Reverse lookup for DataFlowAnalyzer

Changelog.md

@@ -5,6 +5,7 @@ Language Features:
 
 Compiler Features:
  * EWasm: Remove EWasm backend.
+ * Optimizer: Introduced an optimized variable assignment map to improve the performance of Yul optimizer steps that rely on data flow analysis.
  * Parser: Introduce ``pragma experimental solidity``, which will enable an experimental language mode that in particular has no stability guarantees between non-breaking releases and is not suited for production use.
 
 

libyul/CMakeLists.txt

@@ -189,6 +189,8 @@ add_library(yul
 	optimiser/UnusedPruner.h
 	optimiser/VarDeclInitializer.cpp
 	optimiser/VarDeclInitializer.h
+	optimiser/VariableAssignmentMap.cpp
+	optimiser/VariableAssignmentMap.h
 	optimiser/VarNameCleaner.cpp
 	optimiser/VarNameCleaner.h
 )

libyul/optimiser/DataFlowAnalyzer.cpp

@@ -271,7 +271,7 @@ void DataFlowAnalyzer::handleAssignment(set<YulString> const& _variables, Expres
 	auto const& referencedVariables = movableChecker.referencedVariables();
 	for (auto const& name: _variables)
 	{
-		m_state.references[name] = referencedVariables;
+		m_state.references.set(name, referencedVariables);
 		if (!_isDeclaration)
 		{
 			// assignment to slot denoted by "name"
@@ -353,9 +353,8 @@ void DataFlowAnalyzer::clearValues(set<YulString> _variables)
 
 	// Also clear variables that reference variables to be cleared.
 	for (auto const& variableToClear: _variables)
-		for (auto const& [ref, names]: m_state.references)
-			if (names.count(variableToClear))
-				_variables.emplace(ref);
+		if (auto&& references = m_state.references.getReversedOrNullptr(variableToClear))
+			_variables += *references;
 
 	// Clear the value and update the reference relation.
 	for (auto const& name: _variables)

libyul/optimiser/DataFlowAnalyzer.h

@@ -25,6 +25,7 @@
 
 #include <libyul/optimiser/ASTWalker.h>
 #include <libyul/optimiser/KnowledgeBase.h>
+#include <libyul/optimiser/VariableAssignmentMap.h>
 #include <libyul/YulString.h>
 #include <libyul/AST.h> // Needed for m_zero below.
 #include <libyul/SideEffects.h>
@@ -104,7 +105,7 @@ public:
 
 	/// @returns the current value of the given variable, if known - always movable.
 	AssignedValue const* variableValue(YulString _variable) const { return util::valueOrNullptr(m_state.value, _variable); }
-	std::set<YulString> const* references(YulString _variable) const { return util::valueOrNullptr(m_state.references, _variable); }
+	std::set<YulString> const* references(YulString _variable) const { return m_state.references.getOrderedOrNullptr(_variable); }
 	std::map<YulString, AssignedValue> const& allValues() const { return m_state.value; }
 	std::optional<YulString> storageValue(YulString _key) const;
 	std::optional<YulString> memoryValue(YulString _key) const;
@@ -179,9 +180,9 @@ private:
 	{
 		/// Current values of variables, always movable.
 		std::map<YulString, AssignedValue> value;
-		/// m_references[a].contains(b) <=> the current expression assigned to a references b
-		std::unordered_map<YulString, std::set<YulString>> references;
-
+        /// references.m_ordered[a].contains(b) <=> the current expression assigned to a references b
+        /// references.m_reversed[b].contains(a) <=> b from current expression assigned to a is references by a
+		VariableAssignmentMap references;
 		Environment environment;
 	};
 

