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
|
; RUN: llc -mtriple=amdgcn -mcpu=bonaire -show-mc-encoding < %s | FileCheck --check-prefixes=GCN,CI,ALL %s
; RUN: llc -mtriple=amdgcn -mcpu=carrizo --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,VI,ALL %s
; RUN: llc -mtriple=amdgcn -mcpu=gfx900 --show-mc-encoding < %s | FileCheck --check-prefixes=GCN,GFX9,ALL %s
; RUN: llc -mcpu=bonaire -mtriple=amdgcn-unknown-amdhsa -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
; RUN: llc -mcpu=carrizo -mtriple=amdgcn-unknown-amdhsa -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
; RUN: llc -mcpu=gfx1010 -mtriple=amdgcn-unknown-amdhsa -mattr=-flat-for-global < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
; RUN: llc -mcpu=gfx1100 -mtriple=amdgcn-unknown-amdhsa -mattr=-flat-for-global,-architected-flat-scratch,-user-sgpr-init16-bug < %s | FileCheck --check-prefixes=GCNHSA,ALL %s
; FIXME: align on alloca seems to be ignored for private_segment_alignment
; ALL-LABEL: {{^}}large_alloca_compute_shader:
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
; GCN-DAG: ; fixup A - offset: 4, value: SCRATCH_RSRC_DWORD0
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
; GCN-DAG: ; fixup A - offset: 4, value: SCRATCH_RSRC_DWORD1
; GCN-DAG: s_mov_b32 s{{[0-9]+}}, -1
; CI-DAG: s_mov_b32 s{{[0-9]+}}, 0xe8f000
; VI-DAG: s_mov_b32 s{{[0-9]+}}, 0xe80000
; GFX9-DAG: s_mov_b32 s{{[0-9]+}}, 0xe00000
; GCNHSA: buffer_store_{{dword|b32}} {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
; GCNHSA: buffer_load_{{dword|b32}} {{v[0-9]+}}, {{v[0-9]+}}, s[0:3], 0 offen
; GCNHSA: .amdhsa_kernel large_alloca_compute_shader
; GCNHSA: .amdhsa_group_segment_fixed_size 0
; GCNHSA: .amdhsa_private_segment_fixed_size 32772
; GCNHSA: .amdhsa_user_sgpr_private_segment_buffer 1
; GCNHSA: .amdhsa_user_sgpr_dispatch_ptr 1
; GCNHSA: .amdhsa_user_sgpr_queue_ptr 1
; GCNHSA: .amdhsa_user_sgpr_kernarg_segment_ptr 1
; GCNHSA: .amdhsa_user_sgpr_dispatch_id 1
; GCNHSA: .amdhsa_user_sgpr_flat_scratch_init 1
; GCNHSA: .amdhsa_user_sgpr_private_segment_size 0
; GCNHSA: .amdhsa_system_sgpr_private_segment_wavefront_offset 1
; GCNHSA: .amdhsa_system_sgpr_workgroup_id_x 1
; GCNHSA: .amdhsa_system_sgpr_workgroup_id_y 1
; GCNHSA: .amdhsa_system_sgpr_workgroup_id_z 1
; GCNHSA: .amdhsa_system_sgpr_workgroup_info 0
; GCNHSA: .amdhsa_system_vgpr_workitem_id 2
; GCNHSA: .amdhsa_next_free_vgpr 3
; GCNHSA: .amdhsa_next_free_sgpr 18
; GCNHSA: .amdhsa_float_round_mode_32 0
; GCNHSA: .amdhsa_float_round_mode_16_64 0
; GCNHSA: .amdhsa_float_denorm_mode_32 3
; GCNHSA: .amdhsa_float_denorm_mode_16_64 3
; GCNHSA: .amdhsa_dx10_clamp 1
; GCNHSA: .amdhsa_ieee_mode 1
; GCNHSA: .amdhsa_exception_fp_ieee_invalid_op 0
; GCNHSA: .amdhsa_exception_fp_denorm_src 0
; GCNHSA: .amdhsa_exception_fp_ieee_div_zero 0
; GCNHSA: .amdhsa_exception_fp_ieee_overflow 0
; GCNHSA: .amdhsa_exception_fp_ieee_underflow 0
; GCNHSA: .amdhsa_exception_fp_ieee_inexact 0
; GCNHSA: .amdhsa_exception_int_div_zero 0
; GCNHSA: .end_amdhsa_kernel
; Scratch size = alloca size + emergency stack slot, align {{.*}}, addrspace(5)
; ALL: ; ScratchSize: 32772
define amdgpu_kernel void @large_alloca_compute_shader(i32 %x, i32 %y) #0 {
%large = alloca [8192 x i32], align 4, addrspace(5)
%gep = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 8191
store volatile i32 %x, ptr addrspace(5) %gep
%gep1 = getelementptr [8192 x i32], ptr addrspace(5) %large, i32 0, i32 %y
%val = load volatile i32, ptr addrspace(5) %gep1
store volatile i32 %val, ptr addrspace(1) undef
ret void
}
attributes #0 = { nounwind }
!llvm.module.flags = !{!0}
!0 = !{i32 1, !"amdhsa_code_object_version", i32 400}
|
