[llvm] [LoopStrengthReduce] Mitigation of issues introduced by compilation time optimization in SolveRecurse. (PR #147588)

[Sergey Shcherbinin via llvm-commits]

================
@@ -5398,54 +5443,69 @@ void LSRInstance::SolveRecurse(SmallVectorImpl<const Formula *> &Solution,
 
   SmallPtrSet<const SCEV *, 16> NewRegs;
   Cost NewCost(L, SE, TTI, AMK);
-  for (const Formula &F : LU.Formulae) {
-    // Ignore formulae which may not be ideal in terms of register reuse of
-    // ReqRegs.  The formula should use all required registers before
-    // introducing new ones.
-    // This can sometimes (notably when trying to favour postinc) lead to
-    // sub-optimial decisions. There it is best left to the cost modelling to
-    // get correct.
-    if (AMK != TTI::AMK_PostIndexed || LU.Kind != LSRUse::Address) {
-      int NumReqRegsToFind = std::min(F.getNumRegs(), ReqRegs.size());
-      for (const SCEV *Reg : ReqRegs) {
-        if ((F.ScaledReg && F.ScaledReg == Reg) ||
-            is_contained(F.BaseRegs, Reg)) {
-          --NumReqRegsToFind;
-          if (NumReqRegsToFind == 0)
-            break;
+  bool FormulaeTested = false;
+  unsigned NumReqRegsToIgnore = 0;
+
+  while (!FormulaeTested) {
+    assert(
+        !NumReqRegsToIgnore ||
+        NumReqRegsToIgnore < ReqRegs.size() &&
+            "at least one formulae should have at least one required register");
+
+    for (const Formula &F : LU.Formulae) {
+      // ReqRegs. The formula should use required registers before
+      // introducing new ones. Firstly try the most aggressive option
+      // (when maximum of required registers are used) and then gradually make
+      // it weaker if all formulae don't satisfy this requirement.
+      //
+      // This can sometimes (notably when trying to favour postinc) lead to
+      // sub-optimal decisions. There it is best left to the cost modeling to
+      // get correct.
+      if (ReqRegs.size() &&
+          (AMK != TTI::AMK_PostIndexed || LU.Kind != LSRUse::Address)) {
+        unsigned NumReqRegsToFind = std::min(F.getNumRegs(), ReqRegs.size());
+        bool ReqRegsFound = false;
+        for (const SCEV *Reg : ReqRegs) {
+          if ((F.ScaledReg && F.ScaledReg == Reg) ||
+              is_contained(F.BaseRegs, Reg)) {
+            ReqRegsFound = true;
+            if (--NumReqRegsToFind == NumReqRegsToIgnore)
+              break;
+          }
+        }
+        if (!ReqRegsFound || NumReqRegsToFind != NumReqRegsToIgnore) {
+          continue;
         }
       }
-      if (NumReqRegsToFind != 0) {
-        // If none of the formulae satisfied the required registers, then we could
-        // clear ReqRegs and try again. Currently, we simply give up in this case.
-        continue;
-      }
-    }
 
-    // Evaluate the cost of the current formula. If it's already worse than
-    // the current best, prune the search at that point.
-    NewCost = CurCost;
-    NewRegs = CurRegs;
-    NewCost.RateFormula(F, NewRegs, VisitedRegs, LU);
-    if (NewCost.isLess(SolutionCost)) {
-      Workspace.push_back(&F);
-      if (Workspace.size() != Uses.size()) {
-        SolveRecurse(Solution, SolutionCost, Workspace, NewCost,
-                     NewRegs, VisitedRegs);
-        if (F.getNumRegs() == 1 && Workspace.size() == 1)
-          VisitedRegs.insert(F.ScaledReg ? F.ScaledReg : F.BaseRegs[0]);
-      } else {
-        LLVM_DEBUG(dbgs() << "New best at "; NewCost.print(dbgs());
-                   dbgs() << ".\nRegs:\n";
-                   for (const SCEV *S : NewRegs) dbgs()
-                      << "- " << *S << "\n";
-                   dbgs() << '\n');
-
-        SolutionCost = NewCost;
-        Solution = Workspace;
+      // Evaluate the cost of the current formula. If it's already worse than
+      // the current best, prune the search at that point.
+      FormulaeTested = true;
+      NewCost = CurCost;
+      NewRegs = CurRegs;
+      NewCost.RateFormula(F, NewRegs, VisitedRegs, LU);
+      if (NewCost.isLess(SolutionCost)) {
+        Workspace.push_back(&F);
+        if (Workspace.size() != Uses.size()) {
+          SolveRecurse(Solution, SolutionCost, Workspace, NewCost, NewRegs,
+                       VisitedRegs);
+          if (F.getNumRegs() == 1 && Workspace.size() == 1)
+            VisitedRegs.insert(F.ScaledReg ? F.ScaledReg : F.BaseRegs[0]);
+        } else {
+          LLVM_DEBUG(dbgs() << "New best at "; NewCost.print(dbgs());
+                     dbgs() << ".\nRegs:\n";
+                     for (const SCEV *S : NewRegs) dbgs() << "- " << *S << "\n";
+                     dbgs() << '\n');
----------------
SergeyShch01 wrote:

Ok, done

https://github.com/llvm/llvm-project/pull/147588