[Loop Peeling] Do not close further unroll/peel if profile based peeling was not used.

Current peeling cost model can decide to peel off not all iterations
but only some of them to eliminate conditions on phi. At the same time 
if any peeling happens the door for further unroll/peel optimizations on that
loop closes because the part of the code thinks that if peeling happened
it is profile based peeling and all iterations are peeled off.

To resolve this inconsistency the patch provides the flag which states whether
the full peeling basing on profile is enabled or not and peeling cost model
is able to modify this field like it does not PeelCount.

In a separate patch I will introduce an option to allow/disallow peeling basing
on profile.

To avoid infinite loop peeling the patch tracks the total number of peeled iteration
through llvm.loop.peeled.count loop metadata.

Reviewers: reames, fhahn
Reviewed By: reames
Subscribers: hiraditya, zzheng, dmgreen, llvm-commits
Differential Revision: https://reviews.llvm.org/D64972

llvm-svn: 367647

3 files changed, 87 insertions, 0 deletions

diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-1.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-1.ll
new file mode 100644
index 00000000000..0c56229d064
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-1.ll
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -S -loop-unroll -loop-unroll -verify-dom-info -debug-only=loop-unroll -unroll-peel-max-count=7 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+declare void @f1()
+declare void @f2()
+
+; Check that we can peel off iterations that make conditions true.
+; The second invocation of loop-unroll will do profile based peeling of
+; remained iterations.
+define void @test1(i32 %k) !prof !4 {
+; CHECK: Loop Unroll: F[test1] Loop %for.body
+; CHECK: PEELING loop %for.body with iteration count 2!
+; CHECK: PEELING loop %for.body with iteration count 4!
+; CHECK: llvm.loop.unroll.disable
+for.body.lr.ph:
+  br label %for.body
+
+for.body:
+  %i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %cmp1 = icmp ult i32 %i.05, 2
+  br i1 %cmp1, label %if.then, label %if.else
+
+if.then:
+  call void @f1()
+  br label %for.inc
+
+if.else:
+  call void @f2()
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.05, 1
+  %cmp = icmp slt i32 %inc, %k
+  br i1 %cmp, label %for.body, label %for.end, !llvm.loop !1, !prof !2
+
+for.end:
+  ret void
+}
+
+!1 = distinct !{!1}
+!2 = !{!"branch_weights", i32 6, i32 1}
+!4 = !{!"function_entry_count", i64 1}
diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-2.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-2.ll
new file mode 100644
index 00000000000..6462283dfaf
--- /dev/null
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions-pgo-2.ll
@@ -0,0 +1,43 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
+; RUN: opt < %s -S -loop-unroll -loop-unroll -verify-dom-info -debug-only=loop-unroll -unroll-peel-max-count=7 2>&1 | FileCheck %s
+; REQUIRES: asserts
+
+declare void @f1()
+declare void @f2()
+
+; Check that we can peel off iterations that make conditions true.
+; The second invocation of loop-unroll will NOT do profile based peeling of
+; remained iterations because the total number of peeled iterations exceeds
+; threashold specified with -unroll-peel-max-count=7.
+define void @test2(i32 %k) !prof !4 {
+; CHECK: Loop Unroll: F[test2] Loop %for.body
+; CHECK: PEELING loop %for.body with iteration count 2!
+; CHECK-NOT: llvm.loop.unroll.disable
+for.body.lr.ph:
+  br label %for.body
+
+for.body:
+  %i.05 = phi i32 [ 0, %for.body.lr.ph ], [ %inc, %for.inc ]
+  %cmp1 = icmp ult i32 %i.05, 2
+  br i1 %cmp1, label %if.then, label %if.else
+
+if.then:
+  call void @f1()
+  br label %for.inc
+
+if.else:
+  call void @f2()
+  br label %for.inc
+
+for.inc:
+  %inc = add nsw i32 %i.05, 1
+  %cmp = icmp slt i32 %inc, %k
+  br i1 %cmp, label %for.body, label %for.end, !llvm.loop !1, !prof !3
+
+for.end:
+  ret void
+}
+
+!1 = distinct !{!1}
+!3 = !{!"branch_weights", i32 8, i32 1}
+!4 = !{!"function_entry_count", i64 1}
diff --git a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
index a9937d9db99..0217e9384f9 100644
--- a/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
+++ b/llvm/test/Transforms/LoopUnroll/peel-loop-conditions.ll
@@ -643,3 +643,4 @@ for.inc:
 for.end:
   ret void
 }
+; CHECK-NOT: llvm.loop.unroll.disable
\ No newline at end of file