This is an automated email from the ASF dual-hosted git repository.
github-bot pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from c9fb8cd3cd [Docs] Clean up stale references from recent refactors
(#18908)
add 141c22fd8a [Refactor] Bring up tirx namespace (#18913)
No new revisions were added by this update.
Summary of changes:
CMakeLists.txt | 2 +-
docs/README.md | 16 +
docs/arch/index.rst | 67 +-
docs/arch/pass_infra.rst | 18 +-
docs/arch/runtime.rst | 2 +-
docs/arch/runtimes/vulkan.rst | 2 +-
docs/conf.py | 8 +-
docs/contribute/pull_request.rst | 4 +-
docs/deep_dive/relax/tutorials/relax_creation.py | 2 +-
docs/deep_dive/tensor_ir/abstraction.rst | 2 +-
docs/deep_dive/tensor_ir/learning.rst | 2 +-
docs/deep_dive/tensor_ir/tutorials/tir_creation.py | 6 +-
.../tensor_ir/tutorials/tir_transformation.py | 10 +-
docs/get_started/overview.rst | 18 +-
docs/how_to/tutorials/optimize_llm.py | 10 +-
docs/reference/api/python/index.rst | 10 +-
docs/reference/api/python/te.rst | 2 +-
.../api/python/{tir => tirx}/analysis.rst | 6 +-
.../api/python/{tir => tirx}/stmt_functor.rst | 6 +-
.../api/python/{tir/tir.rst => tirx/tirx.rst} | 6 +-
.../api/python/{tir => tirx}/transform.rst | 6 +-
include/tvm/arith/analyzer.h | 2 +-
include/tvm/arith/bound.h | 14 +-
include/tvm/arith/int_set.h | 10 +-
include/tvm/arith/int_solver.h | 10 +-
include/tvm/arith/iter_affine_map.h | 2 +-
include/tvm/arith/pattern.h | 6 +-
include/tvm/ir/function.h | 2 +-
include/tvm/relax/analysis.h | 26 +-
include/tvm/relax/attrs/manipulate.h | 4 +-
include/tvm/relax/attrs/sorting.h | 2 +-
include/tvm/relax/distributed/axis_group_graph.h | 10 +-
include/tvm/relax/distributed/transform.h | 4 +-
include/tvm/relax/expr.h | 4 +-
include/tvm/relax/expr_functor.h | 2 +-
include/tvm/relax/struct_info.h | 2 +-
include/tvm/relax/tir_pattern.h | 12 +-
include/tvm/relax/transform.h | 18 +-
include/tvm/relax/type.h | 2 +-
include/tvm/relax/utils.h | 6 +-
include/tvm/s_tir/analysis.h | 12 +-
include/tvm/s_tir/backend/adreno/transform.h | 6 +-
include/tvm/s_tir/data_layout.h | 24 +-
include/tvm/s_tir/meta_schedule/arg_info.h | 4 +-
include/tvm/s_tir/meta_schedule/database.h | 4 +-
include/tvm/s_tir/meta_schedule/extracted_task.h | 4 +-
include/tvm/s_tir/sblock_dependence_info.h | 4 +-
include/tvm/s_tir/sblock_scope.h | 12 +-
include/tvm/s_tir/schedule/instruction.h | 2 +-
include/tvm/s_tir/schedule/schedule.h | 4 +-
include/tvm/s_tir/schedule/state.h | 6 +-
include/tvm/s_tir/schedule/trace.h | 2 +-
include/tvm/s_tir/stmt.h | 5 +-
include/tvm/s_tir/transform.h | 8 +-
include/tvm/s_tir/utils.h | 10 +-
include/tvm/script/ir_builder/base.h | 6 +-
.../tvm/script/ir_builder/{tir => tirx}/frame.h | 73 +-
include/tvm/script/ir_builder/{tir => tirx}/ir.h | 31 +-
include/tvm/target/codegen.h | 2 +-
include/tvm/te/operation.h | 6 +-
include/tvm/te/tensor.h | 6 +-
include/tvm/{tir => tirx}/analysis.h | 22 +-
include/tvm/{tir => tirx}/buffer.h | 22 +-
include/tvm/{tir => tirx}/builtin.h | 8 +-
include/tvm/{tir => tirx}/expr.h | 82 +-
include/tvm/{tir => tirx}/expr_functor.h | 12 +-
include/tvm/{tir => tirx}/function.h | 42 +-
include/tvm/{tir => tirx}/index_map.h | 12 +-
include/tvm/{tir => tirx}/op.h | 125 +--
include/tvm/{tir => tirx}/op_attr_types.h | 8 +-
include/tvm/{tir => tirx}/stmt.h | 42 +-
include/tvm/{tir => tirx}/stmt_functor.h | 16 +-
include/tvm/{tir => tirx}/transform.h | 14 +-
include/tvm/{tir => tirx}/var.h | 24 +-
include/tvm/topi/broadcast.h | 44 +-
include/tvm/topi/detail/broadcast.h | 18 +-
include/tvm/topi/detail/constant_utils.h | 12 +-
include/tvm/topi/detail/extern.h | 18 +-
include/tvm/topi/detail/pad_utils.h | 4 +-
include/tvm/topi/detail/strided_slice.h | 4 +-
include/tvm/topi/elemwise.h | 12 +-
include/tvm/topi/nn.h | 68 +-
include/tvm/topi/nn/pooling.h | 36 +-
include/tvm/topi/reduction.h | 24 +-
include/tvm/topi/transform.h | 38 +-
python/tvm/__init__.py | 4 +-
python/tvm/arith/analyzer.py | 36 +-
python/tvm/arith/int_solver.py | 16 +-
python/tvm/arith/pattern.py | 4 +-
python/tvm/contrib/cblas.py | 4 +-
python/tvm/contrib/cublas.py | 4 +-
python/tvm/contrib/cublaslt.py | 2 +-
python/tvm/contrib/cudnn.py | 18 +-
python/tvm/contrib/cutlass/build.py | 6 +-
python/tvm/contrib/cutlass/gen_tensor_op.py | 8 +-
python/tvm/contrib/cutlass/library.py | 2 +-
python/tvm/contrib/dnnl.py | 4 +-
python/tvm/contrib/hexagon/hexagon_profiler.py | 2 +-
python/tvm/contrib/hexagon/tools.py | 8 +-
python/tvm/contrib/hipblas.py | 4 +-
python/tvm/contrib/mkl.py | 6 +-
python/tvm/contrib/nnpack.py | 8 +-
python/tvm/contrib/random.py | 6 +-
python/tvm/driver/build_module.py | 10 +-
python/tvm/exec/popen_worker.py | 16 +
python/tvm/ir/attrs.py | 2 +-
python/tvm/ir/base.py | 4 +-
python/tvm/ir/expr.py | 2 +-
python/tvm/relax/analysis/analysis.py | 24 +-
python/tvm/relax/analysis/estimate_memory_usage.py | 2 +-
python/tvm/relax/backend/adreno/clml.py | 4 +-
python/tvm/relax/backend/adreno/pipeline.py | 2 +-
python/tvm/relax/backend/cuda/cublas.py | 14 +-
python/tvm/relax/backend/cuda/cudnn.py | 2 +-
python/tvm/relax/backend/cuda/cutlass.py | 4 +-
python/tvm/relax/backend/dispatch_sort_scan.py | 2 +-
python/tvm/relax/backend/gpu_generic/cumsum.py | 6 +-
python/tvm/relax/backend/gpu_generic/sampling.py | 6 +-
python/tvm/relax/backend/patterns.py | 2 +-
python/tvm/relax/backend/rocm/hipblas.py | 8 +-
python/tvm/relax/base_py_module.py | 10 +-
python/tvm/relax/block_builder.py | 22 +-
python/tvm/relax/dpl/pattern.py | 2 +-
python/tvm/relax/expr.py | 20 +-
python/tvm/relax/frontend/nn/_tensor_op.py | 4 +-
python/tvm/relax/frontend/nn/core.py | 30 +-
python/tvm/relax/frontend/nn/exporter.py | 24 +-
python/tvm/relax/frontend/nn/extern.py | 8 +-
python/tvm/relax/frontend/nn/llm/kv_cache.py | 132 +--
.../relax/frontend/nn/llm/position_embedding.py | 188 ++--
python/tvm/relax/frontend/nn/llm/tree_attn.py | 26 +-
python/tvm/relax/frontend/nn/modules.py | 18 +-
python/tvm/relax/frontend/nn/op.py | 4 +-
python/tvm/relax/frontend/nn/subroutine.py | 2 +-
python/tvm/relax/frontend/onnx/onnx_frontend.py | 63 +-
.../frontend/stablehlo/stablehlo_translator.py | 4 +-
.../frontend/torch/base_fx_graph_translator.py | 10 +-
python/tvm/relax/frontend/torch/dynamo.py | 2 +-
.../frontend/torch/exported_program_translator.py | 40 +-
python/tvm/relax/op/_op_gradient.py | 2 +-
python/tvm/relax/op/base.py | 8 +-
python/tvm/relax/op/distributed/distributed.py | 4 +-
python/tvm/relax/op/manipulate.py | 2 +-
python/tvm/relax/op/memory/view.py | 2 +-
python/tvm/relax/op/nn/nn.py | 2 +-
python/tvm/relax/struct_info.py | 6 +-
python/tvm/relax/testing/ast_printer.py | 2 +-
python/tvm/relax/testing/attention.py | 2 +-
python/tvm/relax/testing/nn.py | 4 +-
python/tvm/relax/testing/vm.py | 2 +-
python/tvm/relax/training/setup_trainer.py | 2 +-
.../fold_batch_norm_to_conv2d_for_inference.py | 4 +-
.../tvm/relax/transform/fuse_transpose_matmul.py | 8 +-
python/tvm/relax/transform/legalize_ops/ccl.py | 4 +-
python/tvm/relax/transform/legalize_ops/common.py | 6 +-
python/tvm/relax/transform/legalize_ops/create.py | 4 +-
.../relax/transform/legalize_ops/distributed.py | 4 +-
python/tvm/relax/transform/legalize_ops/grad.py | 20 +-
python/tvm/relax/transform/legalize_ops/index.py | 26 +-
.../tvm/relax/transform/legalize_ops/inspect_op.py | 10 +-
.../relax/transform/legalize_ops/linear_algebra.py | 8 +-
.../tvm/relax/transform/legalize_ops/manipulate.py | 14 +-
python/tvm/relax/transform/legalize_ops/nn.py | 36 +-
python/tvm/relax/transform/legalize_ops/qdq.py | 16 +-
.../relax/transform/legalize_ops/statistical.py | 14 +-
python/tvm/relax/transform/legalize_ops/vision.py | 12 +-
python/tvm/relax/transform/transform.py | 20 +-
python/tvm/relax/utils.py | 54 +-
python/tvm/relax/vm_build.py | 4 +-
python/tvm/runtime/script_printer.py | 4 +-
python/tvm/s_tir/__init__.py | 2 +-
python/tvm/s_tir/analysis/__init__.py | 16 +-
python/tvm/s_tir/backend/adreno/pipeline.py | 62 +-
python/tvm/s_tir/dlight/adreno/convolution.py | 8 +-
python/tvm/s_tir/dlight/adreno/fallback.py | 6 +-
python/tvm/s_tir/dlight/adreno/layout_transform.py | 8 +-
python/tvm/s_tir/dlight/adreno/pool.py | 4 +-
.../tvm/s_tir/dlight/analysis/common_analysis.py | 70 +-
python/tvm/s_tir/dlight/analysis/gemv.py | 20 +-
python/tvm/s_tir/dlight/base/schedule_rule.py | 12 +-
python/tvm/s_tir/dlight/base/transform.py | 18 +-
python/tvm/s_tir/dlight/base/utils.py | 10 +-
python/tvm/s_tir/dlight/benchmark/bench.py | 4 +-
python/tvm/s_tir/dlight/benchmark/extract.py | 24 +-
python/tvm/s_tir/dlight/benchmark/utils.py | 2 +-
python/tvm/s_tir/dlight/cpu/gemv.py | 8 +-
python/tvm/s_tir/dlight/gpu/fallback.py | 6 +-
python/tvm/s_tir/dlight/gpu/gemv.py | 20 +-
python/tvm/s_tir/dlight/gpu/general_reduction.py | 20 +-
python/tvm/s_tir/dlight/gpu/low_batch_gemv.py | 42 +-
python/tvm/s_tir/dlight/gpu/matmul.py | 68 +-
python/tvm/s_tir/dlight/gpu/reduction.py | 14 +-
python/tvm/s_tir/dlight/gpu/rmsnorm.py | 10 +-
python/tvm/s_tir/dlight/gpu/transpose.py | 10 +-
python/tvm/s_tir/meta_schedule/arg_info.py | 2 +-
.../s_tir/meta_schedule/database/json_database.py | 2 +-
.../meta_schedule/database/memory_database.py | 2 +-
.../meta_schedule/database/schedule_fn_database.py | 2 +-
.../tvm/s_tir/meta_schedule/relax_integration.py | 10 +-
.../schedule/cuda/layout_transform.py | 2 +-
.../tvm/s_tir/meta_schedule/testing/te_workload.py | 6 +-
.../tvm/s_tir/meta_schedule/testing/tune_utils.py | 4 +-
python/tvm/s_tir/meta_schedule/tir_integration.py | 22 +-
python/tvm/s_tir/meta_schedule/tune.py | 2 +-
python/tvm/s_tir/meta_schedule/tune_context.py | 4 +-
python/tvm/s_tir/meta_schedule/utils.py | 2 +-
python/tvm/s_tir/pipeline.py | 68 +-
python/tvm/s_tir/sblock_dependence_info.py | 2 +-
python/tvm/s_tir/sblock_scope.py | 2 +-
python/tvm/s_tir/schedule/analysis.py | 8 +-
python/tvm/s_tir/schedule/schedule.py | 34 +-
python/tvm/s_tir/schedule/state.py | 2 +-
python/tvm/s_tir/schedule/testing.py | 6 +-
python/tvm/s_tir/schedule/trace.py | 4 +-
python/tvm/s_tir/tensor_intrin/arm_cpu.py | 20 +-
python/tvm/s_tir/tensor_intrin/cuda.py | 10 +-
.../tvm/s_tir/tensor_intrin/dot_product_common.py | 2 +-
python/tvm/s_tir/tensor_intrin/hexagon.py | 2 +-
python/tvm/s_tir/tensor_intrin/metal.py | 4 +-
python/tvm/s_tir/tensor_intrin/riscv_cpu.py | 4 +-
python/tvm/s_tir/tensor_intrin/rocm.py | 8 +-
python/tvm/s_tir/tensor_intrin/x86.py | 2 +-
python/tvm/s_tir/transform/__init__.py | 2 +-
python/tvm/s_tir/transform/_ffi_api.py | 2 +-
python/tvm/script/ir_builder/base.py | 8 +-
python/tvm/script/ir_builder/relax/ir.py | 2 +-
.../script/ir_builder/{tir => tirx}/__init__.py | 2 +-
.../script/ir_builder/{tir => tirx}/_ffi_api.py | 2 +-
.../ir_builder/{tir => tirx}/external_kernel.py | 10 +-
.../tvm/script/ir_builder/{tir => tirx}/frame.py | 26 +-
python/tvm/script/ir_builder/{tir => tirx}/ir.py | 36 +-
.../tvm/script/ir_builder/{tir => tirx}/triton.py | 10 +-
.../tvm/script/ir_builder/{tir => tirx}/utils.py | 14 +-
python/tvm/script/parser/core/dispatch.py | 4 +-
python/tvm/script/parser/core/entry.py | 8 +-
python/tvm/script/parser/core/evaluator.py | 4 +-
python/tvm/script/parser/relax/dist.py | 2 +-
python/tvm/script/parser/relax/entry.py | 2 +-
python/tvm/script/parser/relax/parser.py | 14 +-
python/tvm/script/parser/{tir => tirx}/__init__.py | 6 +-
python/tvm/script/parser/{tir => tirx}/entry.py | 20 +-
.../tvm/script/parser/{tir => tirx}/operation.py | 36 +-
python/tvm/script/parser/{tir => tirx}/parser.py | 90 +-
python/tvm/script/printer/doc.py | 2 +-
python/tvm/script/{tir.py => tirx.py} | 2 +-
python/tvm/target/datatype.py | 20 +-
python/tvm/target/intrin.py | 8 +-
python/tvm/te/__init__.py | 20 +-
python/tvm/te/operation.py | 64 +-
python/tvm/te/tag.py | 2 +-
python/tvm/te/tensor.py | 4 +-
python/tvm/testing/tir.py | 2 +-
python/tvm/testing/utils.py | 26 +-
python/tvm/tir/_ffi_api.py | 21 -
python/tvm/tir/analysis/_ffi_api.py | 21 -
python/tvm/tir/transform/_ffi_api.py | 21 -
python/tvm/{tir => tirx}/__init__.py | 0
python/tvm/{rpc => tirx}/_ffi_api.py | 4 +-
python/tvm/{tir => tirx}/analysis/__init__.py | 0
python/tvm/{arith => tirx/analysis}/_ffi_api.py | 4 +-
python/tvm/{tir => tirx}/analysis/analysis.py | 10 +-
python/tvm/{tir => tirx}/backend/__init__.py | 0
.../tvm/{tir => tirx}/backend/adreno/__init__.py | 0
python/tvm/{tir => tirx}/buffer.py | 12 +-
python/tvm/{tir => tirx}/build.py | 30 +-
python/tvm/{tir => tirx}/expr.py | 78 +-
python/tvm/{tir => tirx}/function.py | 38 +-
python/tvm/{tir => tirx}/functor.py | 8 +-
python/tvm/{tir => tirx}/generic.py | 2 +-
python/tvm/{tir => tirx}/op.py | 306 +++---
python/tvm/{tir => tirx}/pipeline.py | 16 +-
python/tvm/{tir => tirx}/stmt.py | 40 +-
python/tvm/{tir => tirx}/stmt_functor.py | 8 +-
python/tvm/{tir => tirx}/transform/__init__.py | 0
python/tvm/{arith => tirx/transform}/_ffi_api.py | 4 +-
.../tvm/{tir => tirx}/transform/function_pass.py | 12 +-
python/tvm/{tir => tirx}/transform/transform.py | 20 +-
python/tvm/topi/generic_op_impl.py | 16 +-
python/tvm/topi/gpu/scan.py | 58 +-
python/tvm/topi/gpu/sort.py | 78 +-
python/tvm/topi/image/grid_sample.py | 42 +-
python/tvm/topi/image/resize.py | 38 +-
python/tvm/topi/index_put.py | 6 +-
python/tvm/topi/math.py | 46 +-
python/tvm/topi/nn/batch_matmul.py | 6 +-
python/tvm/topi/nn/bitserial_conv2d.py | 12 +-
python/tvm/topi/nn/bitserial_dense.py | 6 +-
python/tvm/topi/nn/bitserial_util.py | 4 +-
python/tvm/topi/nn/bnn.py | 4 +-
python/tvm/topi/nn/conv2d.py | 12 +-
python/tvm/topi/nn/deformable_conv2d.py | 12 +-
python/tvm/topi/nn/dense.py | 16 +-
python/tvm/topi/nn/depth_to_space.py | 12 +-
python/tvm/topi/nn/depthwise_conv2d.py | 12 +-
python/tvm/topi/nn/dilate.py | 10 +-
python/tvm/topi/nn/elemwise.py | 16 +-
python/tvm/topi/nn/fifo_buffer.py | 20 +-
python/tvm/topi/nn/flatten.py | 4 +-
python/tvm/topi/nn/lstm.py | 8 +-
python/tvm/topi/nn/pad.py | 18 +-
python/tvm/topi/nn/pixel_shuffle.py | 8 +-
python/tvm/topi/nn/qnn.py | 22 +-
python/tvm/topi/nn/space_to_depth.py | 16 +-
python/tvm/topi/nn/upsampling.py | 4 +-
python/tvm/topi/nn/utils.py | 4 +-
python/tvm/topi/scan.py | 4 +-
python/tvm/topi/scatter.py | 12 +-
python/tvm/topi/scatter_elements.py | 10 +-
python/tvm/topi/searchsorted.py | 2 +-
python/tvm/topi/signal.py | 38 +-
python/tvm/topi/sort.py | 26 +-
python/tvm/topi/sparse_reshape.py | 4 +-
python/tvm/topi/transform.py | 34 +-
python/tvm/topi/unique.py | 14 +-
python/tvm/topi/utils.py | 70 +-
python/tvm/topi/vision/nms.py | 48 +-
python/tvm/topi/vision/nms_util.py | 22 +-
src/arith/analyzer.cc | 32 +-
src/arith/bound_deducer.cc | 6 +-
src/arith/canonical_simplify.cc | 16 +-
src/arith/conjunctive_normal_form.cc | 6 +-
src/arith/conjunctive_normal_form.h | 2 +-
src/arith/const_fold.h | 46 +-
src/arith/const_int_bound.cc | 20 +-
src/arith/constraint_extract.cc | 2 +-
src/arith/constraint_extract.h | 2 +-
src/arith/detect_linear_equation.cc | 14 +-
src/arith/domain_touched.cc | 6 +-
src/arith/int_constraints.cc | 28 +-
src/arith/int_operator.h | 12 +-
src/arith/int_set.cc | 82 +-
src/arith/interval_set.h | 2 +-
src/arith/ir_mutator_with_analyzer.cc | 14 +-
src/arith/ir_mutator_with_analyzer.h | 36 +-
src/arith/ir_visitor_with_analyzer.cc | 12 +-
src/arith/ir_visitor_with_analyzer.h | 26 +-
src/arith/iter_affine_map.cc | 26 +-
src/arith/modular_set.cc | 12 +-
src/arith/narrow_predicate_expression.cc | 14 +-
src/arith/narrow_predicate_expression.h | 4 +-
src/arith/pattern_match.h | 116 +-
src/arith/presburger_set.cc | 8 +-
src/arith/presburger_set.h | 2 +-
src/arith/product_normal_form.h | 16 +-
src/arith/rewrite_simplify.cc | 24 +-
src/arith/rewrite_simplify.h | 4 +-
src/arith/scalable_expression.cc | 20 +-
src/arith/solve_linear_equation.cc | 42 +-
src/arith/solve_linear_inequality.cc | 14 +-
src/arith/transitive_comparison_analyzer.cc | 16 +-
src/arith/unwrap_vector_expr.cc | 12 +-
src/arith/unwrap_vector_expr.h | 2 +-
src/ir/apply_pass_to_function.cc | 10 +-
src/ir/attr_functor.h | 58 +-
src/ir/env_func.cc | 2 +-
src/ir/expr.cc | 6 +-
src/ir/function.cc | 14 +-
src/ir/op.cc | 4 +-
src/relax/analysis/analysis.cc | 2 +-
src/relax/analysis/collect_call_map.cc | 2 +-
src/relax/analysis/computable_at_compile_time.cc | 2 +-
src/relax/analysis/detect_recursion.cc | 2 +-
src/relax/analysis/layout_transformation.cc | 46 +-
src/relax/analysis/struct_info_analysis.cc | 86 +-
src/relax/analysis/tir_op_pattern_kind.cc | 56 +-
src/relax/analysis/well_formed.cc | 28 +-
.../backend/adreno/annotate_custom_storage.cc | 14 +-
.../backend/adreno/fold_vdevice_scope_change.cc | 2 +-
.../backend/contrib/codegen_json/codegen_json.h | 2 +-
src/relax/backend/contrib/utils.h | 2 +-
src/relax/backend/task_extraction.cc | 16 +-
src/relax/backend/vm/codegen_vm.cc | 2 +-
src/relax/backend/vm/codegen_vm_tir.cc | 108 +-
src/relax/backend/vm/lower_runtime_builtin.cc | 2 +-
src/relax/backend/vm/vm_shape_lower.cc | 40 +-
src/relax/distributed/axis_group_graph.cc | 10 +-
.../distributed/transform/legalize_redistribute.cc | 2 +-
src/relax/distributed/transform/lower_distir.cc | 2 +-
.../transform/lower_global_view_to_local_view.cc | 12 +-
.../distributed/transform/propagate_sharding.cc | 4 +-
src/relax/distributed/transform/utils.h | 6 +-
src/relax/ir/block_builder.cc | 26 +-
src/relax/ir/dataflow_block_rewriter.cc | 2 +-
src/relax/ir/dataflow_expr_rewriter.cc | 2 +-
src/relax/ir/dataflow_matcher.cc | 8 +-
src/relax/ir/emit_te.cc | 6 +-
src/relax/ir/emit_te.h | 2 +-
src/relax/ir/expr.cc | 4 +-
src/relax/ir/tir_pattern.cc | 2 +-
src/relax/ir/transform.cc | 16 +-
src/relax/op/nn/attention.cc | 2 +-
src/relax/op/nn/convolution.cc | 6 +-
src/relax/op/nn/pooling.cc | 4 +-
src/relax/op/op.cc | 6 +-
