tvm.relay.dataflow_pattern¶

The Relay Pattern Language and tooling.

Classes

`AltPattern`(left, right)	Create a Pattern that can match one of two conditions
`AttrPattern`(pattern, attrs)	Get match an expression with a certain attributes.
`CallPattern`(op, args, attrs, type_args)	A pattern matching a function call node in Relay.
`Callable`	Callable type; Callable[[int], str] is a function of (int) -> str.
`ConstantPattern`()	A pattern matching a Relay Constant.
`DFPattern`	Base class of all Patterns.
`DFPatternCallback`([require_type])	A Callback for Pattern Rewriting.
`DataTypePattern`(pattern, dtype)	A pattern that matches another pattern with certain data type
`Dict`
`DominatorPattern`(parent, path, child)	Match a domination graph.
`Expr`	Base class of all non-primitive expressions.
`ExprPattern`(expr)	A pattern which matches a constant expression.
`List`
`ShapePattern`(pattern, shape)	A pattern that matches another pattern with a certain tensor shape
`TupleGetItemPattern`(tuple_value, index)	Get index-th item from a TuplePattern.
`TuplePattern`(fields)	A patern matching a Relay Tuple.
`TypePattern`(pattern, ttype)	A pattern that matches another pattern with a certain type annotation.
`VarPattern`(name_hint, type_annotation)	A local variable in Relay.
`WildcardPattern`()	A pattern which matches anything.

Functions

`dominates`(parent, path, child)	Syntatic sugar for creating an Dominator pattern
`get`(op_name)	Get the Op for a given name
`has_attr`(attrs[, pattern])	Syntatic sugar for creating an AttrPattern
`has_dtype`(dtype, pattern)	Syntatic sugar for creating a DataTypePattern
`has_shape`(shape, pattern)	Syntatic sugar for creating a ShapePattern
`has_type`(ttype, pattern)	Syntatic sugar for creating a TypePattern
`is_constant`()	Syntatic sugar for creating a ConstantPattern.
`is_expr`(expr)	Syntatic sugar for creating an ExprPattern.
`is_op`(op_name)	Syntatic sugar for creating an operator ExprPattern.
`is_tuple`(fields)	Syntatic sugar for creating an ExprPattern.
`is_tuple_get_item`(tuple_value, index)	Syntatic sugar for creating an ExprPattern.
`is_var`(name)	Syntatic sugar for creating an optionally named VarPattern.
`make_node`(type_key, **kwargs)	Make a new IR node by its type key and fields
`match`(pattern, expr)	Match a pattern to an expression
`partition`(pattern, expr, attrs, …)	Parition the expression into a series of functions that match the pattern
`register_df_node`([type_key])	Register a Relay node type.
`rewrite`(callbacks, expr, mod)	Rewrite expression with the given callbacks.
`wildcard`()	Syntatic sugar for creating a WildcardPattern.

class tvm.relay.dataflow_pattern.Callable¶

Callable type; Callable[[int], str] is a function of (int) -> str.

The subscription syntax must always be used with exactly two values: the argument list and the return type. The argument list must be a list of types or ellipsis; the return type must be a single type.

There is no syntax to indicate optional or keyword arguments, such function types are rarely used as callback types.

class tvm.relay.dataflow_pattern.Dict¶

class tvm.relay.dataflow_pattern.List¶

tvm.relay.dataflow_pattern.Expr¶: alias of tvm.ir.expr.RelayExpr

tvm.relay.dataflow_pattern.make_node(type_key, **kwargs)¶

Make a new IR node by its type key and fields

Parameters

type_key (str) – The type key of the node.
**kwargs (dict) – The fields of the node.

Returns

node – The corresponding IR Node

Return type

Node

Note

If the created node is instance of AttrsNode, then the creator function will also run bound checks and default value setup as supported by Attrs.

