mirror of
https://github.com/RPCS3/llvm-mirror.git
synced 2024-11-25 12:12:47 +01:00
a76ecb87cf
- Add target id support (https://clang.llvm.org/docs/ClangOffloadBundler.html#target-id) - Add code object v4 support (https://llvm.org/docs/AMDGPUUsage.html#elf-code-object) - Add kernarg_size to kernel descriptor - Change trap handler ABI to no longer move queue pointer into s[0:1] - Cleanup ELF definitions - Add V2, V3, V4 suffixes to make a clear distinction for code object version - Consolidate note names Differential Revision: https://reviews.llvm.org/D95638
1182 lines
63 KiB
LLVM
1182 lines
63 KiB
LLVM
; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 --amdhsa-code-object-version=2 -verify-machineinstrs < %s | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V2 %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 --amdhsa-code-object-version=3 -verify-machineinstrs < %s | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V3 %s
|
|
; RUN: llc -march=amdgcn -mcpu=gfx900 --amdhsa-code-object-version=4 -verify-machineinstrs < %s | FileCheck --check-prefix=NOHSA-TRAP-GFX900-V4 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=2 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX803-V2 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=3 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX803-V3 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 --amdhsa-code-object-version=4 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX803-V4 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=2 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX900-V2 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=3 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX900-V3 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 --amdhsa-code-object-version=4 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-TRAP-GFX900-V4 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler --amdhsa-code-object-version=2 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V2 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler --amdhsa-code-object-version=3 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V3 %s
|
|
; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -mattr=-trap-handler --amdhsa-code-object-version=4 -verify-machineinstrs < %s | FileCheck --check-prefix=HSA-NOTRAP-GFX900-V4 %s
|
|
|
|
declare void @llvm.trap() #0
|
|
declare void @llvm.debugtrap() #1
|
|
|
|
define amdgpu_kernel void @trap(i32 addrspace(1)* nocapture readonly %arg0) {
|
|
; NOHSA-TRAP-GFX900-V2-LABEL: trap:
|
|
; NOHSA-TRAP-GFX900-V2: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V3-LABEL: trap:
|
|
; NOHSA-TRAP-GFX900-V3: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V4-LABEL: trap:
|
|
; NOHSA-TRAP-GFX900-V4: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX803-V2-LABEL: trap:
|
|
; HSA-TRAP-GFX803-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_major = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_stepping = 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX803-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_xnack_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_vgpr_count = 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX803-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX803-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_load_dwordx2 s[2:3], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v0, s2
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v1, s3
|
|
; HSA-TRAP-GFX803-V2-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX803-V3-LABEL: trap:
|
|
; HSA-TRAP-GFX803-V3: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_load_dwordx2 s[2:3], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v0, s2
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v1, s3
|
|
; HSA-TRAP-GFX803-V3-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX803-V4-LABEL: trap:
|
|
; HSA-TRAP-GFX803-V4: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_load_dwordx2 s[2:3], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v0, s2
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v1, s3
|
|
; HSA-TRAP-GFX803-V4-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V2-LABEL: trap:
|
|
; HSA-TRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_vgpr_count = 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[2:3], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V3-LABEL: trap:
|
|
; HSA-TRAP-GFX900-V3: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[2:3], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[2:3]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V4-LABEL: trap:
|
|
; HSA-TRAP-GFX900-V4: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_trap 2
|
|
;
|
|
; HSA-NOTRAP-GFX900-V2-LABEL: trap:
|
|
; HSA-NOTRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_vgpr_count = 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V3-LABEL: trap:
|
|
; HSA-NOTRAP-GFX900-V3: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V4-LABEL: trap:
|
|
; HSA-NOTRAP-GFX900-V4: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_endpgm
|
|
store volatile i32 1, i32 addrspace(1)* %arg0
|
|
call void @llvm.trap()
|
|
unreachable
|
|
store volatile i32 2, i32 addrspace(1)* %arg0
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @non_entry_trap(i32 addrspace(1)* nocapture readonly %arg0) local_unnamed_addr {
|
|
; NOHSA-TRAP-GFX900-V2-LABEL: non_entry_trap:
|
|
; NOHSA-TRAP-GFX900-V2: ; %bb.0: ; %entry
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_and_b64 vcc, exec, vcc
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_cbranch_vccz BB1_2
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: ; %bb.1: ; %ret
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 3
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: BB1_2: ; %trap
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
|
|
; NOHSA-TRAP-GFX900-V3: ; %bb.0: ; %entry
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_and_b64 vcc, exec, vcc
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_cbranch_vccz BB1_2
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: ; %bb.1: ; %ret
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 3
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: BB1_2: ; %trap
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V4-LABEL: non_entry_trap:
|
|
; NOHSA-TRAP-GFX900-V4: ; %bb.0: ; %entry
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_and_b64 vcc, exec, vcc
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_cbranch_vccz BB1_2
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: ; %bb.1: ; %ret
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 3
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: BB1_2: ; %trap
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX803-V2-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX803-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_major = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_stepping = 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_wavefront_sgpr_count = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX803-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_xnack_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_sgpr_count = 10
