xref: /llvm-project/llvm/test/CodeGen/AArch64/sve-alloca.ll (revision c5253aa136ac6ba683b367b2bae0dde1a543d1df) 
1; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
2; RUN: llc -mtriple=aarch64 -mattr=+sve < %s | FileCheck %s
3
4declare void @bar(ptr)
5
6define void @foo(<vscale x 4 x i64> %dst, i1 %cond) {
7; CHECK-LABEL: foo:
8; CHECK:       // %bb.0: // %entry
9; CHECK-NEXT:    tbz w0, #0, .LBB0_2
10; CHECK-NEXT:  // %bb.1: // %if.then
11; CHECK-NEXT:    stp x29, x30, [sp, #-32]! // 16-byte Folded Spill
12; CHECK-NEXT:    stp x28, x19, [sp, #16] // 16-byte Folded Spill
13; CHECK-NEXT:    mov x29, sp
14; CHECK-NEXT:    addvl sp, sp, #-18
15; CHECK-NEXT:    str p15, [sp, #4, mul vl] // 2-byte Folded Spill
16; CHECK-NEXT:    str p14, [sp, #5, mul vl] // 2-byte Folded Spill
17; CHECK-NEXT:    str p13, [sp, #6, mul vl] // 2-byte Folded Spill
18; CHECK-NEXT:    str p12, [sp, #7, mul vl] // 2-byte Folded Spill
19; CHECK-NEXT:    str p11, [sp, #8, mul vl] // 2-byte Folded Spill
20; CHECK-NEXT:    str p10, [sp, #9, mul vl] // 2-byte Folded Spill
21; CHECK-NEXT:    str p9, [sp, #10, mul vl] // 2-byte Folded Spill
22; CHECK-NEXT:    str p8, [sp, #11, mul vl] // 2-byte Folded Spill
23; CHECK-NEXT:    str p7, [sp, #12, mul vl] // 2-byte Folded Spill
24; CHECK-NEXT:    str p6, [sp, #13, mul vl] // 2-byte Folded Spill
25; CHECK-NEXT:    str p5, [sp, #14, mul vl] // 2-byte Folded Spill
26; CHECK-NEXT:    str p4, [sp, #15, mul vl] // 2-byte Folded Spill
27; CHECK-NEXT:    str z23, [sp, #2, mul vl] // 16-byte Folded Spill
28; CHECK-NEXT:    str z22, [sp, #3, mul vl] // 16-byte Folded Spill
29; CHECK-NEXT:    str z21, [sp, #4, mul vl] // 16-byte Folded Spill
30; CHECK-NEXT:    str z20, [sp, #5, mul vl] // 16-byte Folded Spill
31; CHECK-NEXT:    str z19, [sp, #6, mul vl] // 16-byte Folded Spill
32; CHECK-NEXT:    str z18, [sp, #7, mul vl] // 16-byte Folded Spill
33; CHECK-NEXT:    str z17, [sp, #8, mul vl] // 16-byte Folded Spill
34; CHECK-NEXT:    str z16, [sp, #9, mul vl] // 16-byte Folded Spill
35; CHECK-NEXT:    str z15, [sp, #10, mul vl] // 16-byte Folded Spill
36; CHECK-NEXT:    str z14, [sp, #11, mul vl] // 16-byte Folded Spill
37; CHECK-NEXT:    str z13, [sp, #12, mul vl] // 16-byte Folded Spill
38; CHECK-NEXT:    str z12, [sp, #13, mul vl] // 16-byte Folded Spill
39; CHECK-NEXT:    str z11, [sp, #14, mul vl] // 16-byte Folded Spill
40; CHECK-NEXT:    str z10, [sp, #15, mul vl] // 16-byte Folded Spill
41; CHECK-NEXT:    str z9, [sp, #16, mul vl] // 16-byte Folded Spill
42; CHECK-NEXT:    str z8, [sp, #17, mul vl] // 16-byte Folded Spill
43; CHECK-NEXT:    mov x19, sp
44; CHECK-NEXT:    .cfi_def_cfa w29, 32
45; CHECK-NEXT:    .cfi_offset w19, -8
46; CHECK-NEXT:    .cfi_offset w28, -16
47; CHECK-NEXT:    .cfi_offset w30, -24
48; CHECK-NEXT:    .cfi_offset w29, -32
49; CHECK-NEXT:    .cfi_escape 0x10, 0x48, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x78, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d8 @ cfa - 32 - 8 * VG
50; CHECK-NEXT:    .cfi_escape 0x10, 0x49, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x70, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d9 @ cfa - 32 - 16 * VG
51; CHECK-NEXT:    .cfi_escape 0x10, 0x4a, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x68, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d10 @ cfa - 32 - 24 * VG
52; CHECK-NEXT:    .cfi_escape 0x10, 0x4b, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x60, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d11 @ cfa - 32 - 32 * VG
