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 b60bc61 Flaky QEMU test
omit c5b415e Disable failing onnx cuda tests
omit 03c5917 flaky test
omit e2c40e6 Merge jenkinsfile
omit a345ad0 Add uses_gpu to onnx node tests
omit df1d4f6 add onnx to CPU tests
omit 60eca6f See if this fixes CI problem
add 8954968 Fix #8510 (#8511)
add 496f10b [Frontend][TENSORFLOW] Add support for unpack with dim 0
after tensorlist stack (#8558)
add 5a96a61 [Bugfix] fix android rpc app undefined reference problem
(#8530)
add 8d9df2d [TensorRT, BYOC] Handling a corner case in TRT RemoveDropout
pass (#8506)
add a17ee9f [BUGFIX] fix illegal memory access bug in reduce op schedule
by constriant threadIdx.y (#8566)
add 2fa26b3 Re-enable Compute library tests. (#8573)
add 774c0e5 [Test] Fix AutoScheduler test to cover Conv2D Winograd (#8539)
add fcbd2b6 fixenhance robustness of DefuseOps (#8564)
add 6b2cbfe [Contrib] Added default non-verbose to download_testdata(),
pass to download() (#8533)
add 92f9558 [Coreml] Fix Coreml Input Shape Handling (#8562)
add 74715f4 [AutoScheduler] Fix task extraction with TE compiler (#8560)
add b6b8269 add support for softmax and log_softmax with MIOpen (#8543)
add a993321 [TOPI][CUDA] minor change on assert statement in
conv2d_NCHWc_int8.cuda (#8554)
add 83ce7fe [TOPI] Fix `nn.pool*d` issue with 'vectorize' function and
add unit tests (#8541)
add 00ad44e [Bugfix] Fix #8536 Get Target When Heterogeneous Execution
(#8537)
add df06c58 [Bugfux] wasm32-standalone app repaired (#8563)
add cb395ff Disable pip cache when creating Docker images (#8575)
add 850abb0 [TOPI] Add transpose_a/b & dynamic shape support for batch
matmul (#8527)
add e39204e [Bugfix] Preserve IRModule type definition and imports in
NameMangleExtFuncs (#8523)
add 66b3cc9 [TIR] cast disparate floating point types for binary ops
(#8517)
add bef7bf9 [Refactor] Remove AttrStmt with storage_scope key (#8516)
add 88dd31b [VM] Bug fix for numpy scalar input in vm (#8553)
add 97f147c [Torch] Reduce testing time of LSTM tests (#8583)
add 8148028 [FIX][CI] hotfix check_grad perf regression (#8581)
add df96cba [Vulkan] Prioritize discrete GPUs as device_id=0. (#8588)
add 22c7d61 speed up reference resize kernel (#8592)
add ff71773 Delete pytest-results as part of CI workspace preparation.
(#8594)
add b7df355 use sizevar when convert any to tir (#8555)
add 12e805f Fix storage_access not visiting else branch (#8525)
add 2b94a7e [AOT][Stack Allocator] Fix Initial Memory Misalignment (#8487)
add c8a892b [Vulkan] Rewrote PointerValueTypeRewrite transform (#8528)
add 5012462 [TensorIR][M2a] Reduction Factoring (RFactor) (#8544)
add 2a8950b [TensorIR] Support for match_buffer from subregion (#8585)
add 7d8a774 [VTA] Recover rpc server support (#8604)
add 28de742 [Refactor] Unify the shared pass prefix between vm and graph
(#8526)
add 4b67dac [CUDA] Support multiple TIR-level dynamic shared memory
allocations (#8571)
add 887324f [TOPI][CUDA] Improve the performance of scatter_nd (#8479)
add 9f29e2a [BUILD] Add caching to CMake (#8373)
add 7653972 [Meta Schedule][M3a] Instruction and Trace (#8615)
add 3113388 Add support for AOT in external code generation tests (#8591)
add b3e832a [CI] Fix global pip cache disable change (#8590)
add 55916a2 [DOCS] Fix scipy docs inv (#8619)
add 47a5a3a [runtime] Remove unused parameter. (#8580)
add 49d5879 Introduce --interface-api={c,packed} parameter (#8280)
add f656a22 Docker env for Arm® Ethos™-U55 Port (#8514)
add 9b97bad [FIX,PROFILING] Add USE_PAPI configuration to config.cmake
(#8567)
add 3cb0e93 [Fix] Fix a typo in include/tvm/ir/function.h (#8617)
add 38fe522 [Relay][Quantization] Extend FakeQuantizationToInteger to
more ops (#8241)
add 804ba27 Fix test_external_codegen, broken by #8591 (#8630)
add 09e234d [DOCS] TVM install addenda for M1 Macs (#8568)
add 5140d90 Parametrize ONNX Unit tests (#8621)
add 4b9d43e [Refactor] Avoid Override Generic Op Strategy in "hls.py"
(#8614)
add d30e4ef [microTVM][RVM] Set the number of cores based on the VM
sizing (#8624)
add 96d10f8 [Target] Enable device querying for all targets. (#8602)
add 9dfcb22 [Runtime] Add graph_executor get_input_index API. (#8633)
add b9204cd [Relay] Change Default "opt_level" of Sequantial from 2 to 0
