[llvm] [VPlan] Use BlockFrequencyInfo in getPredBlockCostDivisor (PR #158690)

[Florian Hahn via llvm-commits]

================
@@ -0,0 +1,154 @@
+; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --check-globals none --version 5
+; RUN: opt -p loop-vectorize -mtriple=aarch64 -mattr=+sve -S %s | FileCheck %s
+
+define void @nested(ptr noalias %p0, ptr noalias %p1, i1 %c0, i1 %c1) {
+; CHECK-LABEL: define void @nested(
+; CHECK-SAME: ptr noalias [[P0:%.*]], ptr noalias [[P1:%.*]], i1 [[C0:%.*]], i1 [[C1:%.*]]) #[[ATTR0:[0-9]+]] {
+; CHECK-NEXT:  [[ENTRY:.*]]:
+; CHECK-NEXT:    br label %[[LOOP:.*]]
+; CHECK:       [[LOOP]]:
+; CHECK-NEXT:    [[X:%.*]] = phi i32 [ 0, %[[ENTRY]] ], [ [[IV_NEXT:%.*]], %[[LATCH:.*]] ]
+; CHECK-NEXT:    br i1 [[C0]], label %[[THEN_0:.*]], label %[[LATCH]]
+; CHECK:       [[THEN_0]]:
+; CHECK-NEXT:    br i1 [[C1]], label %[[THEN_1:.*]], label %[[LATCH]]
+; CHECK:       [[THEN_1]]:
+; CHECK-NEXT:    [[GEP0:%.*]] = getelementptr i64, ptr [[P0]], i32 [[X]]
+; CHECK-NEXT:    [[X1:%.*]] = load i64, ptr [[GEP0]], align 8
+; CHECK-NEXT:    [[GEP1:%.*]] = getelementptr i64, ptr [[P1]], i32 [[X]]
+; CHECK-NEXT:    [[Y:%.*]] = load i64, ptr [[GEP1]], align 8
+; CHECK-NEXT:    [[Z:%.*]] = udiv i64 [[X1]], [[Y]]
+; CHECK-NEXT:    store i64 [[Z]], ptr [[GEP1]], align 8
+; CHECK-NEXT:    br label %[[LATCH]]
+; CHECK:       [[LATCH]]:
+; CHECK-NEXT:    [[IV_NEXT]] = add i32 [[X]], 1
+; CHECK-NEXT:    [[DONE:%.*]] = icmp eq i32 [[IV_NEXT]], 1024
+; CHECK-NEXT:    br i1 [[DONE]], label %[[EXIT:.*]], label %[[LOOP]]
+; CHECK:       [[EXIT]]:
+; CHECK-NEXT:    ret void
+;
+entry:
+  br label %loop
+
+loop:
+  %iv = phi i32 [ 0, %entry ], [ %iv.next, %latch ]
+  br i1 %c0, label %then.0, label %latch
+
+then.0:
+  br i1 %c1, label %then.1, label %latch
+
+then.1:
+  %gep0 = getelementptr i64, ptr %p0, i32 %iv
+  %x = load i64, ptr %gep0
+  %gep1 = getelementptr i64, ptr %p1, i32 %iv
+  %y = load i64, ptr %gep1
+  %z = udiv i64 %x, %y
+  store i64 %z, ptr %gep1
+  br label %latch
+
+latch:
+  %iv.next = add i32 %iv, 1
+  %done = icmp eq i32 %iv.next, 1024
+  br i1 %done, label %exit, label %loop
+
+exit:
+  ret void
+}
+
+define void @always_taken(ptr noalias %p0, ptr noalias %p1, i1 %c0, i1 %c1) {
----------------
fhahn wrote:

Could you add a comment on why this should be vectorized (!prof metadata)

https://github.com/llvm/llvm-project/pull/158690