You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by ar...@apache.org on 2021/04/29 04:31:46 UTC
[tvm] branch ci-docker-staging updated (9941632 -> a3f172e)
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a change to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git.
omit 9941632 update ci_qemu
omit 7241c7b comment
omit ca7d394 Merge branch 'update-zephyr-2.5' of github.com:mehrdadh/tvm into update-zephyr-2.5
omit 9dc379b fix packer log
omit ede42f6 remove debug mode
omit 6cf1f46 update ci script
omit d55741a nit
omit 927ba46 remove debugger
omit 86e98e3 cleanup
omit 92360f6 cleanup
omit f8002d4 fix buffer size
omit bfc146b7 Merge remote-tracking branch 'areusch/update-zephyr-2.5' into update-zephyr-2.5
omit 9d49771 update to zephyr 2.5
omit e18f023 size down ring buf, shouldn't need to be so large
omit 5d4ab58 fix transport with debug false
omit 9244303 add qemu debugging
omit 09288ca always create packer.log
omit 31b9287 fix stack size
omit 5204e2d unbreak test_zephyr
omit 0e5b51b update to zephyr 2.5
add 3825161 [CodeGen][OpenCL] Limit OpenCL built-in vector lanes to 2, 3, 4, 8, 16. (#7777)
add 46c4de4 [ARITH] Subspace division (#7760)
add f8c44e2 [microTVM] Fix RVM onnx dependency and Zephyr document update (#7774)
add b95803f [Profiling,VM] Profiling interface for VM and Graph Runtime (#7624)
add 8e35840 [CI] Rust CI Changes (#7773)
add df52388 Fix compilation errors with clang 11 (#7783)
add 7b43db1 [Hexagon] Reenable compilation of TVM runtime for Hexagon (#7784)
add 43c61a2 add the --net=host cmd line arg to the docker/bash.it script (#7780)
add ca0f928 [ONNX] Dynamic Gather (#7787)
add d12dd95 [TVMC] Separate model loading from model compilation in TVMC. (#7739)
add 861eefd5 [docs] Getting Started With TVM: Tensor Expressions (#7768)
add 1c1a2b5 [TVMC] Allow direct numpy inputs to run_module (#7788)
add 7e68b4d [PatternMatcher] Support matching tuples, call nodes, and functions with variable numbers of inputs (#7754)
add 7071fda Disable Rust CI (#7793)
add 1f59139 [Target] Fix empty target and host for autotvm task (#7791)
add d31d048 [AutoScheduler] Add task.desc for its function name (#7794)
add 91311b3 [Relay]Frontend][Onnx] Remove pop that interferes with nested loops. (#7781)
add 2f109a7 [microTVM] Update Zephyr 2.5 (#7786)
add 4142abc [µTVM] Try to fix qemu hangs in the CI #7590 (#7769)
add f0fddc8 [CI] docker images build script cmd line args optional (#7776)
add 32d80d6 [docs] Getting Started with TVM: Auto Tuning with Python (#7767)
add ebba196 ONNX bitshfit (#7800)
add 0d302b6 [FIX] tvm.testing.parametrize_targets documentation for arguments does not match what it is acutally using. (#7778)
add 1386c48 [µTVM] apps: Fix Zephyr code example for STM32F746 boards (#7772)
add 417c598 [TVMC] Runner.py Updates (#7779)
add 2d3f7816 [ONNX] Initial work to import pre-quantized ONNX Models (#7802)
add 3ce74f0 [FIX] Make HashCombine stable across platforms (#7801)
add bdb708a [COMMUNITY] @kevinthesun -> PMC (#7803)
add bf0f87d [M1b] Scaffolding ScheduleState data structure (#7765)
add e426458 [TVMC][VitisAI] Enable Vitis AI target through TVMC (#7577)
add 648f53a [Rust] Make TVM Rust bindings installable via Cargo. (#7503)
add f2a5b3b Added missing include file (#7808)
add 24e62ca introduce pass lower_init_block (#7806)
add 4d13733 [microTVM] Zephyr: RISCV support for Zephyr QEMU RISCV-32/64 (#7804)
add 461d06e [TF frontend][bugfix]Avoid making a new node when already has span info (#7789)
add dec51c5 Add logical_not shape registration. (#7820)
add 5bc1cec [Vulkan] Support uniform buffer object for passing many scalar arguments (#7717)
add ab0dc2e Revert "[Vulkan] Support uniform buffer object for passing many scalar arguments (#7717)" (#7821)
add f38ae65 [ONNX] Support optional outputs for ONNX nodes (#7818)
add fc0a48f fix compiling warning in simplify_expr.h (#7828)
add bf862d4 [BugFix] Fix the race condition issue of packed func. (#7246). (#7619)
add 81afb14 [DOC] Grammar fix (#7824)
add eb00a03 Fix Metal accuracy problem caused by <dtype>3 vectors usage (#7830)
add ef68e20 [TVMC] --disable-pass option added to compile mode (#7816)
add e992dcc [COMMUNITY] Bohan Hou -> reviewer (#7837)
add 5c7ea7c [COMMUNITY] Siyuan Feng -> reviewer (#7836)
add 9782e6e [µTVM] Add support for mps2_an521 board (#7813)
add 7f56726 [TensorIR] [Script] adding support for opaque block (#7829)
add ce86454 [RUNTIME] Add clear() function in tvm::Map class (#7826)
add 90dce48 [Topi & Relay] Add quantization support for the vision transform model in GPU (#7814)
add 1e9c1bf [Relay][Pass] SimplifyCastLike/Cast and ConcretizeFullLikeRewrite rewrites for SimplifyExpr (#7827)
add ced4cee Misc. improvements to documentation/build setup for first-time builds. (#7840)
