[SCCP] Enable PredicateInfo for non-interprocedural SCCP (#153003)

SCCP can use PredicateInfo to constrain ranges based on assume and
branch conditions. Currently, this is only enabled during IPSCCP.

This enables it for SCCP as well, which runs after functions have
already been simplified, while IPSCCP runs pre-inline. To a large
degree, CVP already handles range-based optimizations, but SCCP is more
reliable for the cases it can handle. In particular, SCCP works reliably
inside loops, which is something that CVP struggles with due to LVI
cycles.

I have made various optimizations to make PredicateInfo more efficient,
but unfortunately this still has significant compile-time cost (around
0.1-0.2%).

Author: nikic

llvm/lib/Transforms/Scalar/SCCP.cpp

@@ -20,6 +20,7 @@
 #include "llvm/ADT/SmallPtrSet.h"
 #include "llvm/ADT/SmallVector.h"
 #include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/AssumptionCache.h"
 #include "llvm/Analysis/DomTreeUpdater.h"
 #include "llvm/Analysis/GlobalsModRef.h"
 #include "llvm/Analysis/TargetLibraryInfo.h"
@@ -31,6 +32,7 @@
 #include "llvm/IR/InstrTypes.h"
 #include "llvm/IR/Instruction.h"
 #include "llvm/IR/Instructions.h"
+#include "llvm/IR/IntrinsicInst.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/IR/Type.h"
 #include "llvm/IR/Value.h"
@@ -53,12 +55,15 @@ STATISTIC(NumInstReplaced,
 // runSCCP() - Run the Sparse Conditional Constant Propagation algorithm,
 // and return true if the function was modified.
 static bool runSCCP(Function &F, const DataLayout &DL,
-                    const TargetLibraryInfo *TLI, DomTreeUpdater &DTU) {
+                    const TargetLibraryInfo *TLI, DominatorTree &DT,
+                    AssumptionCache &AC) {
   LLVM_DEBUG(dbgs() << "SCCP on function '" << F.getName() << "'\n");
   SCCPSolver Solver(
       DL, [TLI](Function &F) -> const TargetLibraryInfo & { return *TLI; },
       F.getContext());
 
+  Solver.addPredicateInfo(F, DT, AC);
+
   // While we don't do any actual inter-procedural analysis, still track
   // return values so we can infer attributes.
   if (canTrackReturnsInterprocedurally(&F))
@@ -101,6 +106,7 @@ static bool runSCCP(Function &F, const DataLayout &DL,
   }
 
   // Remove unreachable blocks and non-feasible edges.
+  DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Lazy);
   for (BasicBlock *DeadBB : BlocksToErase)
     NumInstRemoved += changeToUnreachable(&*DeadBB->getFirstNonPHIIt(),
                                           /*PreserveLCSSA=*/false, &DTU);
@@ -113,6 +119,8 @@ static bool runSCCP(Function &F, const DataLayout &DL,
     if (!DeadBB->hasAddressTaken())
       DTU.deleteBB(DeadBB);
 
+  Solver.removeSSACopies(F);
+
   Solver.inferReturnAttributes();
 
   return MadeChanges;
@@ -121,9 +129,9 @@ static bool runSCCP(Function &F, const DataLayout &DL,
 PreservedAnalyses SCCPPass::run(Function &F, FunctionAnalysisManager &AM) {
   const DataLayout &DL = F.getDataLayout();
   auto &TLI = AM.getResult<TargetLibraryAnalysis>(F);
-  auto *DT = AM.getCachedResult<DominatorTreeAnalysis>(F);
-  DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Lazy);
-  if (!runSCCP(F, DL, &TLI, DTU))
+  auto &DT = AM.getResult<DominatorTreeAnalysis>(F);
+  auto &AC = AM.getResult<AssumptionAnalysis>(F);
+  if (!runSCCP(F, DL, &TLI, DT, AC))
     return PreservedAnalyses::all();
 
   auto PA = PreservedAnalyses();

llvm/test/Transforms/PhaseOrdering/deletion-of-loops-that-became-side-effect-free.ll

@@ -96,35 +96,10 @@ while.end:
 }
 
 define dso_local zeroext i1 @is_not_empty_variant3(ptr %p) {
-; O3-LABEL: @is_not_empty_variant3(
-; O3-NEXT:  entry:
-; O3-NEXT:    [[TOBOOL_NOT4_I:%.*]] = icmp ne ptr [[P:%.*]], null
-; O3-NEXT:    ret i1 [[TOBOOL_NOT4_I]]
-;
-; O2-LABEL: @is_not_empty_variant3(
-; O2-NEXT:  entry:
-; O2-NEXT:    [[TOBOOL_NOT4_I:%.*]] = icmp ne ptr [[P:%.*]], null
-; O2-NEXT:    ret i1 [[TOBOOL_NOT4_I]]
-;
-; O1-LABEL: @is_not_empty_variant3(
-; O1-NEXT:  entry:
-; O1-NEXT:    [[TOBOOL_NOT4_I:%.*]] = icmp eq ptr [[P:%.*]], null
-; O1-NEXT:    br i1 [[TOBOOL_NOT4_I]], label [[COUNT_NODES_VARIANT3_EXIT:%.*]], label [[WHILE_BODY_I:%.*]]
-; O1:       while.body.i:
-; O1-NEXT:    [[SIZE_06_I:%.*]] = phi i64 [ [[INC_I:%.*]], [[WHILE_BODY_I]] ], [ 0, [[ENTRY:%.*]] ]
-; O1-NEXT:    [[P_ADDR_05_I:%.*]] = phi ptr [ [[TMP0:%.*]], [[WHILE_BODY_I]] ], [ [[P]], [[ENTRY]] ]
-; O1-NEXT:    [[CMP_I:%.*]] = icmp ne i64 [[SIZE_06_I]], -1
-; O1-NEXT:    call void @llvm.assume(i1 [[CMP_I]])
-; O1-NEXT:    [[TMP0]] = load ptr, ptr [[P_ADDR_05_I]], align 8
-; O1-NEXT:    [[INC_I]] = add i64 [[SIZE_06_I]], 1
-; O1-NEXT:    [[TOBOOL_NOT_I:%.*]] = icmp eq ptr [[TMP0]], null
-; O1-NEXT:    br i1 [[TOBOOL_NOT_I]], label [[COUNT_NODES_VARIANT3_EXIT_LOOPEXIT:%.*]], label [[WHILE_BODY_I]], !llvm.loop [[LOOP0:![0-9]+]]
-; O1:       count_nodes_variant3.exit.loopexit:
-; O1-NEXT:    [[PHI_CMP:%.*]] = icmp ne i64 [[INC_I]], 0
-; O1-NEXT:    br label [[COUNT_NODES_VARIANT3_EXIT]]
-; O1:       count_nodes_variant3.exit:
-; O1-NEXT:    [[SIZE_0_LCSSA_I:%.*]] = phi i1 [ false, [[ENTRY]] ], [ [[PHI_CMP]], [[COUNT_NODES_VARIANT3_EXIT_LOOPEXIT]] ]
-; O1-NEXT:    ret i1 [[SIZE_0_LCSSA_I]]
+; ALL-LABEL: @is_not_empty_variant3(
+; ALL-NEXT:  entry:
+; ALL-NEXT:    [[TOBOOL_NOT4_I:%.*]] = icmp ne ptr [[P:%.*]], null
+; ALL-NEXT:    ret i1 [[TOBOOL_NOT4_I]]
 ;
 entry:
   %p.addr = alloca ptr, align 8
@@ -182,3 +157,7 @@ declare void @llvm.assume(i1 noundef)
 !1 = !{!"llvm.loop.mustprogress"}
 !2 = distinct !{!2, !1}
 !3 = distinct !{!3, !1}
+;; NOTE: These prefixes are unused and the list is autogenerated. Do not add tests below this line:
+; O1: {{.*}}
+; O2: {{.*}}
+; O3: {{.*}}

llvm/test/Transforms/SCCP/pr27712.ll

@@ -2,7 +2,7 @@
 ; RUN: opt -passes=sccp -S < %s | FileCheck %s
 
 define i32 @main() {
-; CHECK-LABEL: define i32 @main() {
+; CHECK-LABEL: define range(i32 33554432, 0) i32 @main() {
 ; CHECK-NEXT:  [[ENTRY:.*]]:
 ; CHECK-NEXT:    br label %[[LBL_1154:.*]]
 ; CHECK:       [[LBL_1154]]:

llvm/test/Transforms/SCCP/sccptest.ll

@@ -43,7 +43,7 @@ define i32 @test2(i32 %i0, i32 %j0) {
 ; CHECK:       BB4:
 ; CHECK-NEXT:    ret i32 1
 ; CHECK:       BB5:
-; CHECK-NEXT:    [[K3]] = add i32 [[K2]], 1
+; CHECK-NEXT:    [[K3]] = add nsw i32 [[K2]], 1
 ; CHECK-NEXT:    br label [[BB7]]
 ; CHECK:       BB7:
 ; CHECK-NEXT:    br label [[BB2]]

