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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
; RUN: llc -mtriple=aarch64-none-linux-gnu < %s -o -| FileCheck %s
define void @matrix_mul_unsigned(i32 %N, i32* nocapture %C, i16* nocapture readonly %A, i16 %val) {
; CHECK-LABEL: matrix_mul_unsigned:
; CHECK: // %bb.0: // %vector.header
; CHECK-NEXT: and w8, w3, #0xffff
; CHECK-NEXT: // kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: dup v0.4h, w8
; CHECK-NEXT: and x8, x0, #0xfffffff8
; CHECK-NEXT: .LBB0_1: // %vector.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: add x9, x2, w0, uxtw #1
; CHECK-NEXT: subs x8, x8, #8
; CHECK-NEXT: ldp d1, d2, [x9]
; CHECK-NEXT: add x9, x1, w0, uxtw #2
; CHECK-NEXT: add w0, w0, #8
; CHECK-NEXT: umull v1.4s, v0.4h, v1.4h
; CHECK-NEXT: umull v2.4s, v0.4h, v2.4h
; CHECK-NEXT: stp q1, q2, [x9]
; CHECK-NEXT: b.ne .LBB0_1
; CHECK-NEXT: // %bb.2: // %for.end12
; CHECK-NEXT: ret
vector.header:
%conv4 = zext i16 %val to i32
%wide.trip.count = zext i32 %N to i64
%0 = add nsw i64 %wide.trip.count, -1
%min.iters.check = icmp ult i32 %N, 8
%1 = trunc i64 %0 to i32
%2 = icmp ugt i64 %0, 4294967295
%n.vec = and i64 %wide.trip.count, 4294967288
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %conv4, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%broadcast.splatinsert31 = insertelement <4 x i32> undef, i32 %conv4, i32 0
%broadcast.splat32 = shufflevector <4 x i32> %broadcast.splatinsert31, <4 x i32> undef, <4 x i32> zeroinitializer
%cmp.n = icmp eq i64 %n.vec, %wide.trip.count
br label %vector.body
vector.body: ; preds = %vector.header, %vector.body
%index = phi i64 [ %index.next, %vector.body ], [ 0, %vector.header ]
%3 = trunc i64 %index to i32
%4 = add i32 %N, %3
%5 = zext i32 %4 to i64
%6 = getelementptr inbounds i16, i16* %A, i64 %5
%7 = bitcast i16* %6 to <4 x i16>*
%wide.load = load <4 x i16>, <4 x i16>* %7, align 2
%8 = getelementptr inbounds i16, i16* %6, i64 4
%9 = bitcast i16* %8 to <4 x i16>*
%wide.load30 = load <4 x i16>, <4 x i16>* %9, align 2
%10 = zext <4 x i16> %wide.load to <4 x i32>
%11 = zext <4 x i16> %wide.load30 to <4 x i32>
%12 = mul nuw nsw <4 x i32> %broadcast.splat, %10
%13 = mul nuw nsw <4 x i32> %broadcast.splat32, %11
%14 = getelementptr inbounds i32, i32* %C, i64 %5
%15 = bitcast i32* %14 to <4 x i32>*
store <4 x i32> %12, <4 x i32>* %15, align 4
%16 = getelementptr inbounds i32, i32* %14, i64 4
%17 = bitcast i32* %16 to <4 x i32>*
store <4 x i32> %13, <4 x i32>* %17, align 4
%index.next = add i64 %index, 8
%18 = icmp eq i64 %index.next, %n.vec
br i1 %18, label %for.end12, label %vector.body
for.end12: ; preds = %vector.body
ret void
}
define void @matrix_mul_signed(i32 %N, i32* nocapture %C, i16* nocapture readonly %A, i16 %val) {
; CHECK-LABEL: matrix_mul_signed:
; CHECK: // %bb.0: // %vector.header
; CHECK-NEXT: sxth w8, w3
; CHECK-NEXT: // kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: dup v0.4h, w8
; CHECK-NEXT: and x8, x0, #0xfffffff8
; CHECK-NEXT: .LBB1_1: // %vector.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: add x9, x2, w0, sxtw #1
; CHECK-NEXT: subs x8, x8, #8
; CHECK-NEXT: ldp d1, d2, [x9]
; CHECK-NEXT: add x9, x1, w0, sxtw #2
; CHECK-NEXT: add w0, w0, #8
; CHECK-NEXT: smull v1.4s, v0.4h, v1.4h
; CHECK-NEXT: smull v2.4s, v0.4h, v2.4h
; CHECK-NEXT: stp q1, q2, [x9]
; CHECK-NEXT: b.ne .LBB1_1
; CHECK-NEXT: // %bb.2: // %for.end12
; CHECK-NEXT: ret
vector.header:
%conv4 = sext i16 %val to i32
%wide.trip.count = sext i32 %N to i64
%0 = add nsw i64 %wide.trip.count, -1
%min.iters.check = icmp ult i32 %N, 8
%1 = trunc i64 %0 to i32
%2 = icmp ugt i64 %0, 4294967295