Example

The following code constructs a IntImm object

x = tvm.ir.make_node("IntImm", dtype="int32", value=10)
assert isinstance(x, tvm.tir.IntImm)
assert x.value == 10

tvm.relay.dataflow_pattern.get(op_name)¶

Get the Op for a given name

Parameters: op_name (str) – The operator name
Returns: op – The op of the corresponding name
Return type: Op

tvm.relay.dataflow_pattern.register_df_node(type_key=None)¶

Register a Relay node type.

Parameters: type_key (str or cls) – The type key of the node.

class tvm.relay.dataflow_pattern.DFPattern¶

Base class of all Patterns.

Methods

`dominates`(parent, path)	Create a dominator for this pattern.
`has_attr`(attrs, tvm.runtime.object.Object])	Add an attribute constraint to this pattern
`has_dtype`(dtype)	Add a type constraint to this pattern
`has_shape`(shape)	Add a type constraint to this pattern
`has_type`(ttype)	Add a type constraint to this pattern
`match`(expr)	Match this pattern to an expression
`optional`(option_constructor, DFPattern])	Create a optional user of this pattern.
`partition`(expr, attrs, …)	Parition the expression into functions defined by this pattern

has_attr(attrs: Dict[str, tvm.runtime.object.Object])¶

Add an attribute constraint to this pattern

Parameters: attrs (Dict[str, Object]) –
Returns: result – The resulting AttrPattern
Return type: tvm.relay.dataflow_pattern.DFPattern

has_type(ttype: tvm.ir.type.Type)¶

Add a type constraint to this pattern

Parameters: ttype (tvm.ir.type.Type) – The type to match
Returns: result – The resulting TypePattern
Return type: tvm.relay.dataflow_pattern.DFPattern

has_dtype(dtype: str)¶

Add a type constraint to this pattern

Parameters: dtype (str) – The dtype to match
Returns: result – The resulting DataTypePattern
Return type: tvm.relay.dataflow_pattern.DFPattern

has_shape(shape: List[tvm.ir.expr.PrimExpr])¶

Add a type constraint to this pattern

Parameters: shape (List[tvm.ir.PrimExpr]) – The shape to match
Returns: result – The resulting ShapePattern
Return type: tvm.relay.dataflow_pattern.DFPattern

match(expr: tvm.ir.expr.RelayExpr) → bool ¶

Match this pattern to an expression

Parameters: expr (tvm.relay.Expr) – The expression to match.
Returns: result – Whether or not the expression matches the pattern
Return type: bool

partition(expr: tvm.ir.expr.RelayExpr, attrs: Optional[Dict[str, tvm.runtime.object.Object]] = None, check: Callable[tvm.ir.expr.RelayExpr, bool] = <function DFPattern.<lambda>>) → tvm.ir.expr.RelayExpr¶

Parition the expression into functions defined by this pattern

Parameters

expr (tvm.relay.Expr) – The expression to match.
attrs (Optional[Dict[str, Object]]) – A dictionary of Attribute name/values to add to the paritioned function
check (Callable[[Expr], bool]) – A function to perform more complicated checks on the matched expression. Returns true if partitioning should proceed, false otherwise.

Returns

result – The Expression with matched subgraphs replaced by function calls to that subgraph

Return type

tvm.relay.Expr

dominates(parent: tvm.relay.dataflow_pattern.DFPattern, path: Optional[tvm.relay.dataflow_pattern.DFPattern] = None)¶

Create a dominator for this pattern.

Parameters

parent (tvm.relay.dataflow_pattern.DFPattern) – The parent pattern this pattern dominates.
path (tvm.relay.dataflow_pattern.DFPattern) – The fuzzy path pattern.

Returns

result – The resulting DominatorPattern.

Return type

tvm.relay.dataflow_pattern.DFPattern

optional(option_constructor: Callable[DFPattern, DFPattern])¶

Create a optional user of this pattern.

Parameters: option_constructor (function) – A function that takes a single Pattern parameter and returns a constructed pattern matching the option
Returns: result – The resulting Pattern
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_var(name: str = '') → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an optionally named VarPattern.

