This is an automated email from the ASF dual-hosted git repository.
github-actions[bot] pushed a change to branch nightly
in repository https://gitbox.apache.org/repos/asf/tvm.git
from bb750012a4 [TIRx] Add a dedicated boolean buffer lowering pass (#19873)
add bd906f082f [ONNX] Fix missing helper in AffineGrid test (#19920)
add 275114b327 [REFACTOR][IR] Unify PrimExpr with Expr typed view (#19910)
No new revisions were added by this update.
Summary of changes:
docs/reference/api/python/relax/relax.rst | 2 +-
docs/tirx/api/tirx.rst | 2 +-
include/tvm/arith/iter_affine_map.h | 16 +-
include/tvm/ir/attrs.h | 1 -
include/tvm/ir/base_expr.h | 207 +++++++-
include/tvm/ir/expr.h | 196 +++----
include/tvm/ir/type.h | 29 +-
include/tvm/relax/dataflow_pattern.h | 8 +-
include/tvm/relax/expr.h | 104 +---
include/tvm/relax/expr_functor.h | 66 +--
include/tvm/relax/type.h | 9 +-
include/tvm/relax/type_functor.h | 2 +
include/tvm/s_tir/schedule/schedule.h | 2 +-
include/tvm/tirx/expr.h | 204 ++++----
include/tvm/tirx/function.h | 2 +-
include/tvm/tirx/op.h | 47 +-
include/tvm/tirx/script/builder/ir.h | 2 +-
include/tvm/tirx/var.h | 8 +-
include/tvm/topi/detail/extern.h | 14 +-
include/tvm/topi/transform.h | 2 +-
python/tvm/arith/analyzer.py | 54 +-
python/tvm/arith/bound.py | 2 +-
python/tvm/arith/int_set.py | 14 +-
python/tvm/arith/int_solver.py | 18 +-
python/tvm/arith/iter_affine_map.py | 42 +-
python/tvm/arith/pattern.py | 8 +-
python/tvm/backend/cuda/lang/pipeline.py | 4 +-
python/tvm/backend/cuda/lang/tile_scheduler.py | 2 +-
python/tvm/backend/cuda/op.py | 525 ++++++++++---------
.../cuda/operator/tile_primitive/copy/_common.py | 2 +-
.../operator/tile_primitive/copy/_swizzle_iter.py | 2 +-
.../tile_primitive/copy_async/tcgen05_cp.py | 4 +-
.../operator/tile_primitive/elementwise/_common.py | 2 +-
.../tile_primitive/elementwise/ops/__init__.py | 6 +-
.../tile_primitive/elementwise/ops/unary.py | 4 +-
.../elementwise/vec_emit/__init__.py | 4 +-
.../elementwise/vec_emit/binary_f32x2.py | 4 +-
.../elementwise/vec_emit/cast_vec2.py | 4 +-
.../elementwise/vec_emit/fma_f32x2.py | 4 +-
.../operator/tile_primitive/gemm_async/tcgen05.py | 2 +-
python/tvm/backend/cuda/script.py | 4 +-
python/tvm/backend/trn/layout.py | 4 +-
.../tile_primitive/instruction_generator.py | 18 +-
python/tvm/contrib/cutlass/build.py | 4 +-
python/tvm/ir/__init__.py | 2 +-
python/tvm/ir/_overload_prim_expr.py | 153 ++++++
python/tvm/ir/_tensor_expr_overload.py | 113 ++++
python/tvm/ir/expr.py | 306 ++++++++++-
python/tvm/ir/type.py | 16 +-
python/tvm/relax/__init__.py | 2 +-
python/tvm/relax/analysis/analysis.py | 10 +-
python/tvm/relax/analysis/estimate_memory_usage.py | 4 +-
python/tvm/relax/backend/adreno/clml.py | 10 +-
python/tvm/relax/backend/metal/coreml.py | 7 +-
python/tvm/relax/dpl/pattern.py | 25 +-
python/tvm/relax/expr.py | 374 +-------------
python/tvm/relax/expr_functor.py | 46 +-
python/tvm/relax/frontend/nn/core.py | 16 +-
python/tvm/relax/frontend/nn/extern.py | 3 +-
