[llvm] 262f2fe - [IndVars] Use symbolic max block exit count to handle the last iter

[Max Kazantsev via llvm-commits]

Author: Max Kazantsev
Date: 2022-12-09T17:06:29+07:00
New Revision: 262f2fed65b83ba9b64227b983d5ed95883fd71e

URL: https://github.com/llvm/llvm-project/commit/262f2fed65b83ba9b64227b983d5ed95883fd71e
DIFF: https://github.com/llvm/llvm-project/commit/262f2fed65b83ba9b64227b983d5ed95883fd71e.diff

LOG: [IndVars] Use symbolic max block exit count to handle the last iter

Old logic: when loop symbolic max exit count matched *exact* block exit count,
assume that all subsequent blocks will do 1 iteration less.

New logic: when loop symbolic max exit count matched *symbolic max* block exit count,
assume that all subsequent blocks will do 1 iteration less.

The new logic is still legal and is more permissive in situations when exact
block exit count is not known.

Differential Revision: https://reviews.llvm.org/D139692
Reviewed By: nikic

Added: 
    

Modified: 
    llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
    llvm/test/Transforms/IndVarSimplify/turn-to-invariant.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
index 26871295b025a..1bfecb829f493 100644
--- a/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
+++ b/llvm/lib/Transforms/Scalar/IndVarSimplify.cpp
@@ -1632,6 +1632,8 @@ bool IndVarSimplify::optimizeLoopExits(Loop *L, SCEVExpander &Rewriter) {
   SmallSet<const SCEV *, 8> DominatingExactExitCounts;
   for (BasicBlock *ExitingBB : ExitingBlocks) {
     const SCEV *ExactExitCount = SE->getExitCount(L, ExitingBB);
+    const SCEV *MaxExitCount = SE->getExitCount(
+        L, ExitingBB, ScalarEvolution::ExitCountKind::SymbolicMaximum);
     if (isa<SCEVCouldNotCompute>(ExactExitCount)) {
       // Okay, we do not know the exit count here. Can we at least prove that it
       // will remain the same within iteration space?
@@ -1663,10 +1665,14 @@ bool IndVarSimplify::optimizeLoopExits(Loop *L, SCEVExpander &Rewriter) {
       else if (SkipLastIter)
         if (OptimizeCond(false, true) || OptimizeCond(true, true))
           Changed = true;
+      if (MaxBECount == MaxExitCount)
+        // If the loop has more than 1 iteration, all further checks will be
+        // executed 1 iteration less.
+        SkipLastIter = true;
       continue;
     }
 
-    if (MaxBECount == ExactExitCount)
+    if (MaxBECount == MaxExitCount)
       // If the loop has more than 1 iteration, all further checks will be
       // executed 1 iteration less.
       SkipLastIter = true;

diff  --git a/llvm/test/Transforms/IndVarSimplify/turn-to-invariant.ll b/llvm/test/Transforms/IndVarSimplify/turn-to-invariant.ll
index 7ef57bd9123b0..b43858ce1b880 100644
--- a/llvm/test/Transforms/IndVarSimplify/turn-to-invariant.ll
+++ b/llvm/test/Transforms/IndVarSimplify/turn-to-invariant.ll
@@ -120,22 +120,20 @@ failed_2:
   ret i32 -2
 }
 
-
-; TODO: Simplified version 1 of test_litter_conditions.
 define i32 @test_litter_conditions_01(i32 %start, i32 %len) {
 ; CHECK-LABEL: @test_litter_conditions_01(
 ; CHECK-NEXT:  entry:
+; CHECK-NEXT:    [[TMP0:%.*]] = add i32 [[START:%.*]], -1
 ; CHECK-NEXT:    br label [[LOOP:%.*]]
 ; CHECK:       loop:
-; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[START:%.*]], [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ]
+; CHECK-NEXT:    [[IV:%.*]] = phi i32 [ [[START]], [[ENTRY:%.*]] ], [ [[IV_NEXT:%.*]], [[BACKEDGE:%.*]] ]
 ; CHECK-NEXT:    [[ZERO_CHECK:%.*]] = icmp ne i32 [[IV]], 0
 ; CHECK-NEXT:    [[FAKE_1:%.*]] = call i1 @cond()
 ; CHECK-NEXT:    [[AND_1:%.*]] = and i1 [[ZERO_CHECK]], [[FAKE_1]]
 ; CHECK-NEXT:    br i1 [[AND_1]], label [[RANGE_CHECK_BLOCK:%.*]], label [[FAILED_1:%.*]]
 ; CHECK:       range_check_block:
-; CHECK-NEXT:    [[IV_MINUS_1:%.*]] = add i32 [[IV]], -1
-; CHECK-NEXT:    [[RANGE_CHECK:%.*]] = icmp ult i32 [[IV_MINUS_1]], [[LEN:%.*]]
-; CHECK-NEXT:    br i1 [[RANGE_CHECK]], label [[BACKEDGE]], label [[FAILED_2:%.*]]
+; CHECK-NEXT:    [[RANGE_CHECK3:%.*]] = icmp ult i32 [[TMP0]], [[LEN:%.*]]
+; CHECK-NEXT:    br i1 [[RANGE_CHECK3]], label [[BACKEDGE]], label [[FAILED_2:%.*]]
 ; CHECK:       backedge:
 ; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[IV]], -1
 ; CHECK-NEXT:    [[LOOP_COND:%.*]] = call i1 @cond()