src/relax/op/op_common.cc | 4 +-
src/relax/op/op_common.h | 14 +-
src/relax/op/tensor/inspect.cc | 99 +-
src/relax/op/tensor/manipulate.cc | 10 +-
src/relax/op/tensor/manipulate.h | 2 +-
src/relax/op/tensor/sampling.cc | 4 +-
src/relax/transform/adjust_matmul_order.cc | 2 +-
src/relax/transform/alter_op_impl.cc | 24 +-
src/relax/transform/annotate_tir_op_pattern.cc | 8 +-
.../transform/attach_attr_layout_free_buffers.cc | 16 +-
src/relax/transform/attach_global_symbol.cc | 6 +-
src/relax/transform/bind_params.cc | 16 +-
src/relax/transform/bind_symbolic_vars.cc | 28 +-
src/relax/transform/call_tir_rewrite.cc | 2 +-
src/relax/transform/canonicalize_bindings.cc | 19 +-
src/relax/transform/compute_prim_value.cc | 18 +-
src/relax/transform/convert_layout.cc | 12 +-
src/relax/transform/dataflow_inplace.cc | 66 +-
src/relax/transform/decompose_ops.cc | 2 +-
src/relax/transform/fold_constant.cc | 22 +-
src/relax/transform/fuse_ops.cc | 16 +-
src/relax/transform/fuse_tir.cc | 196 ++--
src/relax/transform/gradient.cc | 2 +-
src/relax/transform/infer_layout_utils.cc | 4 +-
src/relax/transform/infer_layout_utils.h | 2 +-
src/relax/transform/kill_after_last_use.cc | 2 +-
src/relax/transform/lazy_transform_params.cc | 6 +-
src/relax/transform/legalize_ops.cc | 6 +-
src/relax/transform/lift_transform_params.cc | 64 +-
src/relax/transform/lower_alloc_tensor.cc | 4 +-
src/relax/transform/merge_composite_functions.cc | 2 +-
src/relax/transform/meta_schedule.cc | 36 +-
src/relax/transform/remove_unused_parameters.cc | 4 +-
src/relax/transform/replace_global_vars.cc | 2 +-
src/relax/transform/rewrite_cuda_graph.cc | 51 +-
src/relax/transform/rewrite_dataflow_reshape.cc | 16 +-
src/relax/transform/run_codegen.cc | 2 +-
.../specialize_primfunc_based_on_callsite.cc | 18 +-
src/relax/transform/split_call_tir_by_pattern.cc | 50 +-
.../transform/split_layout_rewrite_preproc.cc | 22 +-
src/relax/transform/static_plan_block_memory.cc | 31 +-
src/relax/transform/to_non_dataflow.cc | 2 +-
src/relax/transform/utils.h | 24 +-
src/relax/utils.cc | 18 +-
src/runtime/metadata.h | 6 +-
src/runtime/vm/attn_backend.cc | 10 +-
src/runtime/vm/vm.cc | 2 +-
src/s_tir/analysis/calculate_allocated_memory.cc | 24 +-
src/s_tir/analysis/estimate_flops.cc | 6 +-
src/s_tir/analysis/find_anchor_sblock.cc | 8 +-
src/s_tir/analysis/identify_memcpy.cc | 10 +-
src/s_tir/analysis/is_pure_function.cc | 8 +-
src/s_tir/analysis/oob_checker.cc | 8 +-
.../analysis/sblock_access_region_detector.cc | 10 +-
.../analysis/sblock_buffer_access_lca_detector.cc | 8 +-
src/s_tir/analysis/verify_gpu_code.cc | 14 +-
src/s_tir/backend/adreno/inject_texture_alloc.cc | 12 +-
src/s_tir/backend/adreno/texture_flatten.cc | 16 +-
src/s_tir/data_layout.cc | 38 +-
src/s_tir/meta_schedule/arg_info.cc | 30 +-
src/s_tir/meta_schedule/database/database_utils.cc | 2 +-
src/s_tir/meta_schedule/extracted_task.cc | 2 +-
.../feature_extractor/per_store_feature.cc | 12 +-
src/s_tir/meta_schedule/module_equality.cc | 14 +-
src/s_tir/meta_schedule/module_equality.h | 2 +-
.../mutator/mutate_compute_location.cc | 2 +-
src/s_tir/meta_schedule/mutator/mutate_parallel.cc | 2 +-
src/s_tir/meta_schedule/mutator/mutate_unroll.cc | 2 +-
.../postproc/disallow_async_strided_mem_copy.cc | 22 +-
.../postproc/disallow_dynamic_loop.cc | 2 +-
.../postproc/rewrite_cooperative_fetch.cc | 16 +-
src/s_tir/meta_schedule/postproc/rewrite_layout.cc | 2 +-
.../postproc/rewrite_parallel_vectorize_unroll.cc | 6 +-
.../postproc/rewrite_reduction_block.cc | 8 +-
.../meta_schedule/postproc/rewrite_tensorize.cc | 12 +-
.../postproc/rewrite_unbound_block.cc | 6 +-
.../meta_schedule/postproc/verify_gpu_code.cc | 32 +-
src/s_tir/meta_schedule/schedule/cpu/winograd.cc | 4 +-
.../meta_schedule/schedule/cuda/thread_bind.cc | 4 +-
src/s_tir/meta_schedule/schedule/cuda/winograd.cc | 4 +-
.../meta_schedule/schedule/generic/winograd.cc | 2 +-
.../meta_schedule/schedule_rule/add_rfactor.cc | 2 +-
.../meta_schedule/schedule_rule/auto_inline.cc | 16 +-
.../schedule_rule/cross_thread_reduction.cc | 12 +-
.../schedule_rule/multi_level_tiling.cc | 14 +-
.../schedule_rule/multi_level_tiling.h | 2 +-
.../multi_level_tiling_tensor_core.cc | 125 +--
.../multi_level_tiling_wide_vector.cc | 8 +-
.../multi_level_tiling_with_intrin.cc | 4 +-
.../schedule_rule/parallel_vectorize_unroll.cc | 2 +-
.../schedule_rule/random_compute_location.cc | 4 +-
.../meta_schedule/schedule_rule/schedule_rule.cc | 14 +-
src/s_tir/meta_schedule/trace_apply.cc | 6 +-
src/s_tir/meta_schedule/utils.h | 22 +-
src/s_tir/sblock_dependence_info.cc | 4 +-
src/s_tir/sblock_scope.cc | 4 +-
src/s_tir/schedule/analysis.h | 18 +-
src/s_tir/schedule/analysis/analysis.cc | 74 +-
src/s_tir/schedule/analysis/layout.cc | 4 +-
src/s_tir/schedule/analysis/reducer.cc | 4 +-
src/s_tir/schedule/analysis/verify.cc | 2 +-
src/s_tir/schedule/concrete_schedule.cc | 6 +-
src/s_tir/schedule/concrete_schedule.h | 2 +-
src/s_tir/schedule/error.cc | 2 +-
src/s_tir/schedule/error.h | 2 +-
src/s_tir/schedule/instruction.cc | 2 +-
src/s_tir/schedule/instruction_traits.h | 2 +-
src/s_tir/schedule/ir_comparator.cc | 2 +-
src/s_tir/schedule/ir_comparator.h | 2 +-
src/s_tir/schedule/primitive.h | 10 +-
src/s_tir/schedule/primitive/annotate.cc | 2 +-
.../schedule/primitive/annotate_buffer_access.cc | 2 +-
src/s_tir/schedule/primitive/block_annotate.cc | 6 +-
src/s_tir/schedule/primitive/blockize_tensorize.cc | 10 +-
src/s_tir/schedule/primitive/cache_index.cc | 4 +-
.../schedule/primitive/cache_index_helpers.cc | 14 +-
src/s_tir/schedule/primitive/cache_index_helpers.h | 14 +-
src/s_tir/schedule/primitive/cache_read_write.cc | 6 +-
src/s_tir/schedule/primitive/compute_at.cc | 2 +-
src/s_tir/schedule/primitive/compute_inline.cc | 6 +-
src/s_tir/schedule/primitive/decompose_padding.cc | 6 +-
src/s_tir/schedule/primitive/for_kind.cc | 4 +-
src/s_tir/schedule/primitive/get_block_loop.cc | 2 +-
src/s_tir/schedule/primitive/hide_buffer_access.cc | 4 +-
.../schedule/primitive/layout_transformation.cc | 14 +-
.../schedule/primitive/loop_transformation.cc | 10 +-
src/s_tir/schedule/primitive/pad_einsum.cc | 6 +-
src/s_tir/schedule/primitive/read_write_at.cc | 2 +-
src/s_tir/schedule/primitive/reduction.cc | 4 +-
.../schedule/primitive/reorder_block_iter_var.cc | 2 +-
src/s_tir/schedule/primitive/rolling_buffer.cc | 4 +-
src/s_tir/schedule/primitive/sampling.cc | 12 +-
src/s_tir/schedule/schedule.cc | 2 +-
src/s_tir/schedule/state.cc | 4 +-
src/s_tir/schedule/trace.cc | 4 +-
src/s_tir/schedule/traced_schedule.cc | 2 +-
src/s_tir/schedule/traced_schedule.h | 2 +-
src/s_tir/schedule/transform.cc | 22 +-
src/s_tir/schedule/transform.h | 6 +-
src/s_tir/schedule/utils.h | 22 +-
src/s_tir/transform/annotate_irregular_loop.cc | 10 +-
src/s_tir/transform/bound_checker.cc | 12 +-
src/s_tir/transform/canonicalize_loop.cc | 8 +-
src/s_tir/transform/compact_buffer_region.cc | 10 +-
src/s_tir/transform/convert_blocks_to_opaque.cc | 6 +-
src/s_tir/transform/decorate_device_scope.cc | 8 +-
src/s_tir/transform/default_gpu_schedule.cc | 22 +-
src/s_tir/transform/hoist_expression.cc | 24 +-
src/s_tir/transform/inject_double_buffer.cc | 8 +-
src/s_tir/transform/inject_permuted_layout.cc | 10 +-
src/s_tir/transform/inject_ptx_async_copy.cc | 28 +-
src/s_tir/transform/inject_ptx_ldg32.cc | 14 +-
src/s_tir/transform/inject_software_pipeline.cc | 6 +-
src/s_tir/transform/inject_virtual_thread.cc | 10 +-
src/s_tir/transform/lift_thread_binding.cc | 6 +-
src/s_tir/transform/loop_partition.cc | 20 +-
src/s_tir/transform/lower_async_dma.cc | 20 +-
.../transform/lower_cross_thread_reduction.cc | 12 +-
src/s_tir/transform/lower_init_block.cc | 8 +-
src/s_tir/transform/lower_match_buffer.cc | 12 +-
src/s_tir/transform/lower_opaque_block.cc | 10 +-
src/s_tir/transform/lower_thread_allreduce.cc | 18 +-
src/s_tir/transform/lower_vtcm_alloc.cc | 6 +-
.../manifest_shared_memory_local_stage.cc | 10 +-
src/s_tir/transform/memhammer_coalesce.cc | 2 +-
.../transform/memhammer_intermediate_stage.cc | 4 +-
src/s_tir/transform/memhammer_lower_auto_copy.cc | 12 +-
src/s_tir/transform/memhammer_rewrite_rule.h | 8 +-
.../transform/memhammer_tensorcore_rewrite.cc | 2 +-
.../transform/merge_shared_memory_allocations.cc | 22 +-
.../plan_update_buffer_allocation_location.cc | 10 +-
src/s_tir/transform/profile_instrumentation.cc | 10 +-
src/s_tir/transform/remove_store_undef.cc | 16 +-
.../remove_weight_layout_rewrite_block.cc | 10 +-
src/s_tir/transform/renew_defs.cc | 8 +-
src/s_tir/transform/renormalize_split_pattern.cc | 12 +-
src/s_tir/transform/rewrite_unsafe_select.cc | 10 +-
src/s_tir/transform/storage_access.cc | 8 +-
src/s_tir/transform/storage_access.h | 6 +-
src/s_tir/transform/tensorcore_infer_fragment.cc | 12 +-
src/s_tir/transform/thread_storage_sync.cc | 18 +-
src/s_tir/transform/transform_mma_buffer_layout.cc | 16 +-
