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
89
90
91
|
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse2 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE2
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+sse42 --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,SSE42
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX1
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,-fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-SLOWGATHER
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx2,+fast-gather --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,AVX2-FASTGATHER
; RUN: opt -loop-vectorize -vectorizer-maximize-bandwidth -S -mattr=+avx512bw --debug-only=loop-vectorize < %s 2>&1 | FileCheck %s --check-prefixes=CHECK,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
@C = global [1024 x i16] zeroinitializer, align 128
; CHECK: LV: Checking a loop in "test"
;
; SSE2: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE2: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE2: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE2: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE2: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; SSE42: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE42: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE42: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE42: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; SSE42: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; AVX1: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX1: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX1: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX1: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX1: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX1: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; AVX2-SLOWGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-SLOWGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; AVX2-FASTGATHER: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX2-FASTGATHER: LV: Found an estimated cost of 3000000 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; AVX512: LV: Found an estimated cost of 1 for VF 1 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 2 for VF 2 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 2 for VF 4 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 1 for VF 8 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 1 for VF 16 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 1 for VF 32 For instruction: %valB.loaded = load i16, i16* %inB, align 2
; AVX512: LV: Found an estimated cost of 2 for VF 64 For instruction: %valB.loaded = load i16, i16* %inB, align 2
;
; CHECK-NOT: LV: Found an estimated cost of {{[0-9]+}} for VF {{[0-9]+}} For instruction: %valB.loaded = load i16, i16* %inB, align 2
define void @test([1024 x i16]* %B) {
entry:
br label %for.body
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %end ]
%inA = getelementptr inbounds [1024 x i8], [1024 x i8]* @A, i64 0, i64 %iv
%valA = load i8, i8* %inA
%canLoad = icmp ne i8 %valA, 0
br i1 %canLoad, label %load, label %mask
load:
%inB = getelementptr inbounds [1024 x i16], [1024 x i16]* %B, i64 0, i64 %iv
%valB.loaded = load i16, i16* %inB
br label %end
mask:
br label %end
end:
%valB = phi i16 [ %valB.loaded, %load ], [ 0, %mask ]
%out = getelementptr inbounds [1024 x i16], [1024 x i16]* @C, i64 0, i64 %iv
store i16 %valB, i16* %out
%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
}
|