python/tvm/relax/frontend/nn/llm/kv_cache.py | 4 +-
.../relax/frontend/nn/llm/position_embedding.py | 10 +-
python/tvm/relax/frontend/nn/modules.py | 16 +-
python/tvm/relax/frontend/nn/op.py | 31 +-
python/tvm/relax/frontend/nn/subroutine.py | 4 +-
python/tvm/relax/frontend/onnx/onnx_frontend.py | 52 +-
.../tvm/relax/frontend/tflite/tflite_frontend.py | 8 +-
.../frontend/torch/base_fx_graph_translator.py | 7 +-
.../frontend/torch/exported_program_translator.py | 6 +-
python/tvm/relax/op/__init__.py | 60 +++
python/tvm/relax/op/_op_gradient.py | 7 +-
python/tvm/relax/op/base.py | 20 +-
python/tvm/relax/op/builtin/builtin.py | 4 +-
python/tvm/relax/op/create.py | 33 +-
python/tvm/relax/op/distributed/distributed.py | 8 +-
python/tvm/relax/op/image/image.py | 20 +-
python/tvm/relax/op/index.py | 4 +-
python/tvm/relax/op/manipulate.py | 28 +-
python/tvm/relax/op/memory/memory.py | 4 +-
python/tvm/relax/op/memory/view.py | 3 +-
python/tvm/relax/op/vm/vm.py | 4 +-
python/tvm/relax/relax_to_pyfunc_converter.py | 8 +-
python/tvm/relax/script/builder/distributed/ir.py | 8 +-
python/tvm/relax/script/builder/ir.py | 16 +-
python/tvm/relax/script/parser/dist.py | 4 +-
python/tvm/relax/script/parser/entry.py | 27 +-
python/tvm/relax/script/parser/parser.py | 3 +-
python/tvm/relax/testing/ast_printer.py | 19 +-
python/tvm/relax/testing/transform.py | 3 +-
python/tvm/relax/training/utils.py | 3 +-
python/tvm/relax/transform/legalize_ops/binary.py | 3 +-
python/tvm/relax/transform/legalize_ops/ccl.py | 3 +-
python/tvm/relax/transform/legalize_ops/common.py | 7 +-
python/tvm/relax/transform/legalize_ops/create.py | 8 +-
.../tvm/relax/transform/legalize_ops/datatype.py | 3 +-
.../relax/transform/legalize_ops/distributed.py | 3 +-
python/tvm/relax/transform/legalize_ops/grad.py | 3 +-
python/tvm/relax/transform/legalize_ops/image.py | 3 +-
python/tvm/relax/transform/legalize_ops/index.py | 7 +-
.../tvm/relax/transform/legalize_ops/inspect_op.py | 3 +-
.../relax/transform/legalize_ops/linear_algebra.py | 3 +-
.../tvm/relax/transform/legalize_ops/manipulate.py | 7 +-
python/tvm/relax/transform/legalize_ops/nn.py | 3 +-
python/tvm/relax/transform/legalize_ops/qdq.py | 3 +-
python/tvm/relax/transform/legalize_ops/search.py | 3 +-
.../relax/transform/legalize_ops/statistical.py | 5 +-
python/tvm/relax/transform/legalize_ops/unary.py | 3 +-
python/tvm/relax/transform/legalize_ops/vision.py | 3 +-
python/tvm/relax/transform/transform.py | 4 +-
python/tvm/relax/type.py | 12 +-
python/tvm/relax/utils.py | 53 +-
.../tvm/s_tir/dlight/analysis/common_analysis.py | 14 +-
python/tvm/s_tir/dlight/analysis/gemv.py | 4 +-
python/tvm/s_tir/dlight/benchmark/extract.py | 6 +-
python/tvm/s_tir/dlight/benchmark/utils.py | 4 +-
python/tvm/s_tir/dlight/gpu/general_reduction.py | 2 +-
python/tvm/s_tir/dlight/gpu/low_batch_gemv.py | 4 +-
python/tvm/s_tir/dlight/gpu/matmul.py | 10 +-
python/tvm/s_tir/dlight/gpu/reduction.py | 2 +-
python/tvm/s_tir/dlight/gpu/rmsnorm.py | 3 +-