(#8634)
add d38bef5 [Target] Allow spaces in target attributes (#8587)
add 0ce7f6c [AMP] Disallow fp16 conversion for arange op (#8644)
add 40a9086 [microTVM][RVM] Fix platform name in base-box-tool (#8612)
add 4d2c5d5 [Target] Several minor corrections to the device property
query (#8651)
add 36bb629 [TEST] Refactor RPC test to isolate runs into a sub-function
(#8656)
add 5b9b16c Fix rust rt link (#8631)
add fe2cdf3 [Frontend][Pytorch] add suppport for
'aten::upsample_bicubic2d' (#8648)
add a495f95 [Bugfix][Target] Correct passing of target-queried bool/int
parameters (#8660)
add 26c2a9a [TensorRT] Add transpose_a/b for TensorRT batch_matmul (#8607)
add 874ea7a [Fix][Frontend][TOPI] minor bugs (#8622)
add cdfae39 [AutoScheduler] Fix deserization of workload registry entry
(#8662)
add 8302524 [TENSORIR] Add `from_legacy_te_schdule` attr to TE PrimFuncs
(#8641)
add 69ddb9b Move flake8 to ci_lint (#8652)
add dc5da05 [Support] Linear Congruential Random Engine (#8642)
add 2c124c9 [Frontend] Unified LSTM cell (#8599)
add 783fe98 [UnitTests] Apply correct requires_gpu() pytest marks for
parametrized target (#8542)
add e1bb7ac [VM] Add get_input_index support. (#8661)
add a0cf2e9 [VTA] Fix vta rpc server, refactor launch cond to not depend
on sys.argv (#8671)
add 40de9ce [FIX] Fix threadpool reset by killing threads before
destroying their shared queue (#8658)
add 338940d [microTVM][Zephyr] Add skip for AOT test (#8628)
add 49756a5 Allow rust tvm build configuration through cargo features
(#8665)
add 11238b5 [Relay][QNN] Support for non scalar zero points in qnn.conv2d
(#8620)
add bf3669d [Topi][Testing] Float16 unittests for dense, conv2d,
depthwise conv2d (#8529)
add 392a757 Add batch_matmul convertion to FQ2I pass (#8635)
add ce3d68f LowerWarpMemory: remove unneeded shuffle when accessing from
the same thread (#8681)
add bca155f [Target] Add __launch_bounds__ directive as part of the CUDA
code generation (#8678)
add a729787 [microTVM] Project API infrastructure (#8380)
add d4d4e89 [Contrib] Support fp16 input in cpu sort (#8672)
add 208a537 [Refactor] Rename .asnumpy() to .numpy() (#8659)
add 1276033 [Relay][TOPI] Remove redundant cuda kernels caused by fusion
of less & logical or (#8618)
add dbfbebe [community] @electriclilies -> Reviewer (#8684)
add babaa74 Fix error when compile tvm with latest llvm14git (#8682)
add 8679b4f [UnitTests] Added cuDNN to default test targets (#8383)
add 005f682 [Relay] Replace compile engine with TE compiler in the VM
(#8501)
add 00bed97 Remove unused variables in AOT tests (#8686)
add 3145867 [Meta Schedule][M3a] Traced Schedule (#8623)
add 39571c1 [microTVM] Add Arduino CLI support to ci-qemu (#8504)
new 0c7f4a2 Rev ci-qemu to 0.07
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 (b60bc61)
\
N -- N -- N refs/heads/ci-docker-staging (0c7f4a2)
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:
CMakeLists.txt | 29 +
CONTRIBUTORS.md | 1 +
Jenkinsfile | 4 +-
apps/android_rpc/app/src/main/jni/tvm_runtime.h | 1 +
apps/bundle_deploy/crt_config/crt_config.h | 4 +-
apps/microtvm/reference-vm/base-box-tool.py | 3 +-
apps/microtvm/reference-vm/zephyr/Vagrantfile | 7 +-
.../reference-vm/zephyr/base-box/test-config.json | 6 +-
apps/microtvm/zephyr/aot_demo/CMakeLists.txt | 27 -
apps/microtvm/zephyr/aot_demo/README.md | 20 -
.../zephyr/aot_demo/boards/mps2_an521.conf | 28 -
.../aot_demo/boards/nrf5340dk_nrf5340_cpuapp.conf | 34 -
.../zephyr/aot_demo/boards/nucleo_l4r5zi.conf | 31 -
.../zephyr/aot_demo/boards/qemu_cortex_r5.conf | 25 -
apps/microtvm/zephyr/aot_demo/boards/qemu_x86.conf | 28 -
apps/microtvm/zephyr/aot_demo/crt/crt_config.h | 62 -
apps/microtvm/zephyr/aot_demo/prj.conf | 32 -
apps/microtvm/zephyr/aot_demo/qemu-hack | 1 -
apps/microtvm/zephyr/host_driven/CMakeLists.txt | 26 -
.../zephyr/host_driven/boards/mps2_an521.conf | 28 -
.../boards/nrf5340dk_nrf5340_cpuapp.conf | 34 -
.../zephyr/host_driven/boards/nucleo_f746zg.conf | 33 -
.../zephyr/host_driven/boards/nucleo_l4r5zi.conf | 31 -
.../zephyr/host_driven/boards/qemu_cortex_r5.conf | 25 -
.../zephyr/host_driven/boards/qemu_riscv32.conf | 32 -
.../zephyr/host_driven/boards/qemu_riscv64.conf | 28 -
