## Rationale
`SizeVar` encodes nonnegativity in runtime subtype identity, which is
fragile under cloning and remapping. Symbolic integer values should use
one `Var` representation, with nonnegative facts recorded in the
analyzer at the use sites that establish them.
## Changes
- Remove `SizeVar` from the C++, Python, TE, TVMScript, FFI, visitor,
and serialization surfaces, and migrate callers to `Var`.
- Preserve the existing Relax constraint ownership model and use
`MarkGlobalNonNegValue` as the canonical path for global nonnegative
facts.
- Preserve `T.handle()` as the normal opaque-handle form. An optional
dtype constructs a typed pointer, with `T.handle("void")` reserved for
an explicit pointer-to-void.
## Summary
- Make `PrimExpr` a typed C++ view over `Expr` values whose
`ExprNode::ty` is `PrimType`, instead of using a separate runtime node
class as the proof of primitive-ness.
- Use the shared `ir::Call` node for Relax, TIRX, and primitive-valued
calls, while keeping primitive-only APIs explicit at their semantic
boundaries.
- Keep Python on the general `Expr` surface for primitive-typed values
so `isinstance` behavior does not imply a nominal primitive-expression
subclass.
## Design Rationale
The main advantage of this change is that common expression nodes such
as `Call` can be unified without specializing each one to `PrimType`. A
single `ir::Call` can represent a Relax tensor call, a Relax scalar
call, or a primitive-valued intrinsic call; the result type stored in
`ExprNode::ty` determines whether that particular value can be viewed as
`PrimExpr`.
This keeps the IR node hierarchy focused on expression structure rather
than result-type categories. Nodes that are intrinsically primitive,
such as integer and floating-point literals or TIRX primitive operators,
still have strongly typed C++ APIs and data structures. General nodes
whose result type may vary, such as `Call`, remain general `Expr` nodes
and are narrowed to `PrimExpr` only where primitive-only semantics are
required.
The PR also keeps the compatibility surface practical: C++
primitive-only APIs continue to accept `PrimExpr`, Python exposes a
compatibility predicate for checking the primitive typed category, and
visitors/printers use one natural `Call` path rather than duplicating
Relax and primitive call handling. Missing expression types are
represented explicitly with `Type::Missing()` so constructors can leave
type inference to later analysis without relying on nullable `Type`
values.
## Summary
This PR adds the initial TIRx support needed for low-level programming
of Blackwell-class GPU architectures. As part of the ongoing TIRx
refactor, it introduces TVMScript support for directly scripting
advanced hardware features without relying on scheduling as the primary
programming interface.
The change keeps existing `s_tir` script support intact while making
direct scripting a first-class path for TIRx programs.
## Main Changes
- Add TIRx operator dispatch and layout infrastructure.
- Add TVMScript support for new low-level TIRx operations.
- Add analysis, transform, and lowering support for TIRx IR nodes.
- Add CUDA/Blackwell-oriented codegen and intrinsic coverage.
- Add Python and C++ integration points for TIRx scripting and runtime
support.
## Validation
- `pre-commit run --all-files`
- `ninja -C build -j32`
- `CUDA_VISIBLE_DEVICES=2 pytest tests/python/tirx/ -n 16`
- `1723 passed, 47 skipped, 32 warnings`
- `CUDA_VISIBLE_DEVICES=2 python -m pytest -v
tests/python/all-platform-minimal-test`
- `37 passed, 105 skipped`
- `TVM_TEST_TARGETS=llvm python -m pytest -v tests/python/tirx-analysis
tests/python/tirx-base tests/python/tirx-transform -n 16`
- `664 passed, 25 skipped, 9 xfailed, 1 xpassed`
## Local CI Notes
Some full CI-equivalent jobs were not locally reproducible because this
machine is missing parts of the Apache TVM CI environment, including
`llvm-config-15/17`, Vulkan, ROCm, Maven, Sphinx, Doxygen, Emscripten,
and ARM/QEMU cross-toolchain components. Metal-specific tests were
skipped locally because no Metal runtime is available.
`topi.scatter_elements` and `topi.scatter_nd` emit bare `T.parallel`
loops in their te.extern IRBuilder bodies which trips `VerifyMemory` on
CUDA targets:
RuntimeError: Memory verification failed
...
Did you forget to bind?
CPU (LLVM) is unaffected.
This fix makes the IRBuilder body in both `topi/scatter_elements.py` and
`topi/scatter.py` target-aware. When `Target.current()` is a GPU target
it emits thread bindings instead of `T.parallel`.