python/tvm/s_tir/schedule/analysis.py | 10 +-
python/tvm/s_tir/schedule/instruction.py | 4 +-
python/tvm/s_tir/schedule/schedule.py | 18 +-
python/tvm/s_tir/tensor_intrin/arm_cpu.py | 6 +-
python/tvm/s_tir/tensor_intrin/metal.py | 4 +-
python/tvm/script/parser/core/dispatch.py | 4 +-
python/tvm/script/parser/core/evaluator.py | 6 +-
python/tvm/target/intrin.py | 8 +-
python/tvm/te/operation.py | 13 +-
python/tvm/testing/utils.py | 8 +-
python/tvm/tirx/__init__.py | 4 +-
python/tvm/tirx/analysis/analysis.py | 12 +-
python/tvm/tirx/bench.py | 20 +-
python/tvm/tirx/buffer.py | 36 +-
python/tvm/tirx/exec_scope.py | 8 +-
python/tvm/tirx/expr.py | 471 ++++++++---------
python/tvm/tirx/expr_functor.py | 12 +-
python/tvm/tirx/function.py | 54 +-
python/tvm/tirx/functor.py | 243 +++++----
python/tvm/tirx/layout.py | 108 ++--
python/tvm/tirx/op.py | 573 +++++++++++----------
.../operator/tile_primitive/dispatch_context.py | 2 +-
python/tvm/tirx/operator/tile_primitive/ops.py | 62 +--
python/tvm/tirx/predicate.py | 8 +-
python/tvm/tirx/script/builder/external_kernel.py | 14 +-
python/tvm/tirx/script/builder/ir.py | 335 ++++++------
python/tvm/tirx/script/builder/tirx.py | 32 +-
python/tvm/tirx/script/builder/triton.py | 4 +-
python/tvm/tirx/script/builder/utils.py | 4 +-
python/tvm/tirx/script/parser/operation.py | 9 +-
python/tvm/tirx/script/parser/parser.py | 18 +-
python/tvm/tirx/stmt.py | 104 ++--
python/tvm/tirx/stmt_functor.py | 30 +-
python/tvm/tirx/transform/common.py | 9 +-
python/tvm/tirx/transform/transform.py | 2 +-
python/tvm/topi/gpu/sort.py | 6 +-
python/tvm/topi/math.py | 11 +-
python/tvm/topi/nn/batch_matmul.py | 2 +-
python/tvm/topi/nn/conv2d.py | 14 +-
python/tvm/topi/nn/conv3d.py | 2 +-
python/tvm/topi/nn/dense.py | 4 +-
python/tvm/topi/nn/pad.py | 4 +-
python/tvm/topi/transform.py | 4 +-
python/tvm/topi/utils.py | 2 +-
src/arith/analyzer.cc | 2 +-
src/arith/canonical_simplify.cc | 54 +-
src/arith/conjunctive_normal_form.cc | 6 +-
src/arith/const_fold.h | 14 +-
src/arith/const_int_bound.cc | 40 +-
src/arith/detect_linear_equation.cc | 2 +-
src/arith/int_set.cc | 24 +-
src/arith/ir_mutator_with_analyzer.cc | 31 +-
src/arith/ir_mutator_with_analyzer.h | 2 +-
src/arith/ir_visitor_with_analyzer.cc | 10 +-
src/arith/ir_visitor_with_analyzer.h | 2 +-
src/arith/modular_set.cc | 14 +-
src/arith/pattern_match.h | 42 +-
src/arith/rewrite_simplify.cc | 85 +--
src/arith/z3_prover.cc | 22 +-
src/backend/cuda/codegen/codegen_cuda.cc | 57 +-
src/backend/cuda/codegen/intrin_rule_cuda.cc | 9 +-
src/backend/cuda/codegen/llvm/codegen_nvptx.cc | 13 +-
src/backend/cuda/codegen/llvm/intrin_rule_nvptx.cc | 13 +-
.../hexagon/codegen/llvm/codegen_hexagon.cc | 5 +-
.../hexagon/codegen/llvm/intrin_rule_hexagon.cc | 30 +-
src/backend/metal/codegen/codegen_metal.cc | 19 +-
src/backend/metal/codegen/intrin_rule_metal.cc | 11 +-
src/backend/opencl/codegen/codegen_opencl.cc | 86 ++--
src/backend/opencl/codegen/intrin_rule_opencl.cc | 16 +-