.../zephyr/host_driven/boards/qemu_x86.conf | 25 -
.../host_driven/boards/stm32f746g_disco.conf | 31 -
apps/microtvm/zephyr/host_driven/prj.conf | 32 -
apps/microtvm/zephyr/host_driven/qemu-hack | 1 -
.../template_project/CMakeLists.txt.template | 49 +
.../{host_driven => template_project}/README.md | 0
.../crt_config}/crt_config.h | 2 +-
.../zephyr/template_project/microtvm_api_server.py | 716 ++++
.../qemu-hack/qemu-system-arm | 0
.../qemu-hack/qemu-system-i386 | 4 +-
.../qemu-hack/qemu-system-riscv32 | 0
.../qemu-hack/qemu-system-riscv64 | 0
.../qemu-hack/qemu-system-xilinx-aarch64 | 0
.../src => template_project/src/aot_demo}/main.c | 14 +-
.../src/aot_demo}/zephyr_uart.c | 0
.../src/aot_demo}/zephyr_uart.h | 0
.../src/host_driven}/main.c | 2 +-
apps/wasm-standalone/README.md | 17 +-
apps/wasm-standalone/wasm-graph/src/lib.rs | 18 +-
apps/wasm-standalone/wasm-graph/src/types.rs | 2 +-
apps/wasm-standalone/wasm-graph/src/utils.rs | 19 +-
.../wasm-graph/tools/build_graph_lib.py | 67 +-
apps/wasm-standalone/wasm-runtime/Cargo.toml | 4 +-
apps/wasm-standalone/wasm-runtime/src/graph.rs | 79 +-
cmake/config.cmake | 20 +
cmake/modules/StandaloneCrt.cmake | 7 +-
docker/Dockerfile.ci_arm | 3 +
docker/Dockerfile.ci_cpu | 13 +
docker/Dockerfile.ci_gpu | 3 +
docker/Dockerfile.ci_i386 | 3 +
docker/Dockerfile.ci_lint | 5 +-
docker/Dockerfile.ci_qemu | 7 +
docker/Dockerfile.ci_wasm | 3 +
...ll_python_venv.sh => ubuntu_install_arduino.sh} | 14 +-
docker/install/ubuntu_install_darknet.sh | 5 +-
.../install/ubuntu_install_ethosu_driver_stack.sh | 94 +
docker/install/ubuntu_install_onnx.sh | 9 +-
docker/install/ubuntu_install_python_package.sh | 19 +-
docker/install/ubuntu_install_redis.sh | 4 +-
docker/install/ubuntu_install_sphinx.sh | 11 +-
docker/install/ubuntu_install_tensorflow.sh | 5 +-
...tall_cmake_source.sh => ubuntu_install_vela.sh} | 15 +-
docs/conf.py | 2 +-
docs/install/from_source.rst | 27 +-
golang/sample/complex.go | 2 +-
include/tvm/ir/affine_type.h | 146 +
include/tvm/ir/function.h | 2 +-
include/tvm/relay/attrs/nn.h | 14 +-
include/tvm/runtime/crt/rpc_common/framing.h | 2 +-
include/tvm/runtime/device_api.h | 9 +
include/tvm/runtime/module.h | 4 +-
include/tvm/support/random_engine.h | 121 +
include/tvm/target/target_kind.h | 3 +-
include/tvm/tir/analysis.h | 22 +-
include/tvm/tir/expr.h | 3 +
include/tvm/tir/schedule/block_scope.h | 2 +-
include/tvm/tir/schedule/instruction.h | 288 ++
include/tvm/tir/schedule/schedule.h | 60 +-
include/tvm/tir/schedule/state.h | 20 +-
include/tvm/tir/schedule/trace.h | 164 +
include/tvm/tir/stmt.h | 21 +-
include/tvm/tir/transform.h | 11 +
include/tvm/topi/detail/ravel_unravel.h | 4 +-
python/gen_requirements.py | 11 +
python/tvm/auto_scheduler/relay_integration.py | 47 +-
python/tvm/auto_scheduler/workload_registry.py | 4 +-
python/tvm/autotvm/tophub.py | 2 +-
python/tvm/contrib/download.py | 119 +-
python/tvm/contrib/graph_executor.py | 16 +
python/tvm/contrib/hexagon.py | 15 +-
python/tvm/contrib/miopen.py | 52 +
python/tvm/contrib/target/onnx.py | 2 +-
python/tvm/contrib/utils.py | 2 +-
python/tvm/driver/build_module.py | 5 +-
python/tvm/ir/__init__.py | 1 +
python/tvm/ir/affine_type.py | 69 +
python/tvm/ir/transform.py | 2 +-
python/tvm/micro/__init__.py | 11 +-
python/tvm/micro/artifact.py | 295 --
python/tvm/micro/build.py | 210 -
python/tvm/micro/compiler.py | 361 --
python/tvm/micro/contrib/__init__.py | 16 -
python/tvm/micro/contrib/base.py | 67 -
python/tvm/micro/contrib/zephyr.py | 789 ----
python/tvm/micro/interface_api.py | 85 +
python/tvm/micro/micro_binary.py | 65 -
python/tvm/micro/micro_library.py | 93 -
python/tvm/micro/model_library_format.py | 51 +-
python/tvm/micro/project.py | 151 +
python/tvm/micro/project_api/client.py | 235 ++
python/tvm/micro/project_api/server.py | 776 ++++
python/tvm/micro/session.py | 24 +-
.../tvm/micro/{transport/base.py => transport.py} | 50 +-
python/tvm/micro/transport/__init__.py | 27 -
python/tvm/micro/transport/debug.py | 64 -
python/tvm/micro/transport/file_descriptor.py | 119 -
python/tvm/micro/transport/serial.py | 135 -
python/tvm/micro/transport/subprocess.py | 67 -
python/tvm/micro/transport/wakeup.py | 79 -
python/tvm/relay/backend/interpreter.py | 3 +-
