vecreduce-fmul-legalization-strict.ll
4.21 KB
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
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc < %s -mtriple=aarch64-none-linux-gnu -mattr=+neon | FileCheck %s --check-prefix=CHECK
; Same as vecreduce-fmul-legalization.ll, but without fmf.
declare half @llvm.experimental.vector.reduce.v2.fmul.f16.v1f16(half, <1 x half>)
declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v1f32(float, <1 x float>)
declare double @llvm.experimental.vector.reduce.v2.fmul.f64.v1f64(double, <1 x double>)
declare fp128 @llvm.experimental.vector.reduce.v2.fmul.f128.v1f128(fp128, <1 x fp128>)
declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v3f32(float, <3 x float>)
declare fp128 @llvm.experimental.vector.reduce.v2.fmul.f128.v2f128(fp128, <2 x fp128>)
declare float @llvm.experimental.vector.reduce.v2.fmul.f32.v16f32(float, <16 x float>)
define half @test_v1f16(<1 x half> %a) nounwind {
; CHECK-LABEL: test_v1f16:
; CHECK: // %bb.0:
; CHECK-NEXT: fcvt s0, h0
; CHECK-NEXT: fmov s1, wzr
; CHECK-NEXT: fmul s0, s0, s1
; CHECK-NEXT: fcvt h0, s0
; CHECK-NEXT: ret
%b = call half @llvm.experimental.vector.reduce.v2.fmul.f16.v1f16(half 0.0, <1 x half> %a)
ret half %b
}
define float @test_v1f32(<1 x float> %a) nounwind {
; CHECK-LABEL: test_v1f32:
; CHECK: // %bb.0:
; CHECK-NEXT: // kill: def $d0 killed $d0 def $q0
; CHECK-NEXT: fmov s1, wzr
; CHECK-NEXT: fmul s0, s1, v0.s[0]
; CHECK-NEXT: ret
%b = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v1f32(float 0.0, <1 x float> %a)
ret float %b
}
define double @test_v1f64(<1 x double> %a) nounwind {
; CHECK-LABEL: test_v1f64:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov d1, xzr
; CHECK-NEXT: fmul d0, d0, d1
; CHECK-NEXT: ret
%b = call double @llvm.experimental.vector.reduce.v2.fmul.f64.v1f64(double 0.0, <1 x double> %a)
ret double %b
}
define fp128 @test_v1f128(<1 x fp128> %a) nounwind {
; CHECK-LABEL: test_v1f128:
; CHECK: // %bb.0:
; CHECK-NEXT: str x30, [sp, #-16]! // 8-byte Folded Spill
; CHECK-NEXT: adrp x8, .LCPI3_0
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI3_0]
; CHECK-NEXT: bl __multf3
; CHECK-NEXT: ldr x30, [sp], #16 // 8-byte Folded Reload
; CHECK-NEXT: ret
%b = call fp128 @llvm.experimental.vector.reduce.v2.fmul.f128.v1f128(fp128 zeroinitializer, <1 x fp128> %a)
ret fp128 %b
}
define float @test_v3f32(<3 x float> %a) nounwind {
; CHECK-LABEL: test_v3f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov s1, wzr
; CHECK-NEXT: fmul s1, s1, v0.s[0]
; CHECK-NEXT: fmul s1, s1, v0.s[1]
; CHECK-NEXT: fmul s0, s1, v0.s[2]
; CHECK-NEXT: ret
%b = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v3f32(float 0.0, <3 x float> %a)
ret float %b
}
define fp128 @test_v2f128(<2 x fp128> %a) nounwind {
; CHECK-LABEL: test_v2f128:
; CHECK: // %bb.0:
; CHECK-NEXT: sub sp, sp, #32 // =32
; CHECK-NEXT: adrp x8, .LCPI5_0
; CHECK-NEXT: str q1, [sp] // 16-byte Folded Spill
; CHECK-NEXT: ldr q1, [x8, :lo12:.LCPI5_0]
; CHECK-NEXT: str x30, [sp, #16] // 8-byte Folded Spill
; CHECK-NEXT: bl __multf3
; CHECK-NEXT: ldr q1, [sp] // 16-byte Folded Reload
; CHECK-NEXT: bl __multf3
; CHECK-NEXT: ldr x30, [sp, #16] // 8-byte Folded Reload
; CHECK-NEXT: add sp, sp, #32 // =32
; CHECK-NEXT: ret
%b = call fp128 @llvm.experimental.vector.reduce.v2.fmul.f128.v2f128(fp128 zeroinitializer, <2 x fp128> %a)
ret fp128 %b
}
define float @test_v16f32(<16 x float> %a) nounwind {
; CHECK-LABEL: test_v16f32:
; CHECK: // %bb.0:
; CHECK-NEXT: fmov s4, wzr
; CHECK-NEXT: fmul s4, s4, v0.s[0]
; CHECK-NEXT: fmul s4, s4, v0.s[1]
; CHECK-NEXT: fmul s4, s4, v0.s[2]
; CHECK-NEXT: fmul s0, s4, v0.s[3]
; CHECK-NEXT: fmul s0, s0, v1.s[0]
; CHECK-NEXT: fmul s0, s0, v1.s[1]
; CHECK-NEXT: fmul s0, s0, v1.s[2]
; CHECK-NEXT: fmul s0, s0, v1.s[3]
; CHECK-NEXT: fmul s0, s0, v2.s[0]
; CHECK-NEXT: fmul s0, s0, v2.s[1]
; CHECK-NEXT: fmul s0, s0, v2.s[2]
; CHECK-NEXT: fmul s0, s0, v2.s[3]
; CHECK-NEXT: fmul s0, s0, v3.s[0]
; CHECK-NEXT: fmul s0, s0, v3.s[1]
; CHECK-NEXT: fmul s0, s0, v3.s[2]
; CHECK-NEXT: fmul s0, s0, v3.s[3]
; CHECK-NEXT: ret
%b = call float @llvm.experimental.vector.reduce.v2.fmul.f32.v16f32(float 0.0, <16 x float> %a)
ret float %b
}