add 2e32f36 [FIX] Fix howto_deploy (#7841)
add 3673cab [ONNX] Make input shape immutable (#7844)
add 303a2f0 [BugFix] Print doubles with precision 17 in SaveJSON and TVM script printer (#7846)
add 390b4d1 [TOPI, Relay] A new NMS op variant for ONNX NMS / TF Combined NMS (#7796)
add 36b7dd9 [BYOC][TVMC] bugfix: disabled_pass -> disable_pass (#7850)
add b24fbe7 Fix PyTorch matmul conversion when given (2-dim, N-dim) input pair (#7845)
add cc7f529 [ConvertLayout] Squeeze and reduce ops (#7835)
add afda9b9 thread local handle for rocblas (#7851)
add 2968c9a Allow microTVM Reference VM to be launched when TVM is a submodule. (#7854)
add 1ebfafd Fix Zephyr flashing on physical hardware, busted in #7813 (#7853)
add f57830b [FIX] Fix RPC for the VM (#7810)
add 6ed37ef Fix typos in comments (#7862)
add aa9cb63 [Vulkan] Support uniform buffer object for passing many scalar arguments (Take 2) (#7833)
add cc79e8f [TIR] Add a new intrinsic count leading zeros for LLVM and SPIR-V (#7825)
add 6aefc26 [TensorIR][M1c] LCA detector (#7848)
add 899bc06 [METAL] Fix issue with GPU fails (#7819)
add e082ef5 [TOPI][SPIRV] Cast to float32 not float64 before log2 in sort/scan (#7669)
add 6d0386b [Hotfix] typo in Vulkan runtime change causing severe perf regression (#7871)
add 2b690ad [TensorIR][M1b] Schedule class (#7847)
add 76eb16f [µTVM] Zephyr: Add STM32F746 disco board as a test platform (#7863)
add 9a72ba3 [frontend][tflite] float16 quant support (#7736)
add 1fb32b0 [TIR] An analysis pass to calculate workspace size for primfuncs (#7859)
add 6981839 [Relay] Recursive destructor call replaced with non-recursive for Call nodes. (#7832)
add 8e25576 [VTA] Update vta-hw dependency (#7874)
add e67c5b7 [BYOC][ACL] ACL migrated to v21.02 (#7649)
add ee5da50 [µTVM] Zephyr: Add MPS2-AN521 board as a test platform (#7864)
add 5ae0ef0 [TensorIR][PASS][M1c] PlanUpdateBufferAllocationLocation (#7873)
add d3e6227 [ONNX] Fix more upstream tests (#7842)
add fbdffeb Protect child process enumeration in AutoTVM (#7887)
add d0a0194 [VTA][OpenCL] intelfocl (#6126)
add bd2520f [PROFILER] Add CSV output to profiler (#7797)
add 78657e1 [Relay] Add support for relay expressions as pad value for static pad (#7860)
add 8bd857d [RPC][REFACTOR] Use PopenWorker to handle RPC Server. (#7889)
add 935a7ad Add support for the quantized RESIZE_BILINEAR operator to relay TFLite frontend (#7866)
add f28c75f [Frontend][Tensorflow] Support SAME padding for dynamic h, w when stride == 1 (#7885)
add 1c71a06 [ONNX][TOPI][RELAY] Resize refactor (#7883)
add 46e0634 [Runtime] Driver version + consistent clock speed units (#7867)
add 9514e9e [Docs] Update Dev. Doc. on how to add a new relay operator (#7893)
add 060e001 [RPC] microtvm: fix RPC large transfer size issue (#7838)
add 8a74388 [Relay][ONNX] 1-D global and adaptive pooling. (#7906)
add 0e2d5ea [ONNX] Support NMS Center Box (#7900)
add a33eff5 Update ICHECK error message with link to documentation page. (#7869)
add 83baec3 Bring back GraphRuntimeFactory loader for now. (#7868)
add 373bac2 [Relay] Shape func fix for all_class_nms and where op (#7910)
add de0bff8 [ONNX] Support importing Conv with missing attributes (#7899)
add 0b24cbf Remove unnecessary bracelet around make_int (#7907)
add 4467a9c RelayTextPrinter is now non-recursive. ExpandDataflow refactored (#7817)
add c7ac5ee [µTVM] Clone Zephyr 2.5.0 from maintenance branch (#7891)
add 60c170e [ConvertLayout] Keep span in ConvertLayout (#7895)
add 251f571 [Target][Lowering] Update Op Intrinsic Lowering Mechanism And Intrinsic Lowering Pass (#7809)
add fad10d7 [Frontend][Tensorflow] SelectV2 and BroadcastArgs op support for tf2 models (#7901)
add a741652 [TIR][SPIR-V] Fix computing clz on int64 input for vulkan (#7913)
add ed16f07 [TE] Fix bug if find a loop in compute_at attach path (#7898)
add f92d7fc [BugFix]: Convert tuple to int (#7880)
add 54fdcc5 Enable StackVM in AutoTVM (#7897)
add 82fecbf [CodeGenC] Fix bugs when calling extern functions (#7911)
add f681359 [FIX] skip_conv_layers will affect quantization of nn.dense (#7795)
add dac7668 Remove pointer arithmetic in StorageObj::AllocNDArray (#7890)
add 09df4ed [Tensorize] Fix compute reusing (#7920)
add dee3133 [TensorIR][PASS] CompactBufferAllocation (#7923)
add 8fce895 [TOPI][RELAY][ONNX] Scatter ND (#7927)
add 7eb2bad Use new SBT Debian Repo before bintray is shutdown (#7926)
add 2129f88 [DOCS] Remove stale Auto TensorCore CodeGen tutorial (#7924)
add aa2b096 [RUNTIME][BUGFIX] Fix DSO module problem when its parent get destructed. (#7918)
add 7a06351 [microTVM] Refactor zephyr installation + Update Zephyr RVM doc (#7915)
new a3f172e Rev ci-qemu container to v0.04.
