Skip to content

Commit f92961d

Browse files
LebedevRILebedevRI
committed
[NFC] Fixup newly-added costmodel tests to actually test what they should
1 parent fc66dbb commit f92961d

6 files changed

+108
-122
lines changed

‎llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-2-indices-0u.ll

Lines changed: 19 additions & 22 deletions
Original file line numberDiff line numberDiff line change
@@ -13,34 +13,31 @@ target triple = "x86_64-unknown-linux-gnu"
1313
; CHECK: LV: Checking a loop in "test"
1414
;
1515
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
16-
; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17-
; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18-
; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
19-
; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
16+
; SSE2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17+
; SSE2: LV: Found an estimated cost of 15 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18+
; SSE2: LV: Found an estimated cost of 30 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
2019
;
2120
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
22-
; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
23-
; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
24-
; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
25-
; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
26-
; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
21+
; AVX1: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
22+
; AVX1: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
23+
; AVX1: LV: Found an estimated cost of 24 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
24+
; AVX1: LV: Found an estimated cost of 48 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
2725
;
2826
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
29-
; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
30-
; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
31-
; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
32-
; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
33-
; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
27+
; AVX2: LV: Found an estimated cost of 5 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
28+
; AVX2: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
29+
; AVX2: LV: Found an estimated cost of 24 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
30+
; AVX2: LV: Found an estimated cost of 48 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
3431
;
3532
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
36-
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
37-
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
38-
; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
39-
; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
40-
; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
41-
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
33+
; AVX512: LV: Found an estimated cost of 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
34+
; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
35+
; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
36+
; AVX512: LV: Found an estimated cost of 2 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
37+
; AVX512: LV: Found an estimated cost of 13 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
38+
; AVX512: LV: Found an estimated cost of 50 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
4239
;
43-
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 2
40+
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
4441

4542
define void @test() {
4643
entry:
@@ -62,7 +59,7 @@ for.body:
6259
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
6360
store i8 %reduce.add.0.narrow, i8* %out
6461

65-
%iv.next = add nuw nsw i64 %iv.0, 2
62+
%iv.next = add nuw nsw i64 %iv, 2
6663
%cmp = icmp ult i64 %iv.next, 1024
6764
br i1 %cmp, label %for.body, label %for.cond.cleanup
6865

‎llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-01u.ll

Lines changed: 18 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -13,32 +13,29 @@ target triple = "x86_64-unknown-linux-gnu"
1313
; CHECK: LV: Checking a loop in "test"
1414
;
1515
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
16-
; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17-
; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18-
; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
19-
; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
16+
; SSE2: LV: Found an estimated cost of 14 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17+
; SSE2: LV: Found an estimated cost of 31 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18+
; SSE2: LV: Found an estimated cost of 62 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
2019
;
2120
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
22-
; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
23-
; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
24-
; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
25-
; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
26-
; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
21+
; AVX1: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
22+
; AVX1: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
23+
; AVX1: LV: Found an estimated cost of 47 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
24+
; AVX1: LV: Found an estimated cost of 94 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
2725
;
2826
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
29-
; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
30-
; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
31-
; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
32-
; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
33-
; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
27+
; AVX2: LV: Found an estimated cost of 12 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
28+
; AVX2: LV: Found an estimated cost of 21 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
29+
; AVX2: LV: Found an estimated cost of 47 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
30+
; AVX2: LV: Found an estimated cost of 94 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
3431
;
3532
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
36-
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
37-
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
38-
; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
39-
; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
40-
; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
41-
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
33+
; AVX512: LV: Found an estimated cost of 3 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
34+
; AVX512: LV: Found an estimated cost of 3 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
35+
; AVX512: LV: Found an estimated cost of 5 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
36+
; AVX512: LV: Found an estimated cost of 9 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
37+
; AVX512: LV: Found an estimated cost of 36 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
38+
; AVX512: LV: Found an estimated cost of 144 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
4239
;
4340
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
4441

@@ -66,7 +63,7 @@ for.body:
6663
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
6764
store i8 %reduce.add.1.narrow, i8* %out
6865

69-
%iv.next = add nuw nsw i64 %iv.0, 3
66+
%iv.next = add nuw nsw i64 %iv, 3
7067
%cmp = icmp ult i64 %iv.next, 1024
7168
br i1 %cmp, label %for.body, label %for.cond.cleanup
7269

