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
|
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; REQUIRES: aarch64-registered-target
; RUN: opt -passes='lower-matrix-intrinsics' -mtriple=arm64-apple-iphoneos -S < %s | FileCheck %s
define <1 x float> @dotproduct_float_v6(<6 x float> %a, <6 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x float> [[A:%.*]], <6 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 1>
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 2>
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 3>
; CHECK-NEXT: [[SPLIT4:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 4>
; CHECK-NEXT: [[SPLIT5:%.*]] = shufflevector <6 x float> [[A]], <6 x float> poison, <1 x i32> <i32 5>
; CHECK-NEXT: [[SPLIT6:%.*]] = shufflevector <6 x float> [[B:%.*]], <6 x float> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x float> [[SPLIT]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x float> poison, float [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <1 x float> [[BLOCK]], [[SPLAT_SPLAT]]
; CHECK-NEXT: [[BLOCK7:%.*]] = shufflevector <1 x float> [[SPLIT1]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 1
; CHECK-NEXT: [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT8]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK7]], <1 x float> [[SPLAT_SPLAT9]], <1 x float> [[TMP1]])
; CHECK-NEXT: [[BLOCK10:%.*]] = shufflevector <1 x float> [[SPLIT2]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 2
; CHECK-NEXT: [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x float> poison, float [[TMP4]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT11]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP5:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK10]], <1 x float> [[SPLAT_SPLAT12]], <1 x float> [[TMP3]])
; CHECK-NEXT: [[BLOCK13:%.*]] = shufflevector <1 x float> [[SPLIT3]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 3
; CHECK-NEXT: [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x float> poison, float [[TMP6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT14]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP7:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK13]], <1 x float> [[SPLAT_SPLAT15]], <1 x float> [[TMP5]])
; CHECK-NEXT: [[BLOCK16:%.*]] = shufflevector <1 x float> [[SPLIT4]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 4
; CHECK-NEXT: [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x float> poison, float [[TMP8]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT17]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK16]], <1 x float> [[SPLAT_SPLAT18]], <1 x float> [[TMP7]])
; CHECK-NEXT: [[BLOCK19:%.*]] = shufflevector <1 x float> [[SPLIT5]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x float> [[SPLIT6]], i64 5
; CHECK-NEXT: [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x float> poison, float [[TMP10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x float> [[SPLAT_SPLATINSERT20]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x float> @llvm.fmuladd.v1f32(<1 x float> [[BLOCK19]], <1 x float> [[SPLAT_SPLAT21]], <1 x float> [[TMP9]])
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x float> [[TMP11]], <1 x float> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <1 x float> poison, <1 x float> [[TMP12]], <1 x i32> <i32 1>
; CHECK-NEXT: ret <1 x float> [[TMP13]]
;
entry:
%c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %a, <6 x float> %b, i32 1, i32 6, i32 1)
ret <1 x float> %c
}
declare <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float>, <6 x float>, i32, i32, i32)
define <1 x float> @dotproduct_float_v1(<1 x float> %a, <1 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v1(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = fmul <1 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v1f32(float 0.000000e+00, <1 x float> [[TMP0]])
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: ret <1 x float> [[TMP2]]
;
entry:
%c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float> %a, <1 x float> %b, i32 1, i32 1, i32 1)
ret <1 x float> %c
}