53; CHECK-NEXT:    .cfi_escape 0x10, 0x4c, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x58, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d12 @ cfa - 32 - 40 * VG
54; CHECK-NEXT:    .cfi_escape 0x10, 0x4d, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x50, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d13 @ cfa - 32 - 48 * VG
55; CHECK-NEXT:    .cfi_escape 0x10, 0x4e, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x48, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d14 @ cfa - 32 - 56 * VG
56; CHECK-NEXT:    .cfi_escape 0x10, 0x4f, 0x0a, 0x11, 0x60, 0x22, 0x11, 0x40, 0x92, 0x2e, 0x00, 0x1e, 0x22 // $d15 @ cfa - 32 - 64 * VG
57; CHECK-NEXT:    rdvl x9, #2
58; CHECK-NEXT:    mov x8, sp
59; CHECK-NEXT:    add x9, x9, #15
60; CHECK-NEXT:    and x9, x9, #0xfffffffffffffff0
61; CHECK-NEXT:    sub x8, x8, x9
62; CHECK-NEXT:    and x0, x8, #0xffffffffffffffe0
63; CHECK-NEXT:    mov sp, x0
64; CHECK-NEXT:    ptrue p0.d
65; CHECK-NEXT:    st1d { z1.d }, p0, [x0, #1, mul vl]
66; CHECK-NEXT:    st1d { z0.d }, p0, [x0]
67; CHECK-NEXT:    bl bar
68; CHECK-NEXT:    addvl sp, x29, #-18
69; CHECK-NEXT:    ldr z23, [sp, #2, mul vl] // 16-byte Folded Reload
70; CHECK-NEXT:    ldr z22, [sp, #3, mul vl] // 16-byte Folded Reload
71; CHECK-NEXT:    ldr z21, [sp, #4, mul vl] // 16-byte Folded Reload
72; CHECK-NEXT:    ldr z20, [sp, #5, mul vl] // 16-byte Folded Reload
73; CHECK-NEXT:    ldr z19, [sp, #6, mul vl] // 16-byte Folded Reload
74; CHECK-NEXT:    ldr z18, [sp, #7, mul vl] // 16-byte Folded Reload
75; CHECK-NEXT:    ldr z17, [sp, #8, mul vl] // 16-byte Folded Reload
76; CHECK-NEXT:    ldr z16, [sp, #9, mul vl] // 16-byte Folded Reload
77; CHECK-NEXT:    ldr z15, [sp, #10, mul vl] // 16-byte Folded Reload
78; CHECK-NEXT:    ldr z14, [sp, #11, mul vl] // 16-byte Folded Reload
79; CHECK-NEXT:    ldr z13, [sp, #12, mul vl] // 16-byte Folded Reload
80; CHECK-NEXT:    ldr z12, [sp, #13, mul vl] // 16-byte Folded Reload
81; CHECK-NEXT:    ldr z11, [sp, #14, mul vl] // 16-byte Folded Reload
82; CHECK-NEXT:    ldr z10, [sp, #15, mul vl] // 16-byte Folded Reload
83; CHECK-NEXT:    ldr z9, [sp, #16, mul vl] // 16-byte Folded Reload
84; CHECK-NEXT:    ldr z8, [sp, #17, mul vl] // 16-byte Folded Reload
85; CHECK-NEXT:    ldr p15, [sp, #4, mul vl] // 2-byte Folded Reload
86; CHECK-NEXT:    ldr p14, [sp, #5, mul vl] // 2-byte Folded Reload
87; CHECK-NEXT:    ldr p13, [sp, #6, mul vl] // 2-byte Folded Reload
88; CHECK-NEXT:    ldr p12, [sp, #7, mul vl] // 2-byte Folded Reload
89; CHECK-NEXT:    ldr p11, [sp, #8, mul vl] // 2-byte Folded Reload
90; CHECK-NEXT:    ldr p10, [sp, #9, mul vl] // 2-byte Folded Reload
91; CHECK-NEXT:    ldr p9, [sp, #10, mul vl] // 2-byte Folded Reload
92; CHECK-NEXT:    ldr p8, [sp, #11, mul vl] // 2-byte Folded Reload
93; CHECK-NEXT:    ldr p7, [sp, #12, mul vl] // 2-byte Folded Reload
94; CHECK-NEXT:    ldr p6, [sp, #13, mul vl] // 2-byte Folded Reload
95; CHECK-NEXT:    ldr p5, [sp, #14, mul vl] // 2-byte Folded Reload
96; CHECK-NEXT:    ldr p4, [sp, #15, mul vl] // 2-byte Folded Reload
97; CHECK-NEXT:    mov sp, x29
98; CHECK-NEXT:    ldp x28, x19, [sp, #16] // 16-byte Folded Reload
99; CHECK-NEXT:    ldp x29, x30, [sp], #32 // 16-byte Folded Reload
100; CHECK-NEXT:  .LBB0_2: // %if.end
101; CHECK-NEXT:    ret
102entry:
103  br i1 %cond, label %if.then, label %if.end
104
105if.then:
106  %ptr = alloca <vscale x 4 x i64>
107  store <vscale x 4 x i64> %dst, ptr %ptr
108  call void @bar(ptr %ptr)
109  br label %if.end
110
111if.end:
112  ret void
113}
114