The current implementation of the WMMA intrinsic ops as they are defined
in the ROCDL tablegen is incorrect. They represent as operands what
should be attributes such as `clamp`, `opsel`, `signA/signB`. This
change performs a refactoring to bring it in line with what we expect.
---------
Signed-off-by: Muzammiluddin Syed <muzasyed@amd.com>
This makes it similar to `mlir::TypedValue` in the MLIR C++ API and
allows users to be more specific about the values they produce or
accept.
Co-authored-by: Maksim Levental <maksim.levental@gmail.com>
This PR exposes `linalg::inferContractionDims(ArrayRef<AffineMap>)` to
Python, allowing users to infer contraction dimensions (batch/m/n/k)
directly from a list of affine maps without needing an operation.
---------
Signed-off-by: Bangtian Liu <liubangtian@gmail.com>
The C++ index switch op has utilities for `getCaseBlock(int i)` and
`getDefaultBlock()`, so these have been added.
Optional body builder args have been added: one for the default case and
one for the switch cases.
Updates the derived Op-classes for the main transform ops to have all
the arguments, etc, from the auto-generated classes. Additionally
updates and adds missing snake_case wrappers for the derived classes
which shadow the snake_case wrappers of the auto-generated classes,
which were hitherto exposed alongside the derived classes.
Adds the first XeGPU transform op, `xegpu.set_desc_layout`, which attachs a `xegpu.layout` attribute to the descriptor that a `xegpu.create_nd_tdesc` op returns.
Add builders on the Python side that match builders in the C++ side, add tests for launching GPU kernels and regions, and correct some small documentation mistakes. This reflects the API decisions already made in the func dialect's Python bindings and makes use of the GPU dialect's bindings work more similar to C++ interface.
By allowing `transform.smt.constrain_params`'s region to yield SMT-vars,
op instances can declare relationships, through constraints, on incoming
params-as-SMT-vars and outgoing SMT-vars-as-params. This makes it
possible to declare that computations on params should be performed.
The semantics are that the yielded SMT-vars should be from any valid
satisfying assignment/model of the constraints in the region.
This test passed locally because I had a python environment with the
`python` command available, but I should have used the `%PYTHON` lit
command substitution instead. Fixes buildbot failures from #163620.
Adds initial support for Python bindings to the OpenACC dialect.
* The bindings do not provide any niceties yet, just the barebones
exposure of the dialect to Python. Construction of OpenACC ops is
therefore verbose and somewhat inconvenient, as evidenced by the test.
* The test only constructs one module, but I attempted to use enough
operations to be meaningful. It does not test all the ops exposed, but
does contain a realistic example of a memcpy idiom.
The func dialect provides a more pythonic interface for constructing
operations, but the gpu dialect does not; this is the first PR to
provide the same conveniences for the gpu dialect, starting with the
gpu.func op.
Changes to linalg `structured.fuse` transform op:
* Adds an optional `use_forall` boolean argument which generates a tiled
`scf.forall` loop instead of `scf.for` loops.
* `tile_sizes` can now be any parameter or handle.
* `tile_interchange` can now be any parameter or handle.
* IR formatting changes from `transform.structured.fuse %0 [4, 8] ...`
to `transform.structured.fuse %0 tile_sizes [4, 8] ...`
- boolean arguments are now `UnitAttrs` and should be set via the op
attr-dict: `{apply_cleanup, use_forall}`
This op enables expressing uncertainty regarding what should be
happening at particular places in transform-dialect schedules. In
particular, it enables representing a choice among alternative regions.
This choice is resolved through providing a `selected_region` argument.
When this argument is provided, the semantics are such that it is valid
to rewrite the op through substituting in the selected region -- with
the op's interpreted semantics corresponding to exactly this.
This op represents another piece of the puzzle w.r.t. a toolkit for
expressing autotuning problems with the transform dialect. Note that
this goes beyond tuning knobs _on_ transforms, going further by making
it tunable which (sequences of) transforms are to be applied.
This is a follow-up to https://github.com/llvm/llvm-project/pull/144307,
where we removed `vector.matrix_multiply` and `vector.flat_transpose`
from the Vector dialect.
This PR:
* Updates comments that were missed in the previous change.