src/s_tir/transform/unify_thread_binding.cc | 10 +-
.../transform/using_assume_to_reduce_branches.cc | 48 +-
src/script/ir_builder/ir/ir.cc | 8 +-
src/script/ir_builder/relax/distributed.cc | 2 +-
src/script/ir_builder/relax/ir.cc | 2 +-
src/script/ir_builder/{tir => tirx}/frame.cc | 46 +-
src/script/ir_builder/{tir => tirx}/ir.cc | 300 ++---
src/script/ir_builder/{tir => tirx}/utils.h | 26 +-
src/script/printer/ir/ir.cc | 2 +-
src/script/printer/relax/call.cc | 2 +-
src/script/printer/relax/function.cc | 2 +-
src/script/printer/relax/struct_info.cc | 6 +-
src/script/printer/relax/tir.cc | 8 +-
src/script/printer/relax/utils.h | 2 +-
src/script/printer/{tir => tirx}/block.cc | 62 +-
src/script/printer/{tir => tirx}/buffer.cc | 52 +-
src/script/printer/{tir => tirx}/expr.cc | 171 +--
src/script/printer/{tir => tirx}/for_loop.cc | 34 +-
src/script/printer/{tir => tirx}/function.cc | 63 +-
src/script/printer/{tir => tirx}/ir.cc | 2 +-
src/script/printer/{tir => tirx}/stmt.cc | 84 +-
src/script/printer/{tir => tirx}/utils.h | 76 +-
src/script/printer/utils.h | 6 +-
src/support/ffi_testing.cc | 2 +-
src/support/nd_int_set.h | 4 +-
src/target/build_common.h | 14 +-
src/target/codegen.cc | 8 +-
src/target/intrin_rule.cc | 118 +-
src/target/intrin_rule.h | 10 +-
src/target/llvm/codegen_aarch64.cc | 2 +-
src/target/llvm/codegen_amdgpu.cc | 2 +-
src/target/llvm/codegen_arm.cc | 12 +-
src/target/llvm/codegen_cpu.cc | 18 +-
src/target/llvm/codegen_hexagon.cc | 4 +-
src/target/llvm/codegen_llvm.cc | 22 +-
src/target/llvm/codegen_llvm.h | 18 +-
src/target/llvm/codegen_nvptx.cc | 2 +-
src/target/llvm/codegen_x86_64.cc | 6 +-
src/target/llvm/intrin_rule_hexagon.cc | 72 +-
src/target/llvm/intrin_rule_llvm.cc | 209 ++--
src/target/llvm/intrin_rule_llvm.h | 12 +-
src/target/llvm/intrin_rule_nvptx.cc | 78 +-
src/target/llvm/intrin_rule_rocm.cc | 98 +-
src/target/llvm/llvm_module.cc | 2 +-
src/target/source/codegen_c.cc | 12 +-
src/target/source/codegen_c.h | 18 +-
src/target/source/codegen_c_host.cc | 2 +-
src/target/source/codegen_c_host.h | 2 +-
src/target/source/codegen_cuda.cc | 82 +-
src/target/source/codegen_cuda.h | 4 +-
src/target/source/codegen_metal.cc | 10 +-
src/target/source/codegen_opencl.cc | 9 +-
src/target/source/codegen_source_base.cc | 4 +-
src/target/source/codegen_source_base.h | 10 +-
src/target/source/codegen_webgpu.cc | 14 +-
src/target/source/intrin_rule_cuda.cc | 97 +-
src/target/source/intrin_rule_metal.cc | 80 +-
src/target/source/intrin_rule_opencl.cc | 66 +-
src/target/source/intrin_rule_webgpu.cc | 68 +-
src/target/spirv/codegen_spirv.cc | 20 +-
src/target/spirv/codegen_spirv.h | 12 +-
src/target/spirv/intrin_rule_spirv.cc | 94 +-
src/target/spirv/ir_builder.h | 2 +-
src/target/spirv/spirv_utils.cc | 6 +-
src/target/target.cc | 2 +-
src/te/operation/compute_op.cc | 34 +-
src/te/operation/create_primfunc.cc | 26 +-
src/te/operation/create_primfunc.h | 6 +-
src/te/operation/extern_op.cc | 4 +-
src/te/operation/graph.cc | 4 +-
src/te/operation/graph.h | 2 +-
src/te/operation/scan_op.cc | 4 +-
src/{tir => tirx}/analysis/check_contains.cc | 6 +-
src/{tir => tirx}/analysis/check_contains.h | 8 +-
src/{tir => tirx}/analysis/collect_call_map.cc | 14 +-
src/{tir => tirx}/analysis/control_flow_graph.cc | 56 +-
src/{tir => tirx}/analysis/control_flow_graph.h | 18 +-
src/{tir => tirx}/analysis/deep_equal.cc | 12 +-
src/{tir => tirx}/analysis/expr_complexity.cc | 10 +-
src/{tir => tirx}/analysis/side_effect.cc | 12 +-
src/{tir => tirx}/analysis/stmt_finding.cc | 18 +-
src/{tir => tirx}/analysis/var_touch.cc | 8 +-
src/{tir => tirx}/analysis/var_use_def_analysis.cc | 6 +-
src/{tir => tirx}/analysis/var_use_def_analysis.h | 10 +-
src/{tir => tirx}/analysis/verify_memory.cc | 20 +-
src/{tir => tirx}/analysis/verify_ssa.cc | 16 +-
src/{tir => tirx}/analysis/verify_well_formed.cc | 22 +-
src/{tir => tirx}/ir/buffer.cc | 68 +-
src/{tir => tirx}/ir/buffer_common.h | 6 +-
src/{tir => tirx}/ir/data_type_rewriter.cc | 18 +-
src/{tir => tirx}/ir/data_type_rewriter.h | 6 +-
src/{tir => tirx}/ir/expr.cc | 99 +-
src/{tir => tirx}/ir/expr_functor.cc | 6 +-
src/{tir => tirx}/ir/function.cc | 28 +-
src/{tir => tirx}/ir/functor_common.h | 6 +-
src/{tir => tirx}/ir/index_map.cc | 24 +-
src/{tir => tirx}/ir/py_functor.cc | 34 +-
src/{tir => tirx}/ir/script/script_complete.cc | 10 +-
src/{tir => tirx}/ir/script/script_complete.h | 10 +-
src/{tir => tirx}/ir/specialize.cc | 26 +-
src/{tir => tirx}/ir/stmt.cc | 65 +-
src/{tir => tirx}/ir/stmt_functor.cc | 22 +-
src/{tir => tirx}/ir/tir_visitor_with_path.cc | 8 +-
src/{tir => tirx}/ir/tir_visitor_with_path.h | 14 +-
src/{tir => tirx}/ir/transform.cc | 48 +-
src/{tir => tirx}/op/builtin.cc | 22 +-
src/{tir => tirx}/op/op.cc | 330 +++---
src/{tir => tirx}/op/runtime.cc | 12 +-
.../transform/annotate_device_regions.cc | 16 +-
src/{tir => tirx}/transform/bind_target.cc | 18 +-
src/{tir => tirx}/transform/common_subexpr_elim.cc | 22 +-
src/{tir => tirx}/transform/dtype_conversion.cc | 4 +-
src/{tir => tirx}/transform/dtype_conversion.h | 10 +-
src/{tir => tirx}/transform/flatten_buffer.cc | 18 +-
.../transform/force_narrow_index_to_i32.cc | 12 +-
.../transform/inline_private_functions.cc | 30 +-
src/{tir => tirx}/transform/ir_utils.cc | 22 +-
src/{tir => tirx}/transform/ir_utils.h | 12 +-
.../transform/lower_custom_datatypes.cc | 14 +-
.../transform/lower_device_kernel_launch.cc | 22 +-
src/{tir => tirx}/transform/lower_intrin.cc | 34 +-
src/{tir => tirx}/transform/lower_tvm_builtin.cc | 28 +-
src/{tir => tirx}/transform/lower_warp_memory.cc | 20 +-
src/{tir => tirx}/transform/make_packed_api.cc | 54 +-
src/{tir => tirx}/transform/narrow_datatype.cc | 14 +-
src/{tir => tirx}/transform/primfunc_utils.cc | 24 +-
src/{tir => tirx}/transform/remap_thread_axis.cc | 20 +-
src/{tir => tirx}/transform/remove_assume.cc | 24 +-
src/{tir => tirx}/transform/remove_no_op.cc | 24 +-
src/{tir => tirx}/transform/remove_no_op.h | 8 +-
src/{tir => tirx}/transform/replace_global_vars.cc | 14 +-
.../transform/replace_selected_expr.cc | 16 +-
.../transform/replace_selected_expr.h | 12 +-
src/{tir => tirx}/transform/simplify.cc | 34 +-
src/{tir => tirx}/transform/simplify.h | 8 +-
src/{tir => tirx}/transform/skip_assert.cc | 14 +-
src/{tir => tirx}/transform/split_host_device.cc | 24 +-
src/{tir => tirx}/transform/storage_rewrite.cc | 34 +-
src/{tir => tirx}/transform/tvm_ffi_binder.cc | 26 +-
src/{tir => tirx}/transform/tvm_ffi_binder.h | 10 +-
src/{tir => tirx}/transform/unroll_loop.cc | 22 +-
.../transform/unsupported_dtype_legalize.cc | 28 +-
.../transform/update_pointer_storage_scope.cc | 12 +-
.../transform/update_pointer_storage_scope.h | 10 +-
src/{tir => tirx}/transform/vectorize_loop.cc | 30 +-
tests/cpp/arith_integer_set_test.cc | 8 +-
tests/cpp/arith_simplify_test.cc | 24 +-
tests/cpp/expr_test.cc | 8 +-
tests/cpp/ir_functor_test.cc | 40 +-
tests/cpp/nested_msg_test.cc | 2 +-
tests/cpp/pattern_match_test.cc | 73 +-
tests/cpp/tir_analysis_side_effect.cc | 18 +-
tests/cpp/tir_scalable_datatype.cc | 14 +-
.../test_runtime_packed_func.py | 10 +-
.../python/arith/test_arith_canonical_simplify.py | 204 ++--
tests/python/arith/test_arith_const_int_bound.py | 84 +-
tests/python/arith/test_arith_deduce_bound.py | 70 +-
tests/python/arith/test_arith_detect_clip_bound.py | 22 +-
.../arith/test_arith_detect_linear_equation.py | 10 +-
tests/python/arith/test_arith_domain_touched.py | 4 +-
tests/python/arith/test_arith_intset.py | 98 +-
tests/python/arith/test_arith_iter_affine_map.py | 268 ++---
tests/python/arith/test_arith_modular_set.py | 58 +-
.../test_arith_narrow_predicate_expression.py | 42 +-
tests/python/arith/test_arith_rewrite_simplify.py | 1148 ++++++++++----------
tests/python/arith/test_arith_simplify.py | 32 +-
.../arith/test_arith_solve_linear_equations.py | 44 +-
.../arith/test_arith_solve_linear_inequality.py | 54 +-
tests/python/codegen/test_codegen_assert.py | 2 +-
.../python/codegen/test_codegen_error_handling.py | 2 +-
tests/python/codegen/test_gpu_codegen_allreduce.py | 2 +-
tests/python/codegen/test_inject_ptx_ldg32.py | 6 +-
tests/python/codegen/test_target_codegen.py | 2 +-
.../python/codegen/test_target_codegen_aarch64.py | 64 +-
tests/python/codegen/test_target_codegen_arm.py | 14 +-
tests/python/codegen/test_target_codegen_blob.py | 2 +-
tests/python/codegen/test_target_codegen_bool.py | 6 +-
tests/python/codegen/test_target_codegen_c_host.py | 14 +-
.../codegen/test_target_codegen_cross_llvm.py | 6 +-
tests/python/codegen/test_target_codegen_cuda.py | 114 +-
.../python/codegen/test_target_codegen_cuda_fp4.py | 8 +-
.../python/codegen/test_target_codegen_cuda_fp8.py | 36 +-
tests/python/codegen/test_target_codegen_device.py | 10 +-
tests/python/codegen/test_target_codegen_extern.py | 2 +-
