[LV] Make test more robust by adding users of inductions.

The modified tests didn't have actual users of all inductions, making it
trivial to eliminate them. Add users to make sure the inductions are
actually used in the vectorized version.

Author: fhahn

llvm/test/Transforms/LoopVectorize/X86/pr36524.ll

@@ -2,30 +2,44 @@
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128-ni:1"
 
-define void @foo() {
+define void @foo(i64* %ptr, i32* %ptr.2) {
 ; CHECK-LABEL: @foo(
 ; CHECK:       vector.body:
 ; CHECK-NEXT:    [[INDEX:%.*]] = phi i64 [ 0, [[VECTOR_PH:%.*]] ], [ [[INDEX_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
 ; CHECK-NEXT:    [[VEC_IND:%.*]] = phi <4 x i64> [ <i64 2, i64 3, i64 4, i64 5>, [[VECTOR_PH]] ], [ [[VEC_IND_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[VEC_IND_TRUNC:%.+]] = phi <4 x i32> [ <i32 2, i32 3, i32 4, i32 5>, %vector.ph ], [ [[VEC_IND_TRUNC_NEXT:%.+]], %vector.body ]
+; CHECK-NEXT:    = add i64 [[INDEX]], 0
 ; CHECK-NEXT:    [[OFFSET_IDX:%.*]] = add i64 2, [[INDEX]]
-; CHECK-NEXT:    [[TMP7:%.*]] = add i64 [[OFFSET_IDX]], 0
-; CHECK-NEXT:    [[TMP8:%.*]] = add i64 [[OFFSET_IDX]], 1
-; CHECK-NEXT:    [[TMP9:%.*]] = add i64 [[OFFSET_IDX]], 2
-; CHECK-NEXT:    [[TMP10:%.*]] = add i64 [[OFFSET_IDX]], 3
+; CHECK-NEXT:    [[TRUNC:%.+]] = trunc i64 [[OFFSET_IDX]] to i32
+; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[TRUNC]], 0
+; CHECK-NEXT:    [[TMP8:%.*]] = add i32 [[TRUNC]], 1
+; CHECK-NEXT:    [[TMP9:%.*]] = add i32 [[TRUNC]], 2
+; CHECK-NEXT:    [[TMP10:%.*]] = add i32 [[TRUNC]], 3
+; CHECK-NEXT:    store i32 [[TMP7]], i32* %ptr.2, align 4
+; CHECK-NEXT:    store i32 [[TMP8]], i32* %ptr.2, align 4
+; CHECK-NEXT:    store i32 [[TMP9]], i32* %ptr.2, align 4
+; CHECK-NEXT:    store i32 [[TMP10]], i32* %ptr.2, align 4
+; CHECK:         store <4 x i64> [[VEC_IND]]
 ; CHECK-NEXT:    [[INDEX_NEXT]] = add nuw i64 [[INDEX]], 4
 ; CHECK-NEXT:    [[VEC_IND_NEXT]] = add <4 x i64> [[VEC_IND]], <i64 4, i64 4, i64 4, i64 4>
+; CHECK-NEXT:    [[VEC_IND_TRUNC_NEXT]] = add <4 x i32> [[VEC_IND_TRUNC]], <i32 4, i32 4, i32 4, i32 4>
 ; CHECK-NEXT:    [[TMP13:%.*]] = icmp eq i64 [[INDEX_NEXT]], 80
-; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+; CHECK-NEXT:    br i1 [[TMP13]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]]
 ;
 entry:
   br label %loop
 
 loop:
+  %can.iv = phi i64 [ 0, %entry ], [ %can.iv.next, %loop ]
   %0 = phi i64 [ 2, %entry ], [ %3, %loop ]
   %1 = and i64 %0, 4294967295
   %2 = trunc i64 %0 to i32
+  store i32 %2, i32* %ptr.2
+  %gep.ptr = getelementptr inbounds i64, i64* %ptr, i64 %can.iv
+  store i64 %0, i64* %gep.ptr
   %3 = add nuw nsw i64 %1, 1
   %4 = icmp sgt i32 %2, 80
+  %can.iv.next = add nuw nsw i64 %can.iv, 1
   br i1 %4, label %exit, label %loop
 
 exit:

llvm/test/Transforms/LoopVectorize/pr35773.ll

@@ -1,10 +1,31 @@
 ; RUN: opt -S -loop-vectorize -force-vector-width=4 -force-vector-interleave=1 < %s 2>&1 | FileCheck %s
+
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
-@a = common local_unnamed_addr global i32 0, align 4
 @b = common local_unnamed_addr global i8 0, align 1
 
