Revert "[HardwareLoops] Change order of SCEV expression construction for InitLoopCount."

Chen Zheng · Chen Zheng · commit 34badc409cc4 · 2021-09-03T02:55:43.000Z
This causes https://bugs.llvm.org/show_bug.cgi?id=51714 and is not a right patch according to comments in D91724 This reverts commit 42eaf4f.
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -98,7 +98,7 @@ struct HardwareLoopInfo {
   Loop *L = nullptr;
   BasicBlock *ExitBlock = nullptr;
   BranchInst *ExitBranch = nullptr;
-  const SCEV *TripCount = nullptr;
+  const SCEV *ExitCount = nullptr;
   IntegerType *CountType = nullptr;
   Value *LoopDecrement = nullptr; // Decrement the loop counter by this
                                   // value in every iteration.
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -167,11 +167,7 @@ bool HardwareLoopInfo::isHardwareLoopCandidate(ScalarEvolution &SE,
     // Note that this block may not be the loop latch block, even if the loop
     // has a latch block.
     ExitBlock = BB;
-    TripCount = SE.getAddExpr(EC, SE.getOne(EC->getType()));
-
-    if (!EC->getType()->isPointerTy() && EC->getType() != CountType)
-      TripCount = SE.getZeroExtendExpr(TripCount, CountType);
-
+    ExitCount = EC;
     break;
   }
 
diff --git a/llvm/lib/CodeGen/HardwareLoops.cpp b/llvm/lib/CodeGen/HardwareLoops.cpp
@@ -187,7 +187,7 @@ namespace {
                  const DataLayout &DL,
                  OptimizationRemarkEmitter *ORE) :
       SE(SE), DL(DL), ORE(ORE), L(Info.L), M(L->getHeader()->getModule()),
-      TripCount(Info.TripCount),
+      ExitCount(Info.ExitCount),
       CountType(Info.CountType),
       ExitBranch(Info.ExitBranch),
       LoopDecrement(Info.LoopDecrement),
@@ -202,7 +202,7 @@ namespace {
     OptimizationRemarkEmitter *ORE = nullptr;
     Loop *L                 = nullptr;
     Module *M               = nullptr;
-    const SCEV *TripCount   = nullptr;
+    const SCEV *ExitCount   = nullptr;
     Type *CountType         = nullptr;
     BranchInst *ExitBranch  = nullptr;
     Value *LoopDecrement    = nullptr;
@@ -296,7 +296,7 @@ bool HardwareLoops::TryConvertLoop(HardwareLoopInfo &HWLoopInfo) {
   }
 
   assert(
-      (HWLoopInfo.ExitBlock && HWLoopInfo.ExitBranch && HWLoopInfo.TripCount) &&
+      (HWLoopInfo.ExitBlock && HWLoopInfo.ExitBranch && HWLoopInfo.ExitCount) &&
       "Hardware Loop must have set exit info.");
 
   BasicBlock *Preheader = L->getLoopPreheader();
@@ -381,13 +381,18 @@ Value *HardwareLoop::InitLoopCount() {
   // loop counter and tests that is not zero?
 
   SCEVExpander SCEVE(SE, DL, "loopcnt");
+  if (!ExitCount->getType()->isPointerTy() &&
+      ExitCount->getType() != CountType)
+    ExitCount = SE.getZeroExtendExpr(ExitCount, CountType);
+
+  ExitCount = SE.getAddExpr(ExitCount, SE.getOne(CountType));
 
   // If we're trying to use the 'test and set' form of the intrinsic, we need
   // to replace a conditional branch that is controlling entry to the loop. It
   // is likely (guaranteed?) that the preheader has an unconditional branch to
   // the loop header, so also check if it has a single predecessor.
-  if (SE.isLoopEntryGuardedByCond(L, ICmpInst::ICMP_NE, TripCount,
-                                  SE.getZero(TripCount->getType()))) {
+  if (SE.isLoopEntryGuardedByCond(L, ICmpInst::ICMP_NE, ExitCount,
+                                  SE.getZero(ExitCount->getType()))) {
     LLVM_DEBUG(dbgs() << " - Attempting to use test.set counter.\n");
     UseLoopGuard |= ForceGuardLoopEntry;
   } else
@@ -399,19 +404,19 @@ Value *HardwareLoop::InitLoopCount() {
     BasicBlock *Predecessor = BB->getSinglePredecessor();
     // If it's not safe to create a while loop then don't force it and create a
     // do-while loop instead
-    if (!isSafeToExpandAt(TripCount, Predecessor->getTerminator(), SE))
+    if (!isSafeToExpandAt(ExitCount, Predecessor->getTerminator(), SE))
         UseLoopGuard = false;
     else
         BB = Predecessor;
   }
 
-  if (!isSafeToExpandAt(TripCount, BB->getTerminator(), SE)) {
-    LLVM_DEBUG(dbgs() << "- Bailing, unsafe to expand TripCount " << *TripCount
-                      << "\n");
+  if (!isSafeToExpandAt(ExitCount, BB->getTerminator(), SE)) {
+    LLVM_DEBUG(dbgs() << "- Bailing, unsafe to expand ExitCount "
+               << *ExitCount << "\n");
     return nullptr;
   }
 
