indirect-addressing-si-gfx9.ll
2.87 KB
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
; RUN: llc -amdgpu-scalarize-global-loads=false -march=amdgcn -mcpu=gfx900 -mattr=-flat-for-global -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN,IDXMODE,GFX9 %s
; indexing of vectors.
; Subtest below moved from file test/CodeGen/AMDGPU/indirect-addressing-si.ll
; to avoid gfx9 scheduling induced issues.
; GCN-LABEL: {{^}}insert_vgpr_offset_multiple_in_block:
; GCN-DAG: s_load_dwordx16 s{{\[}}[[S_ELT0:[0-9]+]]:[[S_ELT15:[0-9]+]]{{\]}}
; GCN-DAG: {{buffer|flat|global}}_load_dword [[IDX0:v[0-9]+]]
; GCN-DAG: v_mov_b32 [[INS0:v[0-9]+]], 62
; GCN-DAG: v_mov_b32_e32 v[[VEC_ELT15:[0-9]+]], s[[S_ELT15]]
; GCN-DAG: v_mov_b32_e32 v[[VEC_ELT0:[0-9]+]], s[[S_ELT0]]
; GCN-DAG: v_add_u32_e32 [[IDX1:v[0-9]+]], 1, [[IDX0]]
; GCN: [[LOOP0:BB[0-9]+_[0-9]+]]:
; GCN-NEXT: v_readfirstlane_b32 [[READLANE:s[0-9]+]], [[IDX0]]
; GCN: v_cmp_eq_u32_e32 vcc, [[READLANE]], [[IDX0]]
; GCN: s_and_saveexec_b64 vcc, vcc
; MOVREL: s_mov_b32 m0, [[READLANE]]
; MOVREL-NEXT: v_movreld_b32_e32 v[[VEC_ELT0]], [[INS0]]
; IDXMODE: s_set_gpr_idx_on [[READLANE]], gpr_idx(DST)
; IDXMODE-NEXT: v_mov_b32_e32 v[[VEC_ELT0]], [[INS0]]
; IDXMODE: s_set_gpr_idx_off
; GCN-NEXT: s_xor_b64 exec, exec, vcc
; GCN: s_cbranch_execnz [[LOOP0]]
; FIXME: Redundant copy
; GCN: s_mov_b64 exec, [[MASK:s\[[0-9]+:[0-9]+\]]]
; GCN: s_mov_b64 [[MASK]], exec
; GCN: [[LOOP1:BB[0-9]+_[0-9]+]]:
; GCN-NEXT: v_readfirstlane_b32 [[READLANE:s[0-9]+]], [[IDX1]]
; GCN: v_cmp_eq_u32_e32 vcc, [[READLANE]], [[IDX1]]
; GCN: s_and_saveexec_b64 vcc, vcc
; MOVREL: s_mov_b32 m0, [[READLANE]]
; MOVREL-NEXT: v_movreld_b32_e32 v{{[0-9]+}}, 63
; IDXMODE: s_set_gpr_idx_on [[READLANE]], gpr_idx(DST)
; IDXMODE-NEXT: v_mov_b32_e32 v{{[0-9]+}}, 63
; IDXMODE: s_set_gpr_idx_off
; GCN-NEXT: s_xor_b64 exec, exec, vcc
; GCN: s_cbranch_execnz [[LOOP1]]
; GCN: buffer_store_dwordx4 v{{\[}}[[VEC_ELT0]]:
; GCN: buffer_store_dword [[INS0]]
define amdgpu_kernel void @insert_vgpr_offset_multiple_in_block(<16 x i32> addrspace(1)* %out0, <16 x i32> addrspace(1)* %out1, i32 addrspace(1)* %in, <16 x i32> %vec0) #0 {
entry:
%id = call i32 @llvm.amdgcn.workitem.id.x() #1
%id.ext = zext i32 %id to i64
%gep = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %id.ext
%idx0 = load volatile i32, i32 addrspace(1)* %gep
%idx1 = add i32 %idx0, 1
%live.out.val = call i32 asm sideeffect "v_mov_b32 $0, 62", "=v"()
%vec1 = insertelement <16 x i32> %vec0, i32 %live.out.val, i32 %idx0
%vec2 = insertelement <16 x i32> %vec1, i32 63, i32 %idx1
store volatile <16 x i32> %vec2, <16 x i32> addrspace(1)* %out0
%cmp = icmp eq i32 %id, 0
br i1 %cmp, label %bb1, label %bb2
bb1:
store volatile i32 %live.out.val, i32 addrspace(1)* undef
br label %bb2
bb2:
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
declare void @llvm.amdgcn.s.barrier() #2
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
attributes #2 = { nounwind convergent }