dace.transformation.interstate package¶
Submodules¶
dace.transformation.interstate.fpga_transform_sdfg module¶
Contains inter-state transformations of an SDFG to run on an FPGA.
-
class
dace.transformation.interstate.fpga_transform_sdfg.
FPGATransformSDFG
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements the FPGATransformSDFG transformation, which takes an entire SDFG and transforms it into an FPGA-capable SDFG.
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
promote_global_trans
¶ If True, transient arrays that are fully internal are pulled out so that they can be allocated on the host.
-
properties
()¶
-
static
dace.transformation.interstate.fpga_transform_state module¶
Contains inter-state transformations of an SDFG to run on an FPGA.
-
class
dace.transformation.interstate.fpga_transform_state.
FPGATransformState
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements the FPGATransformState transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
-
dace.transformation.interstate.fpga_transform_state.
fpga_update
(sdfg, state, depth)¶
dace.transformation.interstate.gpu_transform_sdfg module¶
Contains inter-state transformations of an SDFG to run on the GPU.
-
class
dace.transformation.interstate.gpu_transform_sdfg.
GPUTransformSDFG
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements the GPUTransformSDFG transformation.
Transforms a whole SDFG to run on the GPU: Steps of the full GPU transform
- Acquire metadata about SDFG and arrays
- Replace all non-transients with their GPU counterparts
- Copy-in state from host to GPU
- Copy-out state from GPU to host
- Re-store Default-top/CPU_Heap transients as GPU_Global
- Global tasklets are wrapped with a map of size 1
- Global Maps are re-scheduled to use the GPU
- Make data ready for interstate edges that use them
- Re-apply strict transformations to get rid of extra states and transients
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg: dace.sdfg.sdfg.SDFG)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
exclude_copyin
¶ Exclude these arrays from being copied into the device (comma-separated)
-
exclude_copyout
¶ Exclude these arrays from being copied out of the device (comma-separated)
-
exclude_tasklets
¶ Exclude these tasklets from being processed as CPU tasklets (comma-separated)
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
properties
()¶
-
register_trans
¶ Make all transients inside GPU maps registers
-
sequential_innermaps
¶ Make all internal maps Sequential
-
skip_scalar_tasklets
¶ If True, does not transform tasklets that manipulate (Default-stored) scalars
-
strict_transform
¶ Reapply strict transformations after modifying graph
-
toplevel_trans
¶ Make all GPU transients top-level
dace.transformation.interstate.loop_detection module¶
Loop detection transformation
-
class
dace.transformation.interstate.loop_detection.
DetectLoop
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Detects a for-loop construct from an SDFG.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
-
dace.transformation.interstate.loop_detection.
find_for_loop
(sdfg: dace.sdfg.sdfg.SDFG, guard: dace.sdfg.state.SDFGState, entry: dace.sdfg.state.SDFGState, itervar: Optional[str] = None) → Optional[Tuple[AnyStr, Tuple[Union[sympy.core.basic.Basic, dace.symbolic.SymExpr], Union[sympy.core.basic.Basic, dace.symbolic.SymExpr], Union[sympy.core.basic.Basic, dace.symbolic.SymExpr]], Tuple[List[dace.sdfg.state.SDFGState], dace.sdfg.state.SDFGState]]]¶ Finds loop range from state machine. :param guard: State from which the outgoing edges detect whether to exit
the loop or not.Parameters: entry – First state in the loop “body”. Returns: - (iteration variable, (start, end, stride),
- (start_states[], last_loop_state)), or None if proper
for-loop was not detected.
end
is inclusive.
dace.transformation.interstate.loop_peeling module¶
Loop unroll transformation
-
class
dace.transformation.interstate.loop_peeling.
LoopPeeling
(*args, **kwargs)¶ Bases:
dace.transformation.interstate.loop_unroll.LoopUnroll
Splits the first count iterations of a state machine for-loop into multiple, separate states.
-
apply
(sdfg: dace.sdfg.sdfg.SDFG)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
begin
¶ If True, peels loop from beginning (first count iterations), otherwise peels last count iterations.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
properties
()¶
-
dace.transformation.interstate.loop_unroll module¶
Loop unroll transformation
-
class
dace.transformation.interstate.loop_unroll.
