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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx900 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX9-DENORM %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX10-DENORM %s
; fold (fsub (fpext (fneg (fmul, x, y))), z) -> (fneg (fma (fpext x), (fpext y), z))
define amdgpu_vs float @test_f16_to_f32_sub_ext_neg_mul(half %x, half %y, float %z) {
; GFX9-DENORM-LABEL: test_f16_to_f32_sub_ext_neg_mul:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v0
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e64 v1, -v1
; GFX9-DENORM-NEXT: v_mad_f32 v0, v0, v1, -v2
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_f16_to_f32_sub_ext_neg_mul:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v0
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e64 v1, -v1
; GFX10-DENORM-NEXT: v_fma_f32 v0, v0, v1, -v2
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast half %x, %y
%b = fneg half %a
%c = fpext half %b to float
%d = fsub fast float %c, %z
ret float %d
}
; fold (fsub (fneg (fpext (fmul, x, y))), z) -> (fneg (fma (fpext x)), (fpext y), z)
define amdgpu_vs float @test_f16_to_f32_sub_neg_ext_mul(half %x, half %y, float %z) {
; GFX9-DENORM-LABEL: test_f16_to_f32_sub_neg_ext_mul:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v0
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e64 v1, -v1
; GFX9-DENORM-NEXT: v_mad_f32 v0, v0, v1, -v2
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_f16_to_f32_sub_neg_ext_mul:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v0
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e64 v1, -v1
; GFX10-DENORM-NEXT: v_fma_f32 v0, v0, v1, -v2
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast half %x, %y
%b = fpext half %a to float
%c = fneg float %b
%d = fsub fast float %c, %z
ret float %d
}
; fold (fsub x, (fpext (fneg (fmul y, z)))) -> (fma (fpext y), (fpext z), x)
define amdgpu_vs float @test_f16_to_f32_sub_ext_neg_mul2(float %x, half %y, half %z) {
; GFX9-DENORM-LABEL: test_f16_to_f32_sub_ext_neg_mul2:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v1, v1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e64 v2, -v2
; GFX9-DENORM-NEXT: v_mad_f32 v0, -v1, v2, v0
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_f16_to_f32_sub_ext_neg_mul2:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v1, v1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e64 v2, -v2
; GFX10-DENORM-NEXT: v_fma_f32 v0, -v1, v2, v0
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast half %y, %z
%b = fneg half %a
%c = fpext half %b to float
%d = fsub fast float %x, %c
ret float %d
}
; fold (fsub x, (fneg (fpext (fmul y, z)))) -> (fma (fpext y), (fpext z), x)
define amdgpu_vs float @test_f16_to_f32_sub_neg_ext_mul2(float %x, half %y, half %z) {
; GFX9-DENORM-LABEL: test_f16_to_f32_sub_neg_ext_mul2:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v1, v1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e64 v2, -v2
; GFX9-DENORM-NEXT: v_mad_f32 v0, -v1, v2, v0
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_f16_to_f32_sub_neg_ext_mul2:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v1, v1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e64 v2, -v2
; GFX10-DENORM-NEXT: v_fma_f32 v0, -v1, v2, v0
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast half %y, %z
%b = fpext half %a to float
%c = fneg float %b
%d = fsub fast float %x, %c
ret float %d
}
; fold (fsub (fpext (fneg (fmul, x, y))), z) -> (fneg (fma (fpext x), (fpext y), z))
define amdgpu_vs <4 x float> @test_v4f16_to_v4f32_sub_ext_neg_mul(<4 x half> %x, <4 x half> %y, <4 x float> %z) {
; GFX9-DENORM-LABEL: test_v4f16_to_v4f32_sub_ext_neg_mul:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v2, v0
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v3, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v9, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_sub_f32_e32 v0, v2, v4
; GFX9-DENORM-NEXT: v_sub_f32_e32 v1, v3, v5
; GFX9-DENORM-NEXT: v_sub_f32_e32 v2, v8, v6
; GFX9-DENORM-NEXT: v_sub_f32_e32 v3, v9, v7
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_v4f16_to_v4f32_sub_ext_neg_mul:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: s_mov_b32 s0, 0x80008000
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v0
; GFX10-DENORM-NEXT: v_xor_b32_e32 v2, s0, v2
; GFX10-DENORM-NEXT: v_xor_b32_e32 v3, s0, v3
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v9, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v10, v1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v11, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v2
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v2, v3
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v3, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_fma_f32 v0, v8, v0, -v4
; GFX10-DENORM-NEXT: v_fma_f32 v1, v9, v1, -v5
; GFX10-DENORM-NEXT: v_fma_f32 v2, v10, v2, -v6
; GFX10-DENORM-NEXT: v_fma_f32 v3, v11, v3, -v7
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast <4 x half> %x, %y
%b = fneg <4 x half> %a
%c = fpext <4 x half> %b to <4 x float>
%d = fsub fast <4 x float> %c, %z
ret <4 x float> %d
}
; fold (fsub (fneg (fpext (fmul, x, y))), z) -> (fneg (fma (fpext x)), (fpext y), z)
define amdgpu_vs <4 x float> @test_v4f16_to_v4f32_sub_neg_ext_mul(<4 x half> %x, <4 x half> %y, <4 x float> %z) {
; GFX9-DENORM-LABEL: test_v4f16_to_v4f32_sub_neg_ext_mul:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_pk_mul_f16 v0, v0, v2 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_pk_mul_f16 v1, v1, v3 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v2, v0