python/tvm/relay/frontend/common.py | 125 +
python/tvm/relay/frontend/coreml.py | 2 +-
python/tvm/relay/frontend/onnx.py | 229 +-
python/tvm/relay/frontend/pytorch.py | 273 +-
python/tvm/relay/frontend/tensorflow.py | 23 +-
python/tvm/relay/frontend/tensorflow2_ops.py | 16 +-
python/tvm/relay/frontend/tensorflow_ops.py | 15 +-
python/tvm/relay/op/_tensor_grad.py | 56 +-
python/tvm/relay/op/contrib/tensorrt.py | 2 +
python/tvm/relay/op/nn/_nn.py | 24 +-
python/tvm/relay/op/nn/nn.py | 26 +-
python/tvm/relay/op/op_attrs.py | 5 +
python/tvm/relay/op/strategy/cuda.py | 15 +-
python/tvm/relay/op/strategy/generic.py | 5 +-
python/tvm/relay/op/strategy/hls.py | 4 +-
python/tvm/relay/op/strategy/rocm.py | 39 +
python/tvm/relay/prelude.py | 80 +-
python/tvm/relay/qnn/op/legalizations.py | 91 +-
python/tvm/relay/testing/__init__.py | 5 +-
python/tvm/relay/testing/byoc.py | 76 +
python/tvm/relay/testing/tf.py | 4 +-
.../transform/fake_quantization_to_integer.py | 212 +-
python/tvm/relay/transform/mixed_precision.py | 3 +
python/tvm/rpc/server.py | 26 +
python/tvm/runtime/vm.py | 19 +-
python/tvm/script/context_maintainer.py | 6 +-
python/tvm/script/parser.py | 22 +-
python/tvm/script/scope_handler.py | 3 +-
python/tvm/script/special_stmt.py | 100 +-
python/tvm/testing.py | 149 +-
python/tvm/tir/buffer.py | 2 +-
python/tvm/tir/ir_builder.py | 2 -
python/tvm/tir/schedule/__init__.py | 4 +-
.../schedule/{_ffi_api_schedule.py => _ffi_api.py} | 0
python/tvm/tir/schedule/block_scope.py | 14 +-
python/tvm/tir/schedule/instruction.py | 166 +
python/tvm/tir/schedule/schedule.py | 337 +-
python/tvm/tir/schedule/state.py | 77 +-
python/tvm/tir/schedule/testing.py | 62 +
python/tvm/tir/schedule/trace.py | 260 ++
python/tvm/tir/transform/transform.py | 23 +
python/tvm/topi/arm_cpu/group_conv2d.py | 7 +-
python/tvm/topi/cuda/batch_matmul.py | 115 +-
python/tvm/topi/cuda/conv2d.py | 11 +-
python/tvm/topi/cuda/conv2d_int8.py | 6 +-
python/tvm/topi/cuda/reduction.py | 35 +-
python/tvm/topi/cuda/scatter.py | 122 +-
python/tvm/topi/cuda/tensorcore_alter_op.py | 11 +-
python/tvm/topi/nn/batch_matmul.py | 134 +-
python/tvm/topi/testing/batch_matmul.py | 17 +-
python/tvm/topi/testing/common.py | 51 +
python/tvm/topi/testing/conv2d_nchw_python.py | 55 +-
python/tvm/topi/testing/depthwise_conv2d_python.py | 118 +-
python/tvm/topi/testing/dilate_python.py | 35 +-
python/tvm/topi/testing/poolnd_python.py | 56 +-
python/tvm/topi/testing/resize_python.py | 100 +-
python/tvm/topi/x86/batch_matmul.py | 149 +-
python/tvm/topi/x86/pooling.py | 6 +-
rust/tvm-graph-rt/src/module/mod.rs | 1 +
rust/tvm-rt/Cargo.toml | 49 +
rust/{tvm/src/runtime => tvm-rt/src}/graph_rt.rs | 4 +-
rust/tvm-rt/src/lib.rs | 63 +-
rust/tvm-sys/Cargo.toml | 50 +-
rust/tvm-sys/build.rs | 187 +-
rust/tvm-sys/src/lib.rs | 1 +
rust/tvm/Cargo.toml | 46 +
rust/tvm/examples/resnet/Cargo.toml | 2 +-
rust/tvm/examples/resnet/build.rs | 10 +-
rust/tvm/examples/resnet/src/build_resnet.py | 3 +
rust/tvm/examples/resnet/src/main.rs | 6 +-
rust/tvm/src/runtime/mod.rs | 2 -
src/arith/canonical_simplify.cc | 6 +-
src/arith/detect_linear_equation.cc | 4 +-
src/driver/driver_api.cc | 31 +-
src/ir/affine_type.cc | 80 +
src/ir/transform.cc | 2 +-
src/printer/tir_text_printer.cc | 25 +-
src/printer/tvmscript_printer.cc | 90 +-
src/relay/backend/aot_executor_codegen.cc | 12 +-
src/relay/backend/build_module.cc | 57 +-
src/relay/backend/te_compiler.cc | 69 +-
src/relay/backend/te_compiler_cache.cc | 3 +-
src/relay/backend/utils.cc | 67 +
src/relay/backend/utils.h | 17 +
src/relay/backend/vm/compiler.cc | 66 +-
src/relay/backend/vm/compiler.h | 7 +-
src/relay/op/make_op.h | 2 +-
src/relay/op/nn/nn.cc | 26 +-
src/relay/op/nn/nn.h | 47 +-
src/relay/qnn/op/batch_matmul.cc | 10 +-
src/relay/qnn/op/convolution.cc | 113 +-
src/relay/qnn/op/quantize.cc | 16 +-
src/relay/qnn/op/requantize.cc | 16 +-
.../transforms/combine_parallel_batch_matmul.cc | 13 +-
src/relay/transforms/combine_parallel_dense.cc | 3 +-
src/relay/transforms/defuse_ops.cc | 26 +-
.../transforms/fake_quantization_to_integer.cc | 109 +-
src/relay/transforms/memory_alloc.cc | 10 +-
src/relay/transforms/partition_graph.cc | 2 +-
src/runtime/contrib/miopen/miopen_utils.cc | 4 +
