[Loop Peeling] Enable peeling for loops with multiple exits

This CL enables peeling of the loop with multiple exits where
one exit should be from latch and others are basic blocks with
call to deopt.

The peeling is enabled under the flag which is false by default.

Reviewers: reames, mkuper, iajbar, fhahn
Reviewed By: reames
Subscribers: xbolva00, hiraditya, zzheng, llvm-commits
Differential Revision: https://reviews.llvm.org/D63923

llvm-svn: 366048

llvm/lib/Transforms/Utils/LoopUnroll.cpp

@@ -402,7 +402,8 @@ LoopUnrollResult llvm::UnrollLoop(Loop *L, UnrollLoopOptions ULO, LoopInfo *LI,
     // counts. If we later unroll the loop, we want these to be updated.
     if (Peeled) {
       // According to our guards and profitability checks the only
-      // meaningful exit should be latch block.
+      // meaningful exit should be latch block. Other exits go to deopt,
+      // so we do not worry about them.
       BasicBlock *ExitingBlock = L->getLoopLatch();
       assert(ExitingBlock && "Loop without exiting block?");
       assert(L->isLoopExiting(ExitingBlock) && "Latch is not exiting?");

llvm/lib/Transforms/Utils/LoopUnrollPeel.cpp

@@ -61,6 +61,10 @@ static cl::opt<unsigned> UnrollForcePeelCount(
     "unroll-force-peel-count", cl::init(0), cl::Hidden,
     cl::desc("Force a peel count regardless of profiling information."));
 
+static cl::opt<bool> UnrollPeelMultiDeoptExit(
+    "unroll-peel-multi-deopt-exit", cl::init(false), cl::Hidden,
+    cl::desc("Allow peeling of loops with multiple deopt exits."));
+
 // Designates that a Phi is estimated to become invariant after an "infinite"
 // number of loop iterations (i.e. only may become an invariant if the loop is
 // fully unrolled).
@@ -73,6 +77,22 @@ bool llvm::canPeel(Loop *L) {
   if (!L->isLoopSimplifyForm())
     return false;
 
+  if (UnrollPeelMultiDeoptExit) {
+    SmallVector<BasicBlock *, 4> Exits;
+    L->getUniqueNonLatchExitBlocks(Exits);
+
+    if (!Exits.empty()) {
+      // Latch's terminator is a conditional branch, Latch is exiting and
+      // all non Latch exits ends up with deoptimize.
+      const BasicBlock *Latch = L->getLoopLatch();
+      const BranchInst *T = dyn_cast<BranchInst>(Latch->getTerminator());
+      return T && T->isConditional() && L->isLoopExiting(Latch) &&
+             all_of(Exits, [](const BasicBlock *BB) {
+               return BB->getTerminatingDeoptimizeCall();
+             });
+    }
+  }
+
   // Only peel loops that contain a single exit
   if (!L->getExitingBlock() || !L->getUniqueExitBlock())
     return false;

llvm/test/Transforms/LoopUnroll/peel-loop-pgo-deopt.ll

@@ -0,0 +1,80 @@
+; RUN: opt < %s -S -debug-only=loop-unroll -loop-unroll -unroll-runtime -unroll-peel-multi-deopt-exit 2>&1 | FileCheck %s
+; RUN: opt < %s -S -debug-only=loop-unroll -unroll-peel-multi-deopt-exit -passes='require<profile-summary>,function(require<opt-remark-emit>,unroll)' 2>&1 | FileCheck %s
+
+; Make sure we use the profile information correctly to peel-off 3 iterations
+; from the loop, and update the branch weights for the peeled loop properly.
+
+; CHECK: Loop Unroll: F[basic]
+; CHECK: PEELING loop %for.body with iteration count 3!
+
+; CHECK-LABEL: @basic
+; CHECK: br i1 %{{.*}}, label %[[NEXT0:.*]], label %for.cond.for.end_crit_edge, !prof !16
+; CHECK: [[NEXT0]]:
+; CHECK: br i1 %{{.*}}, label %[[NEXT1:.*]], label %for.cond.for.end_crit_edge, !prof !17
+; CHECK: [[NEXT1]]:
+; CHECK: br i1 %{{.*}}, label %[[NEXT2:.*]], label %for.cond.for.end_crit_edge, !prof !18
+; CHECK: [[NEXT2]]:
+; CHECK: br i1 %{{.*}}, label %for.body, label %{{.*}}, !prof !19
+
+define i32 @basic(i32* %p, i32 %k, i1 %c) #0 !prof !15 {
+entry:
+  %cmp3 = icmp slt i32 0, %k
+  br i1 %cmp3, label %for.body.lr.ph, label %for.end
+
+for.body.lr.ph:                                   ; preds = %entry
+  br label %for.body
+
+for.body:                                         ; preds = %for.body.lr.ph, %for.body
+  %i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %continue ]
+  %p.addr.04 = phi i32* [ %p, %for.body.lr.ph ], [ %incdec.ptr, %continue ]
+  %incdec.ptr = getelementptr inbounds i32, i32* %p.addr.04, i32 1
+  store i32 %i.05, i32* %p.addr.04, align 4
+  %inc = add nsw i32 %i.05, 1
+  %cmp = icmp slt i32 %inc, %k
+  br i1 %c, label %continue, label %side_exit, !prof !17
+
+continue:
+  br i1 %cmp, label %for.body, label %for.cond.for.end_crit_edge, !prof !16
+
+for.cond.for.end_crit_edge:                       ; preds = %for.body
+  br label %for.end
+
+for.end:                                          ; preds = %for.cond.for.end_crit_edge, %entry
+  %res = phi i32 [ 0, %entry ], [ %inc, %for.cond.for.end_crit_edge ]
+  ret i32 %res
+
+side_exit:
+  %rval = call i32(...) @llvm.experimental.deoptimize.i32() [ "deopt"(i32 %inc) ]
+  ret i32 %rval
+}
+
+declare i32 @llvm.experimental.deoptimize.i32(...)
+
+attributes #0 = { nounwind }
+attributes #1 = { nounwind optsize }
+
+!llvm.module.flags = !{!1}
+
+!1 = !{i32 1, !"ProfileSummary", !2}
+!2 = !{!3, !4, !5, !6, !7, !8, !9, !10}
+!3 = !{!"ProfileFormat", !"InstrProf"}
+!4 = !{!"TotalCount", i64 10}
+!5 = !{!"MaxCount", i64 3}
+!6 = !{!"MaxInternalCount", i64 1}
+!7 = !{!"MaxFunctionCount", i64 3}
+!8 = !{!"NumCounts", i64 2}
+!9 = !{!"NumFunctions", i64 2}
+!10 = !{!"DetailedSummary", !11}
+!11 = !{!12, !13, !14}
+!12 = !{i32 10000, i64 3, i32 2}
+!13 = !{i32 999000, i64 1, i32 10}
+!14 = !{i32 999999, i64 1, i32 10}
+!15 = !{!"function_entry_count", i64 1}
+!16 = !{!"branch_weights", i32 3001, i32 1001}
+!17 = !{!"branch_weights", i32 1, i32 0}
+
+;CHECK: !16 = !{!"branch_weights", i32 900, i32 101}
+;CHECK: !17 = !{!"branch_weights", i32 540, i32 360}
+;CHECK: !18 = !{!"branch_weights", i32 162, i32 378}
+;CHECK: !19 = !{!"branch_weights", i32 1399, i32 162}
+