src/backend/rocm/codegen/llvm/codegen_amdgpu.cc | 7 +-
src/backend/rocm/codegen/llvm/intrin_rule_rocm.cc | 32 +-
src/backend/trn/codegen/codegen_trn.cc | 9 +-
src/backend/trn/transform/lower_trainium_layout.cc | 4 +-
src/backend/vulkan/codegen/codegen_spirv.cc | 105 ++--
src/backend/vulkan/codegen/codegen_spirv.h | 1 +
src/backend/vulkan/codegen/intrin_rule_spirv.cc | 14 +-
src/backend/vulkan/codegen/spirv_utils.cc | 4 +-
src/backend/webgpu/codegen/codegen_webgpu.cc | 31 +-
src/backend/webgpu/codegen/intrin_rule_webgpu.cc | 7 +-
src/ir/expr.cc | 37 +-
src/ir/type.cc | 30 +-
src/relax/analysis/type_analysis.cc | 23 +-
src/relax/analysis/well_formed.cc | 17 +-
.../backend/adreno/annotate_custom_storage.cc | 11 +-
.../backend/adreno/fold_vdevice_scope_change.cc | 2 +-
.../backend/contrib/codegen_json/codegen_json.h | 4 +-
src/relax/backend/contrib/tensorrt/codegen.cc | 8 +-
src/relax/backend/vm/codegen_vm.cc | 8 +-
src/relax/backend/vm/codegen_vm_tir.cc | 52 +-
src/relax/backend/vm/lower_runtime_builtin.cc | 37 +-
src/relax/backend/vm/vm_shape_lower.cc | 105 +++-
src/relax/distributed/transform/lower_distir.cc | 2 +-
.../transform/lower_global_view_to_local_view.cc | 3 +-
.../distributed/transform/propagate_sharding.cc | 2 +-
src/relax/distributed/transform/utils.cc | 2 +-
src/relax/distributed/type.cc | 3 +-
src/relax/ir/block_builder.cc | 37 +-
src/relax/ir/dataflow_block_rewriter.cc | 2 +-
src/relax/ir/dataflow_expr_rewriter.cc | 4 +-
src/relax/ir/dataflow_matcher.cc | 2 +-
src/relax/ir/dependent_type.cc | 25 +-
src/relax/ir/emit_te.cc | 2 +-
src/relax/ir/expr.cc | 142 +----
src/relax/ir/expr_functor.cc | 61 ++-
src/relax/ir/py_expr_functor.cc | 55 +-
src/relax/ir/type.cc | 2 +-
src/relax/op/ccl/ccl.cc | 8 +-
src/relax/op/distributed/binary.h | 2 +-
src/relax/op/distributed/distributed.cc | 12 +-
src/relax/op/distributed/manipulate.cc | 2 +-
src/relax/op/image/resize.cc | 8 +-
src/relax/op/memory/view.cc | 27 +-
src/relax/op/nn/attention.cc | 8 +-
src/relax/op/nn/convolution.cc | 6 +-
src/relax/op/nn/convolution.h | 2 +-
src/relax/op/nn/nn.cc | 40 +-
src/relax/op/nn/pooling.cc | 12 +-
src/relax/op/op.cc | 110 ++--
src/relax/op/op_common.h | 4 +-
src/relax/op/tensor/binary.h | 2 +-
src/relax/op/tensor/create.cc | 42 +-
src/relax/op/tensor/datatype.cc | 4 +-
src/relax/op/tensor/grad.cc | 21 +-
src/relax/op/tensor/index.cc | 11 +-
src/relax/op/tensor/inspect.cc | 49 +-
src/relax/op/tensor/linear_algebra.cc | 6 +-
src/relax/op/tensor/manipulate.cc | 64 +--
src/relax/op/tensor/qdq.cc | 6 +-
src/relax/op/tensor/sampling.cc | 5 +-
src/relax/op/tensor/search.cc | 8 +-
src/relax/op/tensor/set.cc | 18 +-
src/relax/op/tensor/sorting.cc | 6 +-
src/relax/op/tensor/statistical.cc | 6 +-
src/relax/op/tensor/statistical.h | 2 +-
src/relax/op/tensor/ternary.cc | 2 +-
src/relax/op/tensor/unary.cc | 6 +-
src/relax/op/vision/multibox_transform_loc.cc | 3 +-
src/relax/op/vision/nms.cc | 7 +-
src/relax/op/vision/roi_align.cc | 2 +-
src/relax/op/vision/roi_pool.cc | 2 +-
src/relax/script/builder/distributed.cc | 6 +-
src/relax/script/builder/ir.cc | 2 +-
src/relax/script/printer/call.cc | 50 +-
src/relax/script/printer/tir.cc | 2 +-
src/relax/script/printer/utils.h | 6 +-
src/relax/transform/allocate_workspace.cc | 6 +-
src/relax/transform/alter_op_impl.cc | 10 +-
src/relax/transform/attach_global_symbol.cc | 6 +-
src/relax/transform/call_tir_rewrite.cc | 10 +-
src/relax/transform/canonicalize_bindings.cc | 9 +-
src/relax/transform/compute_prim_value.cc | 41 +-
src/relax/transform/convert_layout.cc | 5 +-
src/relax/transform/dataflow_inplace.cc | 4 +-
src/relax/transform/dead_code_elimination.cc | 2 +-
src/relax/transform/decompose_ops.cc | 8 +-
src/relax/transform/eliminate_common_subexpr.cc | 2 +-
src/relax/transform/fold_constant.cc | 9 +-
src/relax/transform/fuse_ops.cc | 16 +-
src/relax/transform/fuse_tir.cc | 20 +-
src/relax/transform/gradient.cc | 13 +-
src/relax/transform/kill_after_last_use.cc | 9 +-
src/relax/transform/lambda_lift.cc | 15 +-
src/relax/transform/lazy_transform_params.cc | 16 +-
src/relax/transform/legalize_ops.cc | 5 +-
src/relax/transform/lift_transform_params.cc | 2 +-
src/relax/transform/lower_alloc_tensor.cc | 13 +-
src/relax/transform/merge_composite_functions.cc | 6 +-
src/relax/transform/normalize.cc | 2 +-
src/relax/transform/realize_vdevice.cc | 2 +-
src/relax/transform/remove_purity_checking.cc | 12 +-
src/relax/transform/remove_unused_outputs.cc | 2 +-
src/relax/transform/rewrite_cuda_graph.cc | 23 +-
src/relax/transform/rewrite_dataflow_reshape.cc | 2 +-
src/relax/transform/run_codegen.cc | 14 +-
src/relax/transform/split_call_tir_by_pattern.cc | 10 +-
.../transform/split_layout_rewrite_preproc.cc | 8 +-
src/relax/transform/static_plan_block_memory.cc | 21 +-
src/relax/transform/to_mixed_precision.cc | 6 +-
src/relax/transform/update_vdevice.cc | 2 +-
src/relax/transform/utils.h | 15 +-
src/relax/utils.cc | 9 +-
src/s_tir/analysis/estimate_flops.cc | 16 +-
src/s_tir/analysis/is_pure_function.cc | 2 +-
.../analysis/sblock_access_region_detector.cc | 11 +-
src/s_tir/analysis/verify_gpu_code.cc | 6 +-
src/s_tir/backend/adreno/inject_texture_alloc.cc | 6 +-
src/s_tir/backend/adreno/texture_flatten.cc | 4 +-
src/s_tir/data_layout.cc | 6 +-
.../feature_extractor/per_store_feature.cc | 24 +-
.../meta_schedule/mutator/mutate_thread_binding.cc | 6 +-
src/s_tir/meta_schedule/mutator/mutate_unroll.cc | 6 +-
.../postproc/rewrite_cooperative_fetch.cc | 6 +-
.../postproc/rewrite_parallel_vectorize_unroll.cc | 2 +-
src/s_tir/schedule/analysis/reducer.cc | 6 +-
src/s_tir/schedule/concrete_schedule.cc | 6 +-
src/s_tir/schedule/instruction.cc | 13 +-
src/s_tir/schedule/ir_comparator.cc | 34 +-
src/s_tir/schedule/primitive/cache_index.cc | 4 +-
src/s_tir/schedule/primitive/cache_read_write.cc | 4 +-
src/s_tir/schedule/primitive/decompose_padding.cc | 12 +-
.../schedule/primitive/layout_transformation.cc | 2 +-
src/s_tir/transform/bound_checker.cc | 3 +-