libyul/optimiser/VariableAssignmentMap.cpp

@@ -0,0 +1,39 @@
+#include <libyul/optimiser/VariableAssignmentMap.h>
+
+using std::set;
+using namespace solidity::yul;
+
+void VariableAssignmentMap::set(YulString const& _variable, std::set<YulString> const& _references)
+{
+	erase(_variable);
+	m_ordered[_variable] = _references;
+	for (auto&& reference: _references)
+		m_reversed[reference].emplace(_variable);
+}
+
+void VariableAssignmentMap::erase(YulString const& _variable)
+{
+	for (auto&& reference: m_ordered[_variable])
+		if (m_reversed.find(reference) != m_reversed.end())
+		{
+			if (m_reversed[reference].size() > 1)
+				m_reversed[reference].erase(_variable);
+			else
+				// Only fully remove an entry if no variables other than _variable
+				// are contained in the set pointed to by reference.
+				m_reversed.erase(reference);
+		}
+	m_ordered.erase(_variable);
+}
+
+set<YulString> const* VariableAssignmentMap::getOrderedOrNullptr(YulString const& _variable) const
+{
+	auto&& it = m_ordered.find(_variable);
+	return (it != m_ordered.end()) ? &it->second : nullptr;
+}
+
+set<YulString> const* VariableAssignmentMap::getReversedOrNullptr(YulString const& _variable) const
+{
+	auto&& it = m_reversed.find(_variable);
+	return (it != m_reversed.end()) ? &it->second : nullptr;
+}

libyul/optimiser/VariableAssignmentMap.h

@@ -0,0 +1,85 @@
+/*
+	This file is part of solidity.
+
+	solidity is free software: you can redistribute it and/or modify
+	it under the terms of the GNU General Public License as published by
+	the Free Software Foundation, either version 3 of the License, or
+	(at your option) any later version.
+
+	solidity is distributed in the hope that it will be useful,
+	but WITHOUT ANY WARRANTY; without even the implied warranty of
+	MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+	GNU General Public License for more details.
+
+	You should have received a copy of the GNU General Public License
+	along with solidity.  If not, see <http://www.gnu.org/licenses/>.
+*/
+
+#pragma once
+
+#include <libyul/YulString.h>
+
+#include <set>
+#include <unordered_map>
+
+namespace solidity::yul
+{
+
+/**
+ * Class that implements a reverse lookup for an ``unordered_map<YulString, set<YulString>>`` by wrapping the
+ * two such maps - one ordered, and one reversed, e.g.
+ *
+ *  m_ordered           m_reversed
+ *  f -> (g,)           g -> (f,)
+ *  c -> (b,d,e,)       d -> (c,)
+ *  a -> (b,c,)         c -> (a,)
+ *                      e -> (c,)
+ *                      b -> (a,c,)
+ *
+ * The above example will from here onwards be referenced as ```Ref 1```.
+ *
+ * This allows us to have simultaneously managed insertion and deletion via a single interface, instead of manually
+ * managing this at the point of usage (see ``DataFlowAnalyzer``).
+ */
+class VariableAssignmentMap
+{
+public:
+	VariableAssignmentMap() = default;
+	/**
+	 * Insert a set of values for the provided key ``_variable`` into ``m_ordered`` and ``m_reversed``.
+	 * This method will erase all references of ``_variable`` from both sets before performing the insertion,
+	 * akin to container assignment with subscript operator, i.e. container[index] = value.
+	 * For example, if ``_variable`` is ``x`` and ``_references`` is ``{"y", "z"}``, the following would be added to ``Ref 1``:
+	 *
+	 * m_ordered        m_reversed
+	 * x -> (y, z,)     y -> (x,)
+	 *                  y -> (z,)
+	 *
+	 * @param _variable current expression variable
+	 * @param _references all referenced variables in the expression assigned to ``_variable``
+	 */
+	void set(YulString const& _variable, std::set<YulString> const& _references);
+
+	/**
+	 * Erase entries in both maps based on provided ``_variable``. The behaviour is the same as ``set("x", {})``.
+	 * For example, after deleting ``c`` for ``Ref 1``, ``Ref 1`` would contain the following:
+	 *
+	 *  m_ordered           m_reversed
+	 *  f -> (g,)           g -> (f,)
+	 *  a -> (b,c,)         c -> (a,)
+	 *                      b -> (a,)
+	 *
+	 * @param _variable variable to erase
+	 */
+	void erase(YulString const& _variable);
+	std::set<YulString> const* getOrderedOrNullptr(YulString const& _variable) const;
+	std::set<YulString> const* getReversedOrNullptr(YulString const& _variable) const;
+
+private:
+	/// m_ordered[a].contains[b] <=> the current expression assigned to ``a`` references ``b``
+	std::unordered_map<YulString, std::set<YulString>> m_ordered;
+	/// m_reversed[b].contains[a] <=> the current expression assigned to ``a`` references ``b``
+	std::unordered_map<YulString, std::set<YulString>> m_reversed;
+};
+
+} // solidity::yul