mlir._mlir_libs._mlir.ir¶

Classes¶

`DiagnosticSeverity`	Generic enumeration.
`WalkOrder`	Generic enumeration.
`WalkResult`	Generic enumeration.
`Diagnostic`
`DiagnosticInfo`
`DiagnosticHandler`
`ThreadPool`
`Context`
`DialectDescriptor`
`Dialects`
`Dialect`
`DialectRegistry`
`Location`
`Module`
`_OperationBase`
`Operation`
`OpView`
`Region`
`Block`
`InsertionPoint`
`Attribute`
`NamedAttribute`
`Type`
`TypeID`
`Value`
`BlockArgument`
`OpResult`
`OpOperand`
`AsmState`
`SymbolTable`
`BlockArgumentList`
`BlockIterator`
`BlockList`
`BlockSuccessors`
`BlockPredecessors`
`OperationIterator`
`OperationList`
`OpAttributeMap`
`OpOperandIterator`
`OpOperandList`
`OpResultList`
`OpSuccessors`
`RegionIterator`
`RegionSequence`
`_GlobalDebug`
`AttrBuilder`
`AffineExpr`
`AffineConstantExpr`
`AffineDimExpr`
`AffineSymbolExpr`
`AffineBinaryExpr`
`AffineAddExpr`
`AffineMulExpr`
`AffineModExpr`
`AffineFloorDivExpr`
`AffineCeilDivExpr`
`AffineMap`
`AffineExprList`
`IntegerSet`
`IntegerSetConstraint`
`IntegerSetConstraintList`
`AffineMapAttr`
`DenseBoolArrayAttr`
`DenseBoolArrayIterator`
`DenseI8ArrayAttr`
`DenseI8ArrayIterator`
`DenseI16ArrayAttr`
`DenseI16ArrayIterator`
`DenseI32ArrayAttr`
`DenseI32ArrayIterator`
`DenseI64ArrayAttr`
`DenseI64ArrayIterator`
`DenseF32ArrayAttr`
`DenseF32ArrayIterator`
`DenseF64ArrayAttr`
`DenseF64ArrayIterator`
`ArrayAttr`
`ArrayAttributeIterator`
`BoolAttr`
`DenseElementsAttr`
`DenseFPElementsAttr`
`DenseIntElementsAttr`
`DenseResourceElementsAttr`
`DictAttr`
`SymbolRefAttr`
`FlatSymbolRefAttr`
`OpaqueAttr`
`FloatAttr`
`IntegerAttr`
`IntegerSetAttr`
`StringAttr`
`TypeAttr`
`UnitAttr`
`StridedLayoutAttr`
`InferTypeOpInterface`
`ShapedTypeComponents`
`InferShapedTypeOpInterface`
`IntegerType`
`FloatType`
`IndexType`
`Float4E2M1FNType`
`Float6E2M3FNType`
`Float6E3M2FNType`
`Float8E4M3FNType`
`Float8E5M2Type`
`Float8E4M3Type`
`Float8E4M3FNUZType`
`Float8E4M3B11FNUZType`
`Float8E5M2FNUZType`
`Float8E3M4Type`
`Float8E8M0FNUType`
`BF16Type`
`F16Type`
`FloatTF32Type`
`F32Type`
`F64Type`
`NoneType`
`ComplexType`
`ShapedType`
`VectorType`
`RankedTensorType`
`UnrankedTensorType`
`MemRefType`
`UnrankedMemRefType`
`TupleType`
`FunctionType`
`OpaqueType`

Module Contents¶

class mlir._mlir_libs._mlir.ir.DiagnosticSeverity¶

Bases: enum.Enum

Generic enumeration.

Derive from this class to define new enumerations.

_member_names_: list = ['ERROR', 'WARNING', 'NOTE', 'REMARK']¶

_member_map_: dict = Ellipsis¶

_value2member_map_: dict = Ellipsis¶

ERROR = 0¶

WARNING = 1¶

NOTE = 2¶

REMARK = 3¶

class mlir._mlir_libs._mlir.ir.WalkOrder¶

Bases: enum.Enum

Generic enumeration.

Derive from this class to define new enumerations.

_member_names_: list = ['PRE_ORDER', 'POST_ORDER']¶

_member_map_: dict = Ellipsis¶

_value2member_map_: dict = Ellipsis¶

PRE_ORDER = 0¶

POST_ORDER = 1¶

class mlir._mlir_libs._mlir.ir.WalkResult¶

Bases: enum.Enum

Generic enumeration.

Derive from this class to define new enumerations.

_member_names_: list = ['ADVANCE', 'INTERRUPT', 'SKIP']¶

_member_map_: dict = Ellipsis¶

_value2member_map_: dict = Ellipsis¶

ADVANCE = 0¶

INTERRUPT = 1¶

SKIP = 2¶

class mlir._mlir_libs._mlir.ir.Diagnostic¶

property severity: DiagnosticSeverity¶: Returns the severity of the diagnostic.

property location: Location¶: Returns the location associated with the diagnostic.

property message: str¶: Returns the message text of the diagnostic.

property notes: tuple¶: Returns a tuple of attached note diagnostics.

__str__() → str¶: Returns the diagnostic message as a string.

class mlir._mlir_libs._mlir.ir.DiagnosticInfo(diag: Diagnostic)¶

property severity: DiagnosticSeverity¶: The severity level of the diagnostic.

property location: Location¶: The location associated with the diagnostic.

property message: str¶: The message text of the diagnostic.

property notes: list[DiagnosticInfo]¶: List of attached note diagnostics.

__str__() → str¶: Returns the diagnostic message as a string.

class mlir._mlir_libs._mlir.ir.DiagnosticHandler¶

detach() → None¶: Detaches the diagnostic handler from the context.

property attached: bool¶: Returns True if the handler is attached to a context.

property had_error: bool¶: Returns True if an error was encountered during diagnostic handling.

__enter__() → object¶: Enters the diagnostic handler as a context manager.

__exit__(exc_type: object | None, exc_value: object | None, traceback: object | None) → None¶: Exits the diagnostic handler context manager.

class mlir._mlir_libs._mlir.ir.ThreadPool¶

get_max_concurrency() → int¶: Returns the maximum number of threads in the pool.

_mlir_thread_pool_ptr() → str¶: Returns the raw pointer to the LLVM thread pool as a string.

class mlir._mlir_libs._mlir.ir.Context¶

static _get_live_count() → int¶: Gets the number of live Context objects.

_get_context_again() → Context¶: Gets another reference to the same context.

_get_live_module_count() → int¶: Gets the number of live modules owned by this context.

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirContext.

static _CAPICreate(arg: object, /) → object¶: Creates a Context from a capsule wrapping MlirContext.

__enter__() → object¶: Enters the context as a context manager.

__exit__(exc_type: object | None, exc_value: object | None, traceback: object | None) → None¶: Exits the context manager.

current: Context | None = Ellipsis¶: Gets the Context bound to the current thread or returns None if no context is set.

property dialects: Dialects¶: Gets a container for accessing dialects by name.

property d: Dialects¶: Alias for dialects.

get_dialect_descriptor(dialect_name: str) → DialectDescriptor¶: Gets or loads a dialect by name, returning its descriptor object.

property allow_unregistered_dialects: bool¶: Controls whether unregistered dialects are allowed in this context.

attach_diagnostic_handler(callback: object) → object¶: Attaches a diagnostic handler that will receive callbacks.

enable_multithreading(enable: bool) → None¶

Enables or disables multi-threading support in the context.

Parameters:: enable – Whether to enable (True) or disable (False) multi-threading.

set_thread_pool(arg: ThreadPool, /) → None¶

Sets a custom thread pool for the context to use.

Parameters:: pool – A ThreadPool object to use for parallel operations.

Note

Multi-threading is automatically disabled before setting the thread pool.

get_num_threads() → int¶: Gets the number of threads in the context’s thread pool.

_mlir_thread_pool_ptr() → str¶: Gets the raw pointer to the LLVM thread pool as a string.

is_registered_operation(operation_name: str) → bool¶

Checks whether an operation with the given name is registered.

Parameters:: operation_name – The fully qualified name of the operation (e.g., arith.addf).
Returns:: True if the operation is registered, False otherwise.

append_dialect_registry(registry: DialectRegistry) → None¶

Appends the contents of a dialect registry to the context.

Parameters:: registry – A DialectRegistry containing dialects to append.

property emit_error_diagnostics: bool¶

Controls whether error diagnostics are emitted to diagnostic handlers.