Parameters: name (str) – The name of the input pattern to match.
Returns: result – The resulting pattern.
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_constant() → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating a ConstantPattern.

Parameters: name (str) – The name of the input pattern to match.
Returns: result – The resulting pattern.
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_expr(expr: tvm.ir.expr.RelayExpr) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an ExprPattern.

Parameters: expr (Expr) – The Relay expression to match.
Returns: result – The resulting pattern.
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_op(op_name: str) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an operator ExprPattern.

Parameters: op_name (String) – The name of the relay op
Returns: result – The resulting ExprPattern
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_tuple(fields: tvm.ir.container.Array) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an ExprPattern.

Parameters: fields (Array[tvm.relay.dataflow_pattern.DFPattern]) – The fields in the tuple.
Returns: result – The resulting pattern.
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.is_tuple_get_item(tuple_value: tvm.relay.dataflow_pattern.DFPattern, index: Optional[int] = None) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an ExprPattern.

Parameters

tuple_value (tvm.relay.dataflow_pattern.DFPattern) – The input tuple expression.
index (Optional[int]) – The index to match; Default (None) to match a TupleGetItem with any index.

Returns

result – The resulting pattern.

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.wildcard() → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating a WildcardPattern.

Returns: result – The resulting pattern.
Return type: tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.has_type(ttype: tvm.ir.type.Type, pattern: Optional[tvm.relay.dataflow_pattern.DFPattern] = None) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating a TypePattern

Parameters

ttype (tvm.ir.type.Type) – The type to match
pattern (tvm.relay.dataflow_pattern.DFPattern) – The pattern that needs type annotation

Returns

result – The resulting TypePattern

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.has_dtype(dtype: str, pattern: Optional[tvm.relay.dataflow_pattern.DFPattern] = None) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating a DataTypePattern

Parameters

dtype (str) – The dtype to match
pattern (tvm.relay.dataflow_pattern.DFPattern) – The pattern that needs type annotation

Returns

result – The resulting DataTypePattern

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.has_shape(shape: List[tvm.ir.expr.PrimExpr], pattern: Optional[tvm.relay.dataflow_pattern.DFPattern] = None) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating a ShapePattern

Parameters

shape (List[tvm.ir.PrimExpr]) – The shape to match
pattern (tvm.relay.dataflow_pattern.DFPattern) – The pattern that needs type annotation

Returns

result – The resulting ShapePattern

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.has_attr(attrs, pattern=None) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an AttrPattern

Parameters

attrs (Dict[str, Object]) – The attributes to match
pattern (Optional[tvm.relay.dataflow_pattern.DFPattern]) – The input pattern.

Returns

result – The resulting AttrPattern

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.dominates(parent: tvm.relay.dataflow_pattern.DFPattern, path: tvm.relay.dataflow_pattern.DFPattern, child: tvm.relay.dataflow_pattern.DFPattern) → tvm.relay.dataflow_pattern.DFPattern ¶

Syntatic sugar for creating an Dominator pattern

Parameters

parent (tvm.relay.dataflow_pattern.DFPattern) – The parent pattern.
path (tvm.relay.dataflow_pattern.DFPattern) – The fuzzy path pattern.
child (tvm.relay.dataflow_pattern.DFPattern) – The child pattern.

Returns

result – The resulting DominatorPattern.

Return type

tvm.relay.dataflow_pattern.DFPattern

tvm.relay.dataflow_pattern.match(pattern: tvm.relay.dataflow_pattern.DFPattern, expr: tvm.ir.expr.RelayExpr) → bool ¶

Match a pattern to an expression

Parameters

pattern (tvm.relay.dataflow_pattern.DFPattern) – The input pattern.
expr (tvm.relay.Expr) – The expression to match.

class tvm.relay.dataflow_pattern.ExprPattern(expr: tvm.ir.expr.RelayExpr)¶

A pattern which matches a constant expression.

