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
|
; RUN: opt -S -passes=loop-vectorize,instcombine -force-vector-interleave=1 -mattr=+sve -mtriple aarch64-unknown-linux-gnu \
; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
; RUN: cat %t | FileCheck %s --check-prefix=CHECK-REMARKS
; RUN: opt -S -passes=loop-vectorize,instcombine -force-vector-interleave=1 -force-target-instruction-cost=1 -mattr=+sve -mtriple aarch64-unknown-linux-gnu \
; RUN: -prefer-predicate-over-epilogue=scalar-epilogue -pass-remarks-missed=loop-vectorize < %s 2>%t | FileCheck %s
; RUN: cat %t | FileCheck %s --check-prefix=CHECK-REMARKS
define void @vec_load(i64 %N, ptr nocapture %a, ptr nocapture readonly %b) {
; CHECK-LABEL: @vec_load
; CHECK: vector.body:
; CHECK: %[[LOAD:.*]] = load <vscale x 2 x double>, ptr
; CHECK: call <vscale x 2 x double> @foo_vec(<vscale x 2 x double> %[[LOAD]])
entry:
%cmp7 = icmp sgt i64 %N, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %for.body.preheader, %for.body
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%arrayidx = getelementptr inbounds double, ptr %b, i64 %iv
%0 = load double, ptr %arrayidx, align 8
%1 = call double @foo(double %0) #0
%add = fadd double %1, 1.000000e+00
%arrayidx2 = getelementptr inbounds double, ptr %a, i64 %iv
store double %add, ptr %arrayidx2, align 8
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %N
br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !1
for.end: ; preds = %for.body, %entry
ret void
}
define void @vec_scalar(i64 %N, ptr nocapture %a) {
; CHECK-LABEL: @vec_scalar
; CHECK: vector.body:
; CHECK: call <vscale x 2 x double> @foo_vec(<vscale x 2 x double> shufflevector (<vscale x 2 x double> insertelement (<vscale x 2 x double> poison, double 1.000000e+01, i64 0), <vscale x 2 x double> poison, <vscale x 2 x i32> zeroinitializer))
entry:
%cmp7 = icmp sgt i64 %N, 0
br i1 %cmp7, label %for.body, label %for.end
for.body: ; preds = %for.body.preheader, %for.body
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%0 = call double @foo(double 10.0) #0
%sub = fsub double %0, 1.000000e+00
%arrayidx = getelementptr inbounds double, ptr %a, i64 %iv
store double %sub, ptr %arrayidx, align 8
%iv.next = add nuw nsw i64 %iv, 1
%exitcond.not = icmp eq i64 %iv.next, %N
br i1 %exitcond.not, label %for.end, label %for.body, !llvm.loop !1
for.end: ; preds = %for.body, %entry
ret void
}
define void @vec_ptr(i64 %N, ptr noalias %a, ptr readnone %b) {
; CHECK-LABEL: @vec_ptr
; CHECK: vector.body:
; CHECK: %[[LOAD:.*]] = load <vscale x 2 x ptr>, ptr
; CHECK: call <vscale x 2 x i64> @bar_vec(<vscale x 2 x ptr> %[[LOAD]])
entry:
%cmp7 = icmp sgt i64 %N, 0
br i1 %cmp7, label %for.body, label %for.end
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%gep = getelementptr ptr, ptr %b, i64 %iv
%load = load ptr, ptr %gep
%call = call i64 @bar(ptr %load) #1
%arrayidx = getelementptr inbounds i64, ptr %a, i64 %iv
store i64 %call, ptr %arrayidx
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, 1024
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
for.end:
ret void
}
define void @vec_intrinsic(i64 %N, ptr nocapture readonly %a) {
; CHECK-LABEL: @vec_intrinsic
; CHECK: vector.body:
; CHECK: %[[LOAD:.*]] = load <vscale x 2 x double>, ptr
; CHECK: call fast <vscale x 2 x double> @sin_vec_nxv2f64(<vscale x 2 x double> %[[LOAD]])
entry:
%cmp7 = icmp sgt i64 %N, 0
br i1 %cmp7, label %for.body, label %for.end
for.body:
%iv = phi i64 [ 0, %entry ], [ %iv.next, %for.body ]
%arrayidx = getelementptr inbounds double, ptr %a, i64 %iv
%0 = load double, ptr %arrayidx, align 8
%1 = call fast double @llvm.sin.f64(double %0) #2
%add = fadd fast double %1, 1.000000e+00
store double %add, ptr %arrayidx, align 8
%iv.next = add nuw nsw i64 %iv, 1
%exitcond = icmp eq i64 %iv.next, %N
br i1 %exitcond, label %for.end, label %for.body, !llvm.loop !1
for.end:
ret void
}
; CHECK-REMARKS: UserVF ignored because of invalid costs.