By default, error diagnostics are captured and reported through MLIRError exceptions.

load_all_available_dialects() → None¶

Loads all dialects available in the registry into the context.

This eagerly loads all dialects that have been registered, making them immediately available for use.

class mlir._mlir_libs._mlir.ir.DialectDescriptor¶

property namespace: str¶: Returns the namespace of the dialect.

__repr__() → str¶: Returns a string representation of the dialect descriptor.

class mlir._mlir_libs._mlir.ir.Dialects¶

__getitem__(arg: str, /) → object¶: Gets a dialect by name using subscript notation.

__getattr__(arg: str, /) → object¶: Gets a dialect by name using attribute notation.

class mlir._mlir_libs._mlir.ir.Dialect(descriptor: object)¶

property descriptor: object¶: Returns the DialectDescriptor for this dialect.

__repr__() → str¶: Returns a string representation of the dialect.

class mlir._mlir_libs._mlir.ir.DialectRegistry¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirDialectRegistry.

static _CAPICreate(arg: object, /) → DialectRegistry¶: Creates a DialectRegistry from a capsule wrapping MlirDialectRegistry.

class mlir._mlir_libs._mlir.ir.Location¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirLocation.

static _CAPICreate(arg: object, /) → Location¶: Creates a Location from a capsule wrapping MlirLocation.

__enter__() → object¶: Enters the location as a context manager.

__exit__(exc_type: object | None, exc_value: object | None, traceback: object | None) → None¶: Exits the location context manager.

__eq__(arg: Location, /) → bool¶
__eq__(arg: object, /) → bool: Compares location with non-location object (always returns False).

current: Location | None = Ellipsis¶: Gets the Location bound to the current thread or raises ValueError.

static unknown(context: Context | None = None) → Location¶: Gets a Location representing an unknown location.

static callsite(callee: Location, frames: collections.abc.Sequence[Location], context: Context | None = None) → Location¶: Gets a Location representing a caller and callsite.

is_a_callsite() → bool¶: Returns True if this location is a CallSiteLoc.

property callee: Location¶: Gets the callee location from a CallSiteLoc.

property caller: Location¶: Gets the caller location from a CallSiteLoc.

static file(filename: str, line: int, col: int, context: Context | None = None) → Location¶
static file(filename: str, start_line: int, start_col: int, end_line: int, end_col: int, context: Context | None = None) → Location: Gets a Location representing a file, line and column range.

is_a_file() → bool¶: Returns True if this location is a FileLineColLoc.

property filename: str¶: Gets the filename from a FileLineColLoc.

property start_line: int¶: Gets the start line number from a FileLineColLoc.

property start_col: int¶: Gets the start column number from a FileLineColLoc.

property end_line: int¶: Gets the end line number from a FileLineColLoc.

property end_col: int¶: Gets the end column number from a FileLineColLoc.

static fused(locations: collections.abc.Sequence[Location], metadata: Attribute | None = None, context: Context | None = None) → Location¶: Gets a Location representing a fused location with optional metadata.

is_a_fused() → bool¶: Returns True if this location is a FusedLoc.

property locations: list[Location]¶: Gets the list of locations from a FusedLoc.

static name(name: str, childLoc: Location | None = None, context: Context | None = None) → Location¶: Gets a Location representing a named location with optional child location.

is_a_name() → bool¶: Returns True if this location is a NameLoc.

property name_str: str¶: Gets the name string from a NameLoc.

property child_loc: Location¶: Gets the child location from a NameLoc.

static from_attr(attribute: Attribute, context: Context | None = None) → Location¶: Gets a Location from a LocationAttr.

property context: Context¶: Context that owns the Location.

property attr: Attribute¶: Get the underlying LocationAttr.

emit_error(message: str) → None¶

Emits an error diagnostic at this location.

Parameters:: message – The error message to emit.

__repr__() → str¶: Returns the assembly representation of the location.

class mlir._mlir_libs._mlir.ir.Module¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirModule.

static _CAPICreate(arg: object, /) → object¶

Creates a Module from a MlirModule wrapped by a capsule (i.e. module._CAPIPtr).

This returns a new object BUT _clear_mlir_module(module) must be called to prevent double-frees (of the underlying mlir::Module).

_clear_mlir_module() → None¶

Clears the internal MLIR module reference.

This is used internally to prevent double-free when ownership is transferred via the C API capsule mechanism. Not intended for normal use.

static parse(asm: str, context: Context | None = None) → Module¶
static parse(asm: bytes, context: Context | None = None) → Module

static parseFile(path: str, context: Context | None = None) → Module¶

Parses a module’s assembly format from a string.

Returns a new MlirModule or raises an MLIRError if the parsing fails.

static create(loc: Location | None = None) → Module¶: Creates an empty module.

property context: Context¶: Context that created the Module.

property operation: Operation¶: Accesses the module as an operation.

property body: Block¶: Return the block for this module.

dump() → None¶: Dumps a debug representation of the object to stderr.

__str__() → str¶

Gets the assembly form of the operation with default options.

If more advanced control over the assembly formatting or I/O options is needed, use the dedicated print or get_asm method, which supports keyword arguments to customize behavior.

__eq__(other: Module) → bool¶: Compares two modules for equality.

__hash__() → int¶: Returns the hash value of the module.

class mlir._mlir_libs._mlir.ir._OperationBase¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirOperation.

__eq__(arg: _OperationBase, /) → bool¶
__eq__(arg: object, /) → bool: Compares operation with non-operation object (always returns False).

__hash__() → int¶: Returns the hash value of the operation.

property attributes: OpAttributeMap¶: Returns a dictionary-like map of operation attributes.

property context: Context¶: Context that owns the operation.

property name: str¶: Returns the fully qualified name of the operation.

property operands: OpOperandList¶: Returns the list of operation operands.

property regions: RegionSequence¶: Returns the list of operation regions.

property results: OpResultList¶: Returns the list of Operation results.

property result: OpResult¶: Shortcut to get an op result if it has only one (throws an error otherwise).

property location: Location¶: Returns the source location the operation was defined or derived from.

property parent: Operation | None¶: Returns the parent operation, or None if at top level.

__str__() → str¶: Returns the assembly form of the operation.

print(state: AsmState, file: object | None = None, binary: bool = False) → None¶

print(large_elements_limit: int | None = None, large_resource_limit: int | None = None, enable_debug_info: bool = False, pretty_debug_info: bool = False, print_generic_op_form: bool = False, use_local_scope: bool = False, use_name_loc_as_prefix: bool = False, assume_verified: bool = False, file: object | None = None, binary: bool = False, skip_regions: bool = False) → None

Prints the assembly form of the operation to a file like object.

Parameters:

large_elements_limit – Whether to elide elements attributes above this number of elements. Defaults to None (no limit).
large_resource_limit – Whether to elide resource attributes above this number of characters. Defaults to None (no limit). If large_elements_limit is set and this is None, the behavior will be to use large_elements_limit as large_resource_limit.
enable_debug_info – Whether to print debug/location information. Defaults to False.
pretty_debug_info – Whether to format debug information for easier reading by a human (warning: the result is unparseable). Defaults to False.
print_generic_op_form – Whether to print the generic assembly forms of all ops. Defaults to False.
use_local_scope – Whether to print in a way that is more optimized for multi-threaded access but may not be consistent with how the overall module prints.
use_name_loc_as_prefix – Whether to use location attributes (NameLoc) as prefixes for the SSA identifiers. Defaults to False.
assume_verified – By default, if not printing generic form, the verifier will be run and if it fails, generic form will be printed with a comment about failed verification. While a reasonable default for interactive use, for systematic use, it is often better for the caller to verify explicitly and report failures in a more robust fashion. Set this to True if doing this in order to avoid running a redundant verification. If the IR is actually invalid, behavior is undefined.
file – The file like object to write to. Defaults to sys.stdout.
binary – Whether to write bytes (True) or str (False). Defaults to False.
skip_regions – Whether to skip printing regions. Defaults to False.

write_bytecode(file: object, desired_version: int | None = None) → None¶

Write the bytecode form of the operation to a file like object.

Parameters:

file – The file like object to write to.
desired_version – Optional version of bytecode to emit.

Returns:

The bytecode writer status.

get_asm(binary: bool = False, large_elements_limit: int | None = None, large_resource_limit: int | None = None, enable_debug_info: bool = False, pretty_debug_info: bool = False, print_generic_op_form: bool = False, use_local_scope: bool = False, use_name_loc_as_prefix: bool = False, assume_verified: bool = False, skip_regions: bool = False) → object¶

Gets the assembly form of the operation with all options available.

Parameters:

binary – Whether to return a bytes (True) or str (False) object. Defaults to False.
... (... others) – See the print() method for common keyword arguments for configuring the printout.

Returns:

Either a bytes or str object, depending on the setting of the binary argument.

verify() → bool¶: Verify the operation. Raises MLIRError if verification fails, and returns true otherwise.

move_after(other: _OperationBase) → None¶: Puts self immediately after the other operation in its parent block.

move_before(other: _OperationBase) → None¶: Puts self immediately before the other operation in its parent block.

is_before_in_block(other: _OperationBase) → bool¶

Checks if this operation is before another in the same block.

Parameters:: other – Another operation in the same parent block.
Returns:: True if this operation is before other in the operation list of the parent block.

clone(ip: object | None = None) → Operation¶

Creates a deep copy of the operation.

Parameters:: ip – Optional insertion point where the cloned operation should be inserted. If None, the current insertion point is used. If False, the operation remains detached.
Returns:: A new Operation that is a clone of this operation.

detach_from_parent() → OpView¶: Detaches the operation from its parent block.

property attached: bool¶: Reports if the operation is attached to its parent block.

erase() → None¶

Erases the operation and frees its memory.

Note: After erasing, any Python references to the operation become invalid.

walk(callback: collections.abc.Callable[[Operation], WalkResult], walk_order: WalkOrder) → None¶

Walks the operation tree with a callback function.

Parameters:

callback – A callable that takes an Operation and returns a WalkResult.
walk_order – The order of traversal (PRE_ORDER or POST_ORDER).

class mlir._mlir_libs._mlir.ir.Operation¶

Bases: _OperationBase

static create(name: str, results: collections.abc.Sequence[Type] | None = None, operands: collections.abc.Sequence[Value] | None = None, attributes: dict | None = None, successors: collections.abc.Sequence[Block] | None = None, regions: int = 0, loc: Location | None = None, ip: object | None = None, infer_type: bool = False) → Operation¶

Creates a new operation.

Parameters:

name – Operation name (e.g. dialect.operation).
results – Optional sequence of Type representing op result types.
operands – Optional operands of the operation.
attributes – Optional Dict of {str: Attribute}.
successors – Optional List of Block for the operation’s successors.
regions – Number of regions to create (default = 0).
location – Optional Location object (defaults to resolve from context manager).
ip – Optional InsertionPoint (defaults to resolve from context manager or set to False to disable insertion, even with an insertion point set in the context manager).
infer_type – Whether to infer result types (default = False).

Returns:

A new detached Operation object. Detached operations can be added to blocks, which causes them to become attached.

static parse(source: str, *, source_name: str = '', context: Context | None = None) → OpView¶: Parses an operation. Supports both text assembly format and binary bytecode format.

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirOperation.

static _CAPICreate(arg: object, /) → object¶: Creates an Operation from a capsule wrapping MlirOperation.

property operation: Operation¶: Returns self (the operation).

property opview: OpView¶

Returns an OpView of this operation.

Note: If the operation has a registered and loaded dialect then this OpView will be concrete wrapper class.

property block: Block¶: Returns the block containing this operation.

property successors: OpSuccessors¶: Returns the list of Operation successors.

_set_invalid() → None¶: Invalidate the operation.

class mlir._mlir_libs._mlir.ir.OpView(operation: Operation)¶

Bases: _OperationBase

property operation: Operation¶

property opview: OpView¶

__str__() → str¶: Returns the assembly form of the operation.

property successors: OpSuccessors¶: Returns the list of Operation successors.

_set_invalid() → None¶: Invalidate the operation.

_ODS_REGIONS: tuple = (0, True)¶

_ODS_OPERAND_SEGMENTS: None = None¶

_ODS_RESULT_SEGMENTS: None = None¶

classmethod build_generic(**kwargs) → Any¶

Builds a specific, generated OpView based on class level attributes.

classmethod parse(**kwargs) → Any¶

(cls: object, source: str, *, source_name: str = ‘’, context: Context | None = None) -> _mlir.ir.OpView

Parses a specific, generated OpView based on class level attributes.

class mlir._mlir_libs._mlir.ir.Region¶

property blocks: BlockList¶: Returns a forward-optimized sequence of blocks.

property owner: OpView¶: Returns the operation owning this region.

__iter__() → BlockIterator¶: Iterates over blocks in the region.

__eq__(arg: Region, /) → bool¶
__eq__(arg: object, /) → bool: Compares region with non-region object (always returns False).

class mlir._mlir_libs._mlir.ir.Block¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirBlock.

property owner: OpView¶: Returns the owning operation of this block.

property region: Region¶: Returns the owning region of this block.

property arguments: BlockArgumentList¶: Returns a list of block arguments.

add_argument(type: Type, loc: Location) → BlockArgument¶

Appends an argument of the specified type to the block.

Parameters:

type – The type of the argument to add.
loc – The source location for the argument.

Returns:

The newly added block argument.

erase_argument(index: int) → None¶

Erases the argument at the specified index.

Parameters:: index – The index of the argument to erase.

property operations: OperationList¶: Returns a forward-optimized sequence of operations.

static create_at_start(parent: Region, arg_types: collections.abc.Sequence = [], arg_locs: collections.abc.Sequence | None = None) → Block¶: Creates and returns a new Block at the beginning of the given region (with given argument types and locations).

append_to(region: Region) → None¶

Appends this block to a region.

Transfers ownership if the block is currently owned by another region.

Parameters:: region – The region to append the block to.

create_before(*arg_types, arg_locs: collections.abc.Sequence | None = None) → Block¶: Creates and returns a new Block before this block (with given argument types and locations).

create_after(*arg_types, arg_locs: collections.abc.Sequence | None = None) → Block¶: Creates and returns a new Block after this block (with given argument types and locations).

__iter__() → OperationIterator¶: Iterates over operations in the block.

__eq__(arg: Block, /) → bool¶
__eq__(arg: object, /) → bool: Compares block with non-block object (always returns False).

__hash__() → int¶: Returns the hash value of the block.

__str__() → str¶: Returns the assembly form of the block.

append(operation: _OperationBase) → None¶

Appends an operation to this block.

If the operation is currently in another block, it will be moved.

Parameters:: operation – The operation to append to the block.

property successors: BlockSuccessors¶: Returns the list of Block successors.

property predecessors: BlockPredecessors¶: Returns the list of Block predecessors.

class mlir._mlir_libs._mlir.ir.InsertionPoint(block: Block)¶

class mlir._mlir_libs._mlir.ir.InsertionPoint(beforeOperation: _OperationBase)

__enter__() → object¶: Enters the insertion point as a context manager.

__exit__(exc_type: object | None, exc_value: object | None, traceback: object | None) → None¶: Exits the insertion point context manager.

current: InsertionPoint = Ellipsis¶: Gets the InsertionPoint bound to the current thread or raises ValueError if none has been set.

static at_block_begin(block: Block) → InsertionPoint¶

Creates an insertion point at the beginning of a block.

Parameters:: block – The block at whose beginning operations should be inserted.
Returns:: An InsertionPoint at the block’s beginning.

static at_block_terminator(block: Block) → InsertionPoint¶

Creates an insertion point before a block’s terminator.

Parameters:: block – The block whose terminator to insert before.
Returns:: An InsertionPoint before the terminator.
Raises:: ValueError – If the block has no terminator.

static after(operation: _OperationBase) → InsertionPoint¶

Creates an insertion point immediately after an operation.

Parameters:: operation – The operation after which to insert.
Returns:: An InsertionPoint after the operation.

insert(operation: _OperationBase) → None¶

Inserts an operation at this insertion point.

Parameters:: operation – The operation to insert.

property block: Block¶: Returns the block that this InsertionPoint points to.

property ref_operation: Operation | None¶: The reference operation before which new operations are inserted, or None if the insertion point is at the end of the block.

class mlir._mlir_libs._mlir.ir.Attribute(cast_from_type: Attribute)¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirAttribute.

static _CAPICreate(arg: object, /) → Attribute¶: Creates an Attribute from a capsule wrapping MlirAttribute.

static parse(asm: str, context: Context | None = None) → Attribute¶: Parses an attribute from an assembly form. Raises an MLIRError on failure.

property context: Context¶: Context that owns the Attribute.

property type: Type¶: Returns the type of the Attribute.

get_named(arg: str, /) → NamedAttribute¶

Binds a name to the attribute, creating a NamedAttribute.

