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
|
// REQUIRES: x86-registered-target, nvptx-registered-target, amdgpu-registered-target
// By default CUDA uses -ffp-contract=fast, HIP uses -ffp-contract=fast-honor-pragmas.
// we should fuse multiply/add into fma instruction.
// In IR, fmul/fadd instructions with contract flag are emitted.
// In backend
// nvptx - assumes fast fp fuse option, which fuses
// mult/add insts disregarding contract flag and
// llvm.fmuladd intrinsics.
// amdgcn - assumes standard fp fuse option, which only
// fuses mult/add insts with contract flag and
// llvm.fmuladd intrinsics.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -target-cpu gfx906 -disable-llvm-passes -o - -x hip %s \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -O3 -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OPT-FAST %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x hip %s \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FASTSTD %s
// Check separate compile/backend steps corresponding to -save-temps.
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
// RUN: -O3 -disable-llvm-passes -target-cpu gfx906 -o %t.ll -x hip %s
// RUN: cat %t.ll | FileCheck -check-prefixes=COMMON,AMD-OPT-FAST-IR %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x ir %t.ll \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FASTSTD %s
// Explicit -ffp-contract=fast
// In IR, fmul/fadd instructions with contract flag are emitted.
// In backend
// nvptx/amdgcn - assumes fast fp fuse option, which fuses
// mult/add insts disregarding contract flag and
// llvm.fmuladd intrinsics.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=fast -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -target-cpu gfx906 -disable-llvm-passes -o - -x hip %s \
// RUN: -ffp-contract=fast \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -O3 -o - %s \
// RUN: -ffp-contract=fast \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OPT-FAST %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x hip %s \
// RUN: -ffp-contract=fast \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FAST %s
// Check separate compile/backend steps corresponding to -save-temps.
// When input is IR, -ffp-contract has no effect. Backend uses default
// default FP fuse option.
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
// RUN: -ffp-contract=fast \
// RUN: -O3 -disable-llvm-passes -target-cpu gfx906 -o %t.ll -x hip %s
// RUN: cat %t.ll | FileCheck -check-prefixes=COMMON,AMD-OPT-FAST-IR %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x ir %t.ll \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FASTSTD %s
// Explicit -ffp-contract=fast-honor-pragmas
// In IR, fmul/fadd instructions with contract flag are emitted.
// In backend
// nvptx/amdgcn - assumes standard fp fuse option, which only
// fuses mult/add insts with contract flag or
// llvm.fmuladd intrinsics.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=fast-honor-pragmas -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -target-cpu gfx906 -disable-llvm-passes -o - -x hip %s \
// RUN: -ffp-contract=fast-honor-pragmas \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -O3 -o - %s \
// RUN: -ffp-contract=fast-honor-pragmas \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OPT-FASTSTD %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x hip %s \
// RUN: -ffp-contract=fast-honor-pragmas \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FASTSTD %s
// Check separate compile/backend steps corresponding to -save-temps.
// When input is IR, -ffp-contract has no effect. Backend uses default
// default FP fuse option.
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
// RUN: -ffp-contract=fast-honor-pragmas \
// RUN: -O3 -disable-llvm-passes -target-cpu gfx906 -o %t.ll -x hip %s
// RUN: cat %t.ll | FileCheck -check-prefixes=COMMON,AMD-OPT-FAST-IR %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x ir %t.ll \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-FASTSTD %s
// Explicit -ffp-contract=on -- fusing by front-end.
// In IR,
// mult/add in the same statement - llvm.fmuladd intrinsic emitted
// mult/add in different statement - fmul/fadd instructions without
// contract flag are emitted.
// In backend
// nvptx/amdgcn - assumes standard fp fuse option, which only
// fuses mult/add insts with contract flag or
// llvm.fmuladd intrinsics.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=on -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -target-cpu gfx906 -disable-llvm-passes -o - -x hip %s \
// RUN: -ffp-contract=on \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -O3 -o - %s \
// RUN: -ffp-contract=on \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OPT-ON %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x hip %s \
// RUN: -ffp-contract=on \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-ON %s
// Check separate compile/backend steps corresponding to -save-temps.