-; Function Attrs: norecurse nounwind uwtable
-define void @doit1() local_unnamed_addr{
+define void @doit1(i32* %ptr) {
+; CHECK-LABEL: @doit1(
+; CHECK:       vector.body:
+; CHECK-NEXT:    [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
+; CHECK-NEXT:    [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
+; CHECK-NEXT:    [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
+
+; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
+
+; CHECK-NEXT:    [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]
+
+; CHECK-NEXT:    [[GEP1:%.+]] = getelementptr inbounds i32, i32* %ptr, i32 [[TMP7]]
+; CHECK-NEXT:    [[GEP2:%.+]] = getelementptr inbounds i32, i32* [[GEP1]], i32 0
+; CHECK-NEXT:    [[GEP_BC:%.+]] = bitcast i32* [[GEP2]] to <4 x i32>*
+; CHECK-NEXT:    store <4 x i32> [[I32_IV]], <4 x i32>* [[GEP_BC]], align 4
+
+; CHECK-NEXT:    [[MAIN_IV_NEXT]] = add nuw i32 [[MAIN_IV]], 4
+; CHECK-NEXT:    [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>
+; CHECK-NEXT:    [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>
+; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16
+; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
+;
 entry:
   br label %for.body
 
@@ -17,30 +38,15 @@ for.body:
   %trunc.to.be.converted.to.new.iv = trunc i32 %i32.iv to i8
   %i8.add = add i8 %i8.iv, %trunc.to.be.converted.to.new.iv
 
+  %ptr.gep = getelementptr inbounds i32, i32* %ptr, i32 %main.iv
+  store i32 %i32.iv, i32* %ptr.gep
   %noop.conv.under.pse = and i32 %i32.iv, 255
   %i32.add = add nuw nsw i32 %noop.conv.under.pse, 9
 
   %inc = add i32 %main.iv, 1
   %tobool = icmp eq i32 %inc, 16
   br i1 %tobool, label %for.cond.for.end_crit_edge, label %for.body
 
-; CHECK-LABEL: @doit1(
-; CHECK:       vector.body:
-; CHECK-NEXT:    [[MAIN_IV:%.*]] = phi i32 [ 0, [[VECTOR_PH:%.*]] ], [ [[MAIN_IV_NEXT:%.*]], [[VECTOR_BODY:%.*]] ]
-; CHECK-NEXT:    [[I8_IV:%.*]] = phi <4 x i8> [ zeroinitializer, [[VECTOR_PH]] ], [ [[I8_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[I32_IV:%.*]] = phi <4 x i32> [ <i32 0, i32 9, i32 18, i32 27>, [[VECTOR_PH]] ], [ [[I32_IV_NEXT:%.*]], [[VECTOR_BODY]] ]
-; CHECK-NEXT:    [[IV_FROM_TRUNC:%.*]] = phi <4 x i8> [ <i8 0, i8 9, i8 18, i8 27>, [[VECTOR_PH]] ], [ [[IV_FROM_TRUNC_NEXT:%.*]], [[VECTOR_BODY]] ]
-
-; CHECK-NEXT:    [[TMP7:%.*]] = add i32 [[MAIN_IV]], 0
-
-; CHECK-NEXT:    [[I8_IV_NEXT]] = add <4 x i8> [[I8_IV]], [[IV_FROM_TRUNC]]
-
-; CHECK-NEXT:    [[MAIN_IV_NEXT]] = add nuw i32 [[MAIN_IV]], 4
-; CHECK-NEXT:    [[I32_IV_NEXT]] = add <4 x i32> [[I32_IV]], <i32 36, i32 36, i32 36, i32 36>
-; CHECK-NEXT:    [[IV_FROM_TRUNC_NEXT]] = add <4 x i8> [[IV_FROM_TRUNC]], <i8 36, i8 36, i8 36, i8 36>
-; CHECK-NEXT:    [[TMP9:%.*]] = icmp eq i32 [[MAIN_IV_NEXT]], 16
-; CHECK-NEXT:    br i1 [[TMP9]], label [[MIDDLE_BLOCK:%.*]], label [[VECTOR_BODY]], !llvm.loop !0
-
 for.cond.for.end_crit_edge:
   store i8 %i8.add, i8* @b, align 1
   br label %for.end