Index: llvm/lib/Target/ARM/ARMISelLowering.h
===================================================================
--- llvm/lib/Target/ARM/ARMISelLowering.h
+++ llvm/lib/Target/ARM/ARMISelLowering.h
@@ -536,7 +536,7 @@
Instruction *emitTrailingFence(IRBuilder<> &Builder, Instruction *Inst,
AtomicOrdering Ord) const override;
- unsigned getMaxSupportedInterleaveFactor() const override { return 4; }
+ unsigned getMaxSupportedInterleaveFactor() const override;
bool lowerInterleavedLoad(LoadInst *LI,
ArrayRef<ShuffleVectorInst *> Shuffles,
Index: llvm/lib/Target/ARM/ARMISelLowering.cpp
===================================================================
--- llvm/lib/Target/ARM/ARMISelLowering.cpp
+++ llvm/lib/Target/ARM/ARMISelLowering.cpp
@@ -16198,6 +16198,13 @@
return VecSize == 64 || VecSize % 128 == 0;
}
+unsigned ARMTargetLowering::getMaxSupportedInterleaveFactor() const
+{
+ if (Subtarget->hasNEON())
+ return 4;
+ return TargetLoweringBase::getMaxSupportedInterleaveFactor();
+}
+
/// Lower an interleaved load into a vldN intrinsic.
///
/// E.g. Lower an interleaved load (Factor = 2):
Index: llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
===================================================================
--- llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
+++ llvm/test/Transforms/LoopVectorize/ARM/mve-interleaved-cost.ll
@@ -121,19 +121,19 @@
br label %for.body
; VF_8-LABEL: Checking a loop in "i8_factor_3"
-; VF_8: Found an estimated cost of 3 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_8: Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_8-NEXT: Found an estimated cost of 3 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_8-NEXT: Found an estimated cost of 216 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
; VF_16-LABEL: Checking a loop in "i8_factor_3"
-; VF_16: Found an estimated cost of 3 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
+; VF_16: Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp0, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp1, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp2, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
-; VF_16-NEXT: Found an estimated cost of 3 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
+; VF_16-NEXT: Found an estimated cost of 816 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i8.3, %i8.3* %data, i64 %i, i32 0
@@ -159,26 +159,26 @@
br label %for.body
; VF_4-LABEL: Checking a loop in "i16_factor_3"
-; VF_4: Found an estimated cost of 3 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_4: Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_4-NEXT: Found an estimated cost of 3 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_4-NEXT: Found an estimated cost of 60 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
; VF_8-LABEL: Checking a loop in "i16_factor_3"
-; VF_8: Found an estimated cost of 3 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_8: Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_8-NEXT: Found an estimated cost of 3 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_8-NEXT: Found an estimated cost of 216 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
; VF_16-LABEL: Checking a loop in "i16_factor_3"
-; VF_16: Found an estimated cost of 6 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
+; VF_16: Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i16, i16* %tmp0, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp1, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp2, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp1, align 2
-; VF_16-NEXT: Found an estimated cost of 6 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
+; VF_16-NEXT: Found an estimated cost of 816 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i16.3, %i16.3* %data, i64 %i, i32 0
@@ -204,33 +204,33 @@
br label %for.body
; VF_2-LABEL: Checking a loop in "i32_factor_3"
-; VF_2: Found an estimated cost of 3 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_2: Found an estimated cost of 30 for VF 2 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_2-NEXT: Found an estimated cost of 3 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_2-NEXT: Found an estimated cost of 18 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
; VF_4-LABEL: Checking a loop in "i32_factor_3"
-; VF_4: Found an estimated cost of 3 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_4: Found an estimated cost of 108 for VF 4 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_4-NEXT: Found an estimated cost of 3 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_4-NEXT: Found an estimated cost of 60 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4
; VF_8-LABEL: Checking a loop in "i32_factor_3"
-; VF_8: Found an estimated cost of 6 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_8: Found an estimated cost of 408 for VF 8 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_8-NEXT: Found an estimated cost of 6 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_8-NEXT: Found an estimated cost of 216 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
; VF_16-LABEL: Checking a loop in "i32_factor_3"
-; VF_16: Found an estimated cost of 12 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
+; VF_16: Found an estimated cost of 1584 for VF 16 For instruction: %tmp3 = load i32, i32* %tmp0, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp1, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp2, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp1, align 4
-; VF_16-NEXT: Found an estimated cost of 12 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
+; VF_16-NEXT: Found an estimated cost of 816 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i32.3, %i32.3* %data, i64 %i, i32 0
@@ -257,23 +257,23 @@
br label %for.body
; VF_8-LABEL: Checking a loop in "i8_factor_4"
-; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_8: Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp0, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_8-NEXT: Found an estimated cost of 288 for VF 8 For instruction: store i8 0, i8* %tmp3, align 1
; VF_16-LABEL: Checking a loop in "i8_factor_4"
-; VF_16: Found an estimated cost of 4 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
+; VF_16: Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i8, i8* %tmp0, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i8, i8* %tmp1, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i8, i8* %tmp2, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i8, i8* %tmp3, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp0, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i8 0, i8* %tmp2, align 1
-; VF_16-NEXT: Found an estimated cost of 4 for VF 16 For instruction: store i8 0, i8* %tmp3, align 1
+; VF_16-NEXT: Found an estimated cost of 1088 for VF 16 For instruction: store i8 0, i8* %tmp3, align 1
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i8.4, %i8.4* %data, i64 %i, i32 0
@@ -302,32 +302,32 @@
br label %for.body
; VF_4-LABEL: Checking a loop in "i16_factor_4"
-; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_4: Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp0, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp1, align 2
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_4-NEXT: Found an estimated cost of 80 for VF 4 For instruction: store i16 0, i16* %tmp3, align 2
; VF_8-LABEL: Checking a loop in "i16_factor_4"
-; VF_8: Found an estimated cost of 4 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_8: Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp0, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp1, align 2
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_8-NEXT: Found an estimated cost of 4 for VF 8 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_8-NEXT: Found an estimated cost of 288 for VF 8 For instruction: store i16 0, i16* %tmp3, align 2
; VF_16-LABEL: Checking a loop in "i16_factor_4"
-; VF_16: Found an estimated cost of 8 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
+; VF_16: Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i16, i16* %tmp0, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i16, i16* %tmp1, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i16, i16* %tmp2, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i16, i16* %tmp3, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp0, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp1, align 2
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i16 0, i16* %tmp2, align 2
-; VF_16-NEXT: Found an estimated cost of 8 for VF 16 For instruction: store i16 0, i16* %tmp3, align 2
+; VF_16-NEXT: Found an estimated cost of 1088 for VF 16 For instruction: store i16 0, i16* %tmp3, align 2
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i16.4, %i16.4* %data, i64 %i, i32 0
@@ -356,41 +356,41 @@
br label %for.body
; VF_2-LABEL: Checking a loop in "i32_factor_4"
-; VF_2: Found an estimated cost of 4 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_2: Found an estimated cost of 40 for VF 2 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp0, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp1, align 4
; VF_2-NEXT: Found an estimated cost of 0 for VF 2 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_2-NEXT: Found an estimated cost of 4 for VF 2 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_2-NEXT: Found an estimated cost of 24 for VF 2 For instruction: store i32 0, i32* %tmp3, align 4
; VF_4-LABEL: Checking a loop in "i32_factor_4"
-; VF_4: Found an estimated cost of 4 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_4: Found an estimated cost of 144 for VF 4 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp0, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp1, align 4
; VF_4-NEXT: Found an estimated cost of 0 for VF 4 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_4-NEXT: Found an estimated cost of 4 for VF 4 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_4-NEXT: Found an estimated cost of 80 for VF 4 For instruction: store i32 0, i32* %tmp3, align 4
; VF_8-LABEL: Checking a loop in "i32_factor_4"
-; VF_8: Found an estimated cost of 8 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_8: Found an estimated cost of 544 for VF 8 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp0, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp1, align 4
; VF_8-NEXT: Found an estimated cost of 0 for VF 8 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_8-NEXT: Found an estimated cost of 8 for VF 8 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_8-NEXT: Found an estimated cost of 288 for VF 8 For instruction: store i32 0, i32* %tmp3, align 4
; VF_16-LABEL: Checking a loop in "i32_factor_4"
-; VF_16: Found an estimated cost of 16 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
+; VF_16: Found an estimated cost of 2112 for VF 16 For instruction: %tmp4 = load i32, i32* %tmp0, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp5 = load i32, i32* %tmp1, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp6 = load i32, i32* %tmp2, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: %tmp7 = load i32, i32* %tmp3, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp0, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp1, align 4
; VF_16-NEXT: Found an estimated cost of 0 for VF 16 For instruction: store i32 0, i32* %tmp2, align 4
-; VF_16-NEXT: Found an estimated cost of 16 for VF 16 For instruction: store i32 0, i32* %tmp3, align 4
+; VF_16-NEXT: Found an estimated cost of 1088 for VF 16 For instruction: store i32 0, i32* %tmp3, align 4
for.body:
%i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
%tmp0 = getelementptr inbounds %i32.4, %i32.4* %data, i64 %i, i32 0