[LV] Make test case more robust

This test case depends on the loop being vectorized without forcing the
vectorization factor. If the profitability ever changes in the future (due to
cost model improvements), the test may no longer work as intended. Instead of
checking the resulting IR, we should just check the instruction costs. The
costs will be computed regardless if vectorization is profitable.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@299545 91177308-0d34-0410-b5e6-96231b3b80d8

test/Transforms/LoopVectorize/AArch64/aarch64-predication.ll

@@ -1,40 +1,55 @@
-; RUN: opt < %s -loop-vectorize -simplifycfg -S | FileCheck %s
-; RUN: opt < %s -force-vector-width=2 -loop-vectorize -simplifycfg -S | FileCheck %s
+; REQUIRES: asserts
+; RUN: opt < %s -loop-vectorize -disable-output -debug-only=loop-vectorize 2>&1 | FileCheck %s --check-prefix=COST
+; RUN: opt < %s -loop-vectorize -force-vector-width=2 -instcombine -simplifycfg -S | FileCheck %s
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 target triple = "aarch64--linux-gnu"
 
-; CHECK-LABEL: predicated_udiv_scalarized_operand
-;
 ; This test checks that we correctly compute the scalarized operands for a
 ; user-specified vectorization factor when interleaving is disabled. We use the
-; "optsize" attribute to disable all interleaving calculations.
+; "optsize" attribute to disable all interleaving calculations.  A cost of 4
+; for %tmp4 indicates that we would scalarize it's operand (%tmp3), giving
+; %tmp4 a lower scalarization overhead.
 ;
-; CHECK: vector.body:
-; CHECK:   %wide.load = load <2 x i64>, <2 x i64>* {{.*}}, align 4
-; CHECK:   br i1 {{.*}}, label %[[IF0:.+]], label %[[CONT0:.+]]
-; CHECK: [[IF0]]:
-; CHECK:   %[[T00:.+]] = extractelement <2 x i64> %wide.load, i32 0
-; CHECK:   %[[T01:.+]] = extractelement <2 x i64> %wide.load, i32 0
-; CHECK:   %[[T02:.+]] = add nsw i64 %[[T01]], %x
-; CHECK:   %[[T03:.+]] = udiv i64 %[[T00]], %[[T02]]
-; CHECK:   %[[T04:.+]] = insertelement <2 x i64> undef, i64 %[[T03]], i32 0
-; CHECK:   br label %[[CONT0]]
-; CHECK: [[CONT0]]:
-; CHECK:   %[[T05:.+]] = phi <2 x i64> [ undef, %vector.body ], [ %[[T04]], %[[IF0]] ]
-; CHECK:   br i1 {{.*}}, label %[[IF1:.+]], label %[[CONT1:.+]]
-; CHECK: [[IF1]]:
-; CHECK:   %[[T06:.+]] = extractelement <2 x i64> %wide.load, i32 1
-; CHECK:   %[[T07:.+]] = extractelement <2 x i64> %wide.load, i32 1
-; CHECK:   %[[T08:.+]] = add nsw i64 %[[T07]], %x
-; CHECK:   %[[T09:.+]] = udiv i64 %[[T06]], %[[T08]]
-; CHECK:   %[[T10:.+]] = insertelement <2 x i64> %[[T05]], i64 %[[T09]], i32 1
-; CHECK:   br label %[[CONT1]]
-; CHECK: [[CONT1]]:
-; CHECK:   phi <2 x i64> [ %[[T05]], %[[CONT0]] ], [ %[[T10]], %[[IF1]] ]
-; CHECK:   br i1 {{.*}}, label %middle.block, label %vector.body
-
-define i64 @predicated_udiv_scalarized_operand(i64* %a, i1 %c, i64 %x) optsize {
+; COST-LABEL:  predicated_udiv_scalarized_operand
+; COST:        LV: Found an estimated cost of 4 for VF 2 For instruction: %tmp4 = udiv i64 %tmp2, %tmp3
+;
+; CHECK-LABEL: @predicated_udiv_scalarized_operand(
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, %entry ], [ [[INDEX_NEXT:%.*]], %[[PRED_UDIV_CONTINUE2:.*]] ]
