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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
; RUN: opt -S -passes=instcombine < %s | FileCheck %s
target triple = "aarch64-unknown-linux-gnu"
; Idempotent fmuls -- should compile to just a ret.
define <vscale x 8 x half> @idempotent_fmul_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
; CHECK-LABEL: define <vscale x 8 x half> @idempotent_fmul_f16(
; CHECK-SAME: <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[TMP0:%.*]]) #[[ATTR0:[0-9]+]] {
; CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
;
%1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 1.0)
%2 = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %1)
ret <vscale x 8 x half> %2
}
define <vscale x 4 x float> @idempotent_fmul_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) #0 {
; CHECK-LABEL: define <vscale x 4 x float> @idempotent_fmul_f32(
; CHECK-SAME: <vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x float> [[TMP0:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 4 x float> [[TMP0]]
;
%1 = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float 1.0)
%2 = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %1)
ret <vscale x 4 x float> %2
}
define <vscale x 2 x double> @idempotent_fmul_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) #0 {
; CHECK-LABEL: define <vscale x 2 x double> @idempotent_fmul_f64(
; CHECK-SAME: <vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> [[TMP0:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 2 x double> [[TMP0]]
;
%1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 1.0)
%2 = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %1)
ret <vscale x 2 x double> %2
}
define <vscale x 2 x double> @idempotent_fmul_different_argument_order(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) #0 {
; CHECK-LABEL: define <vscale x 2 x double> @idempotent_fmul_different_argument_order(
; CHECK-SAME: <vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG]], <vscale x 2 x double> splat (double 1.000000e+00), <vscale x 2 x double> [[A]])
; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
;
%1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 1.0)
; Different argument order to the above tests.
%2 = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %1, <vscale x 2 x double> %a)
ret <vscale x 2 x double> %2
}
define <vscale x 8 x half> @idempotent_fmul_with_predicated_dup(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
; CHECK-LABEL: define <vscale x 8 x half> @idempotent_fmul_with_predicated_dup(
; CHECK-SAME: <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[TMP0:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 8 x half> [[TMP0]]
;
%1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.nxv8f16(<vscale x 8 x half> undef, <vscale x 8 x i1> %pg, half 1.0)
%2 = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %1)
ret <vscale x 8 x half> %2
}
define <vscale x 8 x half> @idempotent_fmul_two_dups(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
; Edge case -- make sure that the case where we're fmultiplying two dups
; together is sane.
; CHECK-LABEL: define <vscale x 8 x half> @idempotent_fmul_two_dups(
; CHECK-SAME: <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: ret <vscale x 8 x half> splat (half 0xH3C00)
;
%1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 1.0)
%2 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 1.0)
%3 = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %1, <vscale x 8 x half> %2)
ret <vscale x 8 x half> %3
}
; Non-idempotent fmuls -- we don't expect these to be optimised out.
define <vscale x 8 x half> @non_idempotent_fmul_f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a) #0 {
; CHECK-LABEL: define <vscale x 8 x half> @non_idempotent_fmul_f16(
; CHECK-SAME: <vscale x 8 x i1> [[PG:%.*]], <vscale x 8 x half> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> [[PG]], <vscale x 8 x half> [[A]], <vscale x 8 x half> splat (half 0xH4000))
; CHECK-NEXT: ret <vscale x 8 x half> [[TMP1]]
;
%1 = call <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half 2.0)
%2 = call <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1> %pg, <vscale x 8 x half> %a, <vscale x 8 x half> %1)
ret <vscale x 8 x half> %2
}
define <vscale x 4 x float> @non_idempotent_fmul_f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a) #0 {
; CHECK-LABEL: define <vscale x 4 x float> @non_idempotent_fmul_f32(
; CHECK-SAME: <vscale x 4 x i1> [[PG:%.*]], <vscale x 4 x float> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> [[PG]], <vscale x 4 x float> [[A]], <vscale x 4 x float> splat (float 2.000000e+00))
; CHECK-NEXT: ret <vscale x 4 x float> [[TMP1]]
;
%1 = call <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float 2.0)
%2 = call <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1> %pg, <vscale x 4 x float> %a, <vscale x 4 x float> %1)
ret <vscale x 4 x float> %2
}
define <vscale x 2 x double> @non_idempotent_fmul_f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a) #0 {
; CHECK-LABEL: define <vscale x 2 x double> @non_idempotent_fmul_f64(
; CHECK-SAME: <vscale x 2 x i1> [[PG:%.*]], <vscale x 2 x double> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG]], <vscale x 2 x double> [[A]], <vscale x 2 x double> splat (double 2.000000e+00))
; CHECK-NEXT: ret <vscale x 2 x double> [[TMP1]]
;
%1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double 2.0)
%2 = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg, <vscale x 2 x double> %a, <vscale x 2 x double> %1)
ret <vscale x 2 x double> %2
}
define <vscale x 2 x double> @non_idempotent_fmul_with_predicated_dup(<vscale x 2 x i1> %pg1, <vscale x 2 x i1> %pg2, <vscale x 2 x double> %a) #0 {
; Different predicates
; CHECK-LABEL: define <vscale x 2 x double> @non_idempotent_fmul_with_predicated_dup(
; CHECK-SAME: <vscale x 2 x i1> [[PG1:%.*]], <vscale x 2 x i1> [[PG2:%.*]], <vscale x 2 x double> [[A:%.*]]) #[[ATTR0]] {
; CHECK-NEXT: [[TMP1:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> [[PG1]], double 1.000000e+00)
; CHECK-NEXT: [[TMP2:%.*]] = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> [[PG2]], <vscale x 2 x double> [[A]], <vscale x 2 x double> [[TMP1]])
; CHECK-NEXT: ret <vscale x 2 x double> [[TMP2]]
;
%1 = call <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x i1> %pg1, double 1.0)
%2 = call <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1> %pg2, <vscale x 2 x double> %a, <vscale x 2 x double> %1)
ret <vscale x 2 x double> %2
}
declare <vscale x 8 x half> @llvm.aarch64.sve.dup.x.nxv8f16(half)
declare <vscale x 4 x float> @llvm.aarch64.sve.dup.x.nxv4f32(float)
declare <vscale x 2 x double> @llvm.aarch64.sve.dup.x.nxv2f64(double)
declare <vscale x 2 x double> @llvm.aarch64.sve.dup.nxv2f64(<vscale x 2 x double>, <vscale x 2 x i1>, double)
declare <vscale x 8 x half> @llvm.aarch64.sve.dup.nxv8f16(<vscale x 8 x half>, <vscale x 8 x i1>, half)
declare <vscale x 8 x half> @llvm.aarch64.sve.fmul.nxv8f16(<vscale x 8 x i1>, <vscale x 8 x half>, <vscale x 8 x half>)
declare <vscale x 4 x float> @llvm.aarch64.sve.fmul.nxv4f32(<vscale x 4 x i1>, <vscale x 4 x float>, <vscale x 4 x float>)
declare <vscale x 2 x double> @llvm.aarch64.sve.fmul.nxv2f64(<vscale x 2 x i1>, <vscale x 2 x double>, <vscale x 2 x double>)
attributes #0 = { "target-features"="+sve" }
|