-  Value *Count = SCEVE.expandCodeFor(TripCount, CountType,
+  Value *Count = SCEVE.expandCodeFor(ExitCount, CountType,
                                      BB->getTerminator());
 
   // FIXME: We've expanded Count where we hope to insert the counter setting
diff --git a/llvm/test/CodeGen/PowerPC/loop-instr-prep-non-const-increasement.ll b/llvm/test/CodeGen/PowerPC/loop-instr-prep-non-const-increasement.ll
@@ -22,12 +22,14 @@ define i64 @foo(i8* %p, i32 signext %n, i32 signext %count) {
 ; CHECK-NEXT:    cmpwi r4, 1
 ; CHECK-NEXT:    blt cr0, .LBB0_4
 ; CHECK-NEXT:  # %bb.1: # %for.body.preheader
-; CHECK-NEXT:    clrldi r4, r4, 32
+; CHECK-NEXT:    addi r4, r4, -1
 ; CHECK-NEXT:    extsw r5, r5
 ; CHECK-NEXT:    li r6, 0
 ; CHECK-NEXT:    li r7, 5
-; CHECK-NEXT:    mtctr r4
 ; CHECK-NEXT:    li r8, 9
+; CHECK-NEXT:    clrldi r4, r4, 32
+; CHECK-NEXT:    addi r4, r4, 1
+; CHECK-NEXT:    mtctr r4
 ; CHECK-NEXT:    li r4, 0
 ; CHECK-NEXT:    .p2align 5
 ; CHECK-NEXT:  .LBB0_2: # %for.body
@@ -93,21 +95,23 @@ define zeroext i8 @foo1(i8* %p, i32 signext %n, i32 signext %count) {
 ; CHECK-NEXT:    cmpwi r4, 1
 ; CHECK-NEXT:    blt cr0, .LBB1_4
 ; CHECK-NEXT:  # %bb.1: # %for.body.preheader
-; CHECK-NEXT:    addi r6, r3, 1000
-; CHECK-NEXT:    clrldi r3, r4, 32
+; CHECK-NEXT:    addi r4, r4, -1
+; CHECK-NEXT:    addi r3, r3, 1000
 ; CHECK-NEXT:    extsw r5, r5
+; CHECK-NEXT:    li r6, 0
+; CHECK-NEXT:    clrldi r4, r4, 32
+; CHECK-NEXT:    addi r4, r4, 1
+; CHECK-NEXT:    mtctr r4
 ; CHECK-NEXT:    li r4, 0
-; CHECK-NEXT:    mtctr r3
-; CHECK-NEXT:    li r3, 0
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB1_2: # %for.body
 ; CHECK-NEXT:    #
-; CHECK-NEXT:    lbzx r7, r6, r4
-; CHECK-NEXT:    add r4, r4, r5
-; CHECK-NEXT:    add r3, r7, r3
+; CHECK-NEXT:    lbzx r7, r3, r6
+; CHECK-NEXT:    add r6, r6, r5
+; CHECK-NEXT:    add r4, r7, r4
 ; CHECK-NEXT:    bdnz .LBB1_2
 ; CHECK-NEXT:  # %bb.3: # %for.cond.cleanup
-; CHECK-NEXT:    clrldi r3, r3, 56
+; CHECK-NEXT:    clrldi r3, r4, 56
 ; CHECK-NEXT:    blr
 ; CHECK-NEXT:  .LBB1_4:
 ; CHECK-NEXT:    li r3, 0
diff --git a/llvm/test/CodeGen/PowerPC/mma-phi-accs.ll b/llvm/test/CodeGen/PowerPC/mma-phi-accs.ll
@@ -263,7 +263,9 @@ define dso_local signext i32 @testNestedPHI(i32 signext %cond, i32 signext %coun
 ; CHECK-NEXT:    cmpwi r4, 1
 ; CHECK-NEXT:    blt cr0, .LBB3_5
 ; CHECK-NEXT:  .LBB3_3: # %for.body.preheader
-; CHECK-NEXT:    clrldi r3, r4, 32
+; CHECK-NEXT:    addi r3, r4, -1
+; CHECK-NEXT:    clrldi r3, r3, 32
+; CHECK-NEXT:    addi r3, r3, 1
 ; CHECK-NEXT:    mtctr r3
 ; CHECK-NEXT:    .p2align 4
 ; CHECK-NEXT:  .LBB3_4: # %for.body
@@ -293,7 +295,9 @@ define dso_local signext i32 @testNestedPHI(i32 signext %cond, i32 signext %coun
 ; CHECK-BE-NEXT:    cmpwi r4, 1
 ; CHECK-BE-NEXT:    blt cr0, .LBB3_5
 ; CHECK-BE-NEXT:  .LBB3_3: # %for.body.preheader
-; CHECK-BE-NEXT:    clrldi r3, r4, 32
+; CHECK-BE-NEXT:    addi r3, r4, -1
+; CHECK-BE-NEXT:    clrldi r3, r3, 32
+; CHECK-BE-NEXT:    addi r3, r3, 1
 ; CHECK-BE-NEXT:    mtctr r3
 ; CHECK-BE-NEXT:    .p2align 4
 ; CHECK-BE-NEXT:  .LBB3_4: # %for.body