; CHECK-REMARKS-NEXT: t.c:3:10: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): load
; CHECK-REMARKS-NEXT: t.c:3:20: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
; CHECK-REMARKS-NEXT: t.c:3:30: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): store
define void @vec_sin_no_mapping(ptr noalias nocapture %dst, ptr noalias nocapture readonly %src, i64 %n) {
; CHECK: @vec_sin_no_mapping
; CHECK: call fast <2 x float> @llvm.sin.v2f32
; CHECK-NOT: <vscale x
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, ptr %src, i64 %i.07
%0 = load float, ptr %arrayidx, align 4, !dbg !11
%1 = tail call fast float @llvm.sin.f32(float %0), !dbg !12
%arrayidx1 = getelementptr inbounds float, ptr %dst, i64 %i.07
store float %1, ptr %arrayidx1, align 4, !dbg !13
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !1
for.cond.cleanup: ; preds = %for.body
ret void
}
; CHECK-REMARKS: UserVF ignored because of invalid costs.
; CHECK-REMARKS-NEXT: t.c:3:10: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): load
; CHECK-REMARKS-NEXT: t.c:3:30: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
; CHECK-REMARKS-NEXT: t.c:3:20: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
; CHECK-REMARKS-NEXT: t.c:3:40: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): store
define void @vec_sin_no_mapping_ite(ptr noalias nocapture %dst, ptr noalias nocapture readonly %src, i64 %n) {
; CHECK: @vec_sin_no_mapping_ite
; CHECK-NOT: <vscale x
; CHECK: ret
entry:
br label %for.body
for.body: ; preds = %entry, %if.end
%i.07 = phi i64 [ %inc, %if.end ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, ptr %src, i64 %i.07
%0 = load float, ptr %arrayidx, align 4, !dbg !11
%cmp = fcmp ugt float %0, 0.0000
br i1 %cmp, label %if.then, label %if.else
if.then:
%1 = tail call fast float @llvm.sin.f32(float %0), !dbg !12
br label %if.end
if.else:
%2 = tail call fast float @llvm.sin.f32(float 0.0), !dbg !13
br label %if.end
if.end:
%3 = phi float [%1, %if.then], [%2, %if.else]
%arrayidx1 = getelementptr inbounds float, ptr %dst, i64 %i.07
store float %3, ptr %arrayidx1, align 4, !dbg !14
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !1
for.cond.cleanup: ; preds = %for.body
ret void
}
; CHECK-REMARKS: UserVF ignored because of invalid costs.
; CHECK-REMARKS-NEXT: t.c:3:10: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): load
; CHECK-REMARKS-NEXT: t.c:3:20: Instruction with invalid costs prevented vectorization at VF=(vscale x 1, vscale x 2): call to llvm.sin.f32
; CHECK-REMARKS-NEXT: t.c:3:30: Instruction with invalid costs prevented vectorization at VF=(vscale x 1): store
define void @vec_sin_fixed_mapping(ptr noalias nocapture %dst, ptr noalias nocapture readonly %src, i64 %n) {
; CHECK: @vec_sin_fixed_mapping
; CHECK: call fast <2 x float> @llvm.sin.v2f32
; CHECK-NOT: <vscale x
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, ptr %src, i64 %i.07
%0 = load float, ptr %arrayidx, align 4, !dbg !11
%1 = tail call fast float @llvm.sin.f32(float %0) #3, !dbg !12
%arrayidx1 = getelementptr inbounds float, ptr %dst, i64 %i.07
store float %1, ptr %arrayidx1, align 4, !dbg !13
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !1
for.cond.cleanup: ; preds = %for.body
ret void
}
; Even though there are no function mappings attached to the call
; in the loop below we can still vectorize the loop because SVE has
; hardware support in the form of the 'fqsrt' instruction.