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 (9941632)
\
N -- N -- N refs/heads/ci-docker-staging (a3f172e)
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:
.gitignore | 5 +
3rdparty/vta-hw | 2 +-
CMakeLists.txt | 6 -
CONTRIBUTORS.md | 10 +-
Jenkinsfile | 5 +-
Makefile | 2 +-
NEWS.md | 0
apps/bundle_deploy/crt_config/crt_config.h | 3 +
apps/howto_deploy/Makefile | 3 +-
apps/howto_deploy/tvm_runtime_pack.cc | 3 +
apps/microtvm/reference-vm/base-box-tool.py | 88 +-
apps/microtvm/reference-vm/zephyr/README.md | 37 +
apps/microtvm/reference-vm/zephyr/Vagrantfile | 4 +-
.../microtvm/reference-vm/zephyr/base-box/setup.sh | 8 +-
apps/microtvm/reference-vm/zephyr/setup.sh | 4 +
.../boards/{nucleo_f746zg.conf => mps2_an521.conf} | 8 +-
.../zephyr/demo_runtime/boards/nucleo_f746zg.conf | 2 +-
.../zephyr/demo_runtime/boards/qemu_riscv32.conf | 18 +-
.../zephyr/demo_runtime/boards/qemu_riscv64.conf | 16 +-
.../{nucleo_f746zg.conf => stm32f746g_disco.conf} | 8 +-
.../zephyr/demo_runtime/qemu-hack/qemu-system-arm | 1 +
.../zephyr/demo_runtime/qemu-hack/qemu-system-i386 | 5 +
.../demo_runtime/qemu-hack/qemu-system-riscv32 | 1 +
.../demo_runtime/qemu-hack/qemu-system-riscv64 | 1 +
apps/microtvm/zephyr/demo_runtime/src/main.c | 14 +-
cmake/modules/Hexagon.cmake | 48 +-
cmake/modules/VTA.cmake | 8 +
docker/Dockerfile.ci_qemu | 1 +
docker/README.md | 36 +-
docker/bash.sh | 15 +-
docker/build.sh | 58 +-
docker/install/ubuntu1804_install_llvm.sh | 2 +-
...is_ai_core.sh => ubuntu_init_zephyr_project.sh} | 20 +-
docker/install/ubuntu_install_arm_compute_lib.sh | 4 +-
docker/install/ubuntu_install_core.sh | 8 +-
docker/install/ubuntu_install_llvm.sh | 2 +-
docker/install/ubuntu_install_sbt.sh | 3 +-
docker/install/ubuntu_install_vitis_ai_core.sh | 0
docker/install/ubuntu_install_zephyr.sh | 10 +-
docs/README.txt | 3 +-
docs/conf.py | 2 +-
docs/contribute/pull_request.rst | 23 +-
docs/deploy/vitis_ai.rst | 78 +-
docs/dev/relay_add_op.rst | 379 +++++++--
docs/dev/runtime.rst | 2 +-
docs/errors.rst | 72 ++
docs/index.rst | 1 +
docs/install/from_source.rst | 4 +-
docs/langref/relay_expr.rst | 8 +-
docs/langref/relay_pattern.rst | 16 +
include/tvm/arith/iter_affine_map.h | 30 +
include/tvm/auto_scheduler/search_task.h | 6 +-
include/tvm/relay/attrs/image.h | 14 +
include/tvm/relay/attrs/nn.h | 29 +-
include/tvm/relay/attrs/transform.h | 5 +-
include/tvm/relay/attrs/vision.h | 11 +-
include/tvm/relay/expr.h | 7 +
include/tvm/relay/expr_functor.h | 103 ++-
include/tvm/runtime/container.h | 7 +
include/tvm/runtime/device_api.h | 3 +-
include/tvm/runtime/logging.h | 5 +-
include/tvm/runtime/object.h | 15 +
include/tvm/runtime/profiling.h | 186 ++++
include/tvm/tir/analysis.h | 15 +
include/tvm/tir/expr.h | 1 +
include/tvm/tir/op.h | 1 +
include/tvm/tir/op_attr_types.h | 13 +-
include/tvm/tir/schedule/block_scope.h | 271 ++++++
include/tvm/tir/schedule/schedule.h | 227 +++++
include/tvm/tir/schedule/state.h | 216 +++++
include/tvm/tir/stmt.h | 21 +-
include/tvm/tir/transform.h | 60 ++
include/tvm/topi/nn/pooling.h | 15 +
include/tvm/topi/transform.h | 2 +-
python/tvm/_ffi/runtime_ctypes.py | 206 ++++-
python/tvm/arith/__init__.py | 2 +-
python/tvm/arith/iter_affine_map.py | 45 +
python/tvm/auto_scheduler/measure.py | 10 +-
python/tvm/auto_scheduler/relay_integration.py | 17 +-
python/tvm/auto_scheduler/search_task.py | 6 +
python/tvm/autotvm/measure/local_executor.py | 2 +-
python/tvm/autotvm/measure/measure_methods.py | 8 +-
python/tvm/autotvm/task/task.py | 4 +-
python/tvm/autotvm/task/topi_integration.py | 11 +-
python/tvm/contrib/debugger/debug_executor.py | 19 +
python/tvm/contrib/popen_pool.py | 3 +-
.../testing/batch_matmul.py => contrib/stackvm.py} | 41 +-