.../codegen/test_target_codegen_gpu_common.py | 4 +-
.../python/codegen/test_target_codegen_hexagon.py | 8 +-
tests/python/codegen/test_target_codegen_llvm.py | 98 +-
.../python/codegen/test_target_codegen_llvm_vla.py | 20 +-
tests/python/codegen/test_target_codegen_metal.py | 8 +-
tests/python/codegen/test_target_codegen_opencl.py | 32 +-
tests/python/codegen/test_target_codegen_riscv.py | 6 +-
tests/python/codegen/test_target_codegen_rocm.py | 6 +-
.../codegen/test_target_codegen_static_init.py | 4 +-
tests/python/codegen/test_target_codegen_vulkan.py | 62 +-
tests/python/codegen/test_target_codegen_x86.py | 6 +-
.../contrib/test_android/test_meta_schedule.py | 2 +-
.../python/contrib/test_hexagon/infrastructure.py | 2 +-
.../test_hexagon/test_2d_physical_buffers.py | 4 +-
.../test_hexagon/test_async_dma_pipeline.py | 18 +-
.../test_hexagon/test_benchmark_elemwise_add.py | 4 +-
.../test_hexagon/test_benchmark_maxpool2d.py | 2 +-
.../contrib/test_hexagon/test_dma_builtin.py | 2 +-
.../contrib/test_hexagon/test_memory_alloc.py | 2 +-
.../contrib/test_hexagon/test_meta_schedule.py | 10 +-
.../contrib/test_hexagon/test_parallel_hvx.py | 8 +-
.../test_hexagon/test_parallel_hvx_load_vtcm.py | 10 +-
.../contrib/test_hexagon/test_parallel_scalar.py | 8 +-
.../test_relax_2d_buffer_allocation.py | 2 +-
tests/python/contrib/test_hexagon/test_sigmoid.py | 2 +-
.../test_hexagon/test_software_pipeline_async.py | 8 +-
tests/python/contrib/test_hexagon/test_take.py | 20 +-
.../contrib/test_hexagon/test_thread_pool.py | 6 +-
tests/python/contrib/test_hexagon/test_vtcm.py | 6 +-
.../contrib/test_hexagon/test_vtcm_bandwidth.py | 2 +-
tests/python/contrib/test_sort.py | 4 +-
.../python/contrib/test_tir_triton_integration.py | 2 +-
tests/python/disco/test_callback.py | 2 +-
tests/python/disco/test_nvshmem.py | 2 +-
tests/python/disco/test_session.py | 2 +-
tests/python/driver/test_compile.py | 4 +-
tests/python/ir/analysis/test_collect_call_map.py | 2 +-
tests/python/ir/test_datatype_nv_fp4.py | 6 +-
tests/python/ir/test_datatype_nv_fp8.py | 6 +-
tests/python/ir/test_ir_container.py | 20 +-
tests/python/ir/test_ir_type.py | 2 +-
tests/python/ir/test_node_reflection.py | 36 +-
tests/python/ir/test_pass_instrument.py | 4 +-
.../python/ir/test_transform_replace_global_var.py | 2 +-
tests/python/nightly/test_nnapi/test_ops.py | 2 +-
tests/python/relax/backend/adreno/mod_utils.py | 6 +-
tests/python/relax/backend/adreno/test_clml_ops.py | 2 +-
.../relax/backend/adreno/test_texture_network.py | 2 +-
.../adreno/test_transform_annotate_custom_scope.py | 4 +-
.../test_transform_fold_vdevice_scope_change.py | 2 +-
tests/python/relax/backend/adreno/utils.py | 2 +-
.../distributed/test_distributed_dtensor_sinfo.py | 4 +-
.../test_distributed_transform_lower_distir.py | 16 +-
...ributed_transform_lower_global_to_local_view.py | 90 +-
...est_distributed_transform_propagate_sharding.py | 58 +-
.../test_distributed_tvmscript_parser.py | 10 +-
.../test_distributed_tvmscript_printer.py | 8 +-
.../test_runtime_builtin_kv_cache_transfer.py | 16 +-
tests/python/relax/test_analysis.py | 20 +-
.../test_analysis_computable_at_compile_time.py | 2 +-
.../python/relax/test_analysis_detect_recursion.py | 2 +-
.../relax/test_analysis_estimate_memory_usage.py | 2 +-
.../relax/test_analysis_struct_info_analysis.py | 82 +-
.../test_analysis_suggest_layout_transforms.py | 12 +-
tests/python/relax/test_analysis_well_formed.py | 36 +-
tests/python/relax/test_ast_printer.py | 24 +-
.../python/relax/test_backend_dispatch_sampling.py | 4 +-
.../relax/test_backend_dispatch_sort_scan.py | 12 +-
.../relax/test_backend_transform_shape_lower.py | 6 +-
tests/python/relax/test_base_py_module.py | 4 +-
tests/python/relax/test_base_py_module_printer.py | 18 +-
.../relax/test_base_py_module_symbolic_shape.py | 42 +-
tests/python/relax/test_bind_params.py | 10 +-
tests/python/relax/test_bind_symbolic_vars.py | 20 +-
tests/python/relax/test_blockbuilder_core.py | 92 +-
tests/python/relax/test_blockbuilder_emit_te.py | 12 +-
tests/python/relax/test_codegen_cublas.py | 6 +-
tests/python/relax/test_codegen_cutlass.py | 30 +-
tests/python/relax/test_codegen_hipblas.py | 6 +-
tests/python/relax/test_contrib_vllm.py | 2 +-
tests/python/relax/test_dataflow_inplace.py | 16 +-
tests/python/relax/test_dataflow_pattern.py | 18 +-
tests/python/relax/test_dataflow_rewriter.py | 2 +-
tests/python/relax/test_dlpack_integration.py | 4 +-
tests/python/relax/test_e2e_op_dynamic.py | 4 +-
...eliminate_pad_branch_using_buffer_assumption.py | 14 +-
tests/python/relax/test_expr.py | 32 +-
tests/python/relax/test_expr_functor.py | 4 +-
tests/python/relax/test_frontend_common.py | 8 +-
tests/python/relax/test_frontend_dynamo.py | 6 +-
.../relax/test_frontend_from_exported_program.py | 2 +-
tests/python/relax/test_frontend_from_fx.py | 2 +-
tests/python/relax/test_frontend_nn_debug.py | 4 +-
tests/python/relax/test_frontend_nn_exporter.py | 22 +-
.../python/relax/test_frontend_nn_extern_module.py | 2 +-
tests/python/relax/test_frontend_nn_jit.py | 6 +-
tests/python/relax/test_frontend_nn_modules.py | 4 +-
tests/python/relax/test_frontend_nn_op.py | 16 +-
tests/python/relax/test_frontend_nn_subroutines.py | 2 +-
tests/python/relax/test_frontend_onnx.py | 2 +-
tests/python/relax/test_frontend_stablehlo.py | 2 +-
tests/python/relax/test_inline_functions.py | 6 +-
.../relax/test_meta_schedule_relax_integration.py | 4 +-
tests/python/relax/test_op_binary.py | 48 +-
tests/python/relax/test_op_ccl.py | 20 +-
tests/python/relax/test_op_create.py | 52 +-
tests/python/relax/test_op_datatype.py | 6 +-
tests/python/relax/test_op_image.py | 14 +-
tests/python/relax/test_op_index.py | 62 +-
tests/python/relax/test_op_linear_algebra.py | 26 +-
tests/python/relax/test_op_manipulate.py | 204 ++--
tests/python/relax/test_op_misc.py | 4 +-
tests/python/relax/test_op_nn.py | 82 +-
tests/python/relax/test_op_nn_convolution.py | 166 +--
tests/python/relax/test_op_nn_pooling.py | 182 ++--
tests/python/relax/test_op_qdq.py | 8 +-
tests/python/relax/test_op_search.py | 22 +-
tests/python/relax/test_op_set.py | 8 +-
tests/python/relax/test_op_sort.py | 20 +-
tests/python/relax/test_op_statistical.py | 24 +-
tests/python/relax/test_op_take.py | 2 +-
tests/python/relax/test_op_ternary.py | 6 +-
tests/python/relax/test_op_unary.py | 10 +-
tests/python/relax/test_op_view.py | 2 +-
tests/python/relax/test_op_vision.py | 8 +-
.../python/relax/test_optimize_layout_transform.py | 6 +-
tests/python/relax/test_pipeline.py | 2 +-
tests/python/relax/test_pytorch_integration.py | 4 +-
tests/python/relax/test_relax_operators.py | 2 +-
.../python/relax/test_relax_to_pyfunc_converter.py | 2 +-
...runtime_builtin_paged_attention_kv_cache_cpu.py | 16 +-
..._builtin_paged_attention_kv_cache_flashinfer.py | 2 +-
...ltin_paged_attention_kv_cache_mla_flashinfer.py | 2 +-
...ime_builtin_paged_attention_kv_cache_mla_tir.py | 6 +-
...runtime_builtin_paged_attention_kv_cache_tir.py | 16 +-
.../python/relax/test_runtime_builtin_rnn_state.py | 8 +-
tests/python/relax/test_struct_info.py | 12 +-
tests/python/relax/test_testing_nn.py | 4 +-
tests/python/relax/test_tir_call_source_kernel.py | 2 +-
tests/python/relax/test_transform.py | 14 +-
.../relax/test_transform_adjust_matmul_order.py | 2 +-
tests/python/relax/test_transform_alter_op_impl.py | 6 +-
.../test_transform_annotate_tir_op_pattern.py | 8 +-
...st_transform_attach_attr_layout_free_buffers.py | 4 +-
.../relax/test_transform_attach_global_symbol.py | 4 +-
tests/python/relax/test_transform_bind_params.py | 2 +-
.../relax/test_transform_bind_symbolic_vars.py | 2 +-
.../relax/test_transform_bundle_model_params.py | 2 +-
.../relax/test_transform_canonicalize_bindings.py | 2 +-
tests/python/relax/test_transform_codegen_pass.py | 4 +-
.../test_transform_combine_parallel_matmul.py | 4 +-
.../relax/test_transform_compute_prim_value.py | 8 +-
.../python/relax/test_transform_convert_layout.py | 2 +-
tests/python/relax/test_transform_cse.py | 2 +-
.../relax/test_transform_dead_code_elimination.py | 2 +-
tests/python/relax/test_transform_decompose_ops.py | 2 +-
.../relax/test_transform_expand_tuple_args.py | 2 +-
tests/python/relax/test_transform_fold_constant.py | 2 +-
tests/python/relax/test_transform_fuse_ops.py | 56 +-
.../relax/test_transform_fuse_ops_by_pattern.py | 2 +-
tests/python/relax/test_transform_fuse_tir.py | 70 +-
.../relax/test_transform_fuse_transpose_matmul.py | 6 +-
tests/python/relax/test_transform_gradient.py | 4 +-
.../relax/test_transform_gradient_te_register.py | 24 +-
.../test_transform_inline_private_functions.py | 2 +-
.../relax/test_transform_ipc_allreduce_rewrite.py | 2 +-
tests/python/relax/test_transform_lambda_lift.py | 2 +-
.../relax/test_transform_lazy_transform_params.py | 2 +-
