-
tests/python/relay/test_pass_alter_op_layout.py | 13 +
tests/python/relay/test_vm.py | 62 +++
tests/python/unittest/test_ci.py | 134 +++++-
.../test_meta_schedule_mutator_mutate_tile_size.py | 2 +-
.../unittest/test_tir_schedule_compute_at.py | 52 +-
.../python/unittest/test_tir_schedule_for_kind.py | 61 +++
tests/python/unittest/test_tvmscript_roundtrip.py | 47 ++
tests/scripts/ping_reviewers.py | 232 +++++++++
web/emcc/tvmjs_support.cc | 14 +-
163 files changed, 7234 insertions(+), 1275 deletions(-)
create mode 100644 .github/workflows/ping_reviewers.yml
copy docker/install/{ubuntu_init_zephyr_project.sh => ubuntu_install_zephyr_sdk.sh} (51%)
create mode 100644 python/tvm/contrib/ethosu/cascader/cascader_options.py
copy docker/install/ubuntu_install_rocm.sh => python/tvm/contrib/ethosu/cascader/pareto.py (57%)
mode change 100755 => 100644
create mode 100644 python/tvm/contrib/ethosu/cascader/plan.py
create mode 100644 python/tvm/contrib/ethosu/cascader/plan_generator.py
create mode 100644 python/tvm/contrib/ethosu/cascader/tensor_config.py
rename python/tvm/topi/cuda/{conv2d_transpose_nchw.py => conv2d_transpose.py} (97%)
create mode 100644 src/contrib/ethosu/cascader/cascader_options.cc
create mode 100644 src/contrib/ethosu/cascader/cascader_options.h
create mode 100644 src/contrib/ethosu/cascader/pareto.cc
create mode 100644 src/contrib/ethosu/cascader/pareto.h
create mode 100644 src/contrib/ethosu/cascader/plan.cc
create mode 100644 src/contrib/ethosu/cascader/plan.h
create mode 100644 src/contrib/ethosu/cascader/plan_generator.cc
create mode 100644 src/contrib/ethosu/cascader/plan_generator.h
create mode 100644 src/contrib/ethosu/cascader/tensor_config.cc
create mode 100644 src/contrib/ethosu/cascader/tensor_config.h
create mode 100644 src/relay/analysis/extract_fake_quantized_ops.cc
create mode 100644 src/relay/backend/contrib/cmsisnn/scalar_to_tensor_constant.cc
copy src/relay/transforms/{expr_subst.cc => fake_quantization_to_integer.h} (53%)
create mode 100644 tests/python/contrib/test_cmsisnn/test_scalar_to_tensor_constant.py
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_pareto.py
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_plan.py
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_plan_generator.py
create mode 100644 tests/python/contrib/test_ethosu/cascader/test_tensor_config.py
create mode 100644 tests/python/relay/test_analysis_extract_fake_quantized_ops.py
create mode 100755 tests/scripts/ping_reviewers.py
[tvm] 01/01: Upgrade tensorflow to version to 2.6.x
Posted by le...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
leandron pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 89aa4fe284f2b17a19585ffdc5b96cf7a620122d
Author: Ophir Frish <op...@arm.com>
AuthorDate: Thu Jan 27 12:28:30 2022 +0200
Upgrade tensorflow to version to 2.6.x
Upgrade the following versions:
keras - from 2.4.3 to 2.6
tensorflow - from 2.4.2 to 2.6.2
h5py - from version < 3.0 to version 3.1.0
---
docker/install/ubuntu_install_tensorflow.sh | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/docker/install/ubuntu_install_tensorflow.sh b/docker/install/ubuntu_install_tensorflow.sh
index 8a51fbb..eaf89ff 100755
--- a/docker/install/ubuntu_install_tensorflow.sh
+++ b/docker/install/ubuntu_install_tensorflow.sh
@@ -21,6 +21,6 @@ set -u
set -o pipefail
pip3 install \
- "h5py<3.0" \
- keras==2.4.3 \
- tensorflow==2.4.2
+ "h5py==3.1.0" \
+ keras==2.6 \
+ tensorflow==2.6.2