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
// RUN: -ffp-contract=on \
// RUN: -O3 -disable-llvm-passes -target-cpu gfx906 -o %t.ll -x hip %s
// RUN: cat %t.ll | FileCheck -check-prefixes=COMMON,AMD-OPT-ON-IR %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x ir %t.ll \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-ON %s
// Explicit -ffp-contract=off should disable instruction fusing.
// In IR, fmul/fadd instructions without contract flag are emitted.
// In backend
// nvptx/amdgcn - assumes standard fp fuse option, which only
// fuses mult/add insts with contract flag or
// llvm.fmuladd intrinsics.
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -ffp-contract=off -disable-llvm-passes -o - %s \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OFF %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -target-cpu gfx906 -disable-llvm-passes -o - -x hip %s \
// RUN: -ffp-contract=off \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OFF %s
// RUN: %clang_cc1 -fcuda-is-device -triple nvptx-nvidia-cuda -S \
// RUN: -O3 -o - %s \
// RUN: -ffp-contract=off \
// RUN: | FileCheck -check-prefixes=COMMON,NV-OPT-OFF %s
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x hip %s \
// RUN: -ffp-contract=off \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-OFF %s
// Check separate compile/backend steps corresponding to -save-temps.
// RUN: %clang_cc1 -fcuda-is-device -triple amdgcn-amd-amdhsa -emit-llvm \
// RUN: -ffp-contract=off \
// RUN: -O3 -disable-llvm-passes -target-cpu gfx906 -o %t.ll -x hip %s
// RUN: cat %t.ll | FileCheck -check-prefixes=COMMON,AMD-OPT-OFF-IR %s
// RUN: %clang_cc1 -triple amdgcn-amd-amdhsa -S \
// RUN: -O3 -target-cpu gfx906 -o - -x ir %t.ll \
// RUN: | FileCheck -check-prefixes=COMMON,AMD-OPT-OFF %s
#include "Inputs/cuda.h"
// Test multiply/add in the same statement, which can be emitted as FMA when
// fp-contract is on or fast.
__host__ __device__ float func(float a, float b, float c) { return a + b * c; }
// COMMON-LABEL: _Z4funcfff
// NV-ON: fma.rn.f32
// NV-ON-NEXT: st.param.f32
// AMD-ON: v_fmac_f32_e64
// AMD-ON-NEXT: s_setpc_b64
// NV-OFF: mul.rn.f32
// NV-OFF-NEXT: add.rn.f32
// NV-OFF-NEXT: st.param.f32
// AMD-OFF: v_mul_f32_e64
// AMD-OFF-NEXT: v_add_f32_e64
// AMD-OFF-NEXT: s_setpc_b64
// NV-OPT-FAST: fma.rn.f32
// NV-OPT-FAST-NEXT: st.param.f32
// NV-OPT-FASTSTD: fma.rn.f32
// NV-OPT-FASTSTD-NEXT: st.param.f32
// NV-OPT-ON: fma.rn.f32
// NV-OPT-ON-NEXT: st.param.f32
// NV-OPT-OFF: mul.rn.f32
// NV-OPT-OFF-NEXT: add.rn.f32
// NV-OPT-OFF-NEXT: st.param.f32
// AMD-OPT-FAST-IR: fmul contract float
// AMD-OPT-FAST-IR: fadd contract float
// AMD-OPT-ON-IR: @llvm.fmuladd.f32
// AMD-OPT-OFF-IR: fmul float
// AMD-OPT-OFF-IR: fadd float
// AMD-OPT-FAST: v_fmac_f32_e32
// AMD-OPT-FAST-NEXT: s_setpc_b64
// AMD-OPT-FASTSTD: v_fmac_f32_e32
// AMD-OPT-FASTSTD-NEXT: s_setpc_b64
// AMD-OPT-ON: v_fmac_f32_e32
// AMD-OPT-ON-NEXT: s_setpc_b64
// AMD-OPT-OFF: v_mul_f32_e32
// AMD-OPT-OFF-NEXT: v_add_f32_e32
// AMD-OPT-OFF-NEXT: s_setpc_b64
// Test multiply/add in the different statements, which can be emitted as
// FMA when fp-contract is fast but not on.