python/tvm/contrib/target/vitis_ai.py | 188 ++--
python/tvm/driver/tvmc/autotuner.py | 2 +-
python/tvm/driver/tvmc/common.py | 33 +-
python/tvm/driver/tvmc/compiler.py | 47 +-
python/tvm/driver/tvmc/composite_target.py | 29 +-
python/tvm/driver/tvmc/runner.py | 64 +-
python/tvm/error.py | 1 +
python/tvm/exec/rpc_server.py | 20 +-
python/tvm/ir/__init__.py | 2 +-
python/tvm/ir/op.py | 37 +
python/tvm/micro/contrib/zephyr.py | 92 +-
python/tvm/relay/dataflow_pattern/__init__.py | 5 +-
python/tvm/relay/frontend/onnx.py | 586 ++++++-------
python/tvm/relay/frontend/pytorch.py | 45 +-
python/tvm/relay/frontend/tensorflow.py | 54 +-
python/tvm/relay/frontend/tflite.py | 46 +-
python/tvm/relay/op/_tensor.py | 1 +
python/tvm/relay/op/_tensor_grad.py | 2 +-
python/tvm/relay/op/_transform.py | 14 +-
python/tvm/relay/op/contrib/arm_compute_lib.py | 13 +-
python/tvm/relay/op/contrib/ethosn.py | 8 +-
python/tvm/relay/op/contrib/vitis_ai.py | 108 ++-
python/tvm/relay/op/dyn/_transform.py | 33 +-
python/tvm/relay/op/dyn/image/_image.py | 14 +-
python/tvm/relay/op/image/_image.py | 18 +-
python/tvm/relay/op/image/image.py | 37 +-
python/tvm/relay/op/nn/_nn.py | 10 +
python/tvm/relay/op/nn/nn.py | 174 +++-
python/tvm/relay/op/op_attrs.py | 5 +
python/tvm/relay/op/strategy/cuda.py | 33 +-
python/tvm/relay/op/strategy/generic.py | 43 +-
python/tvm/relay/op/transform.py | 13 +-
python/tvm/relay/op/vision/_vision.py | 19 +
python/tvm/relay/op/vision/nms.py | 48 ++
python/tvm/relay/quantize/_annotate.py | 25 +
python/tvm/relay/quantize/_calibrate.py | 28 +
python/tvm/relay/quantize/quantize.py | 5 +-
python/tvm/relay/testing/tf.py | 2 +-
python/tvm/rpc/client.py | 2 +-
python/tvm/rpc/proxy.py | 6 +-
python/tvm/rpc/server.py | 206 ++---
python/tvm/rpc/testing.py | 69 ++
python/tvm/runtime/__init__.py | 1 +
python/tvm/runtime/module.py | 4 +
python/tvm/runtime/profiler_vm.py | 36 +-
.../batch_matmul.py => runtime/profiling.py} | 48 +-
python/tvm/runtime/vm.py | 39 +-
python/tvm/script/parser.py | 10 +-
python/tvm/script/scope_handler.py | 36 +-
python/tvm/target/__init__.py | 3 +-
python/tvm/target/intrin.py | 54 +-
python/tvm/target/target.py | 4 +
python/tvm/testing.py | 2 +-
python/tvm/tir/__init__.py | 5 +-
python/tvm/tir/analysis/analysis.py | 39 +-
python/tvm/tir/op.py | 19 +-
.../tvm/tir/schedule/__init__.py | 17 +-
.../tvm/tir/schedule/_ffi_api_schedule.py | 19 +-
python/tvm/tir/schedule/block_scope.py | 152 ++++
python/tvm/tir/schedule/schedule.py | 242 ++++++
python/tvm/tir/schedule/state.py | 185 ++++
python/tvm/tir/stmt.py | 19 +-
python/tvm/tir/transform/transform.py | 74 ++
python/tvm/topi/arm_cpu/tensor_intrin.py | 5 +-
python/tvm/topi/cuda/__init__.py | 2 +-
python/tvm/topi/cuda/batch_matmul.py | 147 ++++
python/tvm/topi/cuda/nms.py | 430 ++++++----
python/tvm/topi/cuda/scan.py | 11 +-
python/tvm/topi/cuda/scatter.py | 66 +-
python/tvm/topi/cuda/sort.py | 37 +-
python/tvm/topi/cuda/vision.py | 2 +-
python/tvm/topi/image/resize.py | 271 +++---
python/tvm/topi/math.py | 34 +
python/tvm/topi/scatter.py | 60 +-
python/tvm/topi/testing/adaptive_pool_python.py | 37 +-
python/tvm/topi/testing/batch_matmul.py | 12 +-
python/tvm/topi/testing/conv2d_hwcn_python.py | 2 +-
python/tvm/topi/vision/nms.py | 193 ++++-
python/tvm/topi/vision/nms_util.py | 282 ++++++
python/tvm/topi/x86/bitserial_dense.py | 2 +-
python/tvm/topi/x86/scatter.py | 60 +-
rust/tvm-graph-rt/Cargo.toml | 6 +-
rust/tvm-graph-rt/README.md | 20 +
rust/tvm-macros/Cargo.toml | 2 +-
rust/tvm-macros/README.md | 20 +
rust/tvm-rt/Cargo.toml | 10 +-
rust/tvm-rt/src/ndarray.rs | 4 +-
rust/tvm-sys/Cargo.toml | 11 +-
rust/tvm-sys/README.md | 28 +
rust/tvm-sys/build.rs | 136 ++-
rust/tvm-sys/src/byte_array.rs | 6 +-
