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
|
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 5
; RUN: llc < %s -mtriple=riscv64 -mattr=+v -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,POSTRA
; RUN: llc < %s -mtriple=riscv64 -mattr=+v -riscv-vsetvl-after-rvv-regalloc=false -verify-machineinstrs | FileCheck %s --check-prefixes=CHECK,PRERA
define void @vid(ptr %p) {
; POSTRA-LABEL: vid:
; POSTRA: # %bb.0:
; POSTRA-NEXT: vsetvli a1, zero, e64, m8, ta, ma
; POSTRA-NEXT: vid.v v8
; POSTRA-NEXT: vs8r.v v8, (a0)
; POSTRA-NEXT: vl8re64.v v16, (a0)
; POSTRA-NEXT: vl8re64.v v24, (a0)
; POSTRA-NEXT: vl8re64.v v0, (a0)
; POSTRA-NEXT: vl8re64.v v8, (a0)
; POSTRA-NEXT: vs8r.v v8, (a0)
; POSTRA-NEXT: vs8r.v v0, (a0)
; POSTRA-NEXT: vs8r.v v24, (a0)
; POSTRA-NEXT: vs8r.v v16, (a0)
; POSTRA-NEXT: vid.v v8
; POSTRA-NEXT: vs8r.v v8, (a0)
; POSTRA-NEXT: ret
;
; PRERA-LABEL: vid:
; PRERA: # %bb.0:
; PRERA-NEXT: addi sp, sp, -16
; PRERA-NEXT: .cfi_def_cfa_offset 16
; PRERA-NEXT: csrr a1, vlenb
; PRERA-NEXT: slli a1, a1, 3
; PRERA-NEXT: sub sp, sp, a1
; PRERA-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; PRERA-NEXT: vsetvli a1, zero, e64, m8, ta, ma
; PRERA-NEXT: vid.v v8
; PRERA-NEXT: vs8r.v v8, (a0)
; PRERA-NEXT: vl8re64.v v16, (a0)
; PRERA-NEXT: addi a1, sp, 16
; PRERA-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; PRERA-NEXT: vl8re64.v v24, (a0)
; PRERA-NEXT: vl8re64.v v0, (a0)
; PRERA-NEXT: vl8re64.v v16, (a0)
; PRERA-NEXT: vs8r.v v16, (a0)
; PRERA-NEXT: vs8r.v v0, (a0)
; PRERA-NEXT: vs8r.v v24, (a0)
; PRERA-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; PRERA-NEXT: vs8r.v v16, (a0)
; PRERA-NEXT: vs8r.v v8, (a0)
; PRERA-NEXT: csrr a0, vlenb
; PRERA-NEXT: slli a0, a0, 3
; PRERA-NEXT: add sp, sp, a0
; PRERA-NEXT: addi sp, sp, 16
; PRERA-NEXT: ret
%vid = call <vscale x 8 x i64> @llvm.riscv.vid.nxv8i64(<vscale x 8 x i64> poison, i64 -1)
store volatile <vscale x 8 x i64> %vid, ptr %p
%a = load volatile <vscale x 8 x i64>, ptr %p
%b = load volatile <vscale x 8 x i64>, ptr %p
%c = load volatile <vscale x 8 x i64>, ptr %p
%d = load volatile <vscale x 8 x i64>, ptr %p
store volatile <vscale x 8 x i64> %d, ptr %p
store volatile <vscale x 8 x i64> %c, ptr %p
store volatile <vscale x 8 x i64> %b, ptr %p
store volatile <vscale x 8 x i64> %a, ptr %p
store volatile <vscale x 8 x i64> %vid, ptr %p
ret void
}
define void @vid_passthru(ptr %p, <vscale x 8 x i64> %v) {
; CHECK-LABEL: vid_passthru:
; CHECK: # %bb.0:
; CHECK-NEXT: addi sp, sp, -16
; CHECK-NEXT: .cfi_def_cfa_offset 16
; CHECK-NEXT: csrr a1, vlenb
; CHECK-NEXT: slli a1, a1, 3
; CHECK-NEXT: sub sp, sp, a1
; CHECK-NEXT: .cfi_escape 0x0f, 0x0d, 0x72, 0x00, 0x11, 0x10, 0x22, 0x11, 0x08, 0x92, 0xa2, 0x38, 0x00, 0x1e, 0x22 # sp + 16 + 8 * vlenb
; CHECK-NEXT: vsetivli zero, 1, e64, m8, tu, ma
; CHECK-NEXT: vid.v v8
; CHECK-NEXT: vs8r.v v8, (a0)
; CHECK-NEXT: vl8re64.v v16, (a0)
; CHECK-NEXT: addi a1, sp, 16
; CHECK-NEXT: vs8r.v v16, (a1) # Unknown-size Folded Spill
; CHECK-NEXT: vl8re64.v v24, (a0)
; CHECK-NEXT: vl8re64.v v0, (a0)
; CHECK-NEXT: vl8re64.v v16, (a0)
; CHECK-NEXT: vs8r.v v16, (a0)
; CHECK-NEXT: vs8r.v v0, (a0)
; CHECK-NEXT: vs8r.v v24, (a0)
; CHECK-NEXT: vl8r.v v16, (a1) # Unknown-size Folded Reload
; CHECK-NEXT: vs8r.v v16, (a0)
; CHECK-NEXT: vs8r.v v8, (a0)
; CHECK-NEXT: csrr a0, vlenb
; CHECK-NEXT: slli a0, a0, 3
; CHECK-NEXT: add sp, sp, a0
; CHECK-NEXT: addi sp, sp, 16
; CHECK-NEXT: ret
%vid = call <vscale x 8 x i64> @llvm.riscv.vid.nxv8i64(<vscale x 8 x i64> %v, i64 1)
store volatile <vscale x 8 x i64> %vid, ptr %p
%a = load volatile <vscale x 8 x i64>, ptr %p
%b = load volatile <vscale x 8 x i64>, ptr %p
%c = load volatile <vscale x 8 x i64>, ptr %p
%d = load volatile <vscale x 8 x i64>, ptr %p
store volatile <vscale x 8 x i64> %d, ptr %p
store volatile <vscale x 8 x i64> %c, ptr %p
store volatile <vscale x 8 x i64> %b, ptr %p
store volatile <vscale x 8 x i64> %a, ptr %p
store volatile <vscale x 8 x i64> %vid, ptr %p
ret void
}
|
