[LoopUnrolling] Fix loop size check for peeling

Summary:
We should check if loop size allows us to peel at least one iteration
before we do so.

Patch by Max Kazantsev!

Reviewers: sanjoy, mkuper, efriedma

Reviewed By: mkuper

Subscribers: llvm-commits

Differential Revision: https://reviews.llvm.org/D30632

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@297122 91177308-0d34-0410-b5e6-96231b3b80d8

lib/Transforms/Utils/LoopUnrollPeel.cpp

@@ -75,7 +75,9 @@ void llvm::computePeelCount(Loop *L, unsigned LoopSize,
   // its only back edge. If there is such Phi, peeling 1 iteration from the
   // loop is profitable, because starting from 2nd iteration we will have an
   // invariant instead of this Phi.
-  if (auto *BackEdge = L->getLoopLatch()) {
+  if (LoopSize <= UP.Threshold) {
+    BasicBlock *BackEdge = L->getLoopLatch();
+    assert(BackEdge && "Loop is not in simplified form?");
     BasicBlock *Header = L->getHeader();
     // Iterate over Phis to find one with invariant input on back edge.
     bool FoundCandidate = false;

test/Transforms/LoopUnroll/peel-loop-not-forced.ll

@@ -1,4 +1,4 @@
-; RUN: opt < %s -S -loop-unroll | FileCheck %s
+; RUN: opt < %s -S -loop-unroll -unroll-threshold=4 | FileCheck %s
 
 define i32 @invariant_backedge_1(i32 %a, i32 %b) {
 ; CHECK-LABEL: @invariant_backedge_1
@@ -18,6 +18,34 @@ loop:
   %incsum = add i32 %sum, %plus
   %inc = add i32 %i, 1
   %cmp = icmp slt i32 %i, 1000
+
+  br i1 %cmp, label %loop, label %exit
+
+exit:
+  ret i32 %sum
+}
+
+; Peeling should fail due to method size.
+define i32 @invariant_backedge_2(i32 %a, i32 %b) {
+; CHECK-LABEL: @invariant_backedge_2
+; CHECK-NOT:   loop.peel:
+; CHECK:       loop:
+; CHECK:         %i = phi
+; CHECK:         %sum = phi
+; CHECK:         %plus = phi
+entry:
+  br label %loop
+
+loop:
+  %i = phi i32 [ 0, %entry ], [ %inc, %loop ]
+  %sum = phi i32 [ 0, %entry ], [ %incsum2, %loop ]
+  %plus = phi i32 [ %a, %entry ], [ %b, %loop ]
+
+  %incsum = add i32 %sum, %plus
+  %incsum2 = add i32 %incsum, %plus
+  %inc = add i32 %i, 1
+  %cmp = icmp slt i32 %i, 1000
+
   br i1 %cmp, label %loop, label %exit
 
 exit: