[LV][NFC] Marked functions as const. Added LLVM_DEBUG. (#96681)

Author: nikolaypanchenko

llvm/lib/Transforms/Vectorize/LoopVectorize.cpp

@@ -1431,29 +1431,40 @@ class LoopVectorizationCostModel {
   /// Returns true if \p I is a memory instruction in an interleaved-group
   /// of memory accesses that can be vectorized with wide vector loads/stores
   /// and shuffles.
-  bool interleavedAccessCanBeWidened(Instruction *I, ElementCount VF);
+  bool interleavedAccessCanBeWidened(Instruction *I, ElementCount VF) const;
 
   /// Check if \p Instr belongs to any interleaved access group.
-  bool isAccessInterleaved(Instruction *Instr) {
+  bool isAccessInterleaved(Instruction *Instr) const {
     return InterleaveInfo.isInterleaved(Instr);
   }
 
   /// Get the interleaved access group that \p Instr belongs to.
   const InterleaveGroup<Instruction> *
-  getInterleavedAccessGroup(Instruction *Instr) {
+  getInterleavedAccessGroup(Instruction *Instr) const {
     return InterleaveInfo.getInterleaveGroup(Instr);
   }
 
   /// Returns true if we're required to use a scalar epilogue for at least
   /// the final iteration of the original loop.
   bool requiresScalarEpilogue(bool IsVectorizing) const {
-    if (!isScalarEpilogueAllowed())
+    if (!isScalarEpilogueAllowed()) {
+      LLVM_DEBUG(dbgs() << "LV: Loop does not require scalar epilogue\n");
       return false;
+    }
     // If we might exit from anywhere but the latch, must run the exiting
     // iteration in scalar form.
-    if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch())
+    if (TheLoop->getExitingBlock() != TheLoop->getLoopLatch()) {
+      LLVM_DEBUG(
+          dbgs() << "LV: Loop requires scalar epilogue: multiple exits\n");
+      return true;
+    }
+    if (IsVectorizing && InterleaveInfo.requiresScalarEpilogue()) {
+      LLVM_DEBUG(dbgs() << "LV: Loop requires scalar epilogue: "
+                           "interleaved group requires scalar epilogue\n");
       return true;
-    return IsVectorizing && InterleaveInfo.requiresScalarEpilogue();
+    }
+    LLVM_DEBUG(dbgs() << "LV: Loop does not require scalar epilogue\n");
+    return false;
   }
 
   /// Returns true if we're required to use a scalar epilogue for at least
@@ -3919,7 +3930,7 @@ LoopVectorizationCostModel::getDivRemSpeculationCost(Instruction *I,
 }
 
 bool LoopVectorizationCostModel::interleavedAccessCanBeWidened(
-    Instruction *I, ElementCount VF) {
+    Instruction *I, ElementCount VF) const {
   assert(isAccessInterleaved(I) && "Expecting interleaved access.");
   assert(getWideningDecision(I, VF) == CM_Unknown &&
          "Decision should not be set yet.");

llvm/test/Transforms/LoopVectorize/RISCV/riscv-vector-reverse.ll

@@ -50,6 +50,8 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV: Scalarizing: %arrayidx3 = getelementptr inbounds i32, ptr %A, i64 %idxprom
 ; CHECK-NEXT:  LV: Scalarizing: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Scalarizing: %indvars.iv.next = add nsw i64 %indvars.iv, -1
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  VPlan 'Initial VPlan for VF={vscale x 4},UF>=1' {
 ; CHECK-NEXT:  Live-in vp<[[VFxUF:%.+]]> = VF * UF
 ; CHECK-NEXT:  Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count
@@ -112,6 +114,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
 ; CHECK-NEXT:  LV: The target has 31 registers of RISCV::GPRRC register class
 ; CHECK-NEXT:  LV: The target has 32 registers of RISCV::VRRC register class
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  LV: Loop cost is 32
 ; CHECK-NEXT:  LV: IC is 1
 ; CHECK-NEXT:  LV: VF is vscale x 4
@@ -121,6 +124,7 @@ define void @vector_reverse_i64(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LEV: Epilogue vectorization is not profitable for this loop
 ; CHECK-NEXT:  Executing best plan with VF=vscale x 4, UF=1
 ; CHECK:       LV: Interleaving disabled by the pass manager
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  LV: Vectorizing: innermost loop.
 ; CHECK-EMPTY:
 ;
@@ -191,6 +195,8 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV: Scalarizing: %arrayidx3 = getelementptr inbounds float, ptr %A, i64 %idxprom
 ; CHECK-NEXT:  LV: Scalarizing: %cmp = icmp ugt i64 %indvars.iv, 1
 ; CHECK-NEXT:  LV: Scalarizing: %indvars.iv.next = add nsw i64 %indvars.iv, -1
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  VPlan 'Initial VPlan for VF={vscale x 4},UF>=1' {
 ; CHECK-NEXT:  Live-in vp<[[VFxUF:%.+]]> = VF * UF
 ; CHECK-NEXT:  Live-in vp<[[VEC_TC:%.+]]> = vector-trip-count
@@ -253,6 +259,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LV(REG): RegisterClass: RISCV::GPRRC, 1 registers
 ; CHECK-NEXT:  LV: The target has 31 registers of RISCV::GPRRC register class
 ; CHECK-NEXT:  LV: The target has 32 registers of RISCV::VRRC register class
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  LV: Loop cost is 32
 ; CHECK-NEXT:  LV: IC is 1
 ; CHECK-NEXT:  LV: VF is vscale x 4
@@ -262,6 +269,7 @@ define void @vector_reverse_f32(ptr nocapture noundef writeonly %A, ptr nocaptur
 ; CHECK-NEXT:  LEV: Epilogue vectorization is not profitable for this loop
 ; CHECK-NEXT:  Executing best plan with VF=vscale x 4, UF=1
 ; CHECK:       LV: Interleaving disabled by the pass manager
+; CHECK-NEXT:  LV: Loop does not require scalar epilogue
 ; CHECK-NEXT:  LV: Vectorizing: innermost loop.
 ;
 entry:

llvm/test/Transforms/LoopVectorize/vplan-printing-before-execute.ll

@@ -8,7 +8,7 @@ target datalayout = "e-m:o-i64:64-i128:128-n32:64-S128"
 ; VF/IC combination.
 define void @test_tc_less_than_16(ptr %A, i64 %N) {
 ; CHECK:      LV: Scalarizing:  %cmp =
-; CHECK-NEXT: VPlan 'Initial VPlan for VF={8},UF>=1' {
+; CHECK:      VPlan 'Initial VPlan for VF={8},UF>=1' {
 ; CHECK-NEXT: Live-in vp<[[VFxUF:%.+]]> = VF * UF
 ; CHECK-NEXT: Live-in vp<[[VTC:%.+]]> = vector-trip-count
 ; CHECK-NEXT: vp<[[TC:%.+]]> = original trip-count