src/runtime/contrib/miopen/miopen_utils.h | 7 +
src/runtime/contrib/miopen/softmax.cc | 92 +
src/runtime/contrib/sort/sort.cc | 71 +-
src/runtime/contrib/tensorrt/tensorrt_logger.h | 2 +-
src/runtime/contrib/tensorrt/tensorrt_ops.cc | 11 +-
src/runtime/crt/crt_config-template.h | 11 +-
src/runtime/crt/graph_executor/graph_executor.c | 32 +-
src/runtime/crt/host/Makefile | 76 +
src/runtime/crt/host/microtvm_api_server.py | 200 +
.../crt/internal/graph_executor/graph_executor.h | 2 +-
src/runtime/crt/memory/stack_allocator.c | 13 +-
src/runtime/crt/microtvm_rpc_common/framing.cc | 20 +
src/runtime/graph_executor/graph_executor.cc | 10 +-
src/runtime/graph_executor/graph_executor.h | 3 +-
src/runtime/meta_data.h | 8 +-
src/runtime/{crt/host => micro}/crt_config.h | 10 +-
src/runtime/micro/micro_session.cc | 15 +-
.../micro/standalone/microtvm_graph_executor.cc | 4 +-
src/runtime/thread_pool.cc | 3 +-
src/runtime/vm/vm.cc | 15 +
src/runtime/vulkan/vulkan_device.cc | 21 +
src/runtime/vulkan/vulkan_device.h | 3 +-
src/runtime/vulkan/vulkan_device_api.cc | 29 +-
src/runtime/vulkan/vulkan_device_api.h | 2 +-
src/target/llvm/codegen_llvm.cc | 4 +
src/target/llvm/llvm_module.cc | 4 +
src/target/source/codegen_c.cc | 18 +-
src/target/source/codegen_c.h | 6 +
src/target/source/codegen_cuda.cc | 41 +
src/target/source/codegen_cuda.h | 1 +
src/target/source/source_module.cc | 89 +-
src/target/spirv/codegen_spirv.cc | 170 +-
src/target/spirv/codegen_spirv.h | 85 +-
src/target/target.cc | 188 +-
src/target/target_kind.cc | 94 +-
src/te/autodiff/ad_simplify.cc | 4 +-
src/te/operation/compute_op.cc | 2 +-
src/te/operation/cross_thread_reduction.cc | 3 -
src/te/operation/tensorize.cc | 4 +-
src/te/schedule/schedule_postproc_to_primfunc.cc | 4 +-
src/tir/analysis/block_access_region_detector.cc | 90 +-
src/tir/analysis/buffer_access_lca_detector.cc | 17 +-
src/tir/analysis/var_touch.cc | 30 +-
src/tir/analysis/verify_gpu_code.cc | 40 +-
src/tir/ir/buffer_common.h | 59 +
src/tir/ir/expr.cc | 42 +-
src/tir/ir/script/script_complete.cc | 24 +-
src/tir/ir/stmt.cc | 90 +-
src/tir/op/op.cc | 30 +-
src/tir/schedule/analysis.h | 127 +-
src/tir/schedule/analysis/analysis.cc | 663 ++-
src/tir/schedule/concrete_schedule.cc | 22 +-
src/tir/schedule/concrete_schedule.h | 31 +-
src/tir/schedule/instruction.cc | 102 +
src/tir/schedule/instruction_traits.h | 536 +++
src/tir/schedule/primitive.h | 47 +-
src/tir/schedule/primitive/compute_inline.cc | 57 +-
src/tir/schedule/primitive/get_block_loop.cc | 113 +
src/tir/schedule/primitive/loop_transformation.cc | 74 +
src/tir/schedule/primitive/reduction.cc | 992 +++++
src/tir/schedule/schedule.cc | 48 +-
src/tir/schedule/state.cc | 73 +-
src/tir/schedule/trace.cc | 533 +++
src/tir/schedule/traced_schedule.cc | 156 +
src/tir/schedule/traced_schedule.h | 73 +
src/tir/schedule/utils.h | 31 +
src/tir/transforms/compact_buffer_region.cc | 29 +-
src/tir/transforms/convert_blocks_to_opaque.cc | 13 +-
src/tir/transforms/flatten_buffer.cc | 13 +-
src/tir/transforms/inject_copy_intrin.cc | 18 +-
src/tir/transforms/inject_double_buffer.cc | 17 +-
src/tir/transforms/inject_prefetch.cc | 13 +-
src/tir/transforms/ir_utils.cc | 62 +-
src/tir/transforms/ir_utils.h | 27 +
src/tir/transforms/loop_partition.cc | 19 +-
.../transforms/lower_device_storage_access_info.cc | 52 +-
src/tir/transforms/lower_init_block.cc | 13 +-
src/tir/transforms/lower_match_buffer.cc | 270 ++
src/tir/transforms/lower_thread_allreduce.cc | 12 +-
src/tir/transforms/lower_warp_memory.cc | 25 +-
.../merge_dynamic_shared_memory_allocations.cc | 149 +
.../plan_update_buffer_allocation_location.cc | 15 +-
src/tir/transforms/storage_access.cc | 1 +
src/tir/transforms/storage_flatten.cc | 21 +-
src/tir/transforms/storage_rewrite.cc | 603 ++-
src/tir/transforms/tensorcore_infer_fragment.cc | 11 +-
src/tir/transforms/update_pointer_storage_scope.cc | 11 -
src/tir/transforms/update_pointer_storage_scope.h | 1 -
tests/cpp/random_engine_test.cc | 71 +
tests/crt/aot_memory_test.cc | 115 +-
tests/lint/check_file_type.py | 35 +-
tests/lint/{jnilint.sh => flake8.sh} | 4 +-
tests/micro/zephyr/conftest.py | 29 +-
tests/micro/zephyr/test_zephyr.py | 260 +-
tests/micro/zephyr/test_zephyr_aot.py | 244 +-
