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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=riscv64 -mattr=+m,+v | FileCheck %s
; Test for an "Invalid size request on a scalable vector". Attempts to reduce
; the test faurther were not successful. The failure requires a shuffle with 2
; scalable->fixed extracts from the same vector. 0 is the only valid index for a
; scalable->fixed extract so the 2 extract must be the same. Shuffles with the
; same source are aggressively canonicalized to a unary shuffle so it requires
; the extracts to become identical through other optimizations without the
; shuffle being canonicalized before it is lowered.
define <2 x i32> @main(ptr %0) {
; CHECK-LABEL: main:
; CHECK: # %bb.0: # %entry
; CHECK-NEXT: vsetivli zero, 16, e32, m4, ta, ma
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: vse32.v v8, (zero)
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT: vmv.v.i v8, 0
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vmv.v.i v10, 0
; CHECK-NEXT: li a2, 64
; CHECK-NEXT: sw zero, 80(zero)
; CHECK-NEXT: lui a1, 7
; CHECK-NEXT: lui a3, 1
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vid.v v11
; CHECK-NEXT: li a4, 16
; CHECK-NEXT: lui a5, 2
; CHECK-NEXT: vsetivli zero, 4, e32, m1, ta, ma
; CHECK-NEXT: vse32.v v10, (a2)
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vmv.v.i v10, 0
; CHECK-NEXT: li a2, 24
; CHECK-NEXT: sh zero, -392(a3)
; CHECK-NEXT: sh zero, 534(a3)
; CHECK-NEXT: sh zero, 1460(a3)
; CHECK-NEXT: li a3, 32
; CHECK-NEXT: vse32.v v10, (a2)
; CHECK-NEXT: li a2, 40
; CHECK-NEXT: vsetivli zero, 8, e32, m2, ta, ma
; CHECK-NEXT: vse32.v v8, (a0)
; CHECK-NEXT: sh zero, -1710(a5)
; CHECK-NEXT: sh zero, -784(a5)
; CHECK-NEXT: sh zero, 142(a5)
; CHECK-NEXT: lw a5, -304(a1)
; CHECK-NEXT: vsetivli zero, 2, e32, mf2, ta, ma
; CHECK-NEXT: vadd.vi v9, v11, -1
; CHECK-NEXT: vse32.v v10, (a3)
; CHECK-NEXT: sh zero, 0(a0)
; CHECK-NEXT: lw a0, -188(a1)
; CHECK-NEXT: vse32.v v10, (a2)
; CHECK-NEXT: lw a2, -188(a1)
; CHECK-NEXT: lw a3, 1244(a1)
; CHECK-NEXT: vmv.v.x v8, a0
; CHECK-NEXT: lw a0, 1244(a1)
; CHECK-NEXT: lw a1, -304(a1)
; CHECK-NEXT: vmv.v.x v10, a3
; CHECK-NEXT: vmv.v.x v11, a5
; CHECK-NEXT: vslide1down.vx v8, v8, zero
; CHECK-NEXT: vslide1down.vx v10, v10, zero
; CHECK-NEXT: vmin.vv v8, v10, v8
; CHECK-NEXT: vmv.v.x v10, a0
; CHECK-NEXT: vslide1down.vx v11, v11, zero
; CHECK-NEXT: vmin.vx v10, v10, a2
; CHECK-NEXT: vmin.vx v10, v10, a1
; CHECK-NEXT: vmin.vv v11, v8, v11
; CHECK-NEXT: vmv1r.v v8, v10
; CHECK-NEXT: vand.vv v9, v11, v9
; CHECK-NEXT: vslideup.vi v8, v10, 1
; CHECK-NEXT: vse32.v v9, (a4)
; CHECK-NEXT: sh zero, 0(zero)
; CHECK-NEXT: ret
entry:
store <16 x i32> zeroinitializer, ptr null, align 4
store <8 x i32> zeroinitializer, ptr %0, align 4
store <4 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 64), align 4
store i32 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 80), align 4
%1 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
%broadcast.splatinsert53 = insertelement <4 x i32> zeroinitializer, i32 %1, i64 0
%2 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
%broadcast.splatinsert55 = insertelement <4 x i32> zeroinitializer, i32 %2, i64 0
%3 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert53, <4 x i32> %broadcast.splatinsert55)
%4 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
%broadcast.splatinsert57 = insertelement <4 x i32> zeroinitializer, i32 %4, i64 0
%5 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %3, <4 x i32> %broadcast.splatinsert57)
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 3704), align 2
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 4630), align 2
%6 = shufflevector <4 x i32> %5, <4 x i32> zeroinitializer, <2 x i32> <i32 0, i32 4>
store <2 x i32> %6, ptr getelementptr inbounds nuw (i8, ptr null, i64 16), align 4
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 5556), align 2
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 6482), align 2
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 24), align 4
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 7408), align 2
store i16 0, ptr getelementptr inbounds nuw (i8, ptr null, i64 8334), align 2
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 32), align 4
store i16 0, ptr %0, align 2
store <2 x i32> zeroinitializer, ptr getelementptr inbounds nuw (i8, ptr null, i64 40), align 4
%7 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
%broadcast.splatinsert165 = insertelement <4 x i32> poison, i32 %7, i64 0
%8 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
%broadcast.splatinsert167 = insertelement <4 x i32> poison, i32 %8, i64 0
%9 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert165, <4 x i32> %broadcast.splatinsert167)
%10 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
%broadcast.splatinsert169 = insertelement <4 x i32> poison, i32 %10, i64 0
%11 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %9, <4 x i32> %broadcast.splatinsert169)
store i16 0, ptr null, align 2
%12 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 29916), align 4
%broadcast.splatinsert179 = insertelement <4 x i32> poison, i32 %12, i64 0
%13 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28484), align 4
%broadcast.splatinsert181 = insertelement <4 x i32> poison, i32 %13, i64 0
%14 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %broadcast.splatinsert179, <4 x i32> %broadcast.splatinsert181)
%15 = load i32, ptr getelementptr inbounds nuw (i8, ptr null, i64 28368), align 4
%broadcast.splatinsert183 = insertelement <4 x i32> poison, i32 %15, i64 0
%16 = call <4 x i32> @llvm.smin.v4i32(<4 x i32> %14, <4 x i32> %broadcast.splatinsert183)
%17 = shufflevector <4 x i32> %11, <4 x i32> %16, <2 x i32> <i32 0, i32 4>
ret <2 x i32> %17
}
|