src/s_tir/transform/canonicalize_loop.cc | 5 +-
src/s_tir/transform/compact_buffer_region.cc | 15 +-
src/s_tir/transform/hoist_expression.cc | 2 +-
src/s_tir/transform/inject_double_buffer.cc | 2 +-
src/s_tir/transform/inject_permuted_layout.cc | 19 +-
src/s_tir/transform/inject_ptx_async_copy.cc | 16 +-
src/s_tir/transform/inject_ptx_ldg32.cc | 9 +-
src/s_tir/transform/inject_software_pipeline.cc | 31 +-
src/s_tir/transform/inject_virtual_thread.cc | 16 +-
src/s_tir/transform/lift_thread_binding.cc | 2 +-
src/s_tir/transform/loop_partition.cc | 6 +-
src/s_tir/transform/lower_async_dma.cc | 32 +-
.../transform/lower_cross_thread_reduction.cc | 3 +-
src/s_tir/transform/lower_thread_allreduce.cc | 14 +-
src/s_tir/transform/lower_vtcm_alloc.cc | 6 +-
.../transform/memhammer_tensorcore_rewrite.cc | 99 ++--
.../transform/merge_shared_memory_allocations.cc | 35 +-
src/s_tir/transform/profile_instrumentation.cc | 12 +-
src/s_tir/transform/renew_defs.cc | 4 +-
src/s_tir/transform/rewrite_unsafe_select.cc | 11 +-
src/s_tir/transform/storage_access.cc | 8 +-
src/s_tir/transform/thread_storage_sync.cc | 10 +-
.../transform/using_assume_to_reduce_branches.cc | 8 +-
src/script/ir_builder/ir/ir.cc | 2 +-
.../printer/doc_printer/python_doc_printer.cc | 2 +-
src/target/intrin_rule.cc | 52 +-
src/target/intrin_rule.h | 7 +-
src/target/llvm/codegen_arm.cc | 19 +-
src/target/llvm/codegen_cpu.cc | 42 +-
src/target/llvm/codegen_llvm.cc | 170 +++---
src/target/llvm/codegen_x86_64.cc | 7 +-
src/target/llvm/intrin_rule_llvm.cc | 26 +-
src/target/llvm/intrin_rule_llvm.h | 14 +-
src/target/source/codegen_c.cc | 92 ++--
src/target/source/codegen_c.h | 2 +
src/target/source/codegen_c_host.cc | 4 +-
src/tirx/analysis/deep_equal.cc | 75 +--
src/tirx/analysis/filter_canonical.cc | 4 +-
src/tirx/ir/buffer.cc | 8 +-
src/tirx/ir/buffer_common.h | 2 +-
src/tirx/ir/data_type_rewriter.cc | 38 +-
src/tirx/ir/exec_scope.cc | 9 +-
src/tirx/ir/expr.cc | 76 +--
src/tirx/ir/expr_functor.cc | 13 +-
src/tirx/ir/function.cc | 2 +-
src/tirx/ir/specialize.cc | 2 +-
src/tirx/ir/stmt.cc | 2 +-
src/tirx/ir/stmt_functor.cc | 2 +-
src/tirx/ir/tir_visitor_with_path.h | 5 +
src/tirx/op/op.cc | 93 ++--
src/tirx/script/builder/ir.cc | 2 +-
src/tirx/script/printer/buffer.cc | 3 +-
src/tirx/script/printer/expr.cc | 185 ++++---
src/tirx/script/printer/function.cc | 2 +-
src/tirx/script/printer/ir.cc | 8 +-
src/tirx/script/printer/stmt.cc | 10 +-
src/tirx/script/printer/utils.h | 2 +
src/tirx/transform/bind_target.cc | 2 +-
src/tirx/transform/force_narrow_index_to_i32.cc | 2 +-
src/tirx/transform/inline_private_functions.cc | 3 +-
src/tirx/transform/ir_utils.cc | 12 +-
src/tirx/transform/ir_utils.h | 10 +-
src/tirx/transform/lower_intrin.cc | 15 +-
src/tirx/transform/lower_tirx_cleanup.cc | 2 +-
src/tirx/transform/lower_tirx_dedup_tensormap.cc | 6 +-
src/tirx/transform/lower_tvm_builtin.cc | 123 +++--
src/tirx/transform/lower_warp_memory.cc | 23 +-
src/tirx/transform/make_packed_api.cc | 36 +-