Parameters: expr (tvm.relay.Expr) – The expression to match.

class tvm.relay.dataflow_pattern.VarPattern(name_hint: str = '', type_annotation: Optional[tvm.ir.type.Type] = None)¶

A local variable in Relay.

Local variable can be used to declare input arguments to a function, or intermediate variables.

Parameters

name_hint (str) – The name of the variable. Optional, if not provided, the pattern will match any VarNode.
type_annotation (tvm.ir.type.Type, optional) – The type annotation on the variable.

class tvm.relay.dataflow_pattern.ConstantPattern¶: A pattern matching a Relay Constant.

class tvm.relay.dataflow_pattern.CallPattern(op: tvm.relay.dataflow_pattern.DFPattern, args: List[DFPattern], attrs: Optional[tvm.ir.attrs.Attrs] = None, type_args: Optional[List[tvm.ir.type.Type]] = None)¶

A pattern matching a function call node in Relay.

Parameters

op (realy.dataflow_pattern.DFPattern) – The operation to be called.
args (List[realy.dataflow_pattern.DFPattern]) – The arguments to the call.
attrs (Optional[tvm.ir.attrs.Attrs]) – Attributes to the call, can be None
type_args (Optional[List[tvm.ir.type.Type]]) – The additional type arguments, this is only used in advanced usecase of template functions.

class tvm.relay.dataflow_pattern.TuplePattern(fields: tvm.ir.container.Array)¶

A patern matching a Relay Tuple.

Parameters: fields (Array[tvm.relay.dataflow_pattern.DFPattern]) – The fields in the tuple.

class tvm.relay.dataflow_pattern.TupleGetItemPattern(tuple_value: tvm.relay.dataflow_pattern.DFPattern, index: Optional[int] = None)¶

Get index-th item from a TuplePattern.

Parameters

tuple_value (tvm.relay.dataflow_pattern.DFPattern) – The input tuple expression.
index (Optional[int]) – The index to match; Default (None) to match a TupleGetItem with any index.

class tvm.relay.dataflow_pattern.AltPattern(left: tvm.relay.dataflow_pattern.DFPattern, right: tvm.relay.dataflow_pattern.DFPattern)¶

Create a Pattern that can match one of two conditions

Parameters

left (tvm.relay.dataflow_pattern.DFPattern) – One possible matching pattern.
right (tvm.relay.dataflow_pattern.DFPattern) – One possible matching pattern.

class tvm.relay.dataflow_pattern.WildcardPattern¶: A pattern which matches anything.

class tvm.relay.dataflow_pattern.TypePattern(pattern: tvm.relay.dataflow_pattern.DFPattern, ttype: tvm.ir.type.Type)¶

A pattern that matches another pattern with a certain type annotation.

Parameters

pattern (tvm.relay.dataflow_pattern.DFPattern) – The input pattern that needs type annotation.
ttype (tvm.ir.type.Type) – The type to match.

class tvm.relay.dataflow_pattern.DataTypePattern(pattern: tvm.relay.dataflow_pattern.DFPattern, dtype: str)¶

A pattern that matches another pattern with certain data type

Parameters

pattern (tvm.relay.dataflow_pattern.DFPattern) – The input pattern that needs type annotation.
dtype (str) – The dtype to match.

class tvm.relay.dataflow_pattern.ShapePattern(pattern: tvm.relay.dataflow_pattern.DFPattern, shape: List[tvm.ir.expr.PrimExpr])¶

A pattern that matches another pattern with a certain tensor shape

Parameters

pattern (tvm.relay.dataflow_pattern.DFPattern) – The input pattern that needs type annotation.
shape (List[tvm.ir.PrimExpr]) – The shape to match.

class tvm.relay.dataflow_pattern.AttrPattern(pattern: tvm.relay.dataflow_pattern.DFPattern, attrs: tvm.ir.attrs.Attrs)¶

Get match an expression with a certain attributes. Currently only supports Op Attributes, not call Attributes.