Parameters:: name – The name to bind to the Attribute.
Returns:: A NamedAttribute with the given name and this attribute.

__eq__(arg: Attribute, /) → bool¶
__eq__(arg: object, /) → bool: Compares attribute with non-attribute object (always returns False).

__hash__() → int¶: Returns the hash value of the attribute.

dump() → None¶: Dumps a debug representation of the object to stderr.

__str__() → str¶: Returns the assembly form of the Attribute.

__repr__() → str¶: Returns a string representation of the attribute.

property typeid: TypeID¶: Returns the TypeID of the attribute.

maybe_downcast() → Attribute¶: Downcasts the attribute to a more specific attribute if possible.

class mlir._mlir_libs._mlir.ir.NamedAttribute¶

__repr__() → str¶: Returns a string representation of the named attribute.

property name: str¶: The name of the NamedAttribute binding.

property attr: Attribute¶: The underlying generic attribute of the NamedAttribute binding.

class mlir._mlir_libs._mlir.ir.Type(cast_from_type: Type)¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirType.

static _CAPICreate(arg: object, /) → Type¶: Creates a Type from a capsule wrapping MlirType.

static parse(asm: str, context: Context | None = None) → Type¶

Parses the assembly form of a type.

Returns a Type object or raises an MLIRError if the type cannot be parsed.

property context: Context¶: Context that owns the Type.

__eq__(arg: Type, /) → bool¶
__eq__(other: object | None) → bool: Compares type with non-type object (always returns False).

__hash__() → int¶: Returns the hash value of the Type.

dump() → None¶: Dumps a debug representation of the object to stderr.

__str__() → str¶: Returns the assembly form of the Type.

__repr__() → str¶: Returns a string representation of the Type.

maybe_downcast() → Type¶: Downcasts the Type to a more specific Type if possible.

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

class mlir._mlir_libs._mlir.ir.TypeID¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirTypeID.

static _CAPICreate(arg: object, /) → TypeID¶: Creates a TypeID from a capsule wrapping MlirTypeID.

__eq__(arg: TypeID, /) → bool¶
__eq__(arg: object, /) → bool: Compares TypeID with non-TypeID object (always returns False).

__hash__() → int¶: Returns the hash value of the TypeID.

class mlir._mlir_libs._mlir.ir.Value(value: Value)¶

property _CAPIPtr: object¶: Gets a capsule wrapping the MlirValue.

static _CAPICreate(arg: object, /) → Value¶: Creates a Value from a capsule wrapping MlirValue.

property context: Context¶: Context in which the value lives.

dump() → None¶: Dumps a debug representation of the object to stderr.

property owner: object¶: Returns the owner of the value (Operation for results, Block for arguments).

property uses: OpOperandIterator¶: Returns an iterator over uses of this value.

__eq__(arg: Value, /) → bool¶
__eq__(arg: object, /) → bool: Compares value with non-value object (always returns False).

__hash__() → int¶: Returns the hash value of the value.

__str__() → str¶

Returns the string form of the value.

If the value is a block argument, this is the assembly form of its type and the position in the argument list. If the value is an operation result, this is equivalent to printing the operation that produced it.

get_name(use_local_scope: bool = False, use_name_loc_as_prefix: bool = False) → str¶
get_name(state: AsmState) → str: Returns the string form of value as an operand (i.e., the ValueID).

property type: Type¶: Returns the type of the value.

set_type(type: Type) → None¶: Sets the type of the value.

replace_all_uses_with(arg: Value, /) → None¶: Replace all uses of value with the new value, updating anything in the IR that uses self to use the other value instead.

replace_all_uses_except(with_: Value, exceptions: Operation) → None¶
replace_all_uses_except(with_: Value, exceptions: list) → None
replace_all_uses_except(with_: Value, exceptions: Operation) → None
replace_all_uses_except(with_: Value, exceptions: collections.abc.Sequence[Operation]) → None

maybe_downcast() → Value¶: Downcasts the Value to a more specific kind if possible.

property location: Location¶: Returns the source location of the value.

class mlir._mlir_libs._mlir.ir.BlockArgument(value: Value)¶

Bases: Value

static isinstance(other_value: Value) → bool¶

maybe_downcast() → BlockArgument¶: Downcasts the Value to a more specific kind if possible.

property owner: Block¶: Returns the block that owns this argument.

property arg_number: int¶: Returns the position of this argument in the block’s argument list.

set_type(type: Type) → None¶: Sets the type of this block argument.

class mlir._mlir_libs._mlir.ir.OpResult(value: Value)¶

Bases: Value

static isinstance(other_value: Value) → bool¶

maybe_downcast() → OpResult¶: Downcasts the Value to a more specific kind if possible.

property owner: Operation¶: Returns the operation that produces this result.

property result_number: int¶: Returns the position of this result in the operation’s result list.

class mlir._mlir_libs._mlir.ir.OpOperand¶

property owner: OpView¶: Returns the operation that owns this operand.

property operand_number: int¶: Returns the operand number in the owning operation.

class mlir._mlir_libs._mlir.ir.AsmState(value: Value, use_local_scope: bool = False)¶
class mlir._mlir_libs._mlir.ir.AsmState(op: _OperationBase, use_local_scope: bool = False)

class mlir._mlir_libs._mlir.ir.SymbolTable(arg: _OperationBase, /)¶

__getitem__(arg: str, /) → OpView¶

Looks up a symbol by name in the symbol table.

Parameters:: name – The name of the symbol to look up.
Returns:: The operation defining the symbol.
Raises:: KeyError – If the symbol is not found.

insert(operation: _OperationBase) → StringAttr¶

Inserts a symbol operation into the symbol table.

Parameters:: operation – An operation with a symbol name to insert.
Returns:: The symbol name attribute of the inserted operation.
Raises:: ValueError – If the operation does not have a symbol name.

erase(operation: _OperationBase) → None¶

Erases a symbol operation from the symbol table.

Parameters:: operation – The symbol operation to erase.

Note

The operation is also erased from the IR and invalidated.

__delitem__(arg: str, /) → None¶: Deletes a symbol by name from the symbol table.

__contains__(arg: str, /) → bool¶: Checks if a symbol with the given name exists in the table.

static set_symbol_name(symbol: _OperationBase, name: str) → None¶: Sets the symbol name for a symbol operation.

static get_symbol_name(symbol: _OperationBase) → StringAttr¶: Gets the symbol name from a symbol operation.

static get_visibility(symbol: _OperationBase) → StringAttr¶: Gets the visibility attribute of a symbol operation.

static set_visibility(symbol: _OperationBase, visibility: str) → None¶: Sets the visibility attribute of a symbol operation.

static replace_all_symbol_uses(old_symbol: str, new_symbol: str, from_op: _OperationBase) → None¶: Replaces all uses of a symbol with a new symbol name within the given operation.

static walk_symbol_tables(from_op: _OperationBase, all_sym_uses_visible: bool, callback: object) → None¶: Walks symbol tables starting from an operation with a callback function.

class mlir._mlir_libs._mlir.ir.BlockArgumentList¶

__add__(arg: BlockArgumentList, /) → list[BlockArgument]¶

property types: list[Type]¶: Returns a list of types for all arguments in this argument list.

class mlir._mlir_libs._mlir.ir.BlockIterator¶

__iter__() → BlockIterator¶: Returns an iterator over the blocks in the operation’s region.

__next__() → Block¶: Returns the next block in the iteration.

class mlir._mlir_libs._mlir.ir.BlockList¶

__getitem__(arg: int, /) → Block¶: Returns the block at the specified index.

__iter__() → BlockIterator¶: Returns an iterator over blocks in the operation’s region.

__len__() → int¶: Returns the number of blocks in the operation’s region.

append(*args, arg_locs: collections.abc.Sequence | None = None) → Block¶

Appends a new block, with argument types as positional args.