tests/python/contrib/test_edgetpu_runtime.py | 7 +-
tests/python/contrib/test_miopen.py | 66 +-
tests/python/contrib/test_random.py | 21 +-
tests/python/contrib/test_tensorrt.py | 17 +-
tests/python/contrib/test_tflite_runtime.py | 24 +-
tests/python/frontend/coreml/test_forward.py | 44 +
tests/python/frontend/mxnet/test_forward.py | 8 +-
tests/python/frontend/onnx/test_forward.py | 4366 ++++++++++----------
tests/python/frontend/pytorch/test_forward.py | 9 +
tests/python/frontend/pytorch/test_lstms.py | 22 +-
tests/python/frontend/tensorflow/test_forward.py | 47 +-
tests/python/frontend/tensorflow2/common.py | 2 +-
.../frontend/tensorflow2/test_functional_models.py | 61 +-
tests/python/integration/test_lower.py | 327 ++
tests/python/relay/aot/aot_test.mk | 25 +-
tests/python/relay/aot/aot_test_utils.py | 326 +-
tests/python/relay/aot/test_crt_aot.py | 390 +-
tests/python/relay/test_any.py | 93 +-
.../test_auto_scheduler_layout_rewrite_networks.py | 2 +-
.../relay/test_auto_scheduler_task_extraction.py | 136 +-
tests/python/relay/test_backend_graph_executor.py | 52 +-
tests/python/relay/test_external_codegen.py | 140 +-
tests/python/relay/test_op_grad_level10.py | 20 +-
tests/python/relay/test_op_level10.py | 83 +-
tests/python/relay/test_op_level3.py | 4 +-
tests/python/relay/test_op_level6.py | 42 +-
tests/python/relay/test_op_qnn_conv2d.py | 101 +-
tests/python/relay/test_op_qnn_quantize.py | 15 +
tests/python/relay/test_op_qnn_requantize.py | 19 +
.../relay/test_op_qnn_simulated_dequantize.py | 8 +-
.../python/relay/test_op_qnn_simulated_quantize.py | 8 +-
tests/python/relay/test_pass_alter_op_layout.py | 1 -
.../relay/test_pass_annotate_spans_defuse.py | 53 +
.../test_pass_fake_quantization_to_integer.py | 314 +-
tests/python/relay/test_pass_manager.py | 28 +
tests/python/relay/test_pass_partition_graph.py | 85 +-
tests/python/relay/test_prng.py | 2 +-
tests/python/relay/test_to_mixed_precision.py | 15 +-
tests/python/relay/test_vm.py | 91 +-
tests/python/topi/python/test_topi_batch_matmul.py | 3 +-
tests/python/topi/python/test_topi_conv2d_nchw.py | 67 +-
tests/python/topi/python/test_topi_conv3d_ncdhw.py | 2 +-
.../topi/python/test_topi_conv3d_winograd.py | 2 +-
tests/python/topi/python/test_topi_dense.py | 48 +-
.../topi/python/test_topi_depthwise_conv2d.py | 61 +-
tests/python/topi/python/test_topi_loss.py | 2 +-
tests/python/topi/python/test_topi_pooling.py | 517 +--
tests/python/topi/python/test_topi_prng.py | 4 +-
tests/python/topi/python/test_topi_relu.py | 2 +-
tests/python/topi/python/test_topi_transform.py | 4 +-
.../python/unittest/test_auto_scheduler_measure.py | 10 +
tests/python/unittest/test_crt.py | 69 +-
tests/python/unittest/test_link_params.py | 37 +-
tests/python/unittest/test_lower_build.py | 27 +-
tests/python/unittest/test_micro_artifact.py | 149 -
.../unittest/test_micro_model_library_format.py | 103 +-
tests/python/unittest/test_micro_project_api.py | 424 ++
tests/python/unittest/test_micro_transport.py | 12 +-
tests/python/unittest/test_runtime_graph.py | 5 +-
tests/python/unittest/test_runtime_graph_debug.py | 6 +-
.../test_runtime_module_based_interface.py | 48 +-
tests/python/unittest/test_runtime_rpc.py | 110 +-
.../python/unittest/test_target_codegen_vulkan.py | 94 +
tests/python/unittest/test_target_target.py | 13 +
tests/python/unittest/test_te_create_primfunc.py | 4 +-
tests/python/unittest/test_te_schedule.py | 2 +-
.../test_tir_analysis_detect_buffer_access_lca.py | 33 +
.../test_tir_analysis_get_block_access_region.py | 78 +
.../unittest/test_tir_analysis_verify_gpu_code.py | 30 +
tests/python/unittest/test_tir_base.py | 65 +-
tests/python/unittest/test_tir_ir_builder.py | 2 -
.../python/unittest/test_tir_lower_match_buffer.py | 455 ++
tests/python/unittest/test_tir_nodes.py | 7 +-
tests/python/unittest/test_tir_ops.py | 19 +-
.../unittest/test_tir_schedule_block_scope.py | 13 +-
.../unittest/test_tir_schedule_compute_inline.py | 66 +-
tests/python/unittest/test_tir_schedule_error.py | 13 +-
.../unittest/test_tir_schedule_instruction.py | 68 +
.../python/unittest/test_tir_schedule_reduction.py | 618 +++
.../unittest/test_tir_schedule_split_fuse.py | 59 +-
