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
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -march=amdgcn -mcpu=gfx1010 -amdgpu-opt-vgpr-liverange=true -verify-machineinstrs < %s | FileCheck -check-prefix=SI %s
; a normal if-else
define amdgpu_ps float @else1(i32 %z, float %v) #0 {
; SI-LABEL: else1:
; SI: ; %bb.0: ; %main_body
; SI-NEXT: v_cmp_gt_i32_e32 vcc_lo, 6, v0
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: s_and_saveexec_b32 s0, vcc_lo
; SI-NEXT: s_xor_b32 s0, exec_lo, s0
; SI-NEXT: s_cbranch_execnz .LBB0_3
; SI-NEXT: ; %bb.1: ; %Flow
; SI-NEXT: s_andn2_saveexec_b32 s0, s0
; SI-NEXT: s_cbranch_execnz .LBB0_4
; SI-NEXT: .LBB0_2: ; %end
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s0
; SI-NEXT: s_branch .LBB0_5
; SI-NEXT: .LBB0_3: ; %else
; SI-NEXT: v_mul_f32_e32 v0, 0x40400000, v1
; SI-NEXT: ; implicit-def: $vgpr1
; SI-NEXT: s_andn2_saveexec_b32 s0, s0
; SI-NEXT: s_cbranch_execz .LBB0_2
; SI-NEXT: .LBB0_4: ; %if
; SI-NEXT: v_add_f32_e32 v0, v1, v1
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s0
; SI-NEXT: s_branch .LBB0_5
; SI-NEXT: .LBB0_5:
main_body:
%cc = icmp sgt i32 %z, 5
br i1 %cc, label %if, label %else
if:
%v.if = fmul float %v, 2.0
br label %end
else:
%v.else = fmul float %v, 3.0
br label %end
end:
%r = phi float [ %v.if, %if ], [ %v.else, %else ]
ret float %r
}
; %v was used after if-else
define amdgpu_ps float @else2(i32 %z, float %v) #0 {
; SI-LABEL: else2:
; SI: ; %bb.0: ; %main_body
; SI-NEXT: v_cmp_gt_i32_e32 vcc_lo, 6, v0
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: s_and_saveexec_b32 s0, vcc_lo
; SI-NEXT: s_xor_b32 s0, exec_lo, s0
; SI-NEXT: ; %bb.1: ; %else
; SI-NEXT: v_mul_f32_e32 v0, 0x40400000, v1
; SI-NEXT: ; %bb.2: ; %Flow
; SI-NEXT: s_andn2_saveexec_b32 s0, s0
; SI-NEXT: ; %bb.3: ; %if
; SI-NEXT: v_add_f32_e32 v1, v1, v1
; SI-NEXT: v_mov_b32_e32 v0, v1
; SI-NEXT: ; %bb.4: ; %end
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s0
; SI-NEXT: v_add_f32_e32 v0, v1, v0
; SI-NEXT: ; return to shader part epilog
main_body:
%cc = icmp sgt i32 %z, 5
br i1 %cc, label %if, label %else
if:
%v.if = fmul float %v, 2.0
br label %end
else:
%v.else = fmul float %v, 3.0
br label %end
end:
%r0 = phi float [ %v.if, %if ], [ %v, %else ]
%r1 = phi float [ %v.if, %if ], [ %v.else, %else ]
%r2 = fadd float %r0, %r1
ret float %r2
}
; if-else inside loop, %x can be optimized, but %v cannot be.