declare <1 x float> @llvm.matrix.multiply.v1f32.v1f32.v1f32(<1 x float>, <1 x float>, i32, i32, i32)
define <1 x float> @dotproduct_float_v3(<3 x float> %a, <3 x float> %b) {
; CHECK-LABEL: @dotproduct_float_v3(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[TMP0:%.*]] = fmul <3 x float> [[A:%.*]], [[B:%.*]]
; CHECK-NEXT: [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v3f32(float 0.000000e+00, <3 x float> [[TMP0]])
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: ret <1 x float> [[TMP2]]
;
entry:
%c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float> %a, <3 x float> %b, i32 1, i32 3, i32 1)
ret <1 x float> %c
}
declare <1 x float> @llvm.matrix.multiply.v1f32.v3f32.v3f32(<3 x float>, <3 x float>, i32, i32, i32)
define <1 x float> @intrinsic_column_major_load_dot_product_float_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_float_v6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <6 x float>, ptr [[RHS_ADDRESS:%.*]], align 4
; CHECK-NEXT: [[TMP0:%.*]] = load <6 x float>, ptr [[LHS_ADDRESS:%.*]], align 32
; CHECK-NEXT: [[TMP1:%.*]] = fmul <6 x float> [[TMP0]], [[COL_LOAD]]
; CHECK-NEXT: [[TMP2:%.*]] = call fast float @llvm.vector.reduce.fadd.v6f32(float 0.000000e+00, <6 x float> [[TMP1]])
; CHECK-NEXT: [[TMP3:%.*]] = insertelement <1 x float> poison, float [[TMP2]], i64 0
; CHECK-NEXT: ret <1 x float> [[TMP3]]
;
entry:
%lhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
%rhs = tail call fast <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
%result = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v6f32.v6f32(<6 x float> %lhs, <6 x float> %rhs, i32 1, i32 6, i32 1)
ret <1 x float> %result
}
declare <6 x float> @llvm.matrix.column.major.load.v6f32.i64(ptr nonnull align 4, i64, i1, i32, i32)
define <1 x float> @LoadInst_dot_product_float_v7(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @LoadInst_dot_product_float_v7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LHS:%.*]] = load <7 x float>, ptr [[LHS_ADDRESS:%.*]], align 32
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <7 x float>, ptr [[RHS_ADDRESS:%.*]], align 32
; CHECK-NEXT: [[TMP0:%.*]] = fmul <7 x float> [[LHS]], [[COL_LOAD]]
; CHECK-NEXT: [[TMP1:%.*]] = call fast float @llvm.vector.reduce.fadd.v7f32(float 0.000000e+00, <7 x float> [[TMP0]])
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <1 x float> poison, float [[TMP1]], i64 0
; CHECK-NEXT: ret <1 x float> [[TMP2]]
;
entry:
%lhs = load <7 x float>, ptr %lhs_address
%rhs = load <7 x float>, ptr %rhs_address
%c = tail call fast <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float> %lhs, <7 x float> %rhs, i32 1, i32 7, i32 1)
ret <1 x float> %c
}
declare <1 x float> @llvm.matrix.multiply.v1f32.v7f32.v7f32(<7 x float>, <7 x float>, i32, i32, i32)
define <1 x double> @dotproduct_double_v6(<6 x double> %a, <6 x double> %b) {
; CHECK-LABEL: @dotproduct_double_v6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[SPLIT:%.*]] = shufflevector <6 x double> [[A:%.*]], <6 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[SPLIT1:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 1>
; CHECK-NEXT: [[SPLIT2:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 2>
; CHECK-NEXT: [[SPLIT3:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 3>
; CHECK-NEXT: [[SPLIT4:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 4>
; CHECK-NEXT: [[SPLIT5:%.*]] = shufflevector <6 x double> [[A]], <6 x double> poison, <1 x i32> <i32 5>
; CHECK-NEXT: [[SPLIT6:%.*]] = shufflevector <6 x double> [[B:%.*]], <6 x double> poison, <6 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5>
; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x double> [[SPLIT]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
; CHECK-NEXT: [[BLOCK7:%.*]] = shufflevector <1 x double> [[SPLIT1]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 1
; CHECK-NEXT: [[SPLAT_SPLATINSERT8:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT9:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT8]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK7]], <1 x double> [[SPLAT_SPLAT9]], <1 x double> [[TMP1]])