tests/python/unittest/test_tir_schedule_state.py | 25 +-
.../test_tir_schedule_state_cached_flags.py | 51 +-
tests/python/unittest/test_tir_schedule_trace.py | 241 ++
.../python/unittest/test_tir_schedule_utilities.py | 55 +-
.../test_tir_transform_compact_buffer_region.py | 62 +-
.../test_tir_transform_convert_blocks_to_opaque.py | 11 +-
.../unittest/test_tir_transform_coproc_sync.py | 4 +-
.../unittest/test_tir_transform_flatten_buffer.py | 11 +-
.../test_tir_transform_inject_double_buffer.py | 4 +-
.../test_tir_transform_inject_virtual_thread.py | 12 +-
.../unittest/test_tir_transform_lift_attr_scope.py | 4 +-
.../unittest/test_tir_transform_loop_partition.py | 4 +-
.../test_tir_transform_lower_init_block.py | 48 +-
.../test_tir_transform_lower_warp_memory.py | 33 +-
...form_merge_dynamic_shared_memory_allocations.py | 259 ++
...sform_plan_update_buffer_allocation_location.py | 40 +-
.../unittest/test_tir_transform_storage_flatten.py | 27 +-
.../unittest/test_tir_transform_storage_rewrite.py | 24 +-
.../unittest/test_tir_transform_thread_sync.py | 64 +-
tests/python/unittest/test_tvm_testing_features.py | 30 +
tests/python/unittest/test_tvmscript_complete.py | 51 +-
.../python/unittest/test_tvmscript_error_report.py | 20 +-
tests/python/unittest/test_tvmscript_roundtrip.py | 42 +-
tests/scripts/task_ci_setup.sh | 3 +
tests/scripts/task_config_build_arm.sh | 1 +
tests/scripts/task_config_build_cpu.sh | 1 +
tests/scripts/task_config_build_gpu.sh | 1 +
tests/scripts/task_config_build_gpu_vulkan.sh | 1 +
tests/scripts/task_config_build_i386.sh | 2 +
tests/scripts/task_config_build_qemu.sh | 1 +
tests/scripts/task_config_build_wasm.sh | 1 +
tests/scripts/task_lint.sh | 1 +
tests/scripts/task_python_arm_compute_library.sh | 3 +-
tests/scripts/task_python_frontend.sh | 7 +-
tests/scripts/task_python_frontend_cpu.sh | 3 -
tutorials/micro/micro_tflite.py | 121 +-
vta/python/vta/__init__.py | 6 +-
vta/python/vta/build_module.py | 65 +-
vta/python/vta/environment.py | 64 -
vta/python/vta/exec/rpc_server.py | 16 +-
web/Makefile | 2 +-
web/tests/python/webgpu_rpc_test.py | 4 +-
web/tests/python/websock_rpc_test.py | 2 +-
444 files changed, 21664 insertions(+), 9754 deletions(-)
delete mode 100644 apps/microtvm/zephyr/aot_demo/CMakeLists.txt
delete mode 100644 apps/microtvm/zephyr/aot_demo/README.md
delete mode 100644 apps/microtvm/zephyr/aot_demo/boards/mps2_an521.conf
delete mode 100644
apps/microtvm/zephyr/aot_demo/boards/nrf5340dk_nrf5340_cpuapp.conf
delete mode 100644 apps/microtvm/zephyr/aot_demo/boards/nucleo_l4r5zi.conf
delete mode 100644 apps/microtvm/zephyr/aot_demo/boards/qemu_cortex_r5.conf
delete mode 100644 apps/microtvm/zephyr/aot_demo/boards/qemu_x86.conf
delete mode 100644 apps/microtvm/zephyr/aot_demo/crt/crt_config.h
delete mode 100644 apps/microtvm/zephyr/aot_demo/prj.conf
delete mode 120000 apps/microtvm/zephyr/aot_demo/qemu-hack
delete mode 100644 apps/microtvm/zephyr/host_driven/CMakeLists.txt
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/mps2_an521.conf
delete mode 100644
apps/microtvm/zephyr/host_driven/boards/nrf5340dk_nrf5340_cpuapp.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/nucleo_f746zg.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/nucleo_l4r5zi.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/qemu_cortex_r5.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/qemu_riscv32.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/qemu_riscv64.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/boards/qemu_x86.conf
delete mode 100644
apps/microtvm/zephyr/host_driven/boards/stm32f746g_disco.conf
delete mode 100644 apps/microtvm/zephyr/host_driven/prj.conf
delete mode 120000 apps/microtvm/zephyr/host_driven/qemu-hack
create mode 100644
apps/microtvm/zephyr/template_project/CMakeLists.txt.template
rename apps/microtvm/zephyr/{host_driven => template_project}/README.md (100%)
rename apps/microtvm/zephyr/{host_driven/crt =>
template_project/crt_config}/crt_config.h (97%)
create mode 100644 apps/microtvm/zephyr/template_project/microtvm_api_server.py
rename apps/microtvm/zephyr/{ => template_project}/qemu-hack/qemu-system-arm
(100%)
rename apps/microtvm/zephyr/{ => template_project}/qemu-hack/qemu-system-i386
(91%)