tests/python/relax/test_transform_legalize_ops.py | 18 +-
.../relax/test_transform_legalize_ops_binary.py | 118 +-
.../relax/test_transform_legalize_ops_ccl.py | 6 +-
.../test_transform_legalize_ops_create_datatype.py | 48 +-
.../test_transform_legalize_ops_distributed.py | 4 +-
.../relax/test_transform_legalize_ops_grad.py | 16 +-
.../relax/test_transform_legalize_ops_image.py | 6 +-
..._transform_legalize_ops_index_linear_algebra.py | 48 +-
.../test_transform_legalize_ops_manipulate.py | 86 +-
.../python/relax/test_transform_legalize_ops_nn.py | 120 +-
.../relax/test_transform_legalize_ops_qdq.py | 24 +-
...st_transform_legalize_ops_search_statistical.py | 46 +-
.../relax/test_transform_legalize_ops_unary.py | 2 +-
.../relax/test_transform_lift_transform_params.py | 10 +-
.../test_transform_lower_gpu_ipc_alloc_storage.py | 2 +-
.../test_transform_merge_composite_functions.py | 6 +-
.../test_transform_meta_schedule_apply_database.py | 12 +-
.../relax/test_transform_meta_schedule_tuning.py | 22 +-
tests/python/relax/test_transform_normalize.py | 8 +-
.../relax/test_transform_normalize_global_var.py | 4 +-
...st_transform_operator_specific_normalization.py | 2 +-
.../python/relax/test_transform_realize_vdevice.py | 2 +-
.../relax/test_transform_remove_unused_outputs.py | 2 +-
.../test_transform_remove_unused_parameters.py | 2 +-
.../test_transform_reorder_take_after_matmul.py | 2 +-
.../relax/test_transform_rewrite_cuda_graph.py | 18 +-
.../test_transform_rewrite_dataflow_reshape.py | 22 +-
...nsform_specialize_primfunc_based_on_callsite.py | 2 +-
.../test_transform_split_layout_rewrite_preproc.py | 8 +-
.../test_transform_static_plan_block_memory.py | 2 +-
.../relax/test_transform_to_mixed_precision.py | 2 +-
.../python/relax/test_transform_update_vdevice.py | 2 +-
tests/python/relax/test_tvmscript_ir_builder.py | 10 +-
tests/python/relax/test_tvmscript_parser.py | 52 +-
tests/python/relax/test_tvmscript_printer_relax.py | 52 +-
tests/python/relax/test_tvmscript_pyfunc.py | 4 +-
tests/python/relax/test_utils.py | 2 +-
.../relax/test_vm_alloc_storage_with_scope.py | 2 +-
tests/python/relax/test_vm_build.py | 26 +-
tests/python/relax/test_vm_builtin_lower.py | 2 +-
tests/python/relax/test_vm_codegen_only.py | 6 +-
tests/python/relax/test_vm_codegen_tir.py | 4 +-
tests/python/relax/test_vm_cuda_graph.py | 2 +-
tests/python/relax/texture/test_texture_nd.py | 8 +-
.../python/runtime/test_evaluator_with_preproc.py | 4 +-
tests/python/runtime/test_executable.py | 16 +-
tests/python/runtime/test_runtime_container.py | 12 +-
tests/python/runtime/test_runtime_extension.py | 2 +-
tests/python/runtime/test_runtime_measure.py | 4 +-
tests/python/runtime/test_runtime_module_export.py | 4 +-
tests/python/runtime/test_runtime_module_load.py | 20 +-
.../python/runtime/test_runtime_module_property.py | 2 +-
tests/python/runtime/test_runtime_rpc.py | 4 +-
tests/python/runtime/test_runtime_trace.py | 50 +-
...st_s_tir_analysis_calculate_allocated_memory.py | 4 +-
.../test_s_tir_analysis_estimate_tir_flops.py | 2 +-
.../test_s_tir_analysis_identify_memcpy.py | 4 +-
.../test_s_tir_analysis_is_pure_function.py | 2 +-
.../s_tir/analysis/test_s_tir_analysis_oob.py | 2 +-
.../s_tir/analysis/test_sblock_access_region.py | 4 +-
.../analysis/test_sblock_buffer_access_lca.py | 2 +-
.../s_tir/base/test_sblock_dependence_info.py | 12 +-
.../s_tir/base/test_tir_te_extern_primfunc.py | 2 +-
tests/python/s_tir/dlight/test_benchmark.py | 10 +-
tests/python/s_tir/dlight/test_cpu_gemv.py | 34 +-
tests/python/s_tir/dlight/test_gpu_conv.py | 4 +-
tests/python/s_tir/dlight/test_gpu_fallback.py | 10 +-
tests/python/s_tir/dlight/test_gpu_gemv.py | 34 +-
.../s_tir/dlight/test_gpu_general_reduction.py | 26 +-
.../python/s_tir/dlight/test_gpu_low_batch_gemv.py | 18 +-
tests/python/s_tir/dlight/test_gpu_matmul.py | 24 +-
.../s_tir/dlight/test_gpu_matmul_tensorize.py | 42 +-
tests/python/s_tir/dlight/test_gpu_reduction.py | 64 +-
tests/python/s_tir/dlight/test_gpu_rmsnorm.py | 10 +-
tests/python/s_tir/dlight/test_gpu_transpose.py | 14 +-
tests/python/s_tir/dlight/test_primitives.py | 4 +-
.../meta_schedule/test_meta_schedule_arg_info.py | 2 +-
.../meta_schedule/test_meta_schedule_builder.py | 8 +-
.../meta_schedule/test_meta_schedule_cost_model.py | 6 +-
.../meta_schedule/test_meta_schedule_database.py | 6 +-
...schedule_feature_extractor_per_store_feature.py | 14 +-
.../test_meta_schedule_measure_callback.py | 2 +-
.../test_meta_schedule_mma_tensorize.py | 2 +-
...eta_schedule_mutator_mutate_compute_location.py | 2 +-
.../test_meta_schedule_mutator_mutate_parallel.py | 2 +-
..._meta_schedule_mutator_mutate_thread_binding.py | 2 +-
.../test_meta_schedule_mutator_mutate_tile_size.py | 2 +-
.../test_meta_schedule_mutator_mutate_unroll.py | 2 +-
.../test_meta_schedule_post_order_apply.py | 4 +-
...ule_postproc_disallow_async_strided_mem_copy.py | 4 +-
...meta_schedule_postproc_disallow_dynamic_loop.py | 4 +-
..._schedule_postproc_rewrite_cooperative_fetch.py | 8 +-
.../test_meta_schedule_postproc_rewrite_layout.py | 12 +-
...e_postproc_rewrite_parallel_vectorize_unroll.py | 6 +-
...ta_schedule_postproc_rewrite_reduction_block.py | 4 +-
...est_meta_schedule_postproc_rewrite_tensorize.py | 10 +-
...meta_schedule_postproc_rewrite_unbound_block.py | 8 +-
.../test_meta_schedule_postproc_verify_gpu_code.py | 6 +-
...est_meta_schedule_postproc_verify_vtcm_limit.py | 6 +-
.../meta_schedule/test_meta_schedule_runner.py | 14 +-
...test_meta_schedule_schedule_rule_add_rfactor.py | 8 +-
...eta_schedule_schedule_rule_apply_custom_rule.py | 4 +-
.../test_meta_schedule_schedule_rule_auto_bind.py | 2 +-
...test_meta_schedule_schedule_rule_auto_inline.py | 10 +-
...chedule_schedule_rule_cross_thread_reduction.py | 14 +-
.../test_meta_schedule_schedule_rule_mlt.py | 24 +-
.../test_meta_schedule_schedule_rule_mlt_intrin.py | 12 +-
.../test_meta_schedule_schedule_rule_mlt_tc.py | 24 +-
...dule_schedule_rule_parallel_vectorize_unroll.py | 6 +-
...hedule_schedule_rule_random_compute_location.py | 2 +-
.../test_meta_schedule_search_strategy.py | 2 +-
.../meta_schedule/test_meta_schedule_space_cpu.py | 92 +-
.../meta_schedule/test_meta_schedule_space_cuda.py | 36 +-
.../test_meta_schedule_space_cuda_async.py | 10 +-
.../test_meta_schedule_space_generator.py | 2 +-
.../test_meta_schedule_space_post_opt.py | 2 +-
.../test_meta_schedule_task_scheduler.py | 8 +-
.../test_meta_schedule_trace_apply.py | 42 +-
.../test_meta_schedule_tune_context.py | 4 +-
.../meta_schedule/test_meta_schedule_tune_tir.py | 2 +-
.../s_tir/schedule/test_tir_schedule_analysis.py | 16 +-
.../test_tir_schedule_annotate_buffer_access.py | 4 +-
.../schedule/test_tir_schedule_block_scope.py | 10 +-
.../s_tir/schedule/test_tir_schedule_blockize.py | 4 +-
.../schedule/test_tir_schedule_cache_index.py | 4 +-
.../schedule/test_tir_schedule_cache_read_write.py | 4 +-
.../s_tir/schedule/test_tir_schedule_compute_at.py | 8 +-
.../schedule/test_tir_schedule_compute_inline.py | 16 +-
.../test_tir_schedule_decompose_padding.py | 4 +-
.../s_tir/schedule/test_tir_schedule_error.py | 6 +-
.../s_tir/schedule/test_tir_schedule_for_kind.py | 4 +-
.../test_tir_schedule_fuse_reduction_epilogue.py | 4 +-
...ir_schedule_fuse_reduction_epilogue_clipping.py | 4 +-
...st_tir_schedule_fuse_reduction_epilogue_relu.py | 4 +-
.../s_tir/schedule/test_tir_schedule_merge.py | 4 +-
.../s_tir/schedule/test_tir_schedule_pad_einsum.py | 12 +-
.../s_tir/schedule/test_tir_schedule_partition.py | 6 +-
.../schedule/test_tir_schedule_read_write_at.py | 4 +-
.../s_tir/schedule/test_tir_schedule_reduction.py | 4 +-
.../s_tir/schedule/test_tir_schedule_reindex.py | 4 +-
.../s_tir/schedule/test_tir_schedule_reorder.py | 4 +-
.../test_tir_schedule_reorder_block_iter_var.py | 4 +-
.../s_tir/schedule/test_tir_schedule_rfactor.py | 8 +-
.../schedule/test_tir_schedule_rolling_buffer.py | 6 +-
.../s_tir/schedule/test_tir_schedule_sampling.py | 4 +-
.../test_tir_schedule_set_axis_separator.py | 6 +-
.../s_tir/schedule/test_tir_schedule_set_dtype.py | 4 +-
.../s_tir/schedule/test_tir_schedule_set_scope.py | 4 +-
.../s_tir/schedule/test_tir_schedule_split_fuse.py | 22 +-
.../s_tir/schedule/test_tir_schedule_state.py | 18 +-
.../test_tir_schedule_state_cached_flags.py | 12 +-
.../schedule/test_tir_schedule_storage_align.py | 4 +-
.../s_tir/schedule/test_tir_schedule_tensorize.py | 28 +-
..._tir_schedule_tensorize_ldmatrix_mma_numeric.py | 2 +-
.../test_tir_schedule_tensorize_mfma_numeric.py | 2 +-
.../s_tir/schedule/test_tir_schedule_trace.py | 8 +-
.../s_tir/schedule/test_tir_schedule_transform.py | 10 +-
.../schedule/test_tir_schedule_transform_layout.py | 28 +-
.../s_tir/schedule/test_tir_schedule_utilities.py | 6 +-
tests/python/s_tir/test_s_tir_renew_defs.py | 8 +-
...test_s_tir_transform_annotate_irregular_loop.py | 4 +-
