summaryrefslogtreecommitdiffstats
path: root/test/CodeGen/R600/mul.ll
blob: be5d6a0a2bacda1332155ead7cd24b8950b2dee1 (plain)
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
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
; RUN: llc -march=r600 -mcpu=redwood < %s | FileCheck -check-prefix=EG %s -check-prefix=FUNC
; RUN: llc -march=r600 -mcpu=verde -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s

; mul24 and mad24 are affected

; FUNC-LABEL: {{^}}test_mul_v2i32:
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}

; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}

define void @test_mul_v2i32(<2 x i32> addrspace(1)* %out, <2 x i32> addrspace(1)* %in) {
  %b_ptr = getelementptr <2 x i32> addrspace(1)* %in, i32 1
  %a = load <2 x i32> addrspace(1) * %in
  %b = load <2 x i32> addrspace(1) * %b_ptr
  %result = mul <2 x i32> %a, %b
  store <2 x i32> %result, <2 x i32> addrspace(1)* %out
  ret void
}

; FUNC-LABEL: {{^}}v_mul_v4i32:
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}
; EG: MULLO_INT {{\*? *}}T{{[0-9]+\.[XYZW], T[0-9]+\.[XYZW], T[0-9]+\.[XYZW]}}

; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}
; SI: v_mul_lo_i32 v{{[0-9]+, v[0-9]+, v[0-9]+}}

define void @v_mul_v4i32(<4 x i32> addrspace(1)* %out, <4 x i32> addrspace(1)* %in) {
  %b_ptr = getelementptr <4 x i32> addrspace(1)* %in, i32 1
  %a = load <4 x i32> addrspace(1) * %in
  %b = load <4 x i32> addrspace(1) * %b_ptr
  %result = mul <4 x i32> %a, %b
  store <4 x i32> %result, <4 x i32> addrspace(1)* %out
  ret void
}

; FUNC-LABEL: {{^}}s_trunc_i64_mul_to_i32:
; SI: s_load_dword
; SI: s_load_dword
; SI: s_mul_i32
; SI: buffer_store_dword
define void @s_trunc_i64_mul_to_i32(i32 addrspace(1)* %out, i64 %a, i64 %b) {
  %mul = mul i64 %b, %a
  %trunc = trunc i64 %mul to i32
  store i32 %trunc, i32 addrspace(1)* %out, align 8
  ret void
}

; FUNC-LABEL: {{^}}v_trunc_i64_mul_to_i32:
; SI: s_load_dword
; SI: s_load_dword
; SI: v_mul_lo_i32
; SI: buffer_store_dword
define void @v_trunc_i64_mul_to_i32(i32 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) nounwind {
  %a = load i64 addrspace(1)* %aptr, align 8
  %b = load i64 addrspace(1)* %bptr, align 8
  %mul = mul i64 %b, %a
  %trunc = trunc i64 %mul to i32
  store i32 %trunc, i32 addrspace(1)* %out, align 8
  ret void
}

; This 64-bit multiply should just use MUL_HI and MUL_LO, since the top
; 32-bits of both arguments are sign bits.
; FUNC-LABEL: {{^}}mul64_sext_c:
; EG-DAG: MULLO_INT
; EG-DAG: MULHI_INT
; SI-DAG: s_mul_i32
; SI-DAG: v_mul_hi_i32
define void @mul64_sext_c(i64 addrspace(1)* %out, i32 %in) {
entry:
  %0 = sext i32 %in to i64
  %1 = mul i64 %0, 80
  store i64 %1, i64 addrspace(1)* %out
  ret void
}

; FUNC-LABEL: {{^}}v_mul64_sext_c:
; EG-DAG: MULLO_INT
; EG-DAG: MULHI_INT
; SI-DAG: v_mul_lo_i32
; SI-DAG: v_mul_hi_i32
; SI: s_endpgm
define void @v_mul64_sext_c(i64 addrspace(1)* %out, i32 addrspace(1)* %in) {
  %val = load i32 addrspace(1)* %in, align 4
  %ext = sext i32 %val to i64
  %mul = mul i64 %ext, 80
  store i64 %mul, i64 addrspace(1)* %out, align 8
  ret void
}