* Renames relevant `-convert-vector-to-llvm=` options:
- `vector-contract-lowering=matmul` → `vector-contract-lowering=llvmintr`
- `vector-transpose-lowering=flat_transpose` → `vector-transpose-lowering=llvmintr`
These new names better reflect the actual transformation target - LLVM
intrinsics - rather than the now-removed abstract operations.
Introduces a Transform-dialect SMT-extension so that we can have an op
to express constrains on Transform-dialect params, in particular when
these params are knobs -- see transform.tune.knob -- and can hence be
seen as symbolic variables. This op allows expressing joint constraints
over multiple params/knobs together.
While the op's semantics are clearly defined, per SMTLIB, the interpreted
semantics -- i.e. the `apply()` method -- for now just defaults to failure. In
the future we should support attaching an implementation so that users
can Bring Your Own Solver and thereby control performance of
interpreting the op. For now the main usage is to walk schedule IR and
collect these constraints so that knobs can be rewritten to constants that
satisfy the constraints.
In this PR we add basic python bindings for IRDL dialect, so that python
users can create and load IRDL dialects in python. This allows users, to
some extent, to define dialects in Python without having to modify
MLIR’s CMake/TableGen/C++ code and rebuild, making prototyping more
convenient.
A basic example is shown below (and also in the added test case):
```python
# create a module with IRDL dialects
module = Module.create()
with InsertionPoint(module.body):
dialect = irdl.DialectOp("irdl_test")
with InsertionPoint(dialect.body):
op = irdl.OperationOp("test_op")
with InsertionPoint(op.body):
f32 = irdl.is_(TypeAttr.get(F32Type.get()))
irdl.operands_([f32], ["input"], [irdl.Variadicity.single])
# load the module
irdl.load_dialects(module)
# use the op defined in IRDL
m = Module.parse("""
module {
%a = arith.constant 1.0 : f32
"irdl_test.test_op"(%a) : (f32) -> ()
}
""")
```
Currently the type hints on the returns of the "value builders" are
`ir.Value`, `Sequence[ir.Value]`, and `ir.Operation`, none of which are
correct. The correct possibilities are `ir.OpResult`, `ir.OpResultList`,
the OpView class itself (e.g., `AttrSizedResultsOp`) or the union of the
3 (for variadic results). This PR fixes those hints.
Currently in MLIR python bindings, operations with inferable result
types (e.g. with `InferTypeOpInterface` or `SameOperandsAndResultType`)
will generate such builder functions:
```python
def my_op(arg1, arg2 .. argN, *, loc=None, ip=None):
... # result types will be inferred automatically
```
However, in some cases we may want to provide the result types
explicitly. For example, the implementation of interface method
`inferResultTypes(..)` can return a failure and then we cannot build the
op in that way. Also, in the C++ side we have multiple `build` methods
for both explicitly specify the result types and automatically inferring
them.
In this PR, we change the signature of this builder function to:
```python
def my_op(arg1, arg2 .. argN, *, results=None, loc=None, ip=None):
... # result types will be inferred automatically if results is None
```
If the `results` is not provided, it will be inferred automatically,
otherwise the provided result types will be utilized. Also, `__init__`
methods of the generated op classes are changed correspondingly. Note
that for operations without inferable result types, the signature remain
unchanged, i.e. `def my_op(res1 .. resN, arg1 .. argN, *, loc=None,
ip=None)`.
---
Previously I have considered an approach like `my_op(arg, *, res1=None,
res2=None, loc=None, ip=None)`, but I quickly realized it had some
issues. For example, if the user only provides some of the arguments—say
`my_op(v1, res1=i32)`—this could lead to problems. Moreover, we don’t
seem to have a mechanism for inferring only part of result types. A
unified `results` parameter seems to be more simple and straightforward.
In order to access and modify resetOffset and boundsCheck of
RawBufferCastOp in pythonic binding, we will have to use Attrs instead
of Property. This is because we do not have python binding support for
property yet. We should move back to property once we add pythonic
binding support for it.
---------
Signed-off-by: Stanley Winata <stanley.winata@amd.com>
This patch specializes the Python bindings for ForallOp and
InParallelOp, similar to the existing one for ForOp. These bindings
create the regions and blocks properly and expose some additional
helpers.
This is mentioned as a "must" in
https://nanobind.readthedocs.io/en/latest/porting.html#type-casters when
implementing type casters.