LoopUnroll
(*args, **kwargs)¶ Bases:
dace.transformation.interstate.loop_detection.DetectLoop
Unrolls a state machine for-loop into multiple states
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
count
¶ Number of iterations to unroll, or zero for all iterations (loop must be constant-sized for 0)
-
instantiate_loop
(sdfg: dace.sdfg.sdfg.SDFG, loop_states: List[dace.sdfg.state.SDFGState], loop_subgraph: dace.sdfg.graph.SubgraphView, itervar: str, value: Union[sympy.core.basic.Basic, dace.symbolic.SymExpr], state_suffix=None)¶
-
properties
()¶
-
dace.transformation.interstate.sdfg_nesting module¶
SDFG nesting transformation.
-
class
dace.transformation.interstate.sdfg_nesting.
ASTRefiner
(to_refine: str, refine_subset: dace.subsets.Subset, sdfg: dace.sdfg.sdfg.SDFG, indices: Set[int] = None)¶ Bases:
ast.NodeTransformer
Python AST transformer used in
RefineNestedAccess
to reduce (refine) the subscript ranges based on the specification given in the transformation.-
visit_Subscript
(node: _ast.Subscript) → _ast.Subscript¶
-
-
class
dace.transformation.interstate.sdfg_nesting.
InlineSDFG
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Inlines a single-state nested SDFG into a top-level SDFG.
In particular, the steps taken are:
- All transient arrays become transients of the parent
- If a source/sink node is one of the inputs/outputs:
- Remove it
- Reconnect through external edges (map/accessnode)
- Replace and reoffset memlets with external data descriptor
- If other nodes carry the names of inputs/outputs:
- Replace data with external data descriptor
- Replace and reoffset memlets with external data descriptor
- If source/sink node is not connected to a source/destination, and the nested SDFG is in a scope, connect to scope with empty memlets
- Remove all unused external inputs/output memlet paths
- Remove isolated nodes resulting from previous step
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg: dace.sdfg.sdfg.SDFG)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
properties
()¶
-
class
dace.transformation.interstate.sdfg_nesting.
InlineTransients
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Inlines all transient arrays that are not used anywhere else into a nested SDFG.
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph: dace.sdfg.state.SDFGState, candidate: Dict[dace.transformation.transformation.PatternNode, int], expr_index: int, sdfg: dace.sdfg.sdfg.SDFG, strict: bool = False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
nsdfg
= <dace.transformation.transformation.PatternNode object>¶
-
properties
()¶
-
static
-
class
dace.transformation.interstate.sdfg_nesting.
NestSDFG
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements SDFG Nesting, taking an SDFG as an input and creating a nested SDFG node from it.
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
promote_global_trans
¶ Promotes transients to be allocated once
-
properties
()¶
-
static
-
class
dace.transformation.interstate.sdfg_nesting.
RefineNestedAccess
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Reduces memlet shape when a memlet is connected to a nested SDFG, but not using all of the contents. Makes the outer memlet smaller in shape and ensures that the offsets in the nested SDFG start with zero. This helps with subsequent transformations on the outer SDFGs.
For example, in the following program:
@dace.program def func_a(y): return y[1:5] + 1 @dace.program def main(x: dace.float32[N]): return func_a(x)
The memlet pointing to
func_a
will contain all ofx
(x[0:N]
), and it is offset toy[1:5]
in the function, withy
’s size beingN
. After the transformation, the memlet connected to the nested SDFG offunc_a
would containx[1:5]
directly and the internaly
array would have a size of 4, accessed asy[0:4]
.-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph: dace.sdfg.state.SDFGState, candidate: Dict[dace.transformation.transformation.PatternNode, int], expr_index: int, sdfg: dace.sdfg.sdfg.SDFG, strict: bool = False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
nsdfg
= <dace.transformation.transformation.PatternNode object>¶
-
properties
()¶
-
static
dace.transformation.interstate.state_elimination module¶
State elimination transformations
-
class
dace.transformation.interstate.state_elimination.
EndStateElimination
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
End-state elimination removes a redundant state that has one incoming edge and no contents.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
-
class
dace.transformation.interstate.state_elimination.