+; CHECK-NEXT:    [[VEC_PHI:%.*]] = phi <2 x i64> [ zeroinitializer, %entry ], [ [[TMP17:%.*]], %[[PRED_UDIV_CONTINUE2]] ]
+; CHECK-NEXT:    [[TMP0:%.*]] = getelementptr inbounds i64, i64* %a, i64 [[INDEX]]
+; CHECK-NEXT:    [[TMP1:%.*]] = bitcast i64* [[TMP0]] to <2 x i64>*
+; CHECK-NEXT:    [[WIDE_LOAD:%.*]] = load <2 x i64>, <2 x i64>* [[TMP1]], align 4
+; CHECK-NEXT:    [[TMP2:%.*]] = icmp sgt <2 x i64> [[WIDE_LOAD]], zeroinitializer
+; CHECK-NEXT:    [[TMP3:%.*]] = extractelement <2 x i1> [[TMP2]], i32 0
+; CHECK-NEXT:    br i1 [[TMP3]], label %[[PRED_UDIV_IF:.*]], label %[[PRED_UDIV_CONTINUE:.*]]
+; CHECK:       [[PRED_UDIV_IF]]:
+; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 0
+; CHECK-NEXT:    [[TMP5:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 0
+; CHECK-NEXT:    [[TMP6:%.*]] = add nsw i64 [[TMP5]], %x
+; CHECK-NEXT:    [[TMP7:%.*]] = udiv i64 [[TMP4]], [[TMP6]]
+; CHECK-NEXT:    [[TMP8:%.*]] = insertelement <2 x i64> undef, i64 [[TMP7]], i32 0
+; CHECK-NEXT:    br label %[[PRED_UDIV_CONTINUE]]
+; CHECK:       [[PRED_UDIV_CONTINUE]]:
+; CHECK-NEXT:    [[TMP9:%.*]] = phi <2 x i64> [ undef, %vector.body ], [ [[TMP8]], %[[PRED_UDIV_IF]] ]
+; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x i1> [[TMP2]], i32 1
+; CHECK-NEXT:    br i1 [[TMP10]], label %[[PRED_UDIV_IF1:.*]], label %[[PRED_UDIV_CONTINUE2]]
+; CHECK:       [[PRED_UDIV_IF1]]:
+; CHECK-NEXT:    [[TMP11:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 1
+; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x i64> [[WIDE_LOAD]], i32 1
+; CHECK-NEXT:    [[TMP13:%.*]] = add nsw i64 [[TMP12]], %x
+; CHECK-NEXT:    [[TMP14:%.*]] = udiv i64 [[TMP11]], [[TMP13]]
+; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <2 x i64> [[TMP9]], i64 [[TMP14]], i32 1
+; CHECK-NEXT:    br label %[[PRED_UDIV_CONTINUE2]]
+; CHECK:       [[PRED_UDIV_CONTINUE2]]:
+; CHECK-NEXT:    [[TMP16:%.*]] = phi <2 x i64> [ [[TMP9]], %[[PRED_UDIV_CONTINUE]] ], [ [[TMP15]], %[[PRED_UDIV_IF1]] ]
+; CHECK-NEXT:    [[PREDPHI:%.*]] = select <2 x i1> [[TMP2]], <2 x i64> [[TMP16]], <2 x i64> [[WIDE_LOAD]]
+; CHECK-NEXT:    [[TMP17]] = add <2 x i64> [[VEC_PHI]], [[PREDPHI]]
+; CHECK-NEXT:    [[INDEX_NEXT]] = add i64 [[INDEX]], 2
+; CHECK:         br i1 {{.*}}, label %middle.block, label %vector.body
+;
+define i64 @predicated_udiv_scalarized_operand(i64* %a, i64 %x) optsize {
 entry:
   br label %for.body
 
@@ -43,7 +58,8 @@ for.body:
   %r = phi i64 [ 0, %entry ], [ %tmp6, %for.inc ]
   %tmp0 = getelementptr inbounds i64, i64* %a, i64 %i
   %tmp2 = load i64, i64* %tmp0, align 4
-  br i1 %c, label %if.then, label %for.inc
+  %cond0 = icmp sgt i64 %tmp2, 0
+  br i1 %cond0, label %if.then, label %for.inc
 
 if.then:
   %tmp3 = add nsw i64 %tmp2, %x
@@ -54,8 +70,8 @@ for.inc:
   %tmp5 = phi i64 [ %tmp2, %for.body ], [ %tmp4, %if.then]
   %tmp6 = add i64 %r, %tmp5
   %i.next = add nuw nsw i64 %i, 1
-  %cond = icmp slt i64 %i.next, 100
-  br i1 %cond, label %for.body, label %for.end
+  %cond1 = icmp slt i64 %i.next, 100
+  br i1 %cond1, label %for.body, label %for.end
 
 for.end:
   %tmp7 = phi i64 [ %tmp6, %for.inc ]