perf: memoize IR plan calls to reduce reevaluation cost

Adds a per-evaluation call memoization stack to the IREvaluationContext.
This currently supports rules, not arbitrary functions, based on arity.
For a policy with many repeated calls, we see evaluation time drop from
~241ms to ~2ms. No regression in compliance tests.

Signed-off-by: Oren Shomron <[email protected]>

Author: shomron

Sources/Rego/IREvaluator.swift

@@ -124,6 +124,12 @@ internal struct IREvaluationContext {
     var policy: IndexedIRPolicy
     var maxCallDepth: Int = 16_384
     var callDepth: Int = 0
+    var callMemo = MemoStack()  // shared stack of memoCache structs
+
+    init(ctx: EvaluationContext, policy: IndexedIRPolicy) {
+        self.ctx = ctx
+        self.policy = policy
+    }
 
     func withIncrementedCallDepth() -> IREvaluationContext {
         var ctx = self
@@ -911,13 +917,16 @@ func evalBlock(
             var newLocals = currentScopePtr.v.locals
             newLocals[stmt.local] = patched
             currentScopePtr = framePtr.v.pushScope(locals: newLocals)
-            // Start executing the block on the new scope we just pushed
-            let blockResult = try await evalBlock(
-                withContext: ctx,
-                framePtr: framePtr,
-                caller: statement,
-                block: stmt.block
-            )
+
+            let blockResult = try await ctx.callMemo.withPush {
+                // Start executing the block on the new scope we just pushed
+                return try await evalBlock(
+                    withContext: ctx,
+                    framePtr: framePtr,
+                    caller: statement,
+                    block: stmt.block
+                )
+            }
 
             // Squash locals from the child frame back into the current frame.
             // Overlay the original (non-patched) value, keep the other side-effects.
@@ -957,6 +966,13 @@ private func evalCall(
     args: [IR.Operand],
     isDynamic: Bool = false
 ) async throws -> AST.RegoValue {
+    // Check memo cache if applicable to save repeated evaluation time for rules
+    let shouldMemoize = args.count == 2  // Currently support _rules_, not _functions_
+    let sig = InvocationKey(funcName: funcName, args: args)
+    if shouldMemoize, let cachedResult = ctx.callMemo[sig] {
+        return cachedResult
+    }
+
     var argValues: [AST.RegoValue] = []
     for arg in args {
         // Note: we do not enforce that args are defined here, it appears
@@ -974,24 +990,35 @@ private func evalCall(
             return .undefined
         }
 
-        return try await callPlanFunc(
+        let result = try await callPlanFunc(
             ctx: ctx,
             frame: frame,
             caller: caller,
             funcName: funcName,
             args: argValues
         )
+
+        if shouldMemoize {
+            ctx.callMemo[sig] = result
+        }
+        return result
     }
 
     // Handle plan-defined functions first
     if ctx.policy.funcs[funcName] != nil {
-        return try await callPlanFunc(
+        let result = try await callPlanFunc(
             ctx: ctx,
             frame: frame,
             caller: caller,
             funcName: funcName,
             args: argValues
         )
+
+        if shouldMemoize {
+            ctx.callMemo[sig] = result
+        }
+
+        return result
     }
 
     // Handle built-in functions last

Sources/Rego/Memo.swift

@@ -0,0 +1,60 @@
+import AST
+import Foundation
+import IR
+
+/// InvocationKey is a key for memoizing an IR function call invocation.
+/// Note we capture the arguments as unresolved operands and not resolved values,
+/// as hashing the values was proving extremely expensive. We instead rely on the
+/// invariant the the plan / evaluator will not modify a local after it has been initally set.
+struct InvocationKey: Hashable {
+    let funcName: String
+    let args: [IR.Operand]
+}
+
+/// MemoCache is a memoization cache of plan invocations
+typealias MemoCache = [InvocationKey: AST.RegoValue]
+
+/// MemoStack is a stack of MemoCaches
+final class MemoStack {
+    var stack: [MemoCache] = []
+}
+
+extension MemoStack {
+    /// Get and set values on the cache at the top of the memo stack.
+    subscript(key: InvocationKey) -> AST.RegoValue? {
+        get {
+            guard !self.stack.isEmpty else {
+                return nil
+            }
+            return self.stack[self.stack.count - 1][key]
+        }
+        set {
+            if self.stack.isEmpty {
+                self.stack.append(MemoCache.init())
+            }
+            self.stack[self.stack.count - 1][key] = newValue
+        }
+    }
+
+    func push() {
+        self.stack.append(MemoCache.init())
+    }
+
+    func pop() {
+        guard !self.stack.isEmpty else {
+            return
+        }
+        self.stack.removeLast()
+    }
+
+    /// withPush returns the result of calling the provided closure with
+    /// a fresh memoCache pushed on the stack. The memoCache will only be
+    /// active during that call, and discarded when it completes.
+    func withPush<T>(_ body: () async throws -> T) async rethrows -> T {
+        self.push()
+        defer {
+            self.pop()
+        }
+        return try await body()
+    }
+}