HoistState
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Move a state out of a nested SDFG
-
apply
(sdfg: dace.sdfg.sdfg.SDFG)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph: dace.sdfg.state.SDFGState, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
nsdfg
= <dace.transformation.transformation.PatternNode object>¶
-
-
class
dace.transformation.interstate.state_elimination.
StateAssignElimination
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
State assign elimination removes all assignments into the final state and subsumes the assigned value into its contents.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
dace.transformation.interstate.state_fusion module¶
State fusion transformation
-
class
dace.transformation.interstate.state_fusion.
CCDesc
(first_inputs: Set[str], first_outputs: Set[str], first_output_nodes: Set[dace.sdfg.nodes.AccessNode], second_inputs: Set[str], second_outputs: Set[str], second_input_nodes: Set[dace.sdfg.nodes.AccessNode])¶ Bases:
object
-
class
dace.transformation.interstate.state_fusion.
StateFusion
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements the state-fusion transformation.
State-fusion takes two states that are connected through a single edge, and fuses them into one state. If strict, only applies if no memory access hazards are created.
-
static
annotates_memlets
()¶ Indicates whether the transformation annotates the edges it creates or modifies with the appropriate memlets. This determines whether to apply memlet propagation after the transformation.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
find_fused_components
(first_cc_input, first_cc_output, second_cc_input, second_cc_output) → List[dace.transformation.interstate.state_fusion.CCDesc]¶
-
first_state
= <dace.transformation.transformation.PatternNode object>¶
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
static
memlets_intersect
(graph_a: dace.sdfg.state.SDFGState, group_a: List[dace.sdfg.nodes.AccessNode], inputs_a: bool, graph_b: dace.sdfg.state.SDFGState, group_b: List[dace.sdfg.nodes.AccessNode], inputs_b: bool) → bool¶ Performs an all-pairs check for subset intersection on two groups of nodes. If group intersects or result is indeterminate, returns True as a precaution. :param graph_a: The graph in which the first set of nodes reside. :param group_a: The first set of nodes to check. :param inputs_a: If True, checks inputs of the first group. :param graph_b: The graph in which the second set of nodes reside. :param group_b: The second set of nodes to check. :param inputs_b: If True, checks inputs of the second group. :returns True if subsets intersect or result is indeterminate.
-
second_state
= <dace.transformation.transformation.PatternNode object>¶
-
static
-
dace.transformation.interstate.state_fusion.
top_level_nodes
(state: dace.sdfg.state.SDFGState)¶
dace.transformation.interstate.transient_reuse module¶
-
class
dace.transformation.interstate.transient_reuse.
TransientReuse
(*args, **kwargs)¶ Bases:
dace.transformation.transformation.Transformation
Implements the TransientReuse transformation. Finds all possible reuses of arrays, decides for a valid combination and changes sdfg accordingly.
-
apply
(sdfg)¶ Applies this transformation instance on the matched pattern graph. :param sdfg: The SDFG to apply the transformation to. :return: A transformation-defined return value, which could be used
to pass analysis data out, or nothing.
-
static
can_be_applied
(graph, candidate, expr_index, sdfg, strict=False)¶ Returns True if this transformation can be applied on the candidate matched subgraph. :param graph: SDFGState object if this Transformation is
single-state, or SDFG object otherwise.Parameters: - candidate – A mapping between node IDs returned from Transformation.expressions and the nodes in graph.
- expr_index – The list index from Transformation.expressions that was matched.
- sdfg – If graph is an SDFGState, its parent SDFG. Otherwise should be equal to graph.
- strict – Whether transformation should run in strict mode.
Returns: True if the transformation can be applied.
-
expansion
()¶
-
static
expressions
()¶ Returns a list of Graph objects that will be matched in the subgraph isomorphism phase. Used as a pre-pass before calling can_be_applied. :see: Transformation.can_be_applied
-
static
match_to_str
(graph, candidate)¶ Returns a string representation of the pattern match on the candidate subgraph. Used when identifying matches in the console UI.
-
properties
()¶
-
Module contents¶
This module initializes the inter-state transformations package.