.../test_s_tir_transform_canonicalize_loop.py | 4 +-
.../test_s_tir_transform_compact_buffer_region.py | 8 +-
...est_s_tir_transform_convert_blocks_to_opaque.py | 6 +-
.../test_s_tir_transform_decorate_device_scope.py | 4 +-
.../test_s_tir_transform_default_gpu_schedule.py | 46 +-
.../test_s_tir_transform_hoist_expression.py | 2 +-
.../transform/test_s_tir_transform_hoist_if.py | 128 +--
.../test_s_tir_transform_inject_double_buffer.py | 20 +-
.../test_s_tir_transform_inject_permuted_layout.py | 6 +-
.../test_s_tir_transform_inject_ptx_async_copy.py | 38 +-
.../test_s_tir_transform_inject_ptx_ldg32.py | 14 +-
...est_s_tir_transform_inject_software_pipeline.py | 8 +-
.../test_s_tir_transform_inject_virtual_thread.py | 22 +-
.../test_s_tir_transform_lift_thread_binding.py | 4 +-
.../test_s_tir_transform_loop_partition.py | 54 +-
...s_tir_transform_lower_cross_thread_reduction.py | 2 +-
.../test_s_tir_transform_lower_init_block.py | 2 +-
.../test_s_tir_transform_lower_match_buffer.py | 6 +-
.../test_s_tir_transform_lower_opaque_block.py | 12 +-
...test_s_tir_transform_lower_thread_all_reduce.py | 2 +-
...transform_manifest_shared_memory_local_stage.py | 10 +-
...st_s_tir_transform_memhammer_lower_auto_copy.py | 8 +-
...form_merge_dynamic_shared_memory_allocations.py | 2 +-
...sform_plan_update_buffer_allocation_location.py | 10 +-
.../test_s_tir_transform_profiling_instr.py | 4 +-
.../transform/test_s_tir_transform_remove_undef.py | 2 +-
...transform_remove_weight_layout_rewrite_block.py | 4 +-
...st_s_tir_transform_renormalize_split_pattern.py | 12 +-
.../test_s_tir_transform_rewrite_unsafe_select.py | 6 +-
.../transform/test_s_tir_transform_thread_sync.py | 10 +-
.../test_s_tir_transform_unify_thread_binding.py | 4 +-
tests/python/target/test_arm_target.py | 10 +-
tests/python/target/test_target_target.py | 2 +-
tests/python/te/test_te_create_primfunc.py | 74 +-
tests/python/te/test_te_tensor.py | 14 +-
.../testing/test_tvm_testing_before_after.py | 2 +-
tests/python/tir-base/test_tir_constructor.py | 218 ----
tests/python/tir-base/test_tir_op_types.py | 352 ------
.../test_tir_analysis_expr_deep_equal.py | 12 +-
.../test_tir_analysis_undefined_vars.py | 46 +-
.../test_tir_analysis_verify_ssa.py | 22 +-
.../test_tir_analysis_verify_well_formed.py | 96 +-
.../{tir-base => tirx-base}/test_tir_base.py | 42 +-
.../{tir-base => tirx-base}/test_tir_buffer.py | 88 +-
tests/python/tirx-base/test_tir_constructor.py | 218 ++++
.../{tir-base => tirx-base}/test_tir_host_func.py | 12 +-
.../{tir-base => tirx-base}/test_tir_imm_values.py | 104 +-
.../{tir-base => tirx-base}/test_tir_index_map.py | 42 +-
.../{tir-base => tirx-base}/test_tir_intrin.py | 68 +-
.../{tir-base => tirx-base}/test_tir_nodes.py | 292 ++---
tests/python/tirx-base/test_tir_op_types.py | 354 ++++++
.../python/{tir-base => tirx-base}/test_tir_ops.py | 118 +-
.../test_tir_ptx_cp_async.py | 8 +-
.../test_tir_ptx_ldmatrix.py | 4 +-
.../{tir-base => tirx-base}/test_tir_ptx_mma.py | 36 +-
.../{tir-base => tirx-base}/test_tir_ptx_mma_sp.py | 10 +-
.../test_tir_scalable_datatype.py | 6 +-
.../{tir-base => tirx-base}/test_tir_specialize.py | 22 +-
.../test_tir_stmt_functor_ir_transform.py | 14 +-
.../test_tir_stmt_functor_substitute.py | 6 +-
.../test_tir_structural_equal_hash.py | 196 ++--
.../test_tir_texture_scope.py | 6 +-
.../test_tir_unsafe_hide_buffer_access.py | 4 +-
.../test_tir_functor.py | 24 +-
.../test_tir_inline_private_functions.py | 14 +-
.../test_tir_transform_annotate_device_regions.py | 6 +-
.../test_tir_transform_bf16_legalize.py | 32 +-
.../test_tir_transform_common_subexpr_elim.py | 166 +--
.../test_tir_transform_convert_ssa.py | 156 +--
.../test_tir_transform_device_kernel_launch.py | 32 +-
.../test_tir_transform_flatten_buffer.py | 6 +-
...test_tir_transform_force_narrow_index_to_i32.py | 24 +-
.../test_tir_transform_fp8_legalize.py | 10 +-
.../test_tir_transform_helpers.py | 40 +-
.../test_tir_transform_lower_intrin.py | 86 +-
.../test_tir_transform_lower_tvm_builtin.py | 40 +-
.../test_tir_transform_make_packed_api.py | 32 +-
.../test_tir_transform_narrow_datatype.py | 30 +-
...est_tir_transform_pointer_value_type_rewrite.py | 10 +-
.../test_tir_transform_prim_func_pass.py | 22 +-
.../test_tir_transform_remove_assume.py | 6 +-
.../test_tir_transform_remove_no_op.py | 62 +-
.../test_tir_transform_simplify.py | 146 +--
.../test_tir_transform_split_host_device.py | 46 +-
.../test_tir_transform_storage_rewrite.py | 70 +-
.../test_tir_transform_unroll_loop.py | 50 +-
.../test_tir_transform_vectorize.py | 112 +-
tests/python/tvmscript/test_tvmscript_complete.py | 40 +-
.../tvmscript/test_tvmscript_error_report.py | 12 +-
.../tvmscript/test_tvmscript_ir_builder_tir.py | 190 ++--
.../tvmscript/test_tvmscript_meta_programming.py | 2 +-
tests/python/tvmscript/test_tvmscript_ops.py | 4 +-
.../tvmscript/test_tvmscript_parser_source.py | 2 +-
.../python/tvmscript/test_tvmscript_parser_tir.py | 18 +-
.../tvmscript/test_tvmscript_pep563_closure.py | 2 +-
.../tvmscript/test_tvmscript_printer_annotation.py | 8 +-
.../tvmscript/test_tvmscript_printer_highlight.py | 4 +-
.../python/tvmscript/test_tvmscript_printer_ir.py | 4 +-
.../tvmscript/test_tvmscript_printer_metadata.py | 10 +-
.../test_tvmscript_printer_structural_equal.py | 2 +-
.../python/tvmscript/test_tvmscript_printer_tir.py | 270 ++---
.../test_tvmscript_printer_underlining.py | 12 +-
.../python/tvmscript/test_tvmscript_regression.py | 4 +-
tests/python/tvmscript/test_tvmscript_roundtrip.py | 160 +--
.../tvmscript/test_tvmscript_syntax_sugar.py | 4 +-
tests/python/tvmscript/test_tvmscript_type.py | 2 +-
tests/scripts/release/make_notes.py | 2 +-
tests/scripts/task_python_unittest.sh | 6 +-
1197 files changed, 12691 insertions(+), 12551 deletions(-)
rename docs/reference/api/python/{tir => tirx}/analysis.rst (91%)
rename docs/reference/api/python/{tir => tirx}/stmt_functor.rst (90%)
rename docs/reference/api/python/{tir/tir.rst => tirx/tirx.rst} (95%)
rename docs/reference/api/python/{tir => tirx}/transform.rst (92%)
rename include/tvm/script/ir_builder/{tir => tirx}/frame.h (87%)
rename include/tvm/script/ir_builder/{tir => tirx}/ir.h (96%)
rename include/tvm/{tir => tirx}/analysis.h (95%)
rename include/tvm/{tir => tirx}/buffer.h (94%)
rename include/tvm/{tir => tirx}/builtin.h (99%)
rename include/tvm/{tir => tirx}/expr.h (90%)
rename include/tvm/{tir => tirx}/expr_functor.h (98%)
rename include/tvm/{tir => tirx}/function.h (90%)
rename include/tvm/{tir => tirx}/index_map.h (97%)
rename include/tvm/{tir => tirx}/op.h (91%)
rename include/tvm/{tir => tirx}/op_attr_types.h (96%)
rename include/tvm/{tir => tirx}/stmt.h (95%)
rename include/tvm/{tir => tirx}/stmt_functor.h (98%)
rename include/tvm/{tir => tirx}/transform.h (97%)
rename include/tvm/{tir => tirx}/var.h (94%)
rename python/tvm/script/ir_builder/{tir => tirx}/__init__.py (96%)
rename python/tvm/script/ir_builder/{tir => tirx}/_ffi_api.py (89%)
rename python/tvm/script/ir_builder/{tir => tirx}/external_kernel.py (97%)
rename python/tvm/script/ir_builder/{tir => tirx}/frame.py (69%)
rename python/tvm/script/ir_builder/{tir => tirx}/ir.py (98%)
rename python/tvm/script/ir_builder/{tir => tirx}/triton.py (95%)
rename python/tvm/script/ir_builder/{tir => tirx}/utils.py (94%)
rename python/tvm/script/parser/{tir => tirx}/__init__.py (90%)
rename python/tvm/script/parser/{tir => tirx}/entry.py (93%)
rename python/tvm/script/parser/{tir => tirx}/operation.py (86%)
rename python/tvm/script/parser/{tir => tirx}/parser.py (89%)
rename python/tvm/script/{tir.py => tirx.py} (89%)
delete mode 100644 python/tvm/tir/_ffi_api.py
delete mode 100644 python/tvm/tir/analysis/_ffi_api.py
delete mode 100644 python/tvm/tir/transform/_ffi_api.py
rename python/tvm/{tir => tirx}/__init__.py (100%)
copy python/tvm/{rpc => tirx}/_ffi_api.py (92%)
rename python/tvm/{tir => tirx}/analysis/__init__.py (100%)
copy python/tvm/{arith => tirx/analysis}/_ffi_api.py (90%)
rename python/tvm/{tir => tirx}/analysis/analysis.py (95%)
rename python/tvm/{tir => tirx}/backend/__init__.py (100%)
rename python/tvm/{tir => tirx}/backend/adreno/__init__.py (100%)
rename python/tvm/{tir => tirx}/buffer.py (97%)
rename python/tvm/{tir => tirx}/build.py (90%)
rename python/tvm/{tir => tirx}/expr.py (95%)
rename python/tvm/{tir => tirx}/function.py (93%)
rename python/tvm/{tir => tirx}/functor.py (99%)
rename python/tvm/{tir => tirx}/generic.py (98%)
rename python/tvm/{tir => tirx}/op.py (89%)
rename python/tvm/{tir => tirx}/pipeline.py (87%)
rename python/tvm/{tir => tirx}/stmt.py (94%)
rename python/tvm/{tir => tirx}/stmt_functor.py (93%)
rename python/tvm/{tir => tirx}/transform/__init__.py (100%)
copy python/tvm/{arith => tirx/transform}/_ffi_api.py (90%)
rename python/tvm/{tir => tirx}/transform/function_pass.py (92%)