Fixes#19451.
This PR brings up the tirx namespace. We have been spliting out the
original tir namespace to include high-level component s_tir and this PR
updates the remaining low-level part as tirx namespace
## Summary
- Remove `body` field from `AllocBufferNode` and `DeclBufferNode`,
making them flat statements consistent with `Bind`
- Buffer scope extends to end of enclosing scope via flat `SeqStmt`
semantics
- 60 files changed across core IR, codegen backends, transforms, script
IR builder, and tests
## Test plan
- All existing test suites pass (tir-transform, tir-base, tvmscript,
s_tir, codegen, C++)
This PR enables ruff pyupgrade (UP) rules with py310 target, auto-fixing
~5600 annotation modernizations (PEP 585 generics, PEP 604 unions,
deprecated typing imports).
Also removes from __future__ import annotations from ir/module.py and
rmsnorm.py, bumps requires-python to >=3.10, and removes absolute_import
aliases from topi/contrib files.
This PR cleans up the target python api.
- Removes the indirections of attribute exposure
- Move tag registry to python so it is easily configurable
- Remove legacy constructors in favor of tags
This PR replaces int64s with int32s in the argsort and parallel_sampling_from_prob
kernels when the target is WebGPU (since WGSL does not currently support i64)
This PR starts the step 0 to phase out relay from the current
development main branch. This PR focuses on the python
components of relay, autotvm, auto_scheduler. To make the change
manageable, we will also do followup steps on te.Schedule and
c++ components in followup PRs.
To continue support community members who depends on
legacy flows, the [v0.19.0](https://github.com/apache/tvm/tree/v0.19.0)
branch will continue contain these components.
As noted in [discussion on phasing out legacy components](https://discuss.tvm.apache.org/t/phasing-out-legacy-components/17703/30),
this would help us to do two purposes:
- By removing outdated or redundant elements, we can significantly
reduce complexity and improve maintainability.
- Unify our focus: Concentrating our efforts on the new unity flow
will allow for more efficient development and innovation.
It is also a good opportunity for us to revisit and reduce CI time.
The past relay legacy flow contains a lot of end to end tests that
requires hardware resources to run and causing long CI time.
Moving onwards, we can focus more on unit-tests that focuses
on structural equality and runs within seconds, while be mindful
about tests that requires hardware resources (by restricting them
to specific folders and CI nightly in some cases).
---
Co-authored-by: Siyuan Feng <hzfengsy@sjtu.edu.cn>
* Make all required adjusts in the code to comply with the new version
* Upadte ci-lint to v0.71, based on tlcpackstaging/ci_lint:20220411-060305-45f3d4a52
* Add explicit copy stage for batch_matmul(x, x) case
* do copy in relay strategy to avoid dup
* add copy to dense op and schedules
* black
* add batch_matmul test
* add dense test
* fix cuda int8 dense test
* remove need_copy flag
* do not use tag to decide if tensors are same
* rename to copy_if_identical and add comment
* black
* one more fix missed
* add length check on input tensors
* one more length check
* fix variable name
* Add Matmul Op
* Recover DenseAttrs
* Add grad for matmul & some update
* Update matmul cuda default schedule
* Add blas support for matmul
* Lint fix add update doc strings
* [Topi][UnitTests] Parametrized tests in test_topi_dense.py
Now, tests run for multiple data types, can be extended with
additional datatypes.
* [Topi] Separated generic-gpu nn.dense implementations into topi.gpu.dense
As a follow-up to the renaming of "gpu" to "cuda", separating
implementations that require CUDA (e.g. dense_cublas.cuda) from
implementations that require any GPU, but not necessarily a CUDA GPU
(e.g. dense_small_batch.gpu).
My intent is to pair this migration with the extension of unit tests
to cover additional GPU runtimes, migrating only implementations that
run correctly on non-CUDA GPU devices.
* [Vulkan][Codegen] Updated storage sync to avoid incorrect matmul results on some GPUs
- In ThreadAllreduceBuilder, separate out load/store so that they can
have a memory barrier in-between.
- In Vulkan codegen, added Workgroup memory sync for subgroup thread
sync, since the different subgroup threads can still access
workgroup memory. Longer-term, may need tir enhancements to
separate out sync of control/memory.
Co-authored-by: Eric Lunderberg <elunderberg@octoml.ai>
Tianqi Chen