rust/tvm-sys/src/lib.rs | 2 +-
rust/tvm/Cargo.toml | 6 +-
rust/tvm/README.md | 6 +-
src/arith/iter_affine_map.cc | 299 +++++++
src/auto_scheduler/search_task.cc | 8 +-
src/ir/op.cc | 8 +
src/node/serialization.cc | 4 +-
src/node/structural_hash.cc | 57 ++
src/printer/relay_text_printer.cc | 39 +-
src/printer/text_printer.h | 10 +-
src/printer/tvmscript_printer.cc | 4 +
src/relay/analysis/dependency_graph.cc | 6 +-
src/relay/backend/compile_engine.cc | 4 +-
.../backend/contrib/vitis_ai/config_vitis_ai.cc | 34 +
src/relay/ir/dataflow_matcher.cc | 107 ++-
src/relay/ir/dataflow_pattern_functor.cc | 18 +-
src/relay/ir/expr.cc | 58 ++
src/relay/ir/indexed_graph.cc | 18 +-
src/relay/op/dyn/image/resize.cc | 6 +-
src/relay/op/image/resize.cc | 6 +-
src/relay/op/make_op.h | 7 +-
src/relay/op/nn/nn.cc | 9 +-
src/relay/op/nn/pad.cc | 40 +-
src/relay/op/nn/pooling.cc | 132 +++
src/relay/op/tensor/reduce.cc | 44 +-
src/relay/op/tensor/transform.cc | 92 +-
src/relay/op/vision/nms.cc | 63 ++
src/relay/qnn/op/convolution.cc | 3 +-
src/relay/quantize/quantize.cc | 1 +
src/relay/quantize/realize.cc | 35 +
.../transforms/combine_parallel_batch_matmul.cc | 12 +-
src/relay/transforms/combine_parallel_dense.cc | 4 +-
src/relay/transforms/convert_layout.cc | 16 +-
src/relay/transforms/dynamic_to_static.cc | 7 +-
src/relay/transforms/fold_explicit_padding.cc | 8 +-
src/relay/transforms/forward_rewrite.cc | 2 +-
src/relay/transforms/pattern_utils.h | 2 +-
src/relay/transforms/simplify_expr.cc | 40 +
src/relay/transforms/simplify_expr.h | 2 +-
src/relay/transforms/transform_layout.h | 2 +-
src/runtime/c_runtime_api.cc | 10 +-
src/runtime/contrib/rocblas/rocblas.cc | 30 +-
src/runtime/contrib/vitis_ai/vitis_ai_runtime.cc | 13 +-
src/runtime/contrib/vitis_ai/vitis_ai_runtime.h | 4 +-
src/runtime/crt/common/crt_runtime_api.c | 35 +-
src/runtime/crt/host/crt_config.h | 4 +-
src/runtime/crt/host/main.cc | 9 +-
src/runtime/cuda/cuda_device_api.cc | 2 +
.../graph_executor/debug/graph_executor_debug.cc | 46 +
src/runtime/graph_executor/graph_executor.cc | 2 +
.../graph_executor/graph_executor_factory.cc | 11 +
src/runtime/hexagon/hexagon_module.cc | 2 +-
src/runtime/hexagon/sim/driver/CMakeLists.txt | 2 +-
src/runtime/library_module.cc | 37 +-
src/runtime/metal/metal_common.h | 45 +-
src/runtime/metal/metal_device_api.mm | 52 +-
src/runtime/metal/metal_module.mm | 5 +-
src/runtime/minrpc/minrpc_server.h | 62 ++
src/runtime/minrpc/rpc_reference.h | 12 +
src/runtime/opencl/opencl_common.h | 11 +
src/runtime/opencl/opencl_device_api.cc | 39 +-
src/runtime/profiling.cc | 353 ++++++++
src/runtime/registry.cc | 2 +-
src/runtime/rocm/rocm_device_api.cc | 2 +
src/runtime/rpc/rpc_device_api.cc | 15 +
src/runtime/rpc/rpc_endpoint.cc | 172 +++-
src/runtime/rpc/rpc_endpoint.h | 10 +
src/runtime/stackvm/stackvm_module.cc | 2 -
src/runtime/vm/memory_manager.cc | 9 +-
src/runtime/vm/profiler/vm.cc | 112 +--
src/runtime/vm/profiler/vm.h | 3 +-
src/runtime/vm/vm.cc | 32 +-
src/runtime/vulkan/vulkan.cc | 426 ++++++----
src/runtime/vulkan/vulkan_common.h | 13 +-
src/runtime/workspace_pool.cc | 1 -
src/support/utils.h | 52 +-
src/target/codegen.cc | 119 ++-
src/target/intrin_rule.cc | 134 +--
src/target/intrin_rule.h | 7 +-
src/target/llvm/codegen_amdgpu.cc | 6 +-
src/target/llvm/codegen_nvptx.cc | 6 +-
src/target/llvm/intrin_rule_hexagon.cc | 54 +-
src/target/llvm/intrin_rule_llvm.cc | 146 ++--
src/target/llvm/intrin_rule_llvm.h | 10 +-
src/target/llvm/intrin_rule_nvptx.cc | 73 +-
src/target/llvm/intrin_rule_rocm.cc | 95 ++-
src/target/source/codegen_c.cc | 14 +-
src/target/source/codegen_c_host.cc | 17 +-
src/target/source/codegen_c_host.h | 6 +-
src/target/source/codegen_cuda.cc | 2 +-
src/target/source/codegen_metal.cc | 11 +
