1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
|
; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py UTC_ARGS: --filter "LV: Found an estimated cost of [0-9]+ for VF [0-9]+ For instruction:\s*store i64 %valB, ptr %out, align 8"
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse4.2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=SSE42
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX1
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX2
; RUN: opt -passes=loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=AVX512
; REQUIRES: asserts
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
@A = global [1024 x i8] zeroinitializer, align 128
@B = global [1024 x i64] zeroinitializer, align 128
@C = global [1024 x i64] zeroinitializer, align 128
define void @test() {
; SSE2-LABEL: 'test'
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
; SSE2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, ptr %out, align 8
; SSE2: LV: Found an estimated cost of 5 for VF 4 For instruction: store i64 %valB, ptr %out, align 8
; SSE2: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, ptr %out, align 8
; SSE2: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, ptr %out, align 8
;
; SSE42-LABEL: 'test'
; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
; SSE42: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, ptr %out, align 8
; SSE42: LV: Found an estimated cost of 4 for VF 4 For instruction: store i64 %valB, ptr %out, align 8
; SSE42: LV: Found an estimated cost of 8 for VF 8 For instruction: store i64 %valB, ptr %out, align 8
; SSE42: LV: Found an estimated cost of 16 for VF 16 For instruction: store i64 %valB, ptr %out, align 8
;
; AVX1-LABEL: 'test'
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
; AVX1: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, ptr %out, align 8
; AVX1: LV: Found an estimated cost of 4 for VF 4 For instruction: store i64 %valB, ptr %out, align 8
; AVX1: LV: Found an estimated cost of 9 for VF 8 For instruction: store i64 %valB, ptr %out, align 8
; AVX1: LV: Found an estimated cost of 18 for VF 16 For instruction: store i64 %valB, ptr %out, align 8
; AVX1: LV: Found an estimated cost of 36 for VF 32 For instruction: store i64 %valB, ptr %out, align 8
;
; AVX2-LABEL: 'test'
; AVX2: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
; AVX2: LV: Found an estimated cost of 2 for VF 2 For instruction: store i64 %valB, ptr %out, align 8
; AVX2: LV: Found an estimated cost of 4 for VF 4 For instruction: store i64 %valB, ptr %out, align 8
; AVX2: LV: Found an estimated cost of 9 for VF 8 For instruction: store i64 %valB, ptr %out, align 8
; AVX2: LV: Found an estimated cost of 18 for VF 16 For instruction: store i64 %valB, ptr %out, align 8
; AVX2: LV: Found an estimated cost of 36 for VF 32 For instruction: store i64 %valB, ptr %out, align 8
;
; AVX512-LABEL: 'test'
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 5 for VF 2 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 11 for VF 4 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 10 for VF 8 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 20 for VF 16 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 40 for VF 32 For instruction: store i64 %valB, ptr %out, align 8
; AVX512: LV: Found an estimated cost of 80 for VF 64 For instruction: store i64 %valB, ptr %out, align 8
;
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %end ]
%inB = getelementptr inbounds [1024 x i64], ptr @B, i64 0, i64 %iv
%valB = load i64, ptr %inB
%inA = getelementptr inbounds [1024 x i8], ptr @A, i64 0, i64 %iv
%valA = load i8, ptr %inA
%canStore = icmp ne i8 %valA, 0
br i1 %canStore, label %store, label %mask
store:
%valA.ext = sext i8 %valA to i64
%out = getelementptr inbounds [1024 x i64], ptr @C, i64 0, i64 %valA.ext
store i64 %valB, ptr %out
br label %end
mask:
br label %end
end:
%iv.next = add nuw nsw i64 %iv, 1
%cmp = icmp ult i64 %iv.next, 1024
br i1 %cmp, label %for.body, label %for.cond.cleanup
for.cond.cleanup:
ret void
}
|
