File: propagate-forward.ll

package info (click to toggle)
llvm-toolchain-14 1%3A14.0.6-12
  • links: PTS, VCS
  • area: main
  • in suites: bookworm
  • size: 1,496,180 kB
  • sloc: cpp: 5,593,972; ansic: 986,872; asm: 585,869; python: 184,223; objc: 72,530; lisp: 31,119; f90: 27,793; javascript: 9,780; pascal: 9,762; sh: 9,482; perl: 7,468; ml: 5,432; awk: 3,523; makefile: 2,538; xml: 953; cs: 573; fortran: 567
file content (150 lines) | stat: -rw-r--r-- 10,839 bytes parent folder | download | duplicates (6)
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
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt -matrix-allow-contract=false -lower-matrix-intrinsics -S < %s | FileCheck  %s
; RUN: opt -matrix-allow-contract=false -passes='lower-matrix-intrinsics' -S < %s | FileCheck %s

; Check that we do not emit shufflevectors to flatten the result of the
; transpose and store the columns directly.
define void @transpose_store(<8 x double> %a, <8 x double>* %Ptr) {
; CHECK-LABEL: @transpose_store(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <2 x double> [[SPLIT]], i64 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[TMP0]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP1]], double [[TMP2]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> [[TMP3]], double [[TMP4]], i64 2
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 3
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[SPLIT]], i64 1
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> undef, double [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 1
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 1
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 1
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> [[TMP11]], double [[TMP12]], i64 2
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 1
; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 3
; CHECK-NEXT:    [[TMP16:%.*]] = bitcast <8 x double>* [[PTR:%.*]] to double*
; CHECK-NEXT:    [[VEC_CAST:%.*]] = bitcast double* [[TMP16]] to <4 x double>*
; CHECK-NEXT:    store <4 x double> [[TMP7]], <4 x double>* [[VEC_CAST]], align 8
; CHECK-NEXT:    [[VEC_GEP:%.*]] = getelementptr double, double* [[TMP16]], i64 4
; CHECK-NEXT:    [[VEC_CAST4:%.*]] = bitcast double* [[VEC_GEP]] to <4 x double>*
; CHECK-NEXT:    store <4 x double> [[TMP15]], <4 x double>* [[VEC_CAST4]], align 8
; CHECK-NEXT:    ret void
;
entry:
  %c  = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
  store <8 x double> %c, <8 x double>* %Ptr, align 8
  ret void
}

declare <8 x double> @llvm.matrix.transpose(<8 x double>, i32, i32)

define <8 x double> @transpose_fadd(<8 x double> %a) {
; CHECK-LABEL: @transpose_fadd(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <2 x double> [[SPLIT]], i64 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[TMP0]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP1]], double [[TMP2]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> [[TMP3]], double [[TMP4]], i64 2
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 3
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[SPLIT]], i64 1
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> undef, double [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 1
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 1
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 1
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> [[TMP11]], double [[TMP12]], i64 2
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 1
; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 3
; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    [[TMP16:%.*]] = fadd <4 x double> [[TMP7]], [[SPLIT4]]
; CHECK-NEXT:    [[TMP17:%.*]] = fadd <4 x double> [[TMP15]], [[SPLIT5]]
; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <4 x double> [[TMP16]], <4 x double> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    ret <8 x double> [[TMP18]]
;
entry:
  %c  = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
  %res = fadd <8 x double> %c, %a
  ret <8 x double> %res
}

define <8 x double> @transpose_fmul(<8 x double> %a) {
; CHECK-LABEL: @transpose_fmul(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <2 x double> [[SPLIT]], i64 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[TMP0]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP1]], double [[TMP2]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> [[TMP3]], double [[TMP4]], i64 2
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 3
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[SPLIT]], i64 1
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> undef, double [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 1
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 1
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 1
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> [[TMP11]], double [[TMP12]], i64 2
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 1
; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 3
; CHECK-NEXT:    [[SPLIT4:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <4 x i32> <i32 0, i32 1, i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT5:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <4 x i32> <i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    [[TMP16:%.*]] = fmul <4 x double> [[TMP7]], [[SPLIT4]]
; CHECK-NEXT:    [[TMP17:%.*]] = fmul <4 x double> [[TMP15]], [[SPLIT5]]
; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <4 x double> [[TMP16]], <4 x double> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    ret <8 x double> [[TMP18]]
;
entry:
  %c  = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
  %res = fmul <8 x double> %c, %a
  ret <8 x double> %res
}

define <8 x double> @transpose_fneg(<8 x double> %a) {
; CHECK-LABEL: @transpose_fneg(
; CHECK-NEXT:  entry:
; CHECK-NEXT:    [[SPLIT:%.*]] = shufflevector <8 x double> [[A:%.*]], <8 x double> poison, <2 x i32> <i32 0, i32 1>
; CHECK-NEXT:    [[SPLIT1:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 2, i32 3>
; CHECK-NEXT:    [[SPLIT2:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 4, i32 5>
; CHECK-NEXT:    [[SPLIT3:%.*]] = shufflevector <8 x double> [[A]], <8 x double> poison, <2 x i32> <i32 6, i32 7>
; CHECK-NEXT:    [[TMP0:%.*]] = extractelement <2 x double> [[SPLIT]], i64 0
; CHECK-NEXT:    [[TMP1:%.*]] = insertelement <4 x double> undef, double [[TMP0]], i64 0
; CHECK-NEXT:    [[TMP2:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 0
; CHECK-NEXT:    [[TMP3:%.*]] = insertelement <4 x double> [[TMP1]], double [[TMP2]], i64 1
; CHECK-NEXT:    [[TMP4:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 0
; CHECK-NEXT:    [[TMP5:%.*]] = insertelement <4 x double> [[TMP3]], double [[TMP4]], i64 2
; CHECK-NEXT:    [[TMP6:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 0
; CHECK-NEXT:    [[TMP7:%.*]] = insertelement <4 x double> [[TMP5]], double [[TMP6]], i64 3
; CHECK-NEXT:    [[TMP8:%.*]] = extractelement <2 x double> [[SPLIT]], i64 1
; CHECK-NEXT:    [[TMP9:%.*]] = insertelement <4 x double> undef, double [[TMP8]], i64 0
; CHECK-NEXT:    [[TMP10:%.*]] = extractelement <2 x double> [[SPLIT1]], i64 1
; CHECK-NEXT:    [[TMP11:%.*]] = insertelement <4 x double> [[TMP9]], double [[TMP10]], i64 1
; CHECK-NEXT:    [[TMP12:%.*]] = extractelement <2 x double> [[SPLIT2]], i64 1
; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x double> [[TMP11]], double [[TMP12]], i64 2
; CHECK-NEXT:    [[TMP14:%.*]] = extractelement <2 x double> [[SPLIT3]], i64 1
; CHECK-NEXT:    [[TMP15:%.*]] = insertelement <4 x double> [[TMP13]], double [[TMP14]], i64 3
; CHECK-NEXT:    [[TMP16:%.*]] = fneg <4 x double> [[TMP7]]
; CHECK-NEXT:    [[TMP17:%.*]] = fneg <4 x double> [[TMP15]]
; CHECK-NEXT:    [[TMP18:%.*]] = shufflevector <4 x double> [[TMP16]], <4 x double> [[TMP17]], <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
; CHECK-NEXT:    ret <8 x double> [[TMP18]]
;
entry:
  %c  = call <8 x double> @llvm.matrix.transpose(<8 x double> %a, i32 2, i32 4)
  %res = fneg <8 x double> %c
  ret <8 x double> %res
}