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
|
; 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-FAST-DENORM %s
; RUN: llc -global-isel -march=amdgcn -mcpu=gfx1010 --denormal-fp-math=preserve-sign < %s | FileCheck -check-prefix=GFX10-FAST-DENORM %s
; fold (fadd fast (fpext (fmul fast x, y)), z) -> (fma (fpext x), (fpext y), z)
; fold (fadd fast x, (fpext (fmul fast y, z))) -> (fma (fpext y), (fpext z), x)
define amdgpu_vs float @test_f16_f32_add_ext_mul(half inreg %x, half inreg %y, float inreg %z) {
; GFX9-FAST-DENORM-LABEL: test_f16_f32_add_ext_mul:
; GFX9-FAST-DENORM: ; %bb.0: ; %.entry
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s1
; GFX9-FAST-DENORM-NEXT: v_mad_f32 v0, v0, v1, s2
; GFX9-FAST-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-FAST-DENORM-LABEL: test_f16_f32_add_ext_mul:
; GFX10-FAST-DENORM: ; %bb.0: ; %.entry
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s1
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v0, v0, v1, s2
; GFX10-FAST-DENORM-NEXT: ; return to shader part epilog
.entry:
%a = fmul fast half %x, %y
%b = fpext half %a to float
%c = fadd fast float %b, %z
ret float %c
}
define amdgpu_vs float @test_f16_f32_add_ext_mul_rhs(half inreg %x, half inreg %y, float inreg %z) {
; GFX9-FAST-DENORM-LABEL: test_f16_f32_add_ext_mul_rhs:
; GFX9-FAST-DENORM: ; %bb.0: ; %.entry
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s1
; GFX9-FAST-DENORM-NEXT: v_mad_f32 v0, v0, v1, s2
; GFX9-FAST-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-FAST-DENORM-LABEL: test_f16_f32_add_ext_mul_rhs:
; GFX10-FAST-DENORM: ; %bb.0: ; %.entry
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s1
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v0, v0, v1, s2
; GFX10-FAST-DENORM-NEXT: ; return to shader part epilog
.entry:
%a = fmul fast half %x, %y
%b = fpext half %a to float
%c = fadd fast float %z, %b
ret float %c
}
define amdgpu_vs <5 x float> @test_5xf16_5xf32_add_ext_mul(<5 x half> inreg %x, <5 x half> inreg %y, <5 x float> inreg %z) {
; GFX9-FAST-DENORM-LABEL: test_5xf16_5xf32_add_ext_mul:
; GFX9-FAST-DENORM: ; %bb.0: ; %.entry
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s3, s3, s3
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s4, s4, s4
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s0, s0, s0
; GFX9-FAST-DENORM-NEXT: s_pack_lh_b32_b16 s1, s1, s1
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v0, s3
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v1, s4
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v2, s5
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v0, s0, v0
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v1, s1, v1
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v2, s2, v2
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, v0
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v5, v1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v6, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v7, v2
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v0, s6, v3
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v1, s7, v4
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v2, s8, v5
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v3, s9, v6
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v4, s10, v7
; GFX9-FAST-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-FAST-DENORM-LABEL: test_5xf16_5xf32_add_ext_mul:
; GFX10-FAST-DENORM: ; %bb.0: ; %.entry
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s11, s0, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s12, s1, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s13, s3, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s14, s4, 16
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s11
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v2, s1
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, s12
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v4, s2
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v5, s3
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v6, s13
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v7, s4
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v8, s14
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v9, s5
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v0, v0, v5, s6
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v1, v1, v6, s7
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v2, v2, v7, s8
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v3, v3, v8, s9
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v4, v4, v9, s10
; GFX10-FAST-DENORM-NEXT: ; return to shader part epilog
.entry:
%a = fmul fast <5 x half> %x, %y
%b = fpext <5 x half> %a to <5 x float>
%c = fadd fast <5 x float> %b, %z
ret <5 x float> %c
}
define amdgpu_vs <6 x float> @test_6xf16_6xf32_add_ext_mul_rhs(<6 x half> inreg %x, <6 x half> inreg %y, <6 x float> inreg %z) {
; GFX9-FAST-DENORM-LABEL: test_6xf16_6xf32_add_ext_mul_rhs:
; GFX9-FAST-DENORM: ; %bb.0: ; %.entry
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v0, s3
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v1, s4
; GFX9-FAST-DENORM-NEXT: v_mov_b32_e32 v2, s5
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v0, s0, v0
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v1, s1, v1
; GFX9-FAST-DENORM-NEXT: v_pk_mul_f16 v2, s2, v2
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, v0
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v4, v0 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v5, v1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v6, v1 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v7, v2
; GFX9-FAST-DENORM-NEXT: v_cvt_f32_f16_sdwa v8, v2 dst_sel:DWORD dst_unused:UNUSED_PAD src0_sel:WORD_1
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v0, s6, v3
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v1, s7, v4
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v2, s8, v5
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v3, s9, v6
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v4, s10, v7
; GFX9-FAST-DENORM-NEXT: v_add_f32_e32 v5, s11, v8
; GFX9-FAST-DENORM-NEXT: ; return to shader part epilog
;
; GFX10-FAST-DENORM-LABEL: test_6xf16_6xf32_add_ext_mul_rhs:
; GFX10-FAST-DENORM: ; %bb.0: ; %.entry
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s12, s0, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s13, s1, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s14, s2, 16
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v0, s0
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v2, s1
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v4, s2
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s0, s3, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s1, s4, 16
; GFX10-FAST-DENORM-NEXT: s_lshr_b32 s2, s5, 16
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v1, s12
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v3, s13
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v5, s14
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v6, s3
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v7, s0
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v8, s4
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v9, s1
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v10, s5
; GFX10-FAST-DENORM-NEXT: v_cvt_f32_f16_e32 v11, s2
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v0, v0, v6, s6
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v1, v1, v7, s7
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v2, v2, v8, s8
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v3, v3, v9, s9
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v4, v4, v10, s10
; GFX10-FAST-DENORM-NEXT: v_fma_f32 v5, v5, v11, s11
; GFX10-FAST-DENORM-NEXT: ; return to shader part epilog
.entry:
%a = fmul fast <6 x half> %x, %y
%b = fpext <6 x half> %a to <6 x float>
%c = fadd fast <6 x float> %z, %b
ret <6 x float> %c
}
|