Returns:: The created block.

class mlir._mlir_libs._mlir.ir.BlockSuccessors¶

__add__(arg: BlockSuccessors, /) → list[Block]¶

class mlir._mlir_libs._mlir.ir.BlockPredecessors¶

__add__(arg: BlockPredecessors, /) → list[Block]¶

class mlir._mlir_libs._mlir.ir.OperationIterator¶

__iter__() → OperationIterator¶: Returns an iterator over the operations in an operation’s block.

__next__() → OpView¶: Returns the next operation in the iteration.

class mlir._mlir_libs._mlir.ir.OperationList¶

__getitem__(arg: int, /) → OpView¶: Returns the operation at the specified index.

__iter__() → OperationIterator¶: Returns an iterator over operations in the list.

__len__() → int¶: Returns the number of operations in the list.

class mlir._mlir_libs._mlir.ir.OpAttributeMap¶

__contains__(name: str) → bool¶: Checks if an attribute with the given name exists in the map.

__len__() → int¶: Returns the number of attributes in the map.

__getitem__(name: str) → Attribute¶
__getitem__(index: int) → NamedAttribute: Gets a named attribute by index.

__setitem__(name: str, attr: Attribute) → None¶: Sets an attribute with the given name.

__delitem__(name: str) → None¶: Deletes an attribute with the given name.

__iter__() → collections.abc.Iterator¶: Iterates over attribute names.

keys() → list¶: Returns a list of attribute names.

values() → list¶: Returns a list of attribute values.

items() → list¶: Returns a list of (name, attribute) tuples.

class mlir._mlir_libs._mlir.ir.OpOperandIterator¶

__iter__() → OpOperandIterator¶: Returns an iterator over operands.

__next__() → OpOperand¶: Returns the next operand in the iteration.

class mlir._mlir_libs._mlir.ir.OpOperandList¶

__add__(arg: OpOperandList, /) → list[Value]¶

__setitem__(index: int, value: Value) → None¶: Sets the operand at the specified index to a new value.

class mlir._mlir_libs._mlir.ir.OpResultList¶

__add__(arg: OpResultList, /) → list[OpResult]¶

property types: list[Type]¶: Returns a list of types for all results in this result list.

property owner: OpView¶: Returns the operation that owns this result list.

class mlir._mlir_libs._mlir.ir.OpSuccessors¶

__add__(arg: OpSuccessors, /) → list[Block]¶

__setitem__(index: int, block: Block) → None¶: Sets the successor block at the specified index.

class mlir._mlir_libs._mlir.ir.RegionIterator¶

__iter__() → RegionIterator¶: Returns an iterator over the regions in the operation.

__next__() → Region¶: Returns the next region in the iteration.

class mlir._mlir_libs._mlir.ir.RegionSequence¶

__add__(arg: RegionSequence, /) → list[Region]¶

__iter__() → RegionIterator¶: Returns an iterator over the regions in the sequence.

class mlir._mlir_libs._mlir.ir._GlobalDebug¶

flag: bool = Ellipsis¶: LLVM-wide debug flag.

static set_types(types: str) → None¶
static set_types(types: collections.abc.Sequence[str]) → None: Sets multiple specific debug types to be produced by LLVM.

class mlir._mlir_libs._mlir.ir.AttrBuilder¶

static contains(attribute_kind: str) → bool¶: Checks whether an attribute builder is registered for the given attribute kind.

static get(attribute_kind: str) → collections.abc.Callable¶: Gets the registered attribute builder for the given attribute kind.

static insert(attribute_kind: str, attr_builder: collections.abc.Callable, replace: bool = False) → None¶: Register an attribute builder for building MLIR attributes from Python values.

class mlir._mlir_libs._mlir.ir.AffineExpr¶

property _CAPIPtr: object¶

_CAPICreate() → AffineExpr¶

__add__(arg: AffineExpr, /) → AffineAddExpr¶
__add__(arg: int, /) → AffineAddExpr

__radd__(arg: int, /) → AffineAddExpr¶

__mul__(arg: AffineExpr, /) → AffineMulExpr¶
__mul__(arg: int, /) → AffineMulExpr

__rmul__(arg: int, /) → AffineMulExpr¶

__mod__(arg: AffineExpr, /) → AffineModExpr¶
__mod__(arg: int, /) → AffineModExpr

__rmod__(arg: int, /) → AffineModExpr¶

__sub__(arg: AffineExpr, /) → AffineAddExpr¶
__sub__(arg: int, /) → AffineAddExpr

__rsub__(arg: int, /) → AffineAddExpr¶

__eq__(arg: AffineExpr, /) → bool¶
__eq__(arg: object, /) → bool

__str__() → str¶

__repr__() → str¶

__hash__() → int¶

property context: Context¶

compose(arg: AffineMap, /) → AffineExpr¶

shift_dims(num_dims: int, shift: int, offset: int = 0) → AffineExpr¶

shift_symbols(num_symbols: int, shift: int, offset: int = 0) → AffineExpr¶

static simplify_affine_expr(expr: AffineExpr, num_dims: int, num_symbols: int) → AffineExpr¶: Simplify an affine expression by flattening and some amount of simple analysis.

static get_add(arg0: AffineExpr, arg1: AffineExpr, /) → AffineAddExpr¶
static get_add(arg0: int, arg1: AffineExpr, /) → AffineAddExpr
static get_add(arg0: AffineExpr, arg1: int, /) → AffineAddExpr: Gets an affine expression containing a sum of an expression and a constant.

static get_mul(arg0: AffineExpr, arg1: AffineExpr, /) → AffineMulExpr¶
static get_mul(arg0: int, arg1: AffineExpr, /) → AffineMulExpr
static get_mul(arg0: AffineExpr, arg1: int, /) → AffineMulExpr: Gets an affine expression containing a product of an expression and a constant.

static get_mod(arg0: AffineExpr, arg1: AffineExpr, /) → AffineModExpr¶
static get_mod(arg0: int, arg1: AffineExpr, /) → AffineModExpr
static get_mod(arg0: AffineExpr, arg1: int, /) → AffineModExpr: Gets an affine expression containing the module of dividingan expression by a constant.

static get_floor_div(arg0: AffineExpr, arg1: AffineExpr, /) → AffineFloorDivExpr¶
static get_floor_div(arg0: int, arg1: AffineExpr, /) → AffineFloorDivExpr
static get_floor_div(arg0: AffineExpr, arg1: int, /) → AffineFloorDivExpr: Gets an affine expression containing the rounded-down result of dividing an expression by a constant.

static get_ceil_div(arg0: AffineExpr, arg1: AffineExpr, /) → AffineCeilDivExpr¶
static get_ceil_div(arg0: int, arg1: AffineExpr, /) → AffineCeilDivExpr
static get_ceil_div(arg0: AffineExpr, arg1: int, /) → AffineCeilDivExpr: Gets an affine expression containing the rounded-up result of dividing an expression by a constant.

static get_constant(value: int, context: Context | None = None) → AffineConstantExpr¶: Gets a constant affine expression with the given value.

static get_dim(position: int, context: Context | None = None) → AffineDimExpr¶: Gets an affine expression of a dimension at the given position.

static get_symbol(position: int, context: Context | None = None) → AffineSymbolExpr¶: Gets an affine expression of a symbol at the given position.

dump() → None¶: Dumps a debug representation of the object to stderr.

