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
|
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
; RUN: llc -amdgpu-scalarize-global-loads=false -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=R600 -check-prefix=FUNC %s
; FUNC-LABEL: {{^}}v_fsub_f32:
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
define amdgpu_kernel void @v_fsub_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 1
%a = load float, ptr addrspace(1) %in, align 4
%b = load float, ptr addrspace(1) %b_ptr, align 4
%result = fsub float %a, %b
store float %result, ptr addrspace(1) %out, align 4
ret void
}
; FUNC-LABEL: {{^}}s_fsub_f32:
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].Z, -KC0[2].W
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
define amdgpu_kernel void @s_fsub_f32(ptr addrspace(1) %out, float %a, float %b) {
%sub = fsub float %a, %b
store float %sub, ptr addrspace(1) %out, align 4
ret void
}
; FUNC-LABEL: {{^}}fsub_v2f32:
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[3].X, -KC0[3].Z
; R600-DAG: ADD {{\** *}}T{{[0-9]+\.[XYZW]}}, KC0[2].W, -KC0[3].Y
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
define amdgpu_kernel void @fsub_v2f32(ptr addrspace(1) %out, <2 x float> %a, <2 x float> %b) {
%sub = fsub <2 x float> %a, %b
store <2 x float> %sub, ptr addrspace(1) %out, align 8
ret void
}
; FUNC-LABEL: {{^}}v_fsub_v4f32:
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; R600: ADD {{\** *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], -T[0-9]+\.[XYZW]}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{v[0-9]+}}, {{v[0-9]+}}
define amdgpu_kernel void @v_fsub_v4f32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
%b_ptr = getelementptr <4 x float>, ptr addrspace(1) %in, i32 1
%a = load <4 x float>, ptr addrspace(1) %in, align 16
%b = load <4 x float>, ptr addrspace(1) %b_ptr, align 16
%result = fsub <4 x float> %a, %b
store <4 x float> %result, ptr addrspace(1) %out, align 16
ret void
}
; FUNC-LABEL: {{^}}s_fsub_v4f32:
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: v_sub_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}, {{v[0-9]+}}
; SI: s_endpgm
define amdgpu_kernel void @s_fsub_v4f32(ptr addrspace(1) %out, <4 x float> %a, <4 x float> %b) {
%result = fsub <4 x float> %a, %b
store <4 x float> %result, ptr addrspace(1) %out, align 16
ret void
}
; FUNC-LABEL: {{^}}v_fneg_fsub_f32:
; SI: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
define amdgpu_kernel void @v_fneg_fsub_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 1
%a = load float, ptr addrspace(1) %in, align 4
%b = load float, ptr addrspace(1) %b_ptr, align 4
%result = fsub float %a, %b
%neg.result = fsub float -0.0, %result
store float %neg.result, ptr addrspace(1) %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_f32:
; SI: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
; SI-NOT: xor
define amdgpu_kernel void @v_fneg_fsub_nsz_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) {
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 1
%a = load float, ptr addrspace(1) %in, align 4
%b = load float, ptr addrspace(1) %b_ptr, align 4
%result = fsub nsz float %a, %b
%neg.result = fsub float -0.0, %result
store float %neg.result, ptr addrspace(1) %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_attribute_f32:
; SI: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
; SI-NOT: xor
define amdgpu_kernel void @v_fneg_fsub_nsz_attribute_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 1
%a = load float, ptr addrspace(1) %in, align 4
%b = load float, ptr addrspace(1) %b_ptr, align 4
%result = fsub float %a, %b
%neg.result = fsub float -0.0, %result
store float %neg.result, ptr addrspace(1) %out, align 4
ret void
}
; For some reason the attribute has a string "true" or "false", so
; make sure it is disabled and the fneg is not folded if it is not
; "true".
; FUNC-LABEL: {{^}}v_fneg_fsub_nsz_false_attribute_f32:
; SI: v_sub_f32_e32 [[SUB:v[0-9]+]], {{v[0-9]+}}, {{v[0-9]+}}
; SI: v_xor_b32_e32 v{{[0-9]+}}, 0x80000000, [[SUB]]
define amdgpu_kernel void @v_fneg_fsub_nsz_false_attribute_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) #1 {
%b_ptr = getelementptr float, ptr addrspace(1) %in, i32 1
%a = load float, ptr addrspace(1) %in, align 4
%b = load float, ptr addrspace(1) %b_ptr, align 4
%result = fsub float %a, %b
%neg.result = fsub float -0.0, %result
store float %neg.result, ptr addrspace(1) %out, align 4
ret void
}
; FUNC-LABEL: {{^}}v_fsub_0_nsz_attribute_f32:
; SI-NOT: v_sub
define amdgpu_kernel void @v_fsub_0_nsz_attribute_f32(ptr addrspace(1) %out, ptr addrspace(1) %in) #0 {
%a = load float, ptr addrspace(1) %in, align 4
%result = fsub float %a, 0.0
store float %result, ptr addrspace(1) %out, align 4
ret void
}
attributes #0 = { nounwind "no-signed-zeros-fp-math"="true" }
attributes #1 = { nounwind "no-signed-zeros-fp-math"="false" }
|