rename apps/microtvm/zephyr/{ =>
template_project}/qemu-hack/qemu-system-riscv32 (100%)
rename apps/microtvm/zephyr/{ =>
template_project}/qemu-hack/qemu-system-riscv64 (100%)
rename apps/microtvm/zephyr/{ =>
template_project}/qemu-hack/qemu-system-xilinx-aarch64 (100%)
rename apps/microtvm/zephyr/{aot_demo/src =>
template_project/src/aot_demo}/main.c (95%)
rename apps/microtvm/zephyr/{aot_demo/src =>
template_project/src/aot_demo}/zephyr_uart.c (100%)
rename apps/microtvm/zephyr/{aot_demo/include =>
template_project/src/aot_demo}/zephyr_uart.h (100%)
rename apps/microtvm/zephyr/{host_driven/src =>
template_project/src/host_driven}/main.c (99%)
mode change 100644 => 100755
apps/wasm-standalone/wasm-graph/tools/build_graph_lib.py
copy docker/install/{ubuntu1804_install_python_venv.sh =>
ubuntu_install_arduino.sh} (72%)
mode change 100755 => 100644
create mode 100755 docker/install/ubuntu_install_ethosu_driver_stack.sh
copy docker/install/{ubuntu_install_cmake_source.sh => ubuntu_install_vela.sh}
(72%)
create mode 100644 include/tvm/ir/affine_type.h
create mode 100644 include/tvm/support/random_engine.h
create mode 100644 include/tvm/tir/schedule/instruction.h
create mode 100644 include/tvm/tir/schedule/trace.h
create mode 100644 python/tvm/ir/affine_type.py
delete mode 100644 python/tvm/micro/artifact.py
delete mode 100644 python/tvm/micro/compiler.py
delete mode 100644 python/tvm/micro/contrib/__init__.py
delete mode 100644 python/tvm/micro/contrib/base.py
delete mode 100644 python/tvm/micro/contrib/zephyr.py
create mode 100644 python/tvm/micro/interface_api.py
delete mode 100644 python/tvm/micro/micro_binary.py
delete mode 100644 python/tvm/micro/micro_library.py
create mode 100644 python/tvm/micro/project.py
create mode 100644 python/tvm/micro/project_api/client.py
create mode 100644 python/tvm/micro/project_api/server.py
rename python/tvm/micro/{transport/base.py => transport.py} (84%)
delete mode 100644 python/tvm/micro/transport/__init__.py
delete mode 100644 python/tvm/micro/transport/debug.py
delete mode 100644 python/tvm/micro/transport/file_descriptor.py
delete mode 100644 python/tvm/micro/transport/serial.py
delete mode 100644 python/tvm/micro/transport/subprocess.py
delete mode 100644 python/tvm/micro/transport/wakeup.py
create mode 100644 python/tvm/relay/testing/byoc.py
rename python/tvm/tir/schedule/{_ffi_api_schedule.py => _ffi_api.py} (100%)
create mode 100644 python/tvm/tir/schedule/instruction.py
create mode 100644 python/tvm/tir/schedule/testing.py
create mode 100644 python/tvm/tir/schedule/trace.py
rename rust/{tvm/src/runtime => tvm-rt/src}/graph_rt.rs (97%)
create mode 100644 src/ir/affine_type.cc
create mode 100644 src/runtime/contrib/miopen/softmax.cc
create mode 100644 src/runtime/crt/host/Makefile
create mode 100644 src/runtime/crt/host/microtvm_api_server.py
rename src/runtime/{crt/host => micro}/crt_config.h (90%)
create mode 100644 src/tir/ir/buffer_common.h
create mode 100644 src/tir/schedule/instruction.cc
create mode 100644 src/tir/schedule/instruction_traits.h
create mode 100644 src/tir/schedule/primitive/get_block_loop.cc
create mode 100644 src/tir/schedule/primitive/reduction.cc
create mode 100644 src/tir/schedule/trace.cc
create mode 100644 src/tir/schedule/traced_schedule.cc
create mode 100644 src/tir/schedule/traced_schedule.h
create mode 100644 src/tir/transforms/lower_match_buffer.cc
create mode 100644
src/tir/transforms/merge_dynamic_shared_memory_allocations.cc
create mode 100644 tests/cpp/random_engine_test.cc
copy tests/lint/{jnilint.sh => flake8.sh} (87%)
create mode 100644 tests/python/integration/test_lower.py
create mode 100644 tests/python/relay/test_pass_annotate_spans_defuse.py
delete mode 100644 tests/python/unittest/test_micro_artifact.py
create mode 100644 tests/python/unittest/test_micro_project_api.py
create mode 100644 tests/python/unittest/test_tir_lower_match_buffer.py
create mode 100644 tests/python/unittest/test_tir_schedule_instruction.py
create mode 100644 tests/python/unittest/test_tir_schedule_reduction.py
create mode 100644 tests/python/unittest/test_tir_schedule_trace.py
create mode 100644
tests/python/unittest/test_tir_transform_merge_dynamic_shared_memory_allocations.py