src/target/source/codegen_opencl.cc | 4 +-
src/target/source/intrin_rule_aocl.cc | 69 +-
src/target/source/intrin_rule_cuda.cc | 99 ++-
src/target/source/intrin_rule_metal.cc | 63 +-
src/target/source/intrin_rule_opencl.cc | 70 +-
src/target/source/intrin_rule_vhls.cc | 60 +-
src/target/spirv/build_vulkan.cc | 5 +-
src/target/spirv/codegen_spirv.cc | 31 +-
src/target/spirv/codegen_spirv.h | 3 +-
src/target/spirv/intrin_rule_spirv.cc | 122 ++-
src/target/spirv/ir_builder.cc | 31 +-
src/target/spirv/ir_builder.h | 32 +-
src/te/operation/tensorize.cc | 2 +-
src/te/schedule/schedule_dataflow_rewrite.cc | 3 +
src/tir/analysis/buffer_access_lca_detector.cc | 173 ++++
src/tir/analysis/calculate_workspace.cc | 78 ++
src/tir/analysis/var_touch.cc | 2 +-
src/tir/ir/script/script_complete.cc | 15 +-
src/tir/ir/stmt.cc | 14 +-
src/tir/op/op.cc | 2 +
src/tir/schedule/analysis.h | 62 ++
src/tir/schedule/analysis/analysis.cc | 94 ++
src/tir/schedule/analysis/verify.cc | 146 ++++
src/tir/schedule/block_scope.cc | 162 ++++
src/tir/schedule/concrete_schedule.cc | 203 +++++
src/tir/schedule/concrete_schedule.h | 244 ++++++
src/tir/schedule/schedule.cc | 127 +++
src/tir/schedule/state.cc | 870 +++++++++++++++++++
src/tir/schedule/utils.h | 93 ++
src/tir/transforms/compact_buffer_region.cc | 468 ++++++++++
src/tir/transforms/convert_blocks_to_opaque.cc | 104 +++
src/tir/transforms/lower_init_block.cc | 85 ++
src/tir/transforms/lower_intrin.cc | 60 +-
src/tir/transforms/lower_tvm_builtin.cc | 197 +++--
.../plan_update_buffer_allocation_location.cc | 169 ++++
tests/cpp/container_test.cc | 10 +
tests/cpp/{profiling.cc => profiling_test.cc} | 0
tests/cpp/relay_dismantler_test.cc | 76 ++
tests/cpp/relay_text_printer_test.cc | 64 ++
tests/cpp/support_test.cc | 13 +
tests/lint/check_file_type.py | 9 +-
tests/micro/zephyr/conftest.py | 14 +-
tests/micro/zephyr/test_zephyr.py | 18 +-
tests/python/contrib/test_cblas.py | 30 +-
.../python/contrib/test_vitis_ai/infrastructure.py | 7 +-
tests/python/driver/tvmc/conftest.py | 3 +-
.../python/driver/tvmc/test_common.py | 32 +-
tests/python/driver/tvmc/test_compiler.py | 70 +-
tests/python/driver/tvmc/test_composite_target.py | 1 +
tests/python/driver/tvmc/test_runner.py | 8 +-
tests/python/frontend/onnx/test_forward.py | 161 ++--
tests/python/frontend/pytorch/test_forward.py | 31 +-
tests/python/frontend/tensorflow/test_forward.py | 90 +-
tests/python/frontend/tflite/test_forward.py | 529 ++++++++----
tests/python/integration/test_tuning.py | 4 +-
.../test_quantization_accuracy_for_vit.py | 148 ++++
tests/python/relay/dyn/test_dynamic_op_level4.py | 18 +-
tests/python/relay/test_any.py | 124 ++-
tests/python/relay/test_dataflow_pattern.py | 80 +-
tests/python/relay/test_op_level10.py | 14 +-
tests/python/relay/test_op_level2.py | 149 +++-
tests/python/relay/test_op_level3.py | 85 +-
tests/python/relay/test_op_level5.py | 103 ++-
tests/python/relay/test_pass_auto_quantize.py | 67 ++
tests/python/relay/test_pass_convert_op_layout.py | 200 +++++
tests/python/relay/test_pass_simplify_expr.py | 25 +
tests/python/relay/test_vm.py | 16 +-
tests/python/topi/python/test_topi_batch_matmul.py | 53 ++
tests/python/topi/python/test_topi_conv2d_hwcn.py | 13 +-
tests/python/topi/python/test_topi_image.py | 6 +-
tests/python/topi/python/test_topi_scatter.py | 70 +-
tests/python/topi/python/test_topi_vision.py | 112 +++
.../python/unittest/test_arith_iter_affine_map.py | 340 ++++++++
tests/python/unittest/test_node_reflection.py | 11 +
.../test_runtime_module_based_interface.py | 31 +-
.../python/unittest/test_runtime_module_export.py | 27 +-
tests/python/unittest/test_runtime_profiling.py | 59 ++
tests/python/unittest/test_runtime_rpc.py | 57 +-