class mlir._mlir_libs._mlir.ir.AffineConstantExpr(expr: AffineExpr)¶

Bases: AffineExpr

static isinstance(other: AffineExpr) → bool¶

static get(value: int, context: Context | None = None) → AffineConstantExpr¶

property value: int¶

class mlir._mlir_libs._mlir.ir.AffineDimExpr(expr: AffineExpr)¶

Bases: AffineExpr

static isinstance(other: AffineExpr) → bool¶

static get(position: int, context: Context | None = None) → AffineDimExpr¶

property position: int¶

class mlir._mlir_libs._mlir.ir.AffineSymbolExpr(expr: AffineExpr)¶

Bases: AffineExpr

static isinstance(other: AffineExpr) → bool¶

static get(position: int, context: Context | None = None) → AffineSymbolExpr¶

property position: int¶

class mlir._mlir_libs._mlir.ir.AffineBinaryExpr(expr: AffineExpr)¶

Bases: AffineExpr

static isinstance(other: AffineExpr) → bool¶

property lhs: AffineExpr¶

property rhs: AffineExpr¶

class mlir._mlir_libs._mlir.ir.AffineAddExpr(expr: AffineExpr)¶

Bases: AffineBinaryExpr

static isinstance(other: AffineExpr) → bool¶

static get(arg0: AffineExpr, arg1: AffineExpr, /) → AffineAddExpr¶

class mlir._mlir_libs._mlir.ir.AffineMulExpr(expr: AffineExpr)¶

Bases: AffineBinaryExpr

static isinstance(other: AffineExpr) → bool¶

static get(arg0: AffineExpr, arg1: AffineExpr, /) → AffineMulExpr¶

class mlir._mlir_libs._mlir.ir.AffineModExpr(expr: AffineExpr)¶

Bases: AffineBinaryExpr

static isinstance(other: AffineExpr) → bool¶

static get(arg0: AffineExpr, arg1: AffineExpr, /) → AffineModExpr¶

class mlir._mlir_libs._mlir.ir.AffineFloorDivExpr(expr: AffineExpr)¶

Bases: AffineBinaryExpr

static isinstance(other: AffineExpr) → bool¶

static get(arg0: AffineExpr, arg1: AffineExpr, /) → AffineFloorDivExpr¶

class mlir._mlir_libs._mlir.ir.AffineCeilDivExpr(expr: AffineExpr)¶

Bases: AffineBinaryExpr

static isinstance(other: AffineExpr) → bool¶

static get(arg0: AffineExpr, arg1: AffineExpr, /) → AffineCeilDivExpr¶

class mlir._mlir_libs._mlir.ir.AffineMap¶

property _CAPIPtr: object¶

_CAPICreate() → AffineMap¶

__eq__(arg: AffineMap, /) → bool¶
__eq__(arg: object, /) → bool

__str__() → str¶

__repr__() → str¶

__hash__() → int¶

static compress_unused_symbols(arg0: list, arg1: Context, /) → list[AffineMap]¶

property context: Context¶: Context that owns the Affine Map

dump() → None¶: Dumps a debug representation of the object to stderr.

static get(dim_count: int, symbol_count: int, exprs: list, context: Context | None = None) → AffineMap¶: Gets a map with the given expressions as results.

static get_constant(value: int, context: Context | None = None) → AffineMap¶: Gets an affine map with a single constant result

static get_empty(context: Context | None = None) → AffineMap¶: Gets an empty affine map.

static get_identity(n_dims: int, context: Context | None = None) → AffineMap¶: Gets an identity map with the given number of dimensions.

static get_minor_identity(n_dims: int, n_results: int, context: Context | None = None) → AffineMap¶: Gets a minor identity map with the given number of dimensions and results.

static get_permutation(permutation: collections.abc.Sequence[int], context: Context | None = None) → AffineMap¶: Gets an affine map that permutes its inputs.

get_submap(result_positions: collections.abc.Sequence[int]) → AffineMap¶

get_major_submap(n_results: int) → AffineMap¶

get_minor_submap(n_results: int) → AffineMap¶

replace(expr: AffineExpr, replacement: AffineExpr, n_result_dims: int, n_result_syms: int) → AffineMap¶

property is_permutation: bool¶

property is_projected_permutation: bool¶

property n_dims: int¶

property n_inputs: int¶

property n_symbols: int¶

property results: AffineExprList¶

class mlir._mlir_libs._mlir.ir.AffineExprList¶

__add__(arg: AffineExprList, /) → list[AffineExpr]¶

class mlir._mlir_libs._mlir.ir.IntegerSet¶

property _CAPIPtr: object¶

_CAPICreate() → IntegerSet¶

__eq__(arg: IntegerSet, /) → bool¶
__eq__(arg: object, /) → bool

__str__() → str¶

__repr__() → str¶

__hash__() → int¶

property context: Context¶

dump() → None¶: Dumps a debug representation of the object to stderr.

static get(num_dims: int, num_symbols: int, exprs: list, eq_flags: collections.abc.Sequence[bool], context: Context | None = None) → IntegerSet¶

static get_empty(num_dims: int, num_symbols: int, context: Context | None = None) → IntegerSet¶

get_replaced(dim_exprs: list, symbol_exprs: list, num_result_dims: int, num_result_symbols: int) → IntegerSet¶

property is_canonical_empty: bool¶

property n_dims: int¶

property n_symbols: int¶

property n_inputs: int¶

property n_equalities: int¶

property n_inequalities: int¶

property constraints: IntegerSetConstraintList¶

class mlir._mlir_libs._mlir.ir.IntegerSetConstraint¶

property expr: AffineExpr¶

property is_eq: bool¶

class mlir._mlir_libs._mlir.ir.IntegerSetConstraintList¶

__add__(arg: IntegerSetConstraintList, /) → list[IntegerSetConstraint]¶

class mlir._mlir_libs._mlir.ir.AffineMapAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(affine_map: AffineMap) → AffineMapAttr¶: Gets an attribute wrapping an AffineMap.

property value: AffineMap¶: Returns the value of the AffineMap attribute

class mlir._mlir_libs._mlir.ir.DenseBoolArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence, context: Context | None = None) → DenseBoolArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → bool¶

__len__() → int¶

__iter__() → DenseBoolArrayIterator¶

__add__(arg: list, /) → DenseBoolArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseBoolArrayIterator¶

__iter__() → DenseBoolArrayIterator¶

__next__() → bool¶

class mlir._mlir_libs._mlir.ir.DenseI8ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[int], context: Context | None = None) → DenseI8ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → int¶

__len__() → int¶

__iter__() → DenseI8ArrayIterator¶

__add__(arg: list, /) → DenseI8ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseI8ArrayIterator¶

__iter__() → DenseI8ArrayIterator¶

__next__() → int¶

class mlir._mlir_libs._mlir.ir.DenseI16ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[int], context: Context | None = None) → DenseI16ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → int¶

__len__() → int¶

__iter__() → DenseI16ArrayIterator¶

__add__(arg: list, /) → DenseI16ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseI16ArrayIterator¶

__iter__() → DenseI16ArrayIterator¶

__next__() → int¶

class mlir._mlir_libs._mlir.ir.DenseI32ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[int], context: Context | None = None) → DenseI32ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → int¶

__len__() → int¶

__iter__() → DenseI32ArrayIterator¶

__add__(arg: list, /) → DenseI32ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseI32ArrayIterator¶

__iter__() → DenseI32ArrayIterator¶

__next__() → int¶

class mlir._mlir_libs._mlir.ir.DenseI64ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[int], context: Context | None = None) → DenseI64ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → int¶

__len__() → int¶

__iter__() → DenseI64ArrayIterator¶

__add__(arg: list, /) → DenseI64ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseI64ArrayIterator¶

__iter__() → DenseI64ArrayIterator¶

__next__() → int¶

class mlir._mlir_libs._mlir.ir.DenseF32ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[float], context: Context | None = None) → DenseF32ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → float¶

__len__() → int¶

__iter__() → DenseF32ArrayIterator¶

__add__(arg: list, /) → DenseF32ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseF32ArrayIterator¶

__iter__() → DenseF32ArrayIterator¶

__next__() → float¶

class mlir._mlir_libs._mlir.ir.DenseF64ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(values: collections.abc.Sequence[float], context: Context | None = None) → DenseF64ArrayAttr¶: Gets a uniqued dense array attribute

__getitem__(arg: int, /) → float¶

__len__() → int¶

__iter__() → DenseF64ArrayIterator¶

__add__(arg: list, /) → DenseF64ArrayAttr¶

class mlir._mlir_libs._mlir.ir.DenseF64ArrayIterator¶

__iter__() → DenseF64ArrayIterator¶

__next__() → float¶

class mlir._mlir_libs._mlir.ir.ArrayAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(attributes: list, context: Context | None = None) → ArrayAttr¶: Gets a uniqued Array attribute

__getitem__(arg: int, /) → Attribute¶

__len__() → int¶

__iter__() → ArrayAttributeIterator¶

__add__(arg: list, /) → ArrayAttr¶

class mlir._mlir_libs._mlir.ir.ArrayAttributeIterator¶

__iter__() → ArrayAttributeIterator¶

__next__() → Attribute¶

class mlir._mlir_libs._mlir.ir.BoolAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(value: bool, context: Context | None = None) → BoolAttr¶: Gets an uniqued bool attribute

property value: bool¶: Returns the value of the bool attribute

__bool__() → bool¶: Converts the value of the bool attribute to a Python bool

class mlir._mlir_libs._mlir.ir.DenseElementsAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

__len__() → int¶

static get(array: typing_extensions.Buffer, signless: bool = True, type: Type | None = None, shape: collections.abc.Sequence[int] | None = None, context: Context | None = None) → DenseElementsAttr¶

static get(attrs: list, type: Type | None = None, context: Context | None = None) → DenseElementsAttr

Gets a DenseElementsAttr from a Python list of attributes.

Note that it can be expensive to construct attributes individually. For a large number of elements, consider using a Python buffer or array instead.