define amdgpu_ps float @else3(i32 %z, float %v, i32 inreg %bound, i32 %x0) #0 {
; SI-LABEL: else3:
; SI: ; %bb.0: ; %entry
; SI-NEXT: v_cmp_gt_i32_e32 vcc_lo, 6, v0
; SI-NEXT: s_mov_b32 s1, 0
; SI-NEXT: s_branch .LBB2_2
; SI-NEXT: .LBB2_1: ; %if.end
; SI-NEXT: ; in Loop: Header=BB2_2 Depth=1
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s2
; SI-NEXT: v_add_nc_u32_e32 v2, 1, v0
; SI-NEXT: s_add_i32 s1, s1, 1
; SI-NEXT: s_cmp_lt_i32 s1, s0
; SI-NEXT: s_cbranch_scc0 .LBB2_6
; SI-NEXT: .LBB2_2: ; %for.body
; SI-NEXT: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: ; implicit-def: $vgpr3
; SI-NEXT: s_and_saveexec_b32 s2, vcc_lo
; SI-NEXT: s_xor_b32 s2, exec_lo, s2
; SI-NEXT: ; %bb.3: ; %else
; SI-NEXT: ; in Loop: Header=BB2_2 Depth=1
; SI-NEXT: v_mul_lo_u32 v0, v2, 3
; SI-NEXT: v_mul_f32_e32 v3, v1, v2
; SI-NEXT: ; implicit-def: $vgpr2
; SI-NEXT: ; %bb.4: ; %Flow
; SI-NEXT: ; in Loop: Header=BB2_2 Depth=1
; SI-NEXT: s_andn2_saveexec_b32 s2, s2
; SI-NEXT: s_cbranch_execz .LBB2_1
; SI-NEXT: ; %bb.5: ; %if
; SI-NEXT: ; in Loop: Header=BB2_2 Depth=1
; SI-NEXT: v_mul_f32_e32 v3, s1, v1
; SI-NEXT: v_add_nc_u32_e32 v0, 1, v2
; SI-NEXT: s_branch .LBB2_1
; SI-NEXT: .LBB2_6: ; %for.end
; SI-NEXT: v_add_f32_e32 v0, v0, v3
; SI-NEXT: ; return to shader part epilog
entry:
; %break = icmp sgt i32 %bound, 0
; br i1 %break, label %for.body, label %for.end
br label %for.body
for.body:
%i = phi i32 [ 0, %entry ], [ %inc, %if.end ]
%x = phi i32 [ %x0, %entry ], [ %xinc, %if.end ]
%cc = icmp sgt i32 %z, 5
br i1 %cc, label %if, label %else
if:
%i.tmp = bitcast i32 %i to float
%v.if = fmul float %v, %i.tmp
%x.if = add i32 %x, 1
br label %if.end
else:
%x.tmp = bitcast i32 %x to float
%v.else = fmul float %v, %x.tmp
%x.else = mul i32 %x, 3
br label %if.end
if.end:
%v.endif = phi float [ %v.if, %if ], [ %v.else, %else ]
%x.endif = phi i32 [ %x.if, %if ], [ %x.else, %else ]
%xinc = add i32 %x.endif, 1
%inc = add i32 %i, 1
%cond = icmp slt i32 %inc, %bound
br i1 %cond, label %for.body, label %for.end
for.end:
%x_float = bitcast i32 %x.endif to float
%r = fadd float %x_float, %v.endif
ret float %r
}
; a loop inside an if-else
define amdgpu_ps float @loop(i32 %z, float %v, i32 inreg %bound, ptr %extern_func, ptr %extern_func2) #0 {
; SI-LABEL: loop:
; SI: ; %bb.0: ; %main_body
; SI-NEXT: v_mov_b32_e32 v6, v0
; SI-NEXT: s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; SI-NEXT: s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; SI-NEXT: s_mov_b32 s14, -1