; FUNC-LABEL: {{^}}v_mul64_sext_inline_imm:
; SI-DAG: v_mul_lo_i32 v{{[0-9]+}}, 9, v{{[0-9]+}}
; SI-DAG: v_mul_hi_i32 v{{[0-9]+}}, 9, v{{[0-9]+}}
; SI: s_endpgm
define void @v_mul64_sext_inline_imm(i64 addrspace(1)* %out, i32 addrspace(1)* %in) {
  %val = load i32 addrspace(1)* %in, align 4
  %ext = sext i32 %val to i64
  %mul = mul i64 %ext, 9
  store i64 %mul, i64 addrspace(1)* %out, align 8
  ret void
}

; FUNC-LABEL: {{^}}s_mul_i32:
; SI: s_load_dword [[SRC0:s[0-9]+]],
; SI: s_load_dword [[SRC1:s[0-9]+]],
; SI: s_mul_i32 [[SRESULT:s[0-9]+]], [[SRC0]], [[SRC1]]
; SI: v_mov_b32_e32 [[VRESULT:v[0-9]+]], [[SRESULT]]
; SI: buffer_store_dword [[VRESULT]],
; SI: s_endpgm
define void @s_mul_i32(i32 addrspace(1)* %out, i32 %a, i32 %b) nounwind {
  %mul = mul i32 %a, %b
  store i32 %mul, i32 addrspace(1)* %out, align 4
  ret void
}

; FUNC-LABEL: {{^}}v_mul_i32:
; SI: v_mul_lo_i32 v{{[0-9]+}}, v{{[0-9]+}}, v{{[0-9]+}}
define void @v_mul_i32(i32 addrspace(1)* %out, i32 addrspace(1)* %in) {
  %b_ptr = getelementptr i32 addrspace(1)* %in, i32 1
  %a = load i32 addrspace(1)* %in
  %b = load i32 addrspace(1)* %b_ptr
  %result = mul i32 %a, %b
  store i32 %result, i32 addrspace(1)* %out
  ret void
}

; A standard 64-bit multiply.  The expansion should be around 6 instructions.
; It would be difficult to match the expansion correctly without writing
; a really complicated list of FileCheck expressions.  I don't want
; to confuse people who may 'break' this test with a correct optimization,
; so this test just uses FUNC-LABEL to make sure the compiler does not
; crash with a 'failed to select' error.

; FUNC-LABEL: {{^}}s_mul_i64:
define void @s_mul_i64(i64 addrspace(1)* %out, i64 %a, i64 %b) nounwind {
  %mul = mul i64 %a, %b
  store i64 %mul, i64 addrspace(1)* %out, align 8
  ret void
}

; FUNC-LABEL: {{^}}v_mul_i64:
; SI: v_mul_lo_i32
define void @v_mul_i64(i64 addrspace(1)* %out, i64 addrspace(1)* %aptr, i64 addrspace(1)* %bptr) {
  %a = load i64 addrspace(1)* %aptr, align 8
  %b = load i64 addrspace(1)* %bptr, align 8
  %mul = mul i64 %a, %b
  store i64 %mul, i64 addrspace(1)* %out, align 8
  ret void
}

; FUNC-LABEL: {{^}}mul32_in_branch:
; SI: s_mul_i32
define void @mul32_in_branch(i32 addrspace(1)* %out, i32 addrspace(1)* %in, i32 %a, i32 %b, i32 %c) {
entry:
  %0 = icmp eq i32 %a, 0
  br i1 %0, label %if, label %else

if:
  %1 = load i32 addrspace(1)* %in
  br label %endif

else:
  %2 = mul i32 %a, %b
  br label %endif

endif:
  %3 = phi i32 [%1, %if], [%2, %else]
  store i32 %3, i32 addrspace(1)* %out
  ret void
}

; FUNC-LABEL: {{^}}mul64_in_branch:
; SI-DAG: s_mul_i32
; SI-DAG: v_mul_hi_u32
; SI: s_endpgm
define void @mul64_in_branch(i64 addrspace(1)* %out, i64 addrspace(1)* %in, i64 %a, i64 %b, i64 %c) {
entry:
  %0 = icmp eq i64 %a, 0
  br i1 %0, label %if, label %else

if:
  %1 = load i64 addrspace(1)* %in
  br label %endif

else:
  %2 = mul i64 %a, %b
  br label %endif

endif:
  %3 = phi i64 [%1, %if], [%2, %else]
  store i64 %3, i64 addrspace(1)* %out
  ret void
}