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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 3
; RUN: llc -global-isel=0 -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,SDAG %s
; RUN: llc -global-isel=1 -mtriple=amdgcn -mcpu=gfx1250 < %s | FileCheck -check-prefixes=GCN,GISEL %s
define amdgpu_ps float @add_max_u32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_u32_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, v0, v1
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_max_u32_e32 v0, v0, v2
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_svv(i32 inreg %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_u32_svv:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, s0, v0
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_max_u32_e32 v0, v0, v1
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_ssv(i32 inreg %a, i32 inreg %b, i32 %c) {
; GCN-LABEL: add_max_u32_ssv:
; GCN: ; %bb.0:
; GCN-NEXT: s_add_co_i32 s0, s0, s1
; GCN-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GCN-NEXT: v_max_u32_e32 v0, s0, v0
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_sss(i32 inreg %a, i32 inreg %b, i32 inreg %c) {
; GCN-LABEL: add_max_u32_sss:
; GCN: ; %bb.0:
; GCN-NEXT: s_add_co_i32 s0, s0, s1
; GCN-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GCN-NEXT: s_max_u32 s0, s0, s2
; GCN-NEXT: v_mov_b32_e32 v0, s0
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_vsi(i32 %a, i32 inreg %b) {
; GCN-LABEL: add_max_u32_vsi:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, s0, v0
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_max_u32_e32 v0, 4, v0
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 4)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_svl(i32 inreg %a, i32 %b) {
; GCN-LABEL: add_max_u32_svl:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, s0, v0
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_max_u32_e32 v0, 0x64, v0
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umax.i32(i32 %add, i32 100)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_u32_slv(i32 inreg %a, i32 %b) {
; GCN-LABEL: add_max_u32_slv:
; GCN: ; %bb.0:
; GCN-NEXT: s_addk_co_i32 s0, 0x64
; GCN-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GCN-NEXT: v_max_u32_e32 v0, s0, v0
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, 100
%max = call i32 @llvm.umax.i32(i32 %add, i32 %b)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_i32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_max_i32_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, v0, v1
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_max_i32_e32 v0, v0, v2
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.smax.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_min_u32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_min_u32_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, v0, v1
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_min_u32_e32 v0, v0, v2
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.umin.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_min_i32_vvv(i32 %a, i32 %b, i32 %c) {
; GCN-LABEL: add_min_i32_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_add_nc_u32_e32 v0, v0, v1
; GCN-NEXT: s_delay_alu instid0(VALU_DEP_1)
; GCN-NEXT: v_min_i32_e32 v0, v0, v2
; GCN-NEXT: ; return to shader part epilog
%add = add i32 %a, %b
%max = call i32 @llvm.smin.i32(i32 %add, i32 %c)
%ret = bitcast i32 %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2u16_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_max_u16 v0, v0, v1, v2
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_svv(<2 x i16> inreg %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2u16_svv:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_max_u16 v0, s0, v0, v1
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_ssv(<2 x i16> inreg %a, <2 x i16> inreg %b, <2 x i16> %c) {
; SDAG-LABEL: add_max_v2u16_ssv:
; SDAG: ; %bb.0:
; SDAG-NEXT: v_pk_add_max_u16 v0, s0, s1, v0
