This is an automated email from the ASF dual-hosted git repository. junrushao pushed a commit to branch unity-staging in repository https://gitbox.apache.org/repos/asf/tvm.git
commit 7828489c6c1486ec97f4989811c95dbd0951305b Merge: ee4e657116 9710d81650 Author: Junru Shao <[email protected]> AuthorDate: Thu Jun 29 20:39:47 2023 -0700 Merge remote-tracking branch 'apache-upstream/main' into unity cmake/modules/LibInfo.cmake | 1 + docs/dev/how_to/how_to.rst | 1 + docs/dev/how_to/setup_rpc_system.rst | 245 ++++ include/tvm/runtime/logging.h | 22 +- include/tvm/tir/buffer.h | 2 + include/tvm/tir/schedule/schedule.h | 18 + include/tvm/tir/transform.h | 12 + python/gen_requirements.py | 2 + python/tvm/_ffi/runtime_ctypes.py | 4 + python/tvm/contrib/rocm.py | 119 +- python/tvm/error.py | 8 +- python/tvm/relay/backend/contrib/ethosu/codegen.py | 3 +- .../backend/contrib/ethosu/softmax_rewriter.py | 75 +- python/tvm/relay/backend/contrib/ethosu/util.py | 14 +- python/tvm/relay/frontend/tflite.py | 3 +- python/tvm/testing/__init__.py | 37 +- python/tvm/testing/rpc_run.py | 162 +++ python/tvm/testing/tir.py | 111 ++ python/tvm/testing/utils.py | 17 +- python/tvm/tir/analysis/analysis.py | 26 +- python/tvm/tir/schedule/schedule.py | 140 ++- python/tvm/tir/tensor_intrin/cuda.py | 318 +++++ python/tvm/tir/tensor_intrin/rocm.py | 433 ++++++- python/tvm/tir/transform/transform.py | 22 + src/arith/iter_affine_map.cc | 2 +- src/driver/driver_api.cc | 6 +- .../feature_extractor/per_store_feature.cc | 3 +- src/meta_schedule/postproc/verify_gpu_code.cc | 3 +- .../schedule_rule/multi_level_tiling.cc | 9 +- .../schedule_rule/multi_level_tiling.h | 15 + .../multi_level_tiling_tensor_core.cc | 330 ++++- src/meta_schedule/schedule_rule/schedule_rule.cc | 15 + src/relay/backend/contrib/ethosu/compiler_attrs.cc | 33 +- src/relay/qnn/op/convolution_transpose.cc | 2 +- src/runtime/builtin_fp16.cc | 2 +- src/runtime/logging.cc | 35 +- src/runtime/thread_storage_scope.h | 21 + src/support/libinfo.cc | 1 + src/target/source/codegen_c_host.h | 2 +- src/target/target_kind.cc | 14 +- src/tir/analysis/var_use_def_analysis.cc | 9 + src/tir/schedule/analysis.h | 18 - src/tir/schedule/analysis/analysis.cc | 4 +- src/tir/schedule/concrete_schedule.cc | 10 + src/tir/schedule/concrete_schedule.h | 3 + src/tir/schedule/primitive.h | 39 +- src/tir/schedule/primitive/compute_inline.cc | 19 + src/tir/schedule/primitive/pad_einsum.cc | 574 +++++---- src/tir/schedule/primitive/sampling.cc | 106 ++ src/tir/schedule/schedule.cc | 2 + src/tir/schedule/traced_schedule.cc | 16 + src/tir/schedule/traced_schedule.h | 3 + src/tir/schedule/transform.cc | 13 + src/tir/transforms/inject_permuted_layout.cc | 266 ++++ src/tir/transforms/inject_software_pipeline.cc | 7 + src/tir/transforms/memhammer_intermediate_stage.cc | 3 +- src/tir/transforms/memhammer_lower_auto_copy.cc | 6 +- src/tir/transforms/memhammer_rewrite_rule.h | 16 + src/tir/transforms/memhammer_tensorcore_rewrite.cc | 210 ++++ src/tir/transforms/renew_defs.cc | 12 + src/tir/transforms/transform_mma_buffer_layout.cc | 192 +++ .../contrib/test_ethosu/test_attr_passing.py | 67 +- tests/python/contrib/test_ethosu/test_legalize.py | 114 +- tests/python/contrib/test_ethosu/test_scheduler.py | 16 + tests/python/driver/tvmc/test_target_options.py | 14 + tests/python/frontend/tflite/test_forward.py | 80 ++ ...meta_schedule_mma_m16n8k8_auto_tensorization.py | 1315 ++++++++++++++++++++ tests/python/unittest/test_tir_renew_defs.py | 20 +- .../python/unittest/test_tir_schedule_analysis.py | 39 +- .../unittest/test_tir_schedule_pad_einsum.py | 277 +++-- .../unittest/test_tir_schedule_tensorize_mfma.py | 314 +++++ ...test_tir_transform_memhammer_lower_auto_copy.py | 127 ++ 72 files changed, 5512 insertions(+), 687 deletions(-)