llvm/test/Transforms/SCCP/undef-resolve.ll

@@ -33,15 +33,15 @@ define i32 @test2() nounwind readnone ssp {
 ; CHECK:       control.outer.outer.split.us:
 ; CHECK-NEXT:    br label [[CONTROL_OUTER_US:%.*]]
 ; CHECK:       control.outer.us:
-; CHECK-NEXT:    [[A_0_PH_US:%.*]] = phi i32 [ [[SWITCHCOND_0_US:%.*]], [[BB3_US:%.*]] ], [ 4, [[CONTROL_OUTER_OUTER_SPLIT_US]] ]
+; CHECK-NEXT:    [[A_0_PH_US:%.*]] = phi i32 [ 3, [[BB3_US:%.*]] ], [ 4, [[CONTROL_OUTER_OUTER_SPLIT_US]] ]
 ; CHECK-NEXT:    [[SWITCHCOND_0_PH_US:%.*]] = phi i32 [ [[A_0_PH_US]], [[BB3_US]] ], [ [[SWITCHCOND_0_PH_PH]], [[CONTROL_OUTER_OUTER_SPLIT_US]] ]
 ; CHECK-NEXT:    br label [[CONTROL_US:%.*]]
 ; CHECK:       bb3.us:
 ; CHECK-NEXT:    br label [[CONTROL_OUTER_US]]
 ; CHECK:       bb0.us:
 ; CHECK-NEXT:    br label [[CONTROL_US]]
 ; CHECK:       control.us:
-; CHECK-NEXT:    [[SWITCHCOND_0_US]] = phi i32 [ [[A_0_PH_US]], [[BB0_US:%.*]] ], [ [[SWITCHCOND_0_PH_US]], [[CONTROL_OUTER_US]] ]
+; CHECK-NEXT:    [[SWITCHCOND_0_US:%.*]] = phi i32 [ [[A_0_PH_US]], [[BB0_US:%.*]] ], [ [[SWITCHCOND_0_PH_US]], [[CONTROL_OUTER_US]] ]
 ; CHECK-NEXT:    switch i32 [[SWITCHCOND_0_US]], label [[CONTROL_OUTER_LOOPEXIT_US_LCSSA_US:%.*]] [
 ; CHECK-NEXT:      i32 0, label [[BB0_US]]
 ; CHECK-NEXT:      i32 1, label [[BB1_US_LCSSA_US:%.*]]
@@ -55,7 +55,7 @@ define i32 @test2() nounwind readnone ssp {
 ; CHECK:       bb4.us-lcssa.us:
 ; CHECK-NEXT:    br label [[BB4:%.*]]
 ; CHECK:       control.outer:
-; CHECK-NEXT:    [[A_0_PH:%.*]] = phi i32 [ [[NEXTID17:%.*]], [[BB3:%.*]] ], [ 4, [[CONTROL_OUTER_OUTER_CONTROL_OUTER_OUTER_SPLIT_CRIT_EDGE]] ]
+; CHECK-NEXT:    [[A_0_PH:%.*]] = phi i32 [ 1, [[BB3:%.*]] ], [ 4, [[CONTROL_OUTER_OUTER_CONTROL_OUTER_OUTER_SPLIT_CRIT_EDGE]] ]
 ; CHECK-NEXT:    [[SWITCHCOND_0_PH:%.*]] = phi i32 [ 0, [[BB3]] ], [ [[SWITCHCOND_0_PH_PH]], [[CONTROL_OUTER_OUTER_CONTROL_OUTER_OUTER_SPLIT_CRIT_EDGE]] ]
 ; CHECK-NEXT:    br label [[CONTROL:%.*]]
 ; CHECK:       control:
@@ -74,7 +74,6 @@ define i32 @test2() nounwind readnone ssp {
 ; CHECK-NEXT:    [[I_0_PH_PH_BE]] = phi i32 [ 1, [[BB4]] ], [ 0, [[CONTROL_OUTER_LOOPEXIT]] ]
 ; CHECK-NEXT:    br label [[CONTROL_OUTER_OUTER]]
 ; CHECK:       bb3:
-; CHECK-NEXT:    [[NEXTID17]] = add i32 [[SWITCHCOND_0]], -2
 ; CHECK-NEXT:    br label [[CONTROL_OUTER]]
 ; CHECK:       bb0:
 ; CHECK-NEXT:    br label [[CONTROL]]