tests/python/unittest/test_runtime_vm_profiler.py | 22 +-
.../python/unittest/test_target_codegen_c_host.py | 37 +
tests/python/unittest/test_target_codegen_spirv.py | 10 +
tests/python/unittest/test_target_target.py | 33 +-
tests/python/unittest/test_te_schedule.py | 28 +
.../python/unittest/test_te_schedule_tensorize.py | 14 +
.../test_tir_analysis_calculate_workspace.py | 106 +++
.../test_tir_analysis_detect_buffer_access_lca.py | 107 +++
tests/python/unittest/test_tir_block_scope.py | 145 ++++
tests/python/unittest/test_tir_intrin.py | 43 +
tests/python/unittest/test_tir_schedule_state.py | 352 ++++++++
.../python/unittest/test_tir_schedule_utilities.py | 115 +++
.../test_tir_transform_compact_buffer_region.py | 331 ++++++++
.../test_tir_transform_convert_blocks_to_opaque.py | 77 ++
.../test_tir_transform_lower_init_block.py | 53 ++
.../test_tir_transform_lower_tvm_builtin.py | 143 ++++
...sform_plan_update_buffer_allocation_location.py | 128 +++
tests/python/unittest/test_tvmscript_complete.py | 28 +-
tests/python/unittest/test_tvmscript_roundtrip.py | 36 +
tests/scripts/task_cpp_unittest.sh | 7 +-
tests/scripts/task_python_integration.sh | 1 +
tests/scripts/task_python_microtvm.sh | 3 -
tests/scripts/task_rust.sh | 14 +-
.../frontend/deploy_object_detection_pytorch.py | 5 +-
tutorials/get_started/auto_tuning_with_python.py | 475 +++++++++++
tutorials/get_started/relay_quick_start.py | 4 +-
tutorials/get_started/tensor_expr_get_started.py | 944 +++++++++++++++++----
tutorials/language/intrin_math.py | 9 +-
tutorials/micro/micro_tflite.py | 64 +-
tutorials/optimize/opt_matmul_auto_tensorcore.py | 544 ------------
vta/python/vta/autotvm.py | 2 +-
vta/python/vta/environment.py | 13 +-
vta/python/vta/program_bitstream.py | 14 +-
vta/python/vta/rpc_client.py | 14 +-
vta/python/vta/testing/simulator.py | 8 +-
vta/python/vta/testing/utils.py | 2 +-
vta/python/vta/top/graphpack.py | 2 +-
vta/python/vta/top/op.py | 138 ++-
vta/python/vta/transform.py | 6 +-
vta/runtime/runtime.cc | 134 ++-
vta/runtime/runtime.h | 2 +
.../integration/test_benchmark_topi_conv2d.py | 2 +-
vta/tutorials/autotvm/tune_alu_vta.py | 320 +++++++
vta/tutorials/frontend/deploy_classification.py | 27 +-
vta/tutorials/vta_get_started.py | 6 +-
392 files changed, 18807 insertions(+), 4044 deletions(-)
mode change 100755 => 100644 NEWS.md
create mode 100644 apps/microtvm/reference-vm/zephyr/README.md
copy apps/microtvm/zephyr/demo_runtime/boards/{nucleo_f746zg.conf => mps2_an521.conf} (86%)
copy tests/scripts/task_python_microtvm.sh => apps/microtvm/zephyr/demo_runtime/boards/qemu_riscv32.conf (64%)
mode change 100755 => 100644
copy tests/scripts/task_python_microtvm.sh => apps/microtvm/zephyr/demo_runtime/boards/qemu_riscv64.conf (71%)
mode change 100755 => 100644
copy apps/microtvm/zephyr/demo_runtime/boards/{nucleo_f746zg.conf => stm32f746g_disco.conf} (86%)
create mode 120000 apps/microtvm/zephyr/demo_runtime/qemu-hack/qemu-system-arm
create mode 120000 apps/microtvm/zephyr/demo_runtime/qemu-hack/qemu-system-riscv32
create mode 120000 apps/microtvm/zephyr/demo_runtime/qemu-hack/qemu-system-riscv64
copy docker/install/{ubuntu_install_vitis_ai_core.sh => ubuntu_init_zephyr_project.sh} (77%)
mode change 100644 => 100755
mode change 100644 => 100755 docker/install/ubuntu_install_vitis_ai_core.sh
create mode 100644 docs/errors.rst
create mode 100644 include/tvm/tir/schedule/block_scope.h
create mode 100644 include/tvm/tir/schedule/schedule.h
create mode 100644 include/tvm/tir/schedule/state.h
copy python/tvm/{topi/testing/batch_matmul.py => contrib/stackvm.py} (60%)
create mode 100644 python/tvm/rpc/testing.py
copy python/tvm/{topi/testing/batch_matmul.py => runtime/profiling.py} (51%)