; CHECK-NEXT: [[BLOCK10:%.*]] = shufflevector <1 x double> [[SPLIT2]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 2
; CHECK-NEXT: [[SPLAT_SPLATINSERT11:%.*]] = insertelement <1 x double> poison, double [[TMP4]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT12:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT11]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP5:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK10]], <1 x double> [[SPLAT_SPLAT12]], <1 x double> [[TMP3]])
; CHECK-NEXT: [[BLOCK13:%.*]] = shufflevector <1 x double> [[SPLIT3]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 3
; CHECK-NEXT: [[SPLAT_SPLATINSERT14:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT15:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT14]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP7:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK13]], <1 x double> [[SPLAT_SPLAT15]], <1 x double> [[TMP5]])
; CHECK-NEXT: [[BLOCK16:%.*]] = shufflevector <1 x double> [[SPLIT4]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 4
; CHECK-NEXT: [[SPLAT_SPLATINSERT17:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT18:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT17]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK16]], <1 x double> [[SPLAT_SPLAT18]], <1 x double> [[TMP7]])
; CHECK-NEXT: [[BLOCK19:%.*]] = shufflevector <1 x double> [[SPLIT5]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x double> [[SPLIT6]], i64 5
; CHECK-NEXT: [[SPLAT_SPLATINSERT20:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT21:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT20]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK19]], <1 x double> [[SPLAT_SPLAT21]], <1 x double> [[TMP9]])
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x double> [[TMP11]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <1 x double> poison, <1 x double> [[TMP12]], <1 x i32> <i32 1>
; CHECK-NEXT: ret <1 x double> [[TMP13]]
;
entry:
%c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %a, <6 x double> %b, i32 1, i32 6, i32 1)
ret <1 x double> %c
}
declare <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double>, <6 x double>, i32, i32, i32)
define <1 x double> @intrinsic_column_major_load_dot_product_double_v6(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @intrinsic_column_major_load_dot_product_double_v6(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <1 x double>, ptr [[LHS_ADDRESS:%.*]], align 4
; CHECK-NEXT: [[VEC_GEP:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 1
; CHECK-NEXT: [[COL_LOAD1:%.*]] = load <1 x double>, ptr [[VEC_GEP]], align 4
; CHECK-NEXT: [[VEC_GEP2:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 2
; CHECK-NEXT: [[COL_LOAD3:%.*]] = load <1 x double>, ptr [[VEC_GEP2]], align 4
; CHECK-NEXT: [[VEC_GEP4:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 3
; CHECK-NEXT: [[COL_LOAD5:%.*]] = load <1 x double>, ptr [[VEC_GEP4]], align 4
; CHECK-NEXT: [[VEC_GEP6:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 4
; CHECK-NEXT: [[COL_LOAD7:%.*]] = load <1 x double>, ptr [[VEC_GEP6]], align 4
; CHECK-NEXT: [[VEC_GEP8:%.*]] = getelementptr double, ptr [[LHS_ADDRESS]], i64 5
; CHECK-NEXT: [[COL_LOAD9:%.*]] = load <1 x double>, ptr [[VEC_GEP8]], align 4
; CHECK-NEXT: [[COL_LOAD10:%.*]] = load <6 x double>, ptr [[RHS_ADDRESS:%.*]], align 4
; CHECK-NEXT: [[BLOCK:%.*]] = shufflevector <1 x double> [[COL_LOAD]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP0:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLATINSERT:%.*]] = insertelement <1 x double> poison, double [[TMP0]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP1:%.*]] = fmul fast <1 x double> [[BLOCK]], [[SPLAT_SPLAT]]
; CHECK-NEXT: [[BLOCK11:%.*]] = shufflevector <1 x double> [[COL_LOAD1]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP2:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 1
; CHECK-NEXT: [[SPLAT_SPLATINSERT12:%.*]] = insertelement <1 x double> poison, double [[TMP2]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT13:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT12]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP3:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK11]], <1 x double> [[SPLAT_SPLAT13]], <1 x double> [[TMP1]])