While most of the existing `from_cpp` methods were already marked
noexcept, many of the `from_python` methods were not. This commit adds
the missing noexcept declarations to all type casters found in
`NanobindAdaptors.h`.
---------
Co-authored-by: Maksim Levental <maksim.levental@gmail.com>
A new transform op to represent that an attribute is to be chosen from a
set of alternatives and that this choice is made available as a
`!transform.param`. When a `selected` argument is provided, the op's
`apply()` semantics is that of just making this selected attribute
available as the result. When `selected` is not provided, `apply()`
complains that nothing has resolved the non-determinism that the op is
representing.
RFC:
https://discourse.llvm.org/t/rfc-deprecate-linalg-elemwise-unary-and-elemwise-binary/87144
Remove the two operations and fix the tests by:
* Cleaning simple operation tests of the old ops
* Changing `linalg.elemwise_{u|bi}nary` with `linalg.{exp|add}` on
transform tests
* Changing some of the tests with `linalg.elementwise` instead, to
broaden test coverage
* Surgically removing the `elemwise_*` part in the Python tests
* Update MLIR transform examples (text and tests) with
`linalg.elementwise` instead
Nothing else changed.
Removes the Debug... prefix on the ops in tablegen, in line with pretty
much all other Transform-dialect extension ops. This means that the ops
in Python look like
`debug.EmitParamAsRemarkOp`/`debug.emit_param_as_remark` instead of
`debug.DebugEmitParamAsRemarkOp`/`debug.debug_emit_param_as_remark`.
Interpret an option value with multiple values, either in the form of an
`ArrayAttr` (either static or passed through a param) or as the multiple
attrs associated to a param, as a comma-separated list, i.e. as a
ListOption on a pass.
Improve ApplyRegisteredPassOp's support for taking options by taking
them as a dict (vs a list of string-valued key-value pairs).
Values of options are provided as either static attributes or as params
(which pass in attributes at interpreter runtime). In either case, the
keys and value attributes are converted to strings and a single
options-string, in the format used on the commandline, is constructed to
pass to the `addToPipeline`-pass API.
…_reduce_matmul.
This patch exposes broadcast and transpose semantics on
'batch_reduce_matmul'. This is the last one in continuation of other two
variant of matmul ops.
The broadcast and transpose semantic are as follows:
Broadcast and Transpose semantics can be appiled by specifying the
explicit attribute 'indexing_maps' as shown below. This is a list
attribute, so must include maps for all arguments if specified.
Example Transpose:
```
linalg.batch_reduce_matmul indexing_maps = [
affine_map<(d0, d1, d2, d3) -> (d0, d3, d1)>, // transpose
affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
affine_map<(d0, d1, d2, d3) -> (d1, d2)>
]
ins(%arg0, %arg1 : memref<2x5x3xf32>,memref<2x5x7xf32>)
outs(%arg2: memref<3x7xf32>)
```
Example Broadcast:
```
linalg.batch_reduce_matmul indexing_maps = [
affine_map<(d0, d1, d2, d3) -> (d3)>, // broadcast
affine_map<(d0, d1, d2, d3) -> (d0, d3, d2)>,
affine_map<(d0, d1, d2, d3) -> (d1, d2)>
]
ins(%arg0, %arg1 : memref<5xf32>, memref<2x5x7xf32>)
outs(%arg2: memref<3x7xf32>)
```
Example Broadcast and Transpose:
```
linalg.batch_reduce_matmul indexing_maps = [
affine_map<(d0, d1, d2, d3) -> (d1, d3)>, // broadcast
affine_map<(d0, d1, d2, d3) -> (d0, d2, d3)>, // transpose
affine_map<(d0, d1, d2, d3) -> (d1, d2)>
]
ins(%arg0, %arg1 : memref<3x5xf32>, memref<2x7x5xf32>)
outs(%arg2: memref<3x7xf32>)
```
RFCs and related PR:
https://discourse.llvm.org/t/rfc-linalg-opdsl-constant-list-attribute-definition/80149https://discourse.llvm.org/t/rfc-op-explosion-in-linalg/82863https://discourse.llvm.org/t/rfc-mlir-linalg-operation-tree/83586https://github.com/llvm/llvm-project/pull/115319https://github.com/llvm/llvm-project/pull/122275