rename python/tvm/{tir => tirx}/transform/transform.py (95%)
rename src/script/ir_builder/{tir => tirx}/frame.cc (81%)
rename src/script/ir_builder/{tir => tirx}/ir.cc (76%)
rename src/script/ir_builder/{tir => tirx}/utils.h (89%)
rename src/script/printer/{tir => tirx}/block.cc (81%)
rename src/script/printer/{tir => tirx}/buffer.cc (89%)
rename src/script/printer/{tir => tirx}/expr.cc (72%)
rename src/script/printer/{tir => tirx}/for_loop.cc (80%)
rename src/script/printer/{tir => tirx}/function.cc (80%)
rename src/script/printer/{tir => tirx}/ir.cc (97%)
rename src/script/printer/{tir => tirx}/stmt.cc (80%)
rename src/script/printer/{tir => tirx}/utils.h (80%)
rename src/{tir => tirx}/analysis/check_contains.cc (98%)
rename src/{tir => tirx}/analysis/check_contains.h (93%)
rename src/{tir => tirx}/analysis/collect_call_map.cc (82%)
rename src/{tir => tirx}/analysis/control_flow_graph.cc (97%)
rename src/{tir => tirx}/analysis/control_flow_graph.h (98%)
rename src/{tir => tirx}/analysis/deep_equal.cc (97%)
rename src/{tir => tirx}/analysis/expr_complexity.cc (90%)
rename src/{tir => tirx}/analysis/side_effect.cc (92%)
rename src/{tir => tirx}/analysis/stmt_finding.cc (81%)
rename src/{tir => tirx}/analysis/var_touch.cc (95%)
rename src/{tir => tirx}/analysis/var_use_def_analysis.cc (98%)
rename src/{tir => tirx}/analysis/var_use_def_analysis.h (94%)
rename src/{tir => tirx}/analysis/verify_memory.cc (93%)
rename src/{tir => tirx}/analysis/verify_ssa.cc (92%)
rename src/{tir => tirx}/analysis/verify_well_formed.cc (96%)
rename src/{tir => tirx}/ir/buffer.cc (93%)
rename src/{tir => tirx}/ir/buffer_common.h (95%)
rename src/{tir => tirx}/ir/data_type_rewriter.cc (98%)
rename src/{tir => tirx}/ir/data_type_rewriter.h (98%)
rename src/{tir => tirx}/ir/expr.cc (90%)
rename src/{tir => tirx}/ir/expr_functor.cc (99%)
rename src/{tir => tirx}/ir/function.cc (89%)
rename src/{tir => tirx}/ir/functor_common.h (95%)
rename src/{tir => tirx}/ir/index_map.cc (97%)
rename src/{tir => tirx}/ir/py_functor.cc (98%)
rename src/{tir => tirx}/ir/script/script_complete.cc (96%)
rename src/{tir => tirx}/ir/script/script_complete.h (89%)
rename src/{tir => tirx}/ir/specialize.cc (96%)
rename src/{tir => tirx}/ir/stmt.cc (92%)
rename src/{tir => tirx}/ir/stmt_functor.cc (98%)
rename src/{tir => tirx}/ir/tir_visitor_with_path.cc (99%)
rename src/{tir => tirx}/ir/tir_visitor_with_path.h (97%)
rename src/{tir => tirx}/ir/transform.cc (78%)
rename src/{tir => tirx}/op/builtin.cc (97%)
rename src/{tir => tirx}/op/op.cc (82%)
rename src/{tir => tirx}/op/runtime.cc (85%)
rename src/{tir => tirx}/transform/annotate_device_regions.cc (88%)
rename src/{tir => tirx}/transform/bind_target.cc (97%)
rename src/{tir => tirx}/transform/common_subexpr_elim.cc (98%)
rename src/{tir => tirx}/transform/dtype_conversion.cc (99%)
rename src/{tir => tirx}/transform/dtype_conversion.h (98%)
rename src/{tir => tirx}/transform/flatten_buffer.cc (95%)
rename src/{tir => tirx}/transform/force_narrow_index_to_i32.cc (92%)
rename src/{tir => tirx}/transform/inline_private_functions.cc (92%)
rename src/{tir => tirx}/transform/ir_utils.cc (98%)
rename src/{tir => tirx}/transform/ir_utils.h (98%)
rename src/{tir => tirx}/transform/lower_custom_datatypes.cc (97%)
rename src/{tir => tirx}/transform/lower_device_kernel_launch.cc (95%)
rename src/{tir => tirx}/transform/lower_intrin.cc (94%)
rename src/{tir => tirx}/transform/lower_tvm_builtin.cc (97%)
rename src/{tir => tirx}/transform/lower_warp_memory.cc (98%)
rename src/{tir => tirx}/transform/make_packed_api.cc (85%)
rename src/{tir => tirx}/transform/narrow_datatype.cc (97%)
rename src/{tir => tirx}/transform/primfunc_utils.cc (79%)
rename src/{tir => tirx}/transform/remap_thread_axis.cc (87%)
rename src/{tir => tirx}/transform/remove_assume.cc (80%)
rename src/{tir => tirx}/transform/remove_no_op.cc (95%)
rename src/{tir => tirx}/transform/remove_no_op.h (93%)
rename src/{tir => tirx}/transform/replace_global_vars.cc (88%)
rename src/{tir => tirx}/transform/replace_selected_expr.cc (94%)
rename src/{tir => tirx}/transform/replace_selected_expr.h (93%)
rename src/{tir => tirx}/transform/simplify.cc (93%)
rename src/{tir => tirx}/transform/simplify.h (89%)
rename src/{tir => tirx}/transform/skip_assert.cc (84%)
rename src/{tir => tirx}/transform/split_host_device.cc (91%)
rename src/{tir => tirx}/transform/storage_rewrite.cc (98%)
rename src/{tir => tirx}/transform/tvm_ffi_binder.cc (98%)
rename src/{tir => tirx}/transform/tvm_ffi_binder.h (99%)
rename src/{tir => tirx}/transform/unroll_loop.cc (95%)
rename src/{tir => tirx}/transform/unsupported_dtype_legalize.cc (97%)
rename src/{tir => tirx}/transform/update_pointer_storage_scope.cc (95%)
rename src/{tir => tirx}/transform/update_pointer_storage_scope.h (93%)
rename src/{tir => tirx}/transform/vectorize_loop.cc (98%)
delete mode 100644 tests/python/tir-base/test_tir_constructor.py
delete mode 100644 tests/python/tir-base/test_tir_op_types.py
rename tests/python/{tir-analysis =>
tirx-analysis}/test_tir_analysis_expr_deep_equal.py (73%)
rename tests/python/{tir-analysis =>
tirx-analysis}/test_tir_analysis_undefined_vars.py (70%)
rename tests/python/{tir-analysis =>
tirx-analysis}/test_tir_analysis_verify_ssa.py (61%)
rename tests/python/{tir-analysis =>
tirx-analysis}/test_tir_analysis_verify_well_formed.py (84%)
rename tests/python/{tir-base => tirx-base}/test_tir_base.py (86%)
rename tests/python/{tir-base => tirx-base}/test_tir_buffer.py (74%)
create mode 100644 tests/python/tirx-base/test_tir_constructor.py
rename tests/python/{tir-base => tirx-base}/test_tir_host_func.py (90%)
rename tests/python/{tir-base => tirx-base}/test_tir_imm_values.py (83%)
rename tests/python/{tir-base => tirx-base}/test_tir_index_map.py (88%)
rename tests/python/{tir-base => tirx-base}/test_tir_intrin.py (84%)
rename tests/python/{tir-base => tirx-base}/test_tir_nodes.py (52%)
create mode 100644 tests/python/tirx-base/test_tir_op_types.py
rename tests/python/{tir-base => tirx-base}/test_tir_ops.py (67%)
rename tests/python/{tir-base => tirx-base}/test_tir_ptx_cp_async.py (94%)
rename tests/python/{tir-base => tirx-base}/test_tir_ptx_ldmatrix.py (96%)
rename tests/python/{tir-base => tirx-base}/test_tir_ptx_mma.py (96%)
rename tests/python/{tir-base => tirx-base}/test_tir_ptx_mma_sp.py (96%)
rename tests/python/{tir-base => tirx-base}/test_tir_scalable_datatype.py (93%)
rename tests/python/{tir-base => tirx-base}/test_tir_specialize.py (94%)
rename tests/python/{tir-base =>
tirx-base}/test_tir_stmt_functor_ir_transform.py (83%)
rename tests/python/{tir-base =>
tirx-base}/test_tir_stmt_functor_substitute.py (94%)
rename tests/python/{tir-base => tirx-base}/test_tir_structural_equal_hash.py
(69%)
rename tests/python/{tir-base => tirx-base}/test_tir_texture_scope.py (96%)
rename tests/python/{tir-base =>
tirx-base}/test_tir_unsafe_hide_buffer_access.py (98%)
rename tests/python/{tir-transform => tirx-transform}/test_tir_functor.py (97%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_inline_private_functions.py (95%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_annotate_device_regions.py (93%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_bf16_legalize.py (93%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_common_subexpr_elim.py (83%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_convert_ssa.py (79%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_device_kernel_launch.py (88%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_flatten_buffer.py (99%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_force_narrow_index_to_i32.py (93%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_fp8_legalize.py (97%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_helpers.py (88%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_lower_intrin.py (66%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_lower_tvm_builtin.py (89%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_make_packed_api.py (94%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_narrow_datatype.py (94%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_pointer_value_type_rewrite.py (94%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_prim_func_pass.py (72%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_remove_assume.py (92%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_remove_no_op.py (93%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_simplify.py (93%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_split_host_device.py (88%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_storage_rewrite.py (89%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_unroll_loop.py (72%)
rename tests/python/{tir-transform =>
tirx-transform}/test_tir_transform_vectorize.py (87%)