%n.vec = and i64 %wide.trip.count, 4294967288
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %conv4, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%broadcast.splatinsert31 = insertelement <4 x i32> undef, i32 %conv4, i32 0
%broadcast.splat32 = shufflevector <4 x i32> %broadcast.splatinsert31, <4 x i32> undef, <4 x i32> zeroinitializer
%cmp.n = icmp eq i64 %n.vec, %wide.trip.count
br label %vector.body
vector.body: ; preds = %vector.header, %vector.body
%index = phi i64 [ %index.next, %vector.body ], [ 0, %vector.header ]
%3 = trunc i64 %index to i32
%4 = add i32 %N, %3
%5 = sext i32 %4 to i64
%6 = getelementptr inbounds i16, i16* %A, i64 %5
%7 = bitcast i16* %6 to <4 x i16>*
%wide.load = load <4 x i16>, <4 x i16>* %7, align 2
%8 = getelementptr inbounds i16, i16* %6, i64 4
%9 = bitcast i16* %8 to <4 x i16>*
%wide.load30 = load <4 x i16>, <4 x i16>* %9, align 2
%10 = sext <4 x i16> %wide.load to <4 x i32>
%11 = sext <4 x i16> %wide.load30 to <4 x i32>
%12 = mul nsw <4 x i32> %broadcast.splat, %10
%13 = mul nsw <4 x i32> %broadcast.splat32, %11
%14 = getelementptr inbounds i32, i32* %C, i64 %5
%15 = bitcast i32* %14 to <4 x i32>*
store <4 x i32> %12, <4 x i32>* %15, align 4
%16 = getelementptr inbounds i32, i32* %14, i64 4
%17 = bitcast i32* %16 to <4 x i32>*
store <4 x i32> %13, <4 x i32>* %17, align 4
%index.next = add i64 %index, 8
%18 = icmp eq i64 %index.next, %n.vec
br i1 %18, label %for.end12, label %vector.body
for.end12: ; preds = %vector.body
ret void
}
define void @matrix_mul_double_shuffle(i32 %N, i32* nocapture %C, i16* nocapture readonly %A, i16 %val) {
; CHECK-LABEL: matrix_mul_double_shuffle:
; CHECK: // %bb.0: // %vector.header
; CHECK-NEXT: and w8, w3, #0xffff
; CHECK-NEXT: // kill: def $w0 killed $w0 def $x0
; CHECK-NEXT: dup v0.4h, w8
; CHECK-NEXT: and x8, x0, #0xfffffff8
; CHECK-NEXT: .LBB2_1: // %vector.body
; CHECK-NEXT: // =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldrh w9, [x2], #16
; CHECK-NEXT: subs x8, x8, #8
; CHECK-NEXT: dup v1.4h, w9
; CHECK-NEXT: mov w9, w0
; CHECK-NEXT: lsl x9, x9, #2
; CHECK-NEXT: add w0, w0, #8
; CHECK-NEXT: umull v1.4s, v0.4h, v1.4h
; CHECK-NEXT: str q1, [x1, x9]
; CHECK-NEXT: b.ne .LBB2_1
; CHECK-NEXT: // %bb.2: // %for.end12
; CHECK-NEXT: ret
vector.header:
%conv4 = zext i16 %val to i32
%wide.trip.count = zext i32 %N to i64
%0 = add nsw i64 %wide.trip.count, -1
%min.iters.check = icmp ult i32 %N, 8
%1 = trunc i64 %0 to i32
%2 = icmp ugt i64 %0, 4294967295
%n.vec = and i64 %wide.trip.count, 4294967288
%broadcast.splatinsert = insertelement <4 x i32> undef, i32 %conv4, i32 0
%broadcast.splat = shufflevector <4 x i32> %broadcast.splatinsert, <4 x i32> undef, <4 x i32> zeroinitializer
%cmp.n = icmp eq i64 %n.vec, %wide.trip.count
br label %vector.body
vector.body: ; preds = %vector.header, %vector.body
%index = phi i64 [ %index.next, %vector.body ], [ 0, %vector.header ]
%g = getelementptr inbounds i16, i16* %A, i64 %index
%val1 = load i16, i16* %g
%splat.input.ext = zext i16 %val1 to i32
%broadcast.splatinsert31 = insertelement <4 x i32> undef, i32 %splat.input.ext, i32 0
%broadcast.splat32 = shufflevector <4 x i32> %broadcast.splatinsert31, <4 x i32> %broadcast.splat, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
%3 = trunc i64 %index to i32
%4 = add i32 %N, %3
%5 = zext i32 %4 to i64
%6 = mul nuw nsw <4 x i32> %broadcast.splat, %broadcast.splat32
%7 = getelementptr inbounds i32, i32* %C, i64 %5
%8 = bitcast i32* %7 to <4 x i32>*
store <4 x i32> %6, <4 x i32>* %8, align 4
%index.next = add i64 %index, 8
%9 = icmp eq i64 %index.next, %n.vec
br i1 %9, label %for.end12, label %vector.body
for.end12: ; preds = %vector.body
ret void
}
|
