[TTI] Add SCEVExpansionBudget to loop unrolling options. (llvm#118316)

Add an extra know to UnrollingPreferences to let backends control the
maximum budget for SCEV expansions.

This gives backends more fine-grained control on the cost of the runtime
checks for runtime unrolling.

PR: llvm#118316
(cherry picked from commit 4226e0a)

Author: fhahn

llvm/include/llvm/Analysis/TargetTransformInfo.h

@@ -614,6 +614,9 @@ class TargetTransformInfo {
     unsigned MaxIterationsCountToAnalyze;
     /// Don't disable runtime unroll for the loops which were vectorized.
     bool UnrollVectorizedLoop = false;
+    /// Don't allow runtime unrolling if expanding the trip count takes more
+    /// than SCEVExpansionBudget.
+    unsigned SCEVExpansionBudget;
   };
 
   /// Get target-customized preferences for the generic loop unrolling

llvm/include/llvm/Transforms/Utils/UnrollLoop.h

@@ -75,6 +75,7 @@ struct UnrollLoopOptions {
   bool UnrollRemainder;
   bool ForgetAllSCEV;
   const Instruction *Heart = nullptr;
+  unsigned SCEVExpansionBudget;
 };
 
 LoopUnrollResult UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
@@ -90,7 +91,7 @@ bool UnrollRuntimeLoopRemainder(
     bool UseEpilogRemainder, bool UnrollRemainder, bool ForgetAllSCEV,
     LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT, AssumptionCache *AC,
     const TargetTransformInfo *TTI, bool PreserveLCSSA,
-    Loop **ResultLoop = nullptr);
+    unsigned SCEVExpansionBudget, Loop **ResultLoop = nullptr);
 
 LoopUnrollResult UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
                                   unsigned TripMultiple, bool UnrollRemainder,

llvm/lib/Transforms/Scalar/LoopUnrollPass.cpp

@@ -58,6 +58,7 @@
 #include "llvm/Transforms/Utils/LoopPeel.h"
 #include "llvm/Transforms/Utils/LoopSimplify.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
+#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
 #include "llvm/Transforms/Utils/SizeOpts.h"
 #include "llvm/Transforms/Utils/UnrollLoop.h"
 #include <algorithm>
@@ -219,6 +220,7 @@ TargetTransformInfo::UnrollingPreferences llvm::gatherUnrollingPreferences(
   UP.UnrollAndJam = false;
   UP.UnrollAndJamInnerLoopThreshold = 60;
   UP.MaxIterationsCountToAnalyze = UnrollMaxIterationsCountToAnalyze;
+  UP.SCEVExpansionBudget = SCEVCheapExpansionBudget;
 
   // Override with any target specific settings
   TTI.getUnrollingPreferences(L, SE, UP, &ORE);
@@ -1350,6 +1352,7 @@ tryToUnrollLoop(Loop *L, DominatorTree &DT, LoopInfo *LI, ScalarEvolution &SE,
   ULO.Runtime = UP.Runtime;
   ULO.ForgetAllSCEV = ForgetAllSCEV;
   ULO.Heart = getLoopConvergenceHeart(L);
+  ULO.SCEVExpansionBudget = UP.SCEVExpansionBudget;
   LoopUnrollResult UnrollResult = UnrollLoop(
       L, ULO, LI, &SE, &DT, &AC, &TTI, &ORE, PreserveLCSSA, &RemainderLoop, AA);
   if (UnrollResult == LoopUnrollResult::Unmodified)

llvm/lib/Transforms/Utils/LoopUnroll.cpp

@@ -63,6 +63,7 @@
 #include "llvm/Transforms/Utils/Local.h"
 #include "llvm/Transforms/Utils/LoopSimplify.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
+#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
 #include "llvm/Transforms/Utils/SimplifyIndVar.h"
 #include "llvm/Transforms/Utils/UnrollLoop.h"
 #include "llvm/Transforms/Utils/ValueMapper.h"
@@ -592,10 +593,10 @@ llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
                                               : isEpilogProfitable(L);
 