copy tests/scripts/task_python_microtvm.sh => python/tvm/tir/schedule/__init__.py (74%)
mode change 100755 => 100644
copy docker/install/ubuntu_install_vitis_ai_core.sh => python/tvm/tir/schedule/_ffi_api_schedule.py (75%)
create mode 100644 python/tvm/tir/schedule/block_scope.py
create mode 100644 python/tvm/tir/schedule/schedule.py
create mode 100644 python/tvm/tir/schedule/state.py
create mode 100644 python/tvm/topi/vision/nms_util.py
create mode 100644 rust/tvm-graph-rt/README.md
create mode 100644 rust/tvm-macros/README.md
create mode 100644 rust/tvm-sys/README.md
create mode 100644 src/tir/analysis/buffer_access_lca_detector.cc
create mode 100644 src/tir/analysis/calculate_workspace.cc
create mode 100644 src/tir/schedule/analysis.h
create mode 100644 src/tir/schedule/analysis/analysis.cc
create mode 100644 src/tir/schedule/analysis/verify.cc
create mode 100644 src/tir/schedule/block_scope.cc
create mode 100644 src/tir/schedule/concrete_schedule.cc
create mode 100644 src/tir/schedule/concrete_schedule.h
create mode 100644 src/tir/schedule/schedule.cc
create mode 100644 src/tir/schedule/state.cc
create mode 100644 src/tir/schedule/utils.h
create mode 100644 src/tir/transforms/compact_buffer_region.cc
create mode 100644 src/tir/transforms/convert_blocks_to_opaque.cc
create mode 100644 src/tir/transforms/lower_init_block.cc
create mode 100644 src/tir/transforms/plan_update_buffer_allocation_location.cc
rename tests/cpp/{profiling.cc => profiling_test.cc} (100%)
create mode 100644 tests/cpp/relay_dismantler_test.cc
create mode 100644 tests/cpp/relay_text_printer_test.cc
copy rust/tvm-sys/Cargo.toml => tests/python/driver/tvmc/test_common.py (57%)
create mode 100644 tests/python/nightly/quantization/test_quantization_accuracy_for_vit.py
create mode 100644 tests/python/unittest/test_runtime_profiling.py
create mode 100644 tests/python/unittest/test_tir_analysis_calculate_workspace.py
create mode 100644 tests/python/unittest/test_tir_analysis_detect_buffer_access_lca.py
create mode 100644 tests/python/unittest/test_tir_block_scope.py
create mode 100644 tests/python/unittest/test_tir_schedule_state.py
create mode 100644 tests/python/unittest/test_tir_schedule_utilities.py
create mode 100644 tests/python/unittest/test_tir_transform_compact_buffer_region.py
create mode 100644 tests/python/unittest/test_tir_transform_convert_blocks_to_opaque.py
create mode 100644 tests/python/unittest/test_tir_transform_lower_init_block.py
create mode 100644 tests/python/unittest/test_tir_transform_lower_tvm_builtin.py
create mode 100644 tests/python/unittest/test_tir_transform_plan_update_buffer_allocation_location.py
create mode 100644 tutorials/get_started/auto_tuning_with_python.py
delete mode 100644 tutorials/optimize/opt_matmul_auto_tensorcore.py
create mode 100644 vta/tutorials/autotvm/tune_alu_vta.py
[tvm] 01/01: Rev ci-qemu container to v0.04.
Posted by ar...@apache.org.
This is an automated email from the ASF dual-hosted git repository.
areusch pushed a commit to branch ci-docker-staging
in repository https://gitbox.apache.org/repos/asf/tvm.git
commit a3f172e0ff07d708aff82b3ac09560cf313fb2b7
Author: Andrew Reusch <ar...@octoml.ai>
AuthorDate: Wed Apr 28 21:30:00 2021 -0700
Rev ci-qemu container to v0.04.
---
Jenkinsfile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Jenkinsfile b/Jenkinsfile
index cbe2e99..0c5eecb 100644
--- a/Jenkinsfile
+++ b/Jenkinsfile
@@ -49,7 +49,7 @@ ci_gpu = "tlcpack/ci-gpu:v0.72"
ci_cpu = "tlcpack/ci-cpu:v0.73"
ci_wasm = "tlcpack/ci-wasm:v0.70"
ci_i386 = "tlcpack/ci-i386:v0.72-t0"
-ci_qemu = "tlcpack/ci-qemu:v0.03"
+ci_qemu = "areusch1/ci-qemu-staging:v0.04"
ci_arm = "tlcpack/ci-arm:v0.03"
// <--- End of regex-scanned config.