__host__ __device__ float func2(float a, float b, float c) {
float t = b * c;
return t + a;
}
// COMMON-LABEL: _Z5func2fff
// NV-OPT-FAST: fma.rn.f32
// NV-OPT-FAST-NEXT: st.param.f32
// NV-OPT-FASTSTD: fma.rn.f32
// NV-OPT-FASTSTD-NEXT: st.param.f32
// NV-OPT-ON: mul.rn.f32
// NV-OPT-ON: add.rn.f32
// NV-OPT-ON-NEXT: st.param.f32
// NV-OPT-OFF: mul.rn.f32
// NV-OPT-OFF: add.rn.f32
// NV-OPT-OFF-NEXT: st.param.f32
// AMD-OPT-FAST-IR: fmul contract float
// AMD-OPT-FAST-IR: fadd contract float
// AMD-OPT-ON-IR: fmul float
// AMD-OPT-ON-IR: fadd float
// AMD-OPT-OFF-IR: fmul float
// AMD-OPT-OFF-IR: fadd float
// AMD-OPT-FAST: v_fmac_f32_e32
// AMD-OPT-FAST-NEXT: s_setpc_b64
// AMD-OPT-FASTSTD: v_fmac_f32_e32
// AMD-OPT-FASTSTD-NEXT: s_setpc_b64
// AMD-OPT-ON: v_mul_f32_e32
// AMD-OPT-ON-NEXT: v_add_f32_e32
// AMD-OPT-ON-NEXT: s_setpc_b64
// AMD-OPT-OFF: v_mul_f32_e32
// AMD-OPT-OFF-NEXT: v_add_f32_e32
// AMD-OPT-OFF-NEXT: s_setpc_b64
// Test multiply/add in the different statements, which is forced
// to be compiled with fp contract on. fmul/fadd without contract
// flags are emitted in IR. In nvptx, they are emitted as FMA in
// fp-contract is fast but not on, as nvptx backend uses the same
// fp fuse option as front end, whereas fast fp fuse option in
// backend fuses fadd/fmul disregarding contract flag. In amdgcn
// they are not fused as amdgcn always use standard fp fusion
// option which respects contract flag.
__host__ __device__ float func3(float a, float b, float c) {
#pragma clang fp contract(on)
float t = b * c;
return t + a;
}
// COMMON-LABEL: _Z5func3fff
// NV-OPT-FAST: fma.rn.f32
// NV-OPT-FAST-NEXT: st.param.f32
// NV-OPT-FASTSTD: mul.rn.f32
// NV-OPT-FASTSTD: add.rn.f32
// NV-OPT-FASTSTD-NEXT: st.param.f32
// NV-OPT-ON: mul.rn.f32
// NV-OPT-ON: add.rn.f32
// NV-OPT-ON-NEXT: st.param.f32
// NV-OPT-OFF: mul.rn.f32
// NV-OPT-OFF: add.rn.f32
// NV-OPT-OFF-NEXT: st.param.f32
// AMD-OPT-FAST-IR: fmul float
// AMD-OPT-FAST-IR: fadd float
// AMD-OPT-ON-IR: fmul float
// AMD-OPT-ON-IR: fadd float
// AMD-OPT-OFF-IR: fmul float
// AMD-OPT-OFF-IR: fadd float
// AMD-OPT-FAST: v_fmac_f32_e32
// AMD-OPT-FAST-NEXT: s_setpc_b64
// AMD-OPT-FASTSTD: v_mul_f32_e32
// AMD-OPT-FASTSTD-NEXT: v_add_f32_e32
// AMD-OPT-FASTSTD-NEXT: s_setpc_b64
// AMD-OPT-ON: v_mul_f32_e32
// AMD-OPT-ON-NEXT: v_add_f32_e32
// AMD-OPT-ON-NEXT: s_setpc_b64
// AMD-OPT-OFF: v_mul_f32_e32
// AMD-OPT-OFF-NEXT: v_add_f32_e32
// AMD-OPT-OFF-NEXT: s_setpc_b64
|