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v3, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v9, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_sub_f32_e32 v0, v2, v4
; GFX9-DENORM-NEXT: v_sub_f32_e32 v1, v3, v5
; GFX9-DENORM-NEXT: v_sub_f32_e32 v2, v8, v6
; GFX9-DENORM-NEXT: v_sub_f32_e32 v3, v9, v7
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_v4f16_to_v4f32_sub_neg_ext_mul:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: s_mov_b32 s0, 0x80008000
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v0
; GFX10-DENORM-NEXT: v_xor_b32_e32 v2, s0, v2
; GFX10-DENORM-NEXT: v_xor_b32_e32 v3, s0, v3
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v9, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v10, v1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v11, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v0, v2
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v1, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v2, v3
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v3, v3 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_fma_f32 v0, v8, v0, -v4
; GFX10-DENORM-NEXT: v_fma_f32 v1, v9, v1, -v5
; GFX10-DENORM-NEXT: v_fma_f32 v2, v10, v2, -v6
; GFX10-DENORM-NEXT: v_fma_f32 v3, v11, v3, -v7
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast <4 x half> %x, %y
%b = fpext <4 x half> %a to <4 x float>
%c = fneg <4 x float> %b
%d = fsub fast <4 x float> %c, %z
ret <4 x float> %d
}
; fold (fsub x, (fpext (fneg (fmul y, z)))) -> (fma (fpext y), (fpext z), x)
define amdgpu_vs <4 x float> @test_v4f16_to_v4f32_sub_ext_neg_mul2(<4 x float> %x, <4 x half> %y, <4 x half> %z) {
; GFX9-DENORM-LABEL: test_v4f16_to_v4f32_sub_ext_neg_mul2:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_pk_mul_f16 v4, v4, v6 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_pk_mul_f16 v5, v5, v7 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v6, v4
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v7, v5
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v5, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_sub_f32_e32 v0, v0, v6
; GFX9-DENORM-NEXT: v_sub_f32_e32 v1, v1, v4
; GFX9-DENORM-NEXT: v_sub_f32_e32 v2, v2, v7
; GFX9-DENORM-NEXT: v_sub_f32_e32 v3, v3, v5
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_v4f16_to_v4f32_sub_ext_neg_mul2:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: s_mov_b32 s0, 0x80008000
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v4
; GFX10-DENORM-NEXT: v_xor_b32_e32 v6, s0, v6
; GFX10-DENORM-NEXT: v_xor_b32_e32 v7, s0, v7
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v9, v5
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v5, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v10, v6
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v6, v6 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v11, v7
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v7, v7 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_fma_f32 v0, -v8, v10, v0
; GFX10-DENORM-NEXT: v_fma_f32 v1, -v4, v6, v1
; GFX10-DENORM-NEXT: v_fma_f32 v2, -v9, v11, v2
; GFX10-DENORM-NEXT: v_fma_f32 v3, -v5, v7, v3
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast <4 x half> %y, %z
%b = fneg <4 x half> %a
%c = fpext <4 x half> %b to <4 x float>
%d = fsub fast <4 x float> %x, %c
ret <4 x float> %d
}
; fold (fsub x, (fneg (fpext (fmul y, z)))) -> (fma (fpext y), (fpext z), x)
define amdgpu_vs <4 x float> @test_v4f16_to_v4f32_sub_neg_ext_mul2(<4 x float> %x, <4 x half> %y, <4 x half> %z) {
; GFX9-DENORM-LABEL: test_v4f16_to_v4f32_sub_neg_ext_mul2:
; GFX9-DENORM: ; %bb.0: ; %entry
; GFX9-DENORM-NEXT: v_pk_mul_f16 v4, v4, v6 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_pk_mul_f16 v5, v5, v7 neg_lo:[0,1] neg_hi:[0,1]
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v6, v4
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_cvt_f32_f16_e32 v7, v5
; GFX9-DENORM-NEXT: v_cvt_f32_f16_sdwa v5, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-DENORM-NEXT: v_sub_f32_e32 v0, v0, v6
; GFX9-DENORM-NEXT: v_sub_f32_e32 v1, v1, v4
; GFX9-DENORM-NEXT: v_sub_f32_e32 v2, v2, v7
; GFX9-DENORM-NEXT: v_sub_f32_e32 v3, v3, v5
; GFX9-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-DENORM-LABEL: test_v4f16_to_v4f32_sub_neg_ext_mul2:
; GFX10-DENORM: ; %bb.0: ; %entry
; GFX10-DENORM-NEXT: s_mov_b32 s0, 0x80008000
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v8, v4
; GFX10-DENORM-NEXT: v_xor_b32_e32 v6, s0, v6
; GFX10-DENORM-NEXT: v_xor_b32_e32 v7, s0, v7
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v4 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v9, v5
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v5, v5 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v10, v6
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v6, v6 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_cvt_f32_f16_e32 v11, v7
; GFX10-DENORM-NEXT: v_cvt_f32_f16_sdwa v7, v7 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX10-DENORM-NEXT: v_fma_f32 v0, -v8, v10, v0
; GFX10-DENORM-NEXT: v_fma_f32 v1, -v4, v6, v1
; GFX10-DENORM-NEXT: v_fma_f32 v2, -v9, v11, v2
; GFX10-DENORM-NEXT: v_fma_f32 v3, -v5, v7, v3
; GFX10-DENORM-NEXT: ; return to shader part epilog
entry:
%a = fmul fast <4 x half> %y, %z
%b = fpext <4 x half> %a to <4 x float>
%c = fneg <4 x float> %b
%d = fsub fast <4 x float> %x, %c
ret <4 x float> %d
}
|