‎llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-3-indices-0uu.ll

Lines changed: 20 additions & 21 deletions
Original file line numberDiff line numberDiff line change
@@ -13,32 +13,31 @@ target triple = "x86_64-unknown-linux-gnu"
1313
; CHECK: LV: Checking a loop in "test"
1414
;
1515
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
16-
; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17-
; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18-
; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
19-
; SSE2: LV: Found an estimated cost of 236 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
16+
; SSE2: LV: Found an estimated cost of 8 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17+
; SSE2: LV: Found an estimated cost of 17 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18+
; SSE2: LV: Found an estimated cost of 34 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
2019
;
2120
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
22-
; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
23-
; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
24-
; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
25-
; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
26-
; AVX1: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
21+
; AVX1: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
22+
; AVX1: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
23+
; AVX1: LV: Found an estimated cost of 25 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
24+
; AVX1: LV: Found an estimated cost of 50 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
2725
;
2826
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
29-
; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
30-
; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
31-
; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
32-
; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
33-
; AVX2: LV: Found an estimated cost of 440 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
27+
; AVX2: LV: Found an estimated cost of 7 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
28+
; AVX2: LV: Found an estimated cost of 11 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
29+
; AVX2: LV: Found an estimated cost of 25 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
30+
; AVX2: LV: Found an estimated cost of 50 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
3431
;
3532
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
36-
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
37-
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
38-
; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
39-
; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
40-
; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
41-
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
33+
; AVX512: LV: Found an estimated cost of 1 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
34+
; AVX512: LV: Found an estimated cost of 1 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
35+
; AVX512: LV: Found an estimated cost of 2 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
36+
; AVX512: LV: Found an estimated cost of 3 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
37+
; AVX512: LV: Found an estimated cost of 21 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
38+
; AVX512: LV: Found an estimated cost of 78 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
39+
;
40+
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
4241

4342
define void @test() {
4443
entry:
@@ -61,7 +60,7 @@ for.body:
6160
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
6261
store i8 %reduce.add.1.narrow, i8* %out
6362

64-
%iv.next = add nuw nsw i64 %iv.0, 3
63+
%iv.next = add nuw nsw i64 %iv, 3
6564
%cmp = icmp ult i64 %iv.next, 1024
6665
br i1 %cmp, label %for.body, label %for.cond.cleanup
6766

‎llvm/test/Analysis/CostModel/X86/interleaved-load-i32-stride-4-indices-012u.ll

Lines changed: 16 additions & 17 deletions
Original file line numberDiff line numberDiff line change
@@ -13,29 +13,28 @@ target triple = "x86_64-unknown-linux-gnu"
1313
; CHECK: LV: Checking a loop in "test"
1414
;
1515
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
16-
; SSE2: LV: Found an estimated cost of 29 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17-
; SSE2: LV: Found an estimated cost of 59 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18-
; SSE2: LV: Found an estimated cost of 118 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
16+
; SSE2: LV: Found an estimated cost of 21 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
17+
; SSE2: LV: Found an estimated cost of 45 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
18+
; SSE2: LV: Found an estimated cost of 90 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
1919
;
2020
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
21-
; AVX1: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
22-
; AVX1: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
23-
; AVX1: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
24-
; AVX1: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
21+
; AVX1: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
22+
; AVX1: LV: Found an estimated cost of 32 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
23+
; AVX1: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
24+
; AVX1: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
2525
;
2626
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
27-
; AVX2: LV: Found an estimated cost of 26 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
28-
; AVX2: LV: Found an estimated cost of 54 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
29-
; AVX2: LV: Found an estimated cost of 110 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
30-
; AVX2: LV: Found an estimated cost of 220 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
27+
; AVX2: LV: Found an estimated cost of 16 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
28+
; AVX2: LV: Found an estimated cost of 32 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
29+
; AVX2: LV: Found an estimated cost of 70 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
30+
; AVX2: LV: Found an estimated cost of 140 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
3131
;
3232
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %v0 = load i32, i32* %in0, align 4
3333
; AVX512: LV: Found an estimated cost of 4 for VF 2 For instruction: %v0 = load i32, i32* %in0, align 4
34-
; AVX512: LV: Found an estimated cost of 6 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
35-
; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
36-
; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
37-
; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
38-
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: %v0 = load i32, i32* %in0, align 4
34+
; AVX512: LV: Found an estimated cost of 4 for VF 4 For instruction: %v0 = load i32, i32* %in0, align 4
35+
; AVX512: LV: Found an estimated cost of 6 for VF 8 For instruction: %v0 = load i32, i32* %in0, align 4
36+
; AVX512: LV: Found an estimated cost of 17 for VF 16 For instruction: %v0 = load i32, i32* %in0, align 4
37+
; AVX512: LV: Found an estimated cost of 71 for VF 32 For instruction: %v0 = load i32, i32* %in0, align 4
3938
;
4039
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %v0 = load i32, i32* %in0, align 4
4140

@@ -67,7 +66,7 @@ for.body:
6766
%out = getelementptr inbounds [1024 x i8], [1024 x i8]* @B, i64 0, i64 %iv.0
6867
store i8 %reduce.add.2.narrow, i8* %out
6968

70-
%iv.next = add nuw nsw i64 %iv.0, 4
69+
%iv.next = add nuw nsw i64 %iv, 4
7170
%cmp = icmp ult i64 %iv.next, 1024
7271
br i1 %cmp, label %for.body, label %for.cond.cleanup
7372

0 commit comments

Comments
 (0)