[LV] Simplify ARM/AArch64 interleaved access cost model tests (NFC)

This patch removes unneeded instructions from the existing ARM/AArch64
interleaved access cost model tests. I'll be adding a similar set of tests in a
follow-on patch to increase coverage.

llvm-svn: 294336

1 files changed, 26 insertions, 28 deletions

diff --git a/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
index de3626b57d8..3ccd9217eee 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/interleaved_cost.ll
@@ -1,39 +1,37 @@
-; RUN: opt -S -debug-only=loop-vectorize -loop-vectorize -instcombine  < %s 2>&1 | FileCheck %s
+; RUN: opt -loop-vectorize -force-vector-width=8 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_8
+; RUN: opt -loop-vectorize -force-vector-width=16 -debug-only=loop-vectorize -disable-output < %s 2>&1 | FileCheck %s --check-prefix=VF_16
 ; REQUIRES: asserts
 
 target datalayout = "e-m:e-i64:64-i128:128-n32:64-S128"
 target triple = "armv8--linux-gnueabihf"
 
-@AB = common global [1024 x i8] zeroinitializer, align 4
-@CD = common global [1024 x i8] zeroinitializer, align 4
-
-define void @test_byte_interleaved_cost(i8 %C, i8 %D) {
+%i8.2 = type {i8, i8}
+define void @i8_factor_2(%i8.2* %data, i64 %n) {
 entry:
   br label %for.body
 
-; 8xi8 and 16xi8 are valid i8 vector types, so the cost of the interleaved
-; access group is 2.
-
-; CHECK: LV: Found an estimated cost of 2 for VF 8 For instruction:   %tmp = load i8, i8* %arrayidx0, align 4
-; CHECK: LV: Found an estimated cost of 2 for VF 16 For instruction:   %tmp = load i8, i8* %arrayidx0, align 4
-
-for.body:                                         ; preds = %for.body, %entry
-  %indvars.iv = phi i64 [ 0, %entry ], [ %indvars.iv.next, %for.body ]
-  %arrayidx0 = getelementptr inbounds [1024 x i8], [1024 x i8]* @AB, i64 0, i64 %indvars.iv
-  %tmp = load i8, i8* %arrayidx0, align 4
-  %tmp1 = or i64 %indvars.iv, 1
-  %arrayidx1 = getelementptr inbounds [1024 x i8], [1024 x i8]* @AB, i64 0, i64 %tmp1
-  %tmp2 = load i8, i8* %arrayidx1, align 4
-  %add = add nsw i8 %tmp, %C
-  %mul = mul nsw i8 %tmp2, %D
-  %arrayidx2 = getelementptr inbounds [1024 x i8], [1024 x i8]* @CD, i64 0, i64 %indvars.iv
-  store i8 %add, i8* %arrayidx2, align 4
-  %arrayidx3 = getelementptr inbounds [1024 x i8], [1024 x i8]* @CD, i64 0, i64 %tmp1
-  store i8 %mul, i8* %arrayidx3, align 4
-  %indvars.iv.next = add nuw nsw i64 %indvars.iv, 2
-  %cmp = icmp slt i64 %indvars.iv.next, 1024
-  br i1 %cmp, label %for.body, label %for.end
+; VF_8-LABEL:  Checking a loop in "i8_factor_2"
+; VF_8:          Found an estimated cost of 2 for VF 8 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
+; VF_8-NEXT:     Found an estimated cost of 0 for VF 8 For instruction: %tmp3 = load i8, i8* %tmp1, 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 2 for VF 8 For instruction: store i8 0, i8* %tmp1, align 1
+; VF_16-LABEL: Checking a loop in "i8_factor_2"
+; VF_16:         Found an estimated cost of 2 for VF 16 For instruction: %tmp2 = load i8, i8* %tmp0, align 1
+; VF_16-NEXT:    Found an estimated cost of 0 for VF 16 For instruction: %tmp3 = load i8, i8* %tmp1, 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 2 for VF 16 For instruction: store i8 0, i8* %tmp1, align 1
+for.body:
+  %i = phi i64 [ 0, %entry ], [ %i.next, %for.body ]
+  %tmp0 = getelementptr inbounds %i8.2, %i8.2* %data, i64 %i, i32 0
+  %tmp1 = getelementptr inbounds %i8.2, %i8.2* %data, i64 %i, i32 1
+  %tmp2 = load i8, i8* %tmp0, align 1
+  %tmp3 = load i8, i8* %tmp1, align 1
+  store i8 0, i8* %tmp0, align 1
+  store i8 0, i8* %tmp1, align 1
+  %i.next = add nuw nsw i64 %i, 1
+  %cond = icmp slt i64 %i.next, %n
+  br i1 %cond, label %for.body, label %for.end
 
-for.end:                                          ; preds = %for.body
+for.end:
   ret void
 }