Parameters:

attrs – A list of attributes.
type – The desired shape and type of the resulting DenseElementsAttr. If not provided, the element type is determined based on the type of the 0th attribute and the shape is [len(attrs)].
context – Explicit context, if not from context manager.

Returns:

DenseElementsAttr on success.

Raises:

ValueError – If the type of the attributes does not match the type specified by shaped_type.

static get_splat(shaped_type: Type, element_attr: Attribute) → DenseElementsAttr¶: Gets a DenseElementsAttr where all values are the same

property is_splat: bool¶

get_splat_value() → Attribute¶

class mlir._mlir_libs._mlir.ir.DenseFPElementsAttr(cast_from_attr: Attribute)¶

Bases: DenseElementsAttr

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

__getitem__(arg: int, /) → float¶

class mlir._mlir_libs._mlir.ir.DenseIntElementsAttr(cast_from_attr: Attribute)¶

Bases: DenseElementsAttr

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

__getitem__(arg: int, /) → int¶

class mlir._mlir_libs._mlir.ir.DenseResourceElementsAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get_from_buffer(array: typing_extensions.Buffer, name: str, type: Type, alignment: int | None = None, is_mutable: bool = False, context: Context | None = None) → DenseResourceElementsAttr¶

Gets a DenseResourceElementsAttr from a Python buffer or array.

This function does minimal validation or massaging of the data, and it is up to the caller to ensure that the buffer meets the characteristics implied by the shape.

The backing buffer and any user objects will be retained for the lifetime of the resource blob. This is typically bounded to the context but the resource can have a shorter lifespan depending on how it is used in subsequent processing.

Parameters:

buffer – The array or buffer to convert.
name – Name to provide to the resource (may be changed upon collision).
type – The explicit ShapedType to construct the attribute with.
context – Explicit context, if not from context manager.

Returns:

DenseResourceElementsAttr on success.

Raises:

ValueError – If the type of the buffer or array cannot be matched to an MLIR type or if the buffer does not meet expectations.

class mlir._mlir_libs._mlir.ir.DictAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

__contains__(arg: str, /) → bool¶

__len__() → int¶

static get(value: dict = {}, context: Context | None = None) → DictAttr¶: Gets an uniqued dict attribute

__getitem__(arg: str, /) → Attribute¶
__getitem__(arg: int, /) → NamedAttribute

class mlir._mlir_libs._mlir.ir.SymbolRefAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(symbols: collections.abc.Sequence[str], context: Context | None = None) → SymbolRefAttr¶: Gets a uniqued SymbolRef attribute from a list of symbol names

property value: list[str]¶: Returns the value of the SymbolRef attribute as a list[str]

class mlir._mlir_libs._mlir.ir.FlatSymbolRefAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(value: str, context: Context | None = None) → FlatSymbolRefAttr¶: Gets a uniqued FlatSymbolRef attribute

property value: str¶: Returns the value of the FlatSymbolRef attribute as a string

class mlir._mlir_libs._mlir.ir.OpaqueAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(dialect_namespace: str, buffer: typing_extensions.Buffer, type: Type, context: Context | None = None) → OpaqueAttr¶: Gets an Opaque attribute.

property dialect_namespace: str¶: Returns the dialect namespace for the Opaque attribute as a string

property data: bytes¶: Returns the data for the Opaqued attributes as bytes

class mlir._mlir_libs._mlir.ir.FloatAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(type: Type, value: float, loc: Location | None = None) → FloatAttr¶: Gets an uniqued float point attribute associated to a type

static get_unchecked(type: Type, value: float, context: Context | None = None) → FloatAttr¶: Gets an uniqued float point attribute associated to a type

static get_f32(value: float, context: Context | None = None) → FloatAttr¶: Gets an uniqued float point attribute associated to a f32 type

static get_f64(value: float, context: Context | None = None) → FloatAttr¶: Gets an uniqued float point attribute associated to a f64 type

property value: float¶: Returns the value of the float attribute

__float__() → float¶: Converts the value of the float attribute to a Python float

class mlir._mlir_libs._mlir.ir.IntegerAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(type: Type, value: int) → IntegerAttr¶: Gets an uniqued integer attribute associated to a type

property value: int¶: Returns the value of the integer attribute

__int__() → int¶: Converts the value of the integer attribute to a Python int

class mlir._mlir_libs._mlir.ir.IntegerSetAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(integer_set: IntegerSet) → IntegerSetAttr¶: Gets an attribute wrapping an IntegerSet.

class mlir._mlir_libs._mlir.ir.StringAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(value: str, context: Context | None = None) → StringAttr¶
static get(value: bytes, context: Context | None = None) → StringAttr

static get_typed(type: Type, value: str) → StringAttr¶: Gets a uniqued string attribute associated to a type

property value: str¶: Returns the value of the string attribute

property value_bytes: bytes¶: Returns the value of the string attribute as bytes

class mlir._mlir_libs._mlir.ir.TypeAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(value: Type, context: Context | None = None) → TypeAttr¶: Gets a uniqued Type attribute

property value: Type¶

class mlir._mlir_libs._mlir.ir.UnitAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(context: Context | None = None) → UnitAttr¶: Create a Unit attribute.

class mlir._mlir_libs._mlir.ir.StridedLayoutAttr(cast_from_attr: Attribute)¶

Bases: Attribute

static isinstance(other: Attribute) → bool¶

property type: Type¶: Returns the type of the Attribute.

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the attribute.

__repr__() → str¶: Returns a string representation of the attribute.

static get(offset: int, strides: collections.abc.Sequence[int], context: Context | None = None) → StridedLayoutAttr¶: Gets a strided layout attribute.

static get_fully_dynamic(rank: int, context: Context | None = None) → StridedLayoutAttr¶: Gets a strided layout attribute with dynamic offset and strides of a given rank.

property offset: int¶: Returns the value of the float point attribute

property strides: list[int]¶: Returns the value of the float point attribute

class mlir._mlir_libs._mlir.ir.InferTypeOpInterface(object: InferTypeOpInterface.__init__.object, context: Context | None = None)¶

property operation: Operation¶: Returns an Operation for which the interface was constructed.

property opview: OpView¶: Returns an OpView subclass instance for which the interface was constructed

inferReturnTypes(operands: list | None = None, attributes: Attribute | None = None, properties: typing_extensions.CapsuleType | None = None, regions: collections.abc.Sequence[Region] | None = None, context: Context | None = None, loc: Location | None = None) → list[Type]¶: Given the arguments required to build an operation, attempts to infer its return types. Raises ValueError on failure.

class mlir._mlir_libs._mlir.ir.ShapedTypeComponents¶

property element_type: Type¶: Returns the element type of the shaped type components.

static get(element_type: Type) → ShapedTypeComponents¶
static get(shape: list, element_type: Type) → ShapedTypeComponents
static get(shape: list, element_type: Type, attribute: Attribute) → ShapedTypeComponents: Create a ranked shaped type components object with attribute.

property has_rank: bool¶: Returns whether the given shaped type component is ranked.

property rank: int | None¶: Returns the rank of the given ranked shaped type components. If the shaped type components does not have a rank, None is returned.

property shape: list | None¶: Returns the shape of the ranked shaped type components as a list of integers. Returns none if the shaped type component does not have a rank.

class mlir._mlir_libs._mlir.ir.InferShapedTypeOpInterface(object: InferShapedTypeOpInterface.__init__.object, context: Context | None = None)¶

property operation: Operation¶: Returns an Operation for which the interface was constructed.

property opview: OpView¶: Returns an OpView subclass instance for which the interface was constructed

inferReturnTypeComponents(operands: list | None = None, attributes: Attribute | None = None, regions: typing_extensions.CapsuleType | None = None, properties: collections.abc.Sequence[Region] | None = None, context: Context | None = None, loc: Location | None = None) → list[ShapedTypeComponents]¶: Given the arguments required to build an operation, attempts to infer its return shaped type components. Raises ValueError on failure.

class mlir._mlir_libs._mlir.ir.IntegerType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get_signless(width: int, context: Context | None = None) → IntegerType¶: Create a signless integer type

static get_signed(width: int, context: Context | None = None) → IntegerType¶: Create a signed integer type

static get_unsigned(width: int, context: Context | None = None) → IntegerType¶: Create an unsigned integer type

property width: int¶: Returns the width of the integer type

property is_signless: bool¶: Returns whether this is a signless integer

property is_signed: bool¶: Returns whether this is a signed integer

property is_unsigned: bool¶: Returns whether this is an unsigned integer

class mlir._mlir_libs._mlir.ir.FloatType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

property width: int¶: Returns the width of the floating-point type

class mlir._mlir_libs._mlir.ir.IndexType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → IndexType¶: Create a index type.