define void @vec_sqrt_no_mapping(ptr noalias nocapture %dst, ptr noalias nocapture readonly %src, i64 %n) #0 {
; CHECK: @vec_sqrt_no_mapping
; CHECK: call fast <vscale x 2 x float> @llvm.sqrt.nxv2f32
entry:
br label %for.body
for.body: ; preds = %entry, %for.body
%i.07 = phi i64 [ %inc, %for.body ], [ 0, %entry ]
%arrayidx = getelementptr inbounds float, ptr %src, i64 %i.07
%0 = load float, ptr %arrayidx, align 4
%1 = tail call fast float @llvm.sqrt.f32(float %0)
%arrayidx1 = getelementptr inbounds float, ptr %dst, i64 %i.07
store float %1, ptr %arrayidx1, align 4
%inc = add nuw nsw i64 %i.07, 1
%exitcond.not = icmp eq i64 %inc, %n
br i1 %exitcond.not, label %for.cond.cleanup, label %for.body, !llvm.loop !1
for.cond.cleanup: ; preds = %for.body
ret void
}
declare double @foo(double)
declare i64 @bar(ptr)
declare double @llvm.sin.f64(double)
declare float @llvm.sin.f32(float)
declare float @llvm.sqrt.f32(float)
declare <vscale x 2 x double> @foo_vec(<vscale x 2 x double>)
declare <vscale x 2 x i64> @bar_vec(<vscale x 2 x ptr>)
declare <vscale x 2 x double> @sin_vec_nxv2f64(<vscale x 2 x double>)
declare <2 x double> @sin_vec_v2f64(<2 x double>)
attributes #0 = { "vector-function-abi-variant"="_ZGV_LLVM_Nxv_foo(foo_vec)" }
attributes #1 = { "vector-function-abi-variant"="_ZGV_LLVM_Nxv_bar(bar_vec)" }
attributes #2 = { "vector-function-abi-variant"="_ZGV_LLVM_Nxv_llvm.sin.f64(sin_vec_nxv2f64)" }
attributes #3 = { "vector-function-abi-variant"="_ZGV_LLVM_N2v_llvm.sin.f64(sin_vec_v2f64)" }
!1 = distinct !{!1, !2, !3}
!2 = !{!"llvm.loop.vectorize.width", i32 2}
!3 = !{!"llvm.loop.vectorize.scalable.enable", i1 true}
!llvm.dbg.cu = !{!4}
!llvm.module.flags = !{!7}
!llvm.ident = !{!8}
!4 = distinct !DICompileUnit(language: DW_LANG_C99, file: !5, producer: "clang", isOptimized: true, runtimeVersion: 0, emissionKind: NoDebug, enums: !6, splitDebugInlining: false, nameTableKind: None)
!5 = !DIFile(filename: "t.c", directory: "somedir")
!6 = !{}
!7 = !{i32 2, !"Debug Info Version", i32 3}
!8 = !{!"clang"}
!9 = distinct !DISubprogram(name: "foo", scope: !5, file: !5, line: 2, type: !10, scopeLine: 2, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !4, retainedNodes: !6)
!10 = !DISubroutineType(types: !6)
!11 = !DILocation(line: 3, column: 10, scope: !9)
!12 = !DILocation(line: 3, column: 20, scope: !9)
!13 = !DILocation(line: 3, column: 30, scope: !9)
!14 = !DILocation(line: 3, column: 40, scope: !9)
|