; SI-NEXT: v_mov_b32_e32 v0, v1
; SI-NEXT: v_cmp_gt_i32_e32 vcc_lo, 6, v6
; SI-NEXT: s_mov_b32 s15, 0x31c16000
; SI-NEXT: s_add_u32 s12, s12, s1
; SI-NEXT: s_addc_u32 s13, s13, 0
; SI-NEXT: s_mov_b32 s32, 0
; SI-NEXT: ; implicit-def: $vgpr1
; SI-NEXT: s_and_saveexec_b32 s0, vcc_lo
; SI-NEXT: s_xor_b32 s6, exec_lo, s0
; SI-NEXT: s_cbranch_execz .LBB3_4
; SI-NEXT: ; %bb.1: ; %else
; SI-NEXT: s_mov_b32 s7, exec_lo
; SI-NEXT: .LBB3_2: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: v_readfirstlane_b32 s4, v4
; SI-NEXT: v_readfirstlane_b32 s5, v5
; SI-NEXT: v_cmp_eq_u64_e32 vcc_lo, s[4:5], v[4:5]
; SI-NEXT: s_and_saveexec_b32 s8, vcc_lo
; SI-NEXT: s_mov_b64 s[0:1], s[12:13]
; SI-NEXT: s_mov_b64 s[2:3], s[14:15]
; SI-NEXT: s_swappc_b64 s[30:31], s[4:5]
; SI-NEXT: v_mov_b32_e32 v1, v0
; SI-NEXT: ; implicit-def: $vgpr4_vgpr5
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: s_xor_b32 exec_lo, exec_lo, s8
; SI-NEXT: s_cbranch_execnz .LBB3_2
; SI-NEXT: ; %bb.3:
; SI-NEXT: s_mov_b32 exec_lo, s7
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: ; implicit-def: $vgpr2
; SI-NEXT: .LBB3_4: ; %Flow
; SI-NEXT: s_andn2_saveexec_b32 s6, s6
; SI-NEXT: s_cbranch_execz .LBB3_8
; SI-NEXT: ; %bb.5: ; %if
; SI-NEXT: s_mov_b32 s7, exec_lo
; SI-NEXT: .LBB3_6: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: v_readfirstlane_b32 s4, v2
; SI-NEXT: v_readfirstlane_b32 s5, v3
; SI-NEXT: v_cmp_eq_u64_e32 vcc_lo, s[4:5], v[2:3]
; SI-NEXT: s_and_saveexec_b32 s8, vcc_lo
; SI-NEXT: s_mov_b64 s[0:1], s[12:13]
; SI-NEXT: s_mov_b64 s[2:3], s[14:15]
; SI-NEXT: s_swappc_b64 s[30:31], s[4:5]
; SI-NEXT: v_mov_b32_e32 v1, v0
; SI-NEXT: ; implicit-def: $vgpr2_vgpr3
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: s_xor_b32 exec_lo, exec_lo, s8
; SI-NEXT: s_cbranch_execnz .LBB3_6
; SI-NEXT: ; %bb.7:
; SI-NEXT: s_mov_b32 exec_lo, s7
; SI-NEXT: .LBB3_8: ; %end
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s6
; SI-NEXT: v_mov_b32_e32 v0, v1
; SI-NEXT: ; return to shader part epilog
main_body:
%cc = icmp sgt i32 %z, 5
br i1 %cc, label %if, label %else
if:
%v.if = call amdgpu_gfx float %extern_func(float %v)
br label %end
else:
%v.else = call amdgpu_gfx float %extern_func2(float %v)
br label %end
end:
%r = phi float [ %v.if, %if ], [ %v.else, %else ]
ret float %r
}
; a loop inside an if-else, but the variable is still in use after the if-else