class mlir._mlir_libs._mlir.ir.Float4E2M1FNType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float4E2M1FNType¶: Create a float4_e2m1fn type.

class mlir._mlir_libs._mlir.ir.Float6E2M3FNType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float6E2M3FNType¶: Create a float6_e2m3fn type.

class mlir._mlir_libs._mlir.ir.Float6E3M2FNType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float6E3M2FNType¶: Create a float6_e3m2fn type.

class mlir._mlir_libs._mlir.ir.Float8E4M3FNType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E4M3FNType¶: Create a float8_e4m3fn type.

class mlir._mlir_libs._mlir.ir.Float8E5M2Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E5M2Type¶: Create a float8_e5m2 type.

class mlir._mlir_libs._mlir.ir.Float8E4M3Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E4M3Type¶: Create a float8_e4m3 type.

class mlir._mlir_libs._mlir.ir.Float8E4M3FNUZType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E4M3FNUZType¶: Create a float8_e4m3fnuz type.

class mlir._mlir_libs._mlir.ir.Float8E4M3B11FNUZType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E4M3B11FNUZType¶: Create a float8_e4m3b11fnuz type.

class mlir._mlir_libs._mlir.ir.Float8E5M2FNUZType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E5M2FNUZType¶: Create a float8_e5m2fnuz type.

class mlir._mlir_libs._mlir.ir.Float8E3M4Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E3M4Type¶: Create a float8_e3m4 type.

class mlir._mlir_libs._mlir.ir.Float8E8M0FNUType(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → Float8E8M0FNUType¶: Create a float8_e8m0fnu type.

class mlir._mlir_libs._mlir.ir.BF16Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → BF16Type¶: Create a bf16 type.

class mlir._mlir_libs._mlir.ir.F16Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → F16Type¶: Create a f16 type.

class mlir._mlir_libs._mlir.ir.FloatTF32Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → FloatTF32Type¶: Create a tf32 type.

class mlir._mlir_libs._mlir.ir.F32Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → F32Type¶: Create a f32 type.

class mlir._mlir_libs._mlir.ir.F64Type(cast_from_type: Type)¶

Bases: FloatType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → F64Type¶: Create a f64 type.

class mlir._mlir_libs._mlir.ir.NoneType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(context: Context | None = None) → NoneType¶: Create a none type.

class mlir._mlir_libs._mlir.ir.ComplexType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(arg: Type, /) → ComplexType¶: Create a complex type

property element_type: Type¶: Returns element type.

class mlir._mlir_libs._mlir.ir.ShapedType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

property element_type: Type¶: Returns the element type of the shaped type.

property has_rank: bool¶: Returns whether the given shaped type is ranked.

property rank: int¶: Returns the rank of the given ranked shaped type.

property has_static_shape: bool¶: Returns whether the given shaped type has a static shape.

is_dynamic_dim(dim: int) → bool¶: Returns whether the dim-th dimension of the given shaped type is dynamic.

is_static_dim(dim: int) → bool¶: Returns whether the dim-th dimension of the given shaped type is static.

get_dim_size(dim: int) → int¶: Returns the dim-th dimension of the given ranked shaped type.

static is_dynamic_size(dim_size: int) → bool¶: Returns whether the given dimension size indicates a dynamic dimension.

static is_static_size(dim_size: int) → bool¶: Returns whether the given dimension size indicates a static dimension.

is_dynamic_stride_or_offset(dim_size: int) → bool¶: Returns whether the given value is used as a placeholder for dynamic strides and offsets in shaped types.

is_static_stride_or_offset(dim_size: int) → bool¶: Returns whether the given shaped type stride or offset value is statically-sized.

property shape: list[int]¶: Returns the shape of the ranked shaped type as a list of integers.

static get_dynamic_size() → int¶: Returns the value used to indicate dynamic dimensions in shaped types.

static get_dynamic_stride_or_offset() → int¶: Returns the value used to indicate dynamic strides or offsets in shaped types.

class mlir._mlir_libs._mlir.ir.VectorType(cast_from_type: Type)¶

Bases: ShapedType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(shape: collections.abc.Sequence[int], element_type: Type, *, scalable: list | None = None, scalable_dims: collections.abc.Sequence[int] | None = None, loc: Location | None = None) → VectorType¶: Create a vector type

static get_unchecked(shape: collections.abc.Sequence[int], element_type: Type, *, scalable: list | None = None, scalable_dims: collections.abc.Sequence[int] | None = None, context: Context | None = None) → VectorType¶: Create a vector type

property scalable: bool¶

property scalable_dims: list[bool]¶

class mlir._mlir_libs._mlir.ir.RankedTensorType(cast_from_type: Type)¶

Bases: ShapedType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(shape: collections.abc.Sequence[int], element_type: Type, encoding: Attribute | None = None, loc: Location | None = None) → RankedTensorType¶: Create a ranked tensor type

static get_unchecked(shape: collections.abc.Sequence[int], element_type: Type, encoding: Attribute | None = None, context: Context | None = None) → RankedTensorType¶: Create a ranked tensor type

property encoding: Attribute | None¶

class mlir._mlir_libs._mlir.ir.UnrankedTensorType(cast_from_type: Type)¶

Bases: ShapedType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(element_type: Type, loc: Location | None = None) → UnrankedTensorType¶: Create a unranked tensor type

static get_unchecked(element_type: Type, context: Context | None = None) → UnrankedTensorType¶: Create a unranked tensor type

class mlir._mlir_libs._mlir.ir.MemRefType(cast_from_type: Type)¶

Bases: ShapedType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(shape: collections.abc.Sequence[int], element_type: Type, layout: Attribute | None = None, memory_space: Attribute | None = None, loc: Location | None = None) → MemRefType¶: Create a memref type

static get_unchecked(shape: collections.abc.Sequence[int], element_type: Type, layout: Attribute | None = None, memory_space: Attribute | None = None, context: Context | None = None) → MemRefType¶: Create a memref type

property layout: Attribute¶: The layout of the MemRef type.

get_strides_and_offset() → tuple[list[int], int]¶: The strides and offset of the MemRef type.

property affine_map: AffineMap¶: The layout of the MemRef type as an affine map.

property memory_space: Attribute | None¶: Returns the memory space of the given MemRef type.

class mlir._mlir_libs._mlir.ir.UnrankedMemRefType(cast_from_type: Type)¶

Bases: ShapedType

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(element_type: Type, memory_space: Attribute | None, loc: Location | None = None) → UnrankedMemRefType¶: Create a unranked memref type

static get_unchecked(element_type: Type, memory_space: Attribute | None, context: Context | None = None) → UnrankedMemRefType¶: Create a unranked memref type

property memory_space: Attribute | None¶: Returns the memory space of the given Unranked MemRef type.

class mlir._mlir_libs._mlir.ir.TupleType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get_tuple(elements: collections.abc.Sequence[Type], context: Context | None = None) → TupleType¶
static get_tuple(elements: collections.abc.Sequence[Type], context: Context | None = None) → TupleType

get_type(pos: int) → Type¶: Returns the pos-th type in the tuple type.

property num_types: int¶: Returns the number of types contained in a tuple.

class mlir._mlir_libs._mlir.ir.FunctionType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(inputs: collections.abc.Sequence[Type], results: collections.abc.Sequence[Type], context: Context | None = None) → FunctionType¶
static get(inputs: collections.abc.Sequence[Type], results: collections.abc.Sequence[Type], context: Context | None = None) → FunctionType

property inputs: list¶: Returns the list of input types in the FunctionType.

property results: list¶: Returns the list of result types in the FunctionType.

class mlir._mlir_libs._mlir.ir.OpaqueType(cast_from_type: Type)¶

Bases: Type

static isinstance(other: Type) → bool¶

static_typeid: TypeID = Ellipsis¶: static_typeid(/) -> TypeID

property typeid: TypeID¶: Returns the TypeID of the Type, or raises ValueError if Type has no TypeID.

__repr__() → str¶: Returns a string representation of the Type.

static get(dialect_namespace: str, buffer: str, context: Context | None = None) → OpaqueType¶: Create an unregistered (opaque) dialect type.

property dialect_namespace: str¶: Returns the dialect namespace for the Opaque type as a string.

property data: str¶: Returns the data for the Opaque type as a string.