   if (ULO.Runtime &&
-      !UnrollRuntimeLoopRemainder(L, ULO.Count, ULO.AllowExpensiveTripCount,
-                                  EpilogProfitability, ULO.UnrollRemainder,
-                                  ULO.ForgetAllSCEV, LI, SE, DT, AC, TTI,
-                                  PreserveLCSSA, RemainderLoop)) {
+      !UnrollRuntimeLoopRemainder(
+          L, ULO.Count, ULO.AllowExpensiveTripCount, EpilogProfitability,
+          ULO.UnrollRemainder, ULO.ForgetAllSCEV, LI, SE, DT, AC, TTI,
+          PreserveLCSSA, ULO.SCEVExpansionBudget, RemainderLoop)) {
     if (ULO.Force)
       ULO.Runtime = false;
     else {

llvm/lib/Transforms/Utils/LoopUnrollAndJam.cpp

@@ -48,6 +48,7 @@
 #include "llvm/Transforms/Utils/BasicBlockUtils.h"
 #include "llvm/Transforms/Utils/Cloning.h"
 #include "llvm/Transforms/Utils/LoopUtils.h"
+#include "llvm/Transforms/Utils/ScalarEvolutionExpander.h"
 #include "llvm/Transforms/Utils/UnrollLoop.h"
 #include "llvm/Transforms/Utils/ValueMapper.h"
 #include <assert.h>
@@ -243,7 +244,8 @@ llvm::UnrollAndJamLoop(Loop *L, unsigned Count, unsigned TripCount,
     if (!UnrollRuntimeLoopRemainder(L, Count, /*AllowExpensiveTripCount*/ false,
                                     /*UseEpilogRemainder*/ true,
                                     UnrollRemainder, /*ForgetAllSCEV*/ false,
-                                    LI, SE, DT, AC, TTI, true, EpilogueLoop)) {
+                                    LI, SE, DT, AC, TTI, true,
+                                    SCEVCheapExpansionBudget, EpilogueLoop)) {
       LLVM_DEBUG(dbgs() << "Won't unroll-and-jam; remainder loop could not be "
                            "generated when assuming runtime trip count\n");
       return LoopUnrollResult::Unmodified;

llvm/lib/Transforms/Utils/LoopUnrollRuntime.cpp

@@ -583,7 +583,8 @@ bool llvm::UnrollRuntimeLoopRemainder(
     Loop *L, unsigned Count, bool AllowExpensiveTripCount,
     bool UseEpilogRemainder, bool UnrollRemainder, bool ForgetAllSCEV,
     LoopInfo *LI, ScalarEvolution *SE, DominatorTree *DT, AssumptionCache *AC,
-    const TargetTransformInfo *TTI, bool PreserveLCSSA, Loop **ResultLoop) {
+    const TargetTransformInfo *TTI, bool PreserveLCSSA,
+    unsigned SCEVExpansionBudget, Loop **ResultLoop) {
   LLVM_DEBUG(dbgs() << "Trying runtime unrolling on Loop: \n");
   LLVM_DEBUG(L->dump());
   LLVM_DEBUG(UseEpilogRemainder ? dbgs() << "Using epilog remainder.\n"
@@ -673,8 +674,8 @@ bool llvm::UnrollRuntimeLoopRemainder(
   const DataLayout &DL = Header->getDataLayout();
   SCEVExpander Expander(*SE, DL, "loop-unroll");
   if (!AllowExpensiveTripCount &&
-      Expander.isHighCostExpansion(TripCountSC, L, SCEVCheapExpansionBudget,
-                                   TTI, PreHeaderBR)) {
+      Expander.isHighCostExpansion(TripCountSC, L, SCEVExpansionBudget, TTI,
+                                   PreHeaderBR)) {
     LLVM_DEBUG(dbgs() << "High cost for expanding trip count scev!\n");
     return false;
   }

llvm/unittests/Transforms/Utils/UnrollLoopTest.cpp

@@ -73,6 +73,6 @@ while.end:                                        ; preds = %while.cond
 
   bool ret =
       UnrollRuntimeLoopRemainder(L, 4, true, false, false, false, &LI, &SE, &DT,
-                                 &AC, /*TTI=*/nullptr, PreserveLCSSA);
+                                 &AC, /*TTI=*/nullptr, PreserveLCSSA, 4);
   EXPECT_FALSE(ret);
 }