Parameters

pattern (tvm.relay.dataflow_pattern.DFPattern) – The input pattern.
attrs (tvm.ir.attrs.Attrs) – The attributes to match.

class tvm.relay.dataflow_pattern.DominatorPattern(parent: tvm.relay.dataflow_pattern.DFPattern, path: tvm.relay.dataflow_pattern.DFPattern, child: tvm.relay.dataflow_pattern.DFPattern)¶

Match a domination graph.

Parameters

parent (tvm.relay.dataflow_pattern.DFPattern) – The parent, i.e., the single node which produces something, later aggregated by the child.
path (tvm.relay.dataflow_pattern.DFPattern) – The fuzzy path pattern between parent and child, typically matches elementwise ops.
child (tvm.relay.dataflow_pattern.DFPattern) – The last node in the domination which is the end user for all nodes in the path and the parent.

class tvm.relay.dataflow_pattern.DFPatternCallback(require_type=False)¶

A Callback for Pattern Rewriting.

When rewrite is called on this DFPatternCallback, the backend will find matches for the pattern, call the callback function, and replace the matched expression with whatever the callback returns.

Users are expect to inherit from this class and provide a “self.pattern” to match

Parameters: require_type (bool) – Whether InferType is required to be run before the callback.

Methods

`callback`(pre, post, node_map)	Callback function to use when we found a match to the pattern
`rewrite`(expr)	Rewrite expression with this callback

rewrite(expr: tvm.ir.expr.RelayExpr) → tvm.ir.expr.RelayExpr¶

Rewrite expression with this callback

Parameters: expr (tvm.relay.Expr) – The expression to rewrite.
Returns: result – The Expression with matched subgraphs rewritten by the callbacks.
Return type: tvm.relay.Expr

callback(pre: tvm.ir.expr.RelayExpr, post: tvm.ir.expr.RelayExpr, node_map: tvm.ir.container.Map) → tvm.ir.expr.RelayExpr¶

Callback function to use when we found a match to the pattern

Parameters

pre (tvm.relay.Expr) – The matching expression from the original graph.
post (tvm.relay.Expr) – The matching expression with rewritten inputs
node_map (tvm.ir.container.Map[DFPattern, List[Expr]]) – The map between patterns and matched expressions

Returns

result – The Expression with matched subgraph rewritten by the callback

Return type

tvm.relay.Expr

tvm.relay.dataflow_pattern.rewrite(callbacks, expr: tvm.ir.expr.RelayExpr, mod: Optional[tvm.ir.module.IRModule] = None) → tvm.ir.expr.RelayExpr¶

Rewrite expression with the given callbacks.

Parameters

callbacks (tvm.relay.dataflow_pattern.DFPatternCallback) – The input callback or list of callbacks.
expr (tvm.relay.Expr) – The expression to rewrite.
mod (Optional[tvm.ir.IRModule]) – The module that associates with the expression.

Returns

result – The Expression with matched subgraphs rewritten by the callbacks.

Return type

tvm.relay.Expr

tvm.relay.dataflow_pattern.partition(pattern: tvm.relay.dataflow_pattern.DFPattern, expr: tvm.ir.expr.RelayExpr, attrs: Optional[Dict[str, tvm.runtime.object.Object]] = None, check: Callable[tvm.ir.expr.RelayExpr, bool] = <function <lambda>>) → tvm.ir.expr.RelayExpr¶

Parition the expression into a series of functions that match the pattern

Parameters

partion (tvm.relay.dataflow_pattern.DFPattern) – The pattern to match
expr (tvm.relay.Expr) – The expression to split into functions
attrs (Optional[Dict[str, Object]]) – A dict of attributes to apply to the partitioned function
check (Callable[[Expr], bool]) – A function to perform more complicated checks on the matched expression. Returns true if partitioning should proceed, false otherwise.

Returns

result – The Expression with matched subgraphs replaced by function calls to that subgraph

Return type

tvm.relay.Expr