; CHECK-NEXT: [[BLOCK14:%.*]] = shufflevector <1 x double> [[COL_LOAD3]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP4:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 2
; CHECK-NEXT: [[SPLAT_SPLATINSERT15:%.*]] = insertelement <1 x double> poison, double [[TMP4]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT16:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT15]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP5:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK14]], <1 x double> [[SPLAT_SPLAT16]], <1 x double> [[TMP3]])
; CHECK-NEXT: [[BLOCK17:%.*]] = shufflevector <1 x double> [[COL_LOAD5]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP6:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 3
; CHECK-NEXT: [[SPLAT_SPLATINSERT18:%.*]] = insertelement <1 x double> poison, double [[TMP6]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT19:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT18]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP7:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK17]], <1 x double> [[SPLAT_SPLAT19]], <1 x double> [[TMP5]])
; CHECK-NEXT: [[BLOCK20:%.*]] = shufflevector <1 x double> [[COL_LOAD7]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP8:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 4
; CHECK-NEXT: [[SPLAT_SPLATINSERT21:%.*]] = insertelement <1 x double> poison, double [[TMP8]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT22:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT21]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP9:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK20]], <1 x double> [[SPLAT_SPLAT22]], <1 x double> [[TMP7]])
; CHECK-NEXT: [[BLOCK23:%.*]] = shufflevector <1 x double> [[COL_LOAD9]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP10:%.*]] = extractelement <6 x double> [[COL_LOAD10]], i64 5
; CHECK-NEXT: [[SPLAT_SPLATINSERT24:%.*]] = insertelement <1 x double> poison, double [[TMP10]], i64 0
; CHECK-NEXT: [[SPLAT_SPLAT25:%.*]] = shufflevector <1 x double> [[SPLAT_SPLATINSERT24]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP11:%.*]] = call fast <1 x double> @llvm.fmuladd.v1f64(<1 x double> [[BLOCK23]], <1 x double> [[SPLAT_SPLAT25]], <1 x double> [[TMP9]])
; CHECK-NEXT: [[TMP12:%.*]] = shufflevector <1 x double> [[TMP11]], <1 x double> poison, <1 x i32> zeroinitializer
; CHECK-NEXT: [[TMP13:%.*]] = shufflevector <1 x double> poison, <1 x double> [[TMP12]], <1 x i32> <i32 1>
; CHECK-NEXT: ret <1 x double> [[TMP13]]
;
entry:
%lhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %lhs_address, i64 1, i1 false, i32 1, i32 6)
%rhs = tail call fast <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4 %rhs_address, i64 6, i1 false, i32 6, i32 1)
%result = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v6f64.v6f64(<6 x double> %lhs, <6 x double> %rhs, i32 1, i32 6, i32 1)
ret <1 x double> %result
}
declare <6 x double> @llvm.matrix.column.major.load.v6f64.i64(ptr nonnull align 4, i64, i1, i32, i32)
define <1 x double> @LoadInst_dot_product_double_v7(ptr %lhs_address, ptr %rhs_address) {
; CHECK-LABEL: @LoadInst_dot_product_double_v7(
; CHECK-NEXT: entry:
; CHECK-NEXT: [[LHS:%.*]] = load <7 x double>, ptr [[LHS_ADDRESS:%.*]], align 64
; CHECK-NEXT: [[COL_LOAD:%.*]] = load <7 x double>, ptr [[RHS_ADDRESS:%.*]], align 64
; CHECK-NEXT: [[TMP0:%.*]] = fmul <7 x double> [[LHS]], [[COL_LOAD]]
; CHECK-NEXT: [[TMP1:%.*]] = call fast double @llvm.vector.reduce.fadd.v7f64(double 0.000000e+00, <7 x double> [[TMP0]])
; CHECK-NEXT: [[TMP2:%.*]] = insertelement <1 x double> poison, double [[TMP1]], i64 0
; CHECK-NEXT: ret <1 x double> [[TMP2]]
;
entry:
%lhs = load <7 x double>, ptr %lhs_address
%rhs = load <7 x double>, ptr %rhs_address
%c = tail call fast <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double> %lhs, <7 x double> %rhs, i32 1, i32 7, i32 1)
ret <1 x double> %c
}
declare <1 x double> @llvm.matrix.multiply.v1f64.v7f64.v7f64(<7 x double>, <7 x double>, i32, i32, i32)
|