src/tirx/transform/narrow_datatype.cc | 13 +-
src/tirx/transform/split_host_device.cc | 34 +-
src/tirx/transform/stmt_simplify.cc | 6 +-
src/tirx/transform/storage_rewrite.cc | 36 +-
src/tirx/transform/tile_primitive_dispatch.cc | 30 +-
src/tirx/transform/tvm_ffi_binder.cc | 35 +-
src/tirx/transform/unsupported_dtype_legalize.cc | 60 +--
src/tirx/transform/vectorize_loop.cc | 107 ++--
tests/cpp/tir_analysis_side_effect.cc | 5 +-
tests/cpp/tir_scalable_datatype.cc | 9 +-
.../python/arith/test_arith_canonical_simplify.py | 2 +-
tests/python/arith/test_arith_intset.py | 4 +-
tests/python/arith/test_arith_iter_affine_map.py | 10 +-
tests/python/arith/test_arith_rewrite_simplify.py | 2 +-
.../codegen/test_target_codegen_cuda_fastmath.py | 4 +-
.../python/codegen/test_target_codegen_cuda_fp8.py | 4 +-
tests/python/codegen/test_target_codegen_llvm.py | 8 +-
tests/python/nightly/test_nnapi/infrastructure.py | 2 +-
tests/python/relax/test_analysis_type_analysis.py | 2 +-
tests/python/relax/test_ast_printer.py | 48 +-
tests/python/relax/test_bind_params.py | 3 +-
tests/python/relax/test_bind_symbolic_vars.py | 2 +-
tests/python/relax/test_codegen_tensorrt.py | 2 +-
tests/python/relax/test_dataflow_rewriter.py | 21 +-
tests/python/relax/test_expr.py | 24 +-
tests/python/relax/test_expr_functor.py | 27 +-
tests/python/relax/test_frontend_nn_op.py | 2 +-
tests/python/relax/test_frontend_onnx.py | 38 +-
tests/python/relax/test_op_gradient_numeric.py | 2 +-
tests/python/relax/test_op_inspect.py | 22 +-
tests/python/relax/test_relax_operators.py | 2 +-
.../python/relax/test_relax_to_pyfunc_converter.py | 4 +-
.../relax/test_transform_fuse_ops_by_pattern.py | 2 +-
.../relax/test_transform_lazy_transform_params.py | 2 +-
tests/python/relax/test_tvmscript_parser.py | 10 +-
tests/python/relax/test_vm_build.py | 4 +-
tests/python/relax/test_vm_codegen_tir.py | 2 +-
.../s_tir/schedule/test_tir_schedule_tensorize.py | 2 +-
.../test_s_tir_transform_inject_double_buffer.py | 2 +-
.../test_s_tir_transform_inject_ptx_async_copy.py | 2 +-
.../test_s_tir_transform_inject_ptx_ldg32.py | 2 +-
tests/python/tirx-base/test_tir_constructor.py | 21 +-
tests/python/tirx-base/test_tir_expr_functor.py | 79 ++-
tests/python/tirx-base/test_tir_specialize.py | 2 +-
.../test_tir_stmt_functor_ir_transform.py | 5 +-
.../test_tir_inline_private_functions.py | 2 +-
.../test_tir_transform_lower_intrin.py | 2 +-
.../tile_primitive/cuda/copy_async/test_dsmem.py | 2 +-
.../tile_primitive/cuda/copy_async/test_tma.py | 26 +-
.../tile_primitive/cuda/elementwise/test_fma.py | 2 +-
tests/python/tirx/test_op_namespace_cleanup.py | 2 +-
tests/python/tirx/test_parser_printer.py | 8 +-
tests/python/tirx/transform/test_stmt_functor.py | 10 +-
.../tirx/transform/test_tirx_expr_functor.py | 79 ++-
.../tvmscript/test_tvmscript_syntax_sugar.py | 6 +-
444 files changed, 5746 insertions(+), 4959 deletions(-)
create mode 100644 python/tvm/ir/_overload_prim_expr.py
create mode 100644 python/tvm/ir/_tensor_expr_overload.py