; SDAG-NEXT: ; return to shader part epilog
;
; GISEL-LABEL: add_max_v2u16_ssv:
; GISEL: ; %bb.0:
; GISEL-NEXT: s_lshr_b32 s2, s0, 16
; GISEL-NEXT: s_lshr_b32 s3, s1, 16
; GISEL-NEXT: s_add_co_i32 s0, s0, s1
; GISEL-NEXT: s_add_co_i32 s2, s2, s3
; GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GISEL-NEXT: s_pack_ll_b32_b16 s0, s0, s2
; GISEL-NEXT: v_pk_max_u16 v0, s0, v0
; GISEL-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_sss(<2 x i16> inreg %a, <2 x i16> inreg %b, <2 x i16> inreg %c) {
; SDAG-LABEL: add_max_v2u16_sss:
; SDAG: ; %bb.0:
; SDAG-NEXT: v_pk_add_u16 v0, s0, s1
; SDAG-NEXT: s_delay_alu instid0(VALU_DEP_1)
; SDAG-NEXT: v_pk_max_u16 v0, v0, s2
; SDAG-NEXT: ; return to shader part epilog
;
; GISEL-LABEL: add_max_v2u16_sss:
; GISEL: ; %bb.0:
; GISEL-NEXT: s_lshr_b32 s3, s0, 16
; GISEL-NEXT: s_lshr_b32 s4, s1, 16
; GISEL-NEXT: s_add_co_i32 s0, s0, s1
; GISEL-NEXT: s_add_co_i32 s3, s3, s4
; GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1)
; GISEL-NEXT: s_pack_ll_b32_b16 s0, s0, s3
; GISEL-NEXT: s_and_b32 s3, s2, 0xffff
; GISEL-NEXT: s_lshr_b32 s1, s0, 16
; GISEL-NEXT: s_and_b32 s0, s0, 0xffff
; GISEL-NEXT: s_lshr_b32 s2, s2, 16
; GISEL-NEXT: s_max_u32 s0, s0, s3
; GISEL-NEXT: s_max_u32 s1, s1, s2
; GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GISEL-NEXT: s_pack_ll_b32_b16 s0, s0, s1
; GISEL-NEXT: v_mov_b32_e32 v0, s0
; GISEL-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_vsi(<2 x i16> %a, <2 x i16> inreg %b) {
; GCN-LABEL: add_max_v2u16_vsi:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_max_u16 v0, v0, s0, 4
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> <i16 4, i16 0>)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_svl(<2 x i16> inreg %a, <2 x i16> %b) {
; GCN-LABEL: add_max_v2u16_svl:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_max_u16 v0, s0, v0, 0x650064
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> <i16 100, i16 101>)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2u16_slv(<2 x i16> inreg %a, <2 x i16> %b) {
; SDAG-LABEL: add_max_v2u16_slv:
; SDAG: ; %bb.0:
; SDAG-NEXT: v_pk_add_max_u16 v0, 0x640064, s0, v0
; SDAG-NEXT: ; return to shader part epilog
;
; GISEL-LABEL: add_max_v2u16_slv:
; GISEL: ; %bb.0:
; GISEL-NEXT: s_lshr_b32 s1, s0, 16
; GISEL-NEXT: s_add_co_i32 s0, s0, 0x640064
; GISEL-NEXT: s_addk_co_i32 s1, 0x64
; GISEL-NEXT: s_delay_alu instid0(SALU_CYCLE_1) | instskip(NEXT) | instid1(SALU_CYCLE_1)
; GISEL-NEXT: s_pack_ll_b32_b16 s0, s0, s1
; GISEL-NEXT: v_pk_max_u16 v0, s0, v0
; GISEL-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, <i16 100, i16 100>
%max = call <2 x i16> @llvm.umax.v216(<2 x i16> %add, <2 x i16> %b)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_max_v2s16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_max_v2s16_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_max_i16 v0, v0, v1, v2
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.smax.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_min_v2u16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_min_v2u16_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_min_u16 v0, v0, v1, v2
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.umin.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
define amdgpu_ps float @add_min_v2s16_vvv(<2 x i16> %a, <2 x i16> %b, <2 x i16> %c) {
; GCN-LABEL: add_min_v2s16_vvv:
; GCN: ; %bb.0:
; GCN-NEXT: v_pk_add_min_i16 v0, v0, v1, v2
; GCN-NEXT: ; return to shader part epilog
%add = add <2 x i16> %a, %b
%max = call <2 x i16> @llvm.smin.v216(<2 x i16> %add, <2 x i16> %c)
%ret = bitcast <2 x i16> %max to float
ret float %ret
}
declare <2 x i16> @llvm.smin.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.smax.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.umin.v216(<2 x i16>, <2 x i16>)
declare <2 x i16> @llvm.umax.v216(<2 x i16>, <2 x i16>)
declare i32 @llvm.smin.i32(i32, i32)
declare i32 @llvm.smax.i32(i32, i32)
declare i32 @llvm.umin.i32(i32, i32)
declare i32 @llvm.umax.i32(i32, i32)
|
