[llvm] 42eaf4f - [HardwareLoops] Change order of SCEV expression construction for InitLoopCount.

[Thomas Preud'homme via llvm-commits]

Author: Janek van Oirschot
Date: 2020-11-24T18:01:42Z
New Revision: 42eaf4fe0adef3344adfd9fbccd49f325cb549ef

URL: https://github.com/llvm/llvm-project/commit/42eaf4fe0adef3344adfd9fbccd49f325cb549ef
DIFF: https://github.com/llvm/llvm-project/commit/42eaf4fe0adef3344adfd9fbccd49f325cb549ef.diff

LOG: [HardwareLoops] Change order of SCEV expression construction for InitLoopCount.

Putting the +1 before the zero-extend will allow scalar evolution to fold the expression in some cases such as the one shown in PowerPC's `shrink-wrap.ll` test.

Reviewed By: samparker

Differential Revision: https://reviews.llvm.org/D91724

Added: 
    

Modified: 
    llvm/include/llvm/Analysis/TargetTransformInfo.h
    llvm/lib/Analysis/TargetTransformInfo.cpp
    llvm/lib/CodeGen/HardwareLoops.cpp
    llvm/test/CodeGen/PowerPC/shrink-wrap.ll

Removed: 
    


################################################################################
diff  --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index 77952247fe3c..9cb5fe78f418 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -93,7 +93,7 @@ struct HardwareLoopInfo {
   Loop *L = nullptr;
   BasicBlock *ExitBlock = nullptr;
   BranchInst *ExitBranch = nullptr;
-  const SCEV *ExitCount = nullptr;
+  const SCEV *TripCount = 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
index b59a1a403e65..2a79aa455fbc 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -216,7 +216,11 @@ 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;
-    ExitCount = EC;
+    TripCount = SE.getAddExpr(EC, SE.getOne(EC->getType()));
+
+    if (!EC->getType()->isPointerTy() && EC->getType() != CountType)
+      TripCount = SE.getZeroExtendExpr(TripCount, CountType);
+
     break;
   }
 

diff  --git a/llvm/lib/CodeGen/HardwareLoops.cpp b/llvm/lib/CodeGen/HardwareLoops.cpp
index 76c9c1470868..810b10c9c82a 100644
--- 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()),
-      ExitCount(Info.ExitCount),
+      TripCount(Info.TripCount),
       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 *ExitCount   = nullptr;
+    const SCEV *TripCount   = nullptr;
     Type *CountType         = nullptr;
     BranchInst *ExitBranch  = nullptr;
     Value *LoopDecrement    = nullptr;
@@ -298,7 +298,7 @@ bool HardwareLoops::TryConvertLoop(HardwareLoopInfo &HWLoopInfo) {
   }
 
   assert(
-      (HWLoopInfo.ExitBlock && HWLoopInfo.ExitBranch && HWLoopInfo.ExitCount) &&
+      (HWLoopInfo.ExitBlock && HWLoopInfo.ExitBranch && HWLoopInfo.TripCount) &&
       "Hardware Loop must have set exit info.");
 
   BasicBlock *Preheader = L->getLoopPreheader();
@@ -383,18 +383,13 @@ 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, ExitCount,
-                                  SE.getZero(ExitCount->getType()))) {
+  if (SE.isLoopEntryGuardedByCond(L, ICmpInst::ICMP_NE, TripCount,
+                                  SE.getZero(TripCount->getType()))) {
     LLVM_DEBUG(dbgs() << " - Attempting to use test.set counter.\n");
     UseLoopGuard |= ForceGuardLoopEntry;
   } else
@@ -406,19 +401,19 @@ 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(ExitCount, Predecessor->getTerminator(), SE))
+    if (!isSafeToExpandAt(TripCount, Predecessor->getTerminator(), SE))
         UseLoopGuard = false;
     else
         BB = Predecessor;
   }
 
-  if (!isSafeToExpandAt(ExitCount, BB->getTerminator(), SE)) {
-    LLVM_DEBUG(dbgs() << "- Bailing, unsafe to expand ExitCount "
-               << *ExitCount << "\n");
+  if (!isSafeToExpandAt(TripCount, BB->getTerminator(), SE)) {
+    LLVM_DEBUG(dbgs() << "- Bailing, unsafe to expand TripCount "
+               << *TripCount << "\n");
     return nullptr;
   }
 
-  Value *Count = SCEVE.expandCodeFor(ExitCount, CountType,
+  Value *Count = SCEVE.expandCodeFor(TripCount, CountType,
                                      BB->getTerminator());
 
   // FIXME: We've expanded Count where we hope to insert the counter setting

diff  --git a/llvm/test/CodeGen/PowerPC/shrink-wrap.ll b/llvm/test/CodeGen/PowerPC/shrink-wrap.ll
index 74a83fee14e8..8bdba1e3ea3e 100644
--- a/llvm/test/CodeGen/PowerPC/shrink-wrap.ll
+++ b/llvm/test/CodeGen/PowerPC/shrink-wrap.ll
@@ -32,9 +32,7 @@ entry:
 ; CHECK:         std 
 ; CHECK:         blt 0, .LBB0_3
 ; CHECK:       # %bb.1:
-; CHECK-NEXT:    addi
 ; CHECK-NEXT:    clrldi
-; CHECK-NEXT:    addi
 ; CHECK-NEXT:    mtctr
 ; CHECK-NEXT:    li 
 ; CHECK:       .LBB0_2: