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
|
; RUN: llc -march=amdgcn -mcpu=SI -enable-misched < %s | FileCheck -check-prefix=SI -check-prefix=GCN -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=bonaire -enable-misched < %s | FileCheck -check-prefix=CI -check-prefix=GCN -check-prefix=FUNC %s
; RUN: llc -march=amdgcn -mcpu=tonga -enable-misched < %s | FileCheck -check-prefix=CI -check-prefix=GCN -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}frem_f32:
; GCN-DAG: buffer_load_dword [[X:v[0-9]+]], {{.*$}}
; GCN-DAG: buffer_load_dword [[Y:v[0-9]+]], {{.*}} offset:16
; GCN: v_div_scale_f32
; GCN: v_rcp_f32_e32
; GCN: v_fma_f32
; GCN: v_mul_f32_e32
; GCN: v_div_fmas_f32
; GCN: v_div_fixup_f32
; GCN: v_trunc_f32_e32
; GCN: v_mad_f32
; GCN: s_endpgm
define void @frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1,
float addrspace(1)* %in2) #0 {
%gep2 = getelementptr float, float addrspace(1)* %in2, i32 4
%r0 = load float, float addrspace(1)* %in1, align 4
%r1 = load float, float addrspace(1)* %gep2, align 4
%r2 = frem float %r0, %r1
store float %r2, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}unsafe_frem_f32:
; GCN: buffer_load_dword [[Y:v[0-9]+]], {{.*}} offset:16
; GCN: buffer_load_dword [[X:v[0-9]+]], {{.*}}
; GCN: v_rcp_f32_e32 [[INVY:v[0-9]+]], [[Y]]
; GCN: v_mul_f32_e32 [[DIV:v[0-9]+]], [[INVY]], [[X]]
; GCN: v_trunc_f32_e32 [[TRUNC:v[0-9]+]], [[DIV]]
; GCN: v_mad_f32 [[RESULT:v[0-9]+]], -[[TRUNC]], [[Y]], [[X]]
; GCN: buffer_store_dword [[RESULT]]
; GCN: s_endpgm
define void @unsafe_frem_f32(float addrspace(1)* %out, float addrspace(1)* %in1,
float addrspace(1)* %in2) #1 {
%gep2 = getelementptr float, float addrspace(1)* %in2, i32 4
%r0 = load float, float addrspace(1)* %in1, align 4
%r1 = load float, float addrspace(1)* %gep2, align 4
%r2 = frem float %r0, %r1
store float %r2, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}frem_f64:
; GCN: buffer_load_dwordx2 [[Y:v\[[0-9]+:[0-9]+\]]], {{.*}}, 0
; GCN: buffer_load_dwordx2 [[X:v\[[0-9]+:[0-9]+\]]], {{.*}}, 0
; GCN-DAG: v_div_fmas_f64
; GCN-DAG: v_div_scale_f64
; GCN-DAG: v_mul_f64
; CI: v_trunc_f64_e32
; CI: v_mul_f64
; GCN: v_add_f64
; GCN: buffer_store_dwordx2
; GCN: s_endpgm
define void @frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
double addrspace(1)* %in2) #0 {
%r0 = load double, double addrspace(1)* %in1, align 8
%r1 = load double, double addrspace(1)* %in2, align 8
%r2 = frem double %r0, %r1
store double %r2, double addrspace(1)* %out, align 8
ret void
}
; FUNC-LABEL: {{^}}unsafe_frem_f64:
; GCN: v_rcp_f64_e32
; GCN: v_mul_f64
; SI: v_bfe_u32
; CI: v_trunc_f64_e32
; GCN: v_fma_f64
; GCN: s_endpgm
define void @unsafe_frem_f64(double addrspace(1)* %out, double addrspace(1)* %in1,
double addrspace(1)* %in2) #1 {
%r0 = load double, double addrspace(1)* %in1, align 8
%r1 = load double, double addrspace(1)* %in2, align 8
%r2 = frem double %r0, %r1
store double %r2, double addrspace(1)* %out, align 8
ret void
}
define void @frem_v2f32(<2 x float> addrspace(1)* %out, <2 x float> addrspace(1)* %in1,
<2 x float> addrspace(1)* %in2) #0 {
%gep2 = getelementptr <2 x float>, <2 x float> addrspace(1)* %in2, i32 4
%r0 = load <2 x float>, <2 x float> addrspace(1)* %in1, align 8
%r1 = load <2 x float>, <2 x float> addrspace(1)* %gep2, align 8
%r2 = frem <2 x float> %r0, %r1
store <2 x float> %r2, <2 x float> addrspace(1)* %out, align 8
ret void
}
define void @frem_v4f32(<4 x float> addrspace(1)* %out, <4 x float> addrspace(1)* %in1,
<4 x float> addrspace(1)* %in2) #0 {
%gep2 = getelementptr <4 x float>, <4 x float> addrspace(1)* %in2, i32 4
%r0 = load <4 x float>, <4 x float> addrspace(1)* %in1, align 16
%r1 = load <4 x float>, <4 x float> addrspace(1)* %gep2, align 16
%r2 = frem <4 x float> %r0, %r1
store <4 x float> %r2, <4 x float> addrspace(1)* %out, align 16
ret void
}
define void @frem_v2f64(<2 x double> addrspace(1)* %out, <2 x double> addrspace(1)* %in1,
<2 x double> addrspace(1)* %in2) #0 {
%gep2 = getelementptr <2 x double>, <2 x double> addrspace(1)* %in2, i32 4
%r0 = load <2 x double>, <2 x double> addrspace(1)* %in1, align 16
%r1 = load <2 x double>, <2 x double> addrspace(1)* %gep2, align 16
%r2 = frem <2 x double> %r0, %r1
store <2 x double> %r2, <2 x double> addrspace(1)* %out, align 16
ret void
}
attributes #0 = { nounwind "unsafe-fp-math"="false" }
attributes #1 = { nounwind "unsafe-fp-math"="true" }
|