define amdgpu_ps float @loop_with_use(i32 %z, float %v, i32 inreg %bound, ptr %extern_func, ptr %extern_func2) #0 {
; SI-LABEL: loop_with_use:
; SI: ; %bb.0: ; %main_body
; SI-NEXT: s_mov_b32 s12, SCRATCH_RSRC_DWORD0
; SI-NEXT: s_mov_b32 s13, SCRATCH_RSRC_DWORD1
; SI-NEXT: s_mov_b32 s14, -1
; SI-NEXT: v_mov_b32_e32 v40, v1
; SI-NEXT: v_cmp_gt_i32_e32 vcc_lo, 6, v0
; SI-NEXT: s_mov_b32 s15, 0x31c16000
; SI-NEXT: s_add_u32 s12, s12, s1
; SI-NEXT: s_addc_u32 s13, s13, 0
; SI-NEXT: s_mov_b32 s32, 0
; SI-NEXT: ; implicit-def: $vgpr0
; SI-NEXT: s_and_saveexec_b32 s0, vcc_lo
; SI-NEXT: s_xor_b32 s6, exec_lo, s0
; SI-NEXT: s_cbranch_execz .LBB4_4
; SI-NEXT: ; %bb.1: ; %else
; SI-NEXT: s_mov_b32 s7, exec_lo
; SI-NEXT: .LBB4_2: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: v_readfirstlane_b32 s4, v4
; SI-NEXT: v_readfirstlane_b32 s5, v5
; SI-NEXT: v_cmp_eq_u64_e32 vcc_lo, s[4:5], v[4:5]
; SI-NEXT: s_and_saveexec_b32 s8, vcc_lo
; SI-NEXT: v_mov_b32_e32 v0, v40
; SI-NEXT: s_mov_b64 s[0:1], s[12:13]
; SI-NEXT: s_mov_b64 s[2:3], s[14:15]
; SI-NEXT: s_swappc_b64 s[30:31], s[4:5]
; SI-NEXT: ; implicit-def: $vgpr4_vgpr5
; SI-NEXT: s_xor_b32 exec_lo, exec_lo, s8
; SI-NEXT: s_cbranch_execnz .LBB4_2
; SI-NEXT: ; %bb.3:
; SI-NEXT: s_mov_b32 exec_lo, s7
; SI-NEXT: ; implicit-def: $vgpr2
; SI-NEXT: .LBB4_4: ; %Flow
; SI-NEXT: s_andn2_saveexec_b32 s6, s6
; SI-NEXT: s_cbranch_execz .LBB4_8
; SI-NEXT: ; %bb.5: ; %if
; SI-NEXT: s_mov_b32 s7, exec_lo
; SI-NEXT: .LBB4_6: ; =>This Inner Loop Header: Depth=1
; SI-NEXT: v_readfirstlane_b32 s4, v2
; SI-NEXT: v_readfirstlane_b32 s5, v3
; SI-NEXT: v_cmp_eq_u64_e32 vcc_lo, s[4:5], v[2:3]
; SI-NEXT: s_and_saveexec_b32 s8, vcc_lo
; SI-NEXT: v_mov_b32_e32 v0, v40
; SI-NEXT: s_mov_b64 s[0:1], s[12:13]
; SI-NEXT: s_mov_b64 s[2:3], s[14:15]
; SI-NEXT: s_swappc_b64 s[30:31], s[4:5]
; SI-NEXT: ; implicit-def: $vgpr2_vgpr3
; SI-NEXT: s_xor_b32 exec_lo, exec_lo, s8
; SI-NEXT: s_cbranch_execnz .LBB4_6
; SI-NEXT: ; %bb.7:
; SI-NEXT: s_mov_b32 exec_lo, s7
; SI-NEXT: .LBB4_8: ; %end
; SI-NEXT: s_or_b32 exec_lo, exec_lo, s6
; SI-NEXT: v_add_f32_e32 v0, v0, v40
; SI-NEXT: ; return to shader part epilog
main_body:
%cc = icmp sgt i32 %z, 5
br i1 %cc, label %if, label %else
if:
%v.if = call amdgpu_gfx float %extern_func(float %v)
br label %end
else:
%v.else = call amdgpu_gfx float %extern_func2(float %v)
br label %end
end:
%r = phi float [ %v.if, %if ], [ %v.else, %else ]
%r2 = fadd float %r, %v
ret float %r2
}
attributes #0 = { nounwind }
|
