xref: /llvm-project/llvm/test/Analysis/CostModel/RISCV/active_lane_mask.ll (revision ee52add6cb4a6a4ba4beb941c1f2cfa82266e0df) 
1; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
2; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v,+f,+d,+zfh | FileCheck %s
3
4define void @get_lane_mask() {
5; CHECK-LABEL: 'get_lane_mask'
6; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
7; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
8; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
9; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
10; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_nxv1i1_i64 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i64(i64 undef, i64 undef)
11; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
12; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
13; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
14; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
15; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_nxv1i1_i32 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32 undef, i32 undef)
16; CHECK-NEXT:  Cost Model: Found an estimated cost of 64 for instruction: %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
17; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
18; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
19; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
20; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
21; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
22; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
23; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
24; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
25; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
26; CHECK-NEXT:  Cost Model: Found an estimated cost of 32 for instruction: %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
27; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
28; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
29;
30  %mask_nxv16i1_i64 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64 undef, i64 undef)
31  %mask_nxv8i1_i64 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64 undef, i64 undef)
32  %mask_nxv4i1_i64 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64 undef, i64 undef)
33  %mask_nxv2i1_i64 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64 undef, i64 undef)
34  %mask_nxv1i1_i64 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i64(i64 undef, i64 undef)
35
36  %mask_nxv16i1_i32 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32 undef, i32 undef)
37  %mask_nxv8i1_i32 = call <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32 undef, i32 undef)
38  %mask_nxv4i1_i32 = call <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32 undef, i32 undef)
39  %mask_nxv2i1_i32 = call <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32 undef, i32 undef)
40  %mask_nxv1i1_i32 = call <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32 undef, i32 undef)
41
42  %mask_nxv32i1_i64 = call <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64 undef, i64 undef)
43  %mask_nxv16i1_i16 = call <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16 undef, i16 undef)
44
45  %mask_v16i1_i64 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64 undef, i64 undef)
46  %mask_v8i1_i64 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64 undef, i64 undef)
47  %mask_v4i1_i64 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64 undef, i64 undef)
48  %mask_v2i1_i64 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64 undef, i64 undef)
49
50  %mask_v16i1_i32 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32 undef, i32 undef)
51  %mask_v8i1_i32 = call <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32 undef, i32 undef)
52  %mask_v4i1_i32 = call <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32 undef, i32 undef)
53  %mask_v2i1_i32 = call <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32 undef, i32 undef)
54
55  %mask_v32i1_i64 = call <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64 undef, i64 undef)
56  %mask_v16i1_i16 = call <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16 undef, i16 undef)
57
58  ret void
59}
60
61declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i64(i64, i64)
62declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i64(i64, i64)
63declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i64(i64, i64)
64declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i64(i64, i64)
65declare <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i64(i64, i64)
66declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i32(i32, i32)
67declare <vscale x 8 x i1> @llvm.get.active.lane.mask.nxv8i1.i32(i32, i32)
68declare <vscale x 4 x i1> @llvm.get.active.lane.mask.nxv4i1.i32(i32, i32)
69declare <vscale x 2 x i1> @llvm.get.active.lane.mask.nxv2i1.i32(i32, i32)
70declare <vscale x 1 x i1> @llvm.get.active.lane.mask.nxv1i1.i32(i32, i32)
71declare <vscale x 32 x i1> @llvm.get.active.lane.mask.nxv32i1.i64(i64, i64)
72declare <vscale x 16 x i1> @llvm.get.active.lane.mask.nxv16i1.i16(i16, i16)
73declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i64(i64, i64)
74declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i64(i64, i64)
75declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i64(i64, i64)
76declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i64(i64, i64)
77declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i32(i32, i32)
78declare <8 x i1> @llvm.get.active.lane.mask.v8i1.i32(i32, i32)
79declare <4 x i1> @llvm.get.active.lane.mask.v4i1.i32(i32, i32)
80declare <2 x i1> @llvm.get.active.lane.mask.v2i1.i32(i32, i32)
81declare <32 x i1> @llvm.get.active.lane.mask.v32i1.i64(i64, i64)
82declare <16 x i1> @llvm.get.active.lane.mask.v16i1.i16(i16, i16)
83