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_vgpr_count = 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX803-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX803-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V2-NEXT: flat_load_dword v0, v[0:1] glc
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_cmp_eq_u32_e32 vcc, -1, v0
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX803-V2-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v2, 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V2-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX803-V2-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX803-V3-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX803-V3: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V3-NEXT: flat_load_dword v0, v[0:1] glc
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_cmp_eq_u32_e32 vcc, -1, v0
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX803-V3-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v2, 3
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V3-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX803-V3-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX803-V4-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX803-V4: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V4-NEXT: flat_load_dword v0, v[0:1] glc
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_cmp_eq_u32_e32 vcc, -1, v0
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX803-V4-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v2, 3
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V4-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX803-V4-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V2-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 10
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_vgpr_count = 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX900-V2-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX900-V2-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V3-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX900-V3: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX900-V3-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX900-V3-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_mov_b64 s[0:1], s[4:5]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_trap 2
|
|
;
|
|
; HSA-TRAP-GFX900-V4-LABEL: non_entry_trap:
|
|
; HSA-TRAP-GFX900-V4: ; %bb.0: ; %entry
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-TRAP-GFX900-V4-NEXT: ; %bb.1: ; %ret
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
; HSA-TRAP-GFX900-V4-NEXT: BB1_2: ; %trap
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_trap 2
|
|
;
|
|
; HSA-NOTRAP-GFX900-V2-LABEL: non_entry_trap:
|
|
; HSA-NOTRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 10
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_vgpr_count = 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: ; %bb.0: ; %entry
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: ; %bb.1: ; %ret
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_endpgm
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: BB1_2: ; %trap
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V3-LABEL: non_entry_trap:
|
|
; HSA-NOTRAP-GFX900-V3: ; %bb.0: ; %entry
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: ; %bb.1: ; %ret
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_endpgm
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: BB1_2: ; %trap
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V4-LABEL: non_entry_trap:
|
|
; HSA-NOTRAP-GFX900-V4: ; %bb.0: ; %entry
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: global_load_dword v1, v0, s[0:1] glc
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_cmp_eq_u32_e32 vcc, -1, v1
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_and_b64 vcc, exec, vcc
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_cbranch_vccz BB1_2
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: ; %bb.1: ; %ret
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 3
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_endpgm
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: BB1_2: ; %trap
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_endpgm
|
|
entry:
|
|
%tmp29 = load volatile i32, i32 addrspace(1)* %arg0
|
|
%cmp = icmp eq i32 %tmp29, -1
|
|
br i1 %cmp, label %ret, label %trap
|
|
|
|
trap:
|
|
call void @llvm.trap()
|
|
unreachable
|
|
|
|
ret:
|
|
store volatile i32 3, i32 addrspace(1)* %arg0
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @debugtrap(i32 addrspace(1)* nocapture readonly %arg0) {
|
|
; NOHSA-TRAP-GFX900-V2-LABEL: debugtrap:
|
|
; NOHSA-TRAP-GFX900-V2: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v2, 2
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V3-LABEL: debugtrap:
|
|
; NOHSA-TRAP-GFX900-V3: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v2, 2
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; NOHSA-TRAP-GFX900-V4-LABEL: debugtrap:
|
|
; NOHSA-TRAP-GFX900-V4: ; %bb.0:
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[0:1], 0x24
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v2, 2
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; NOHSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX803-V2-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX803-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_major = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: amd_machine_version_stepping = 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX803-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: is_xnack_enabled = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-TRAP-GFX803-V2-NEXT: workitem_vgpr_count = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX803-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX803-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX803-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX803-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX803-V2-NEXT: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v3, 2
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V2-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V2-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX803-V2-NEXT: flat_store_dword v[0:1], v3
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V2-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX803-V3-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX803-V3: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v3, 2
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V3-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V3-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX803-V3-NEXT: flat_store_dword v[0:1], v3
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V3-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX803-V4-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX803-V4: ; %bb.0:
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v2, 1
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v3, 2
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v0, s0
|
|
; HSA-TRAP-GFX803-V4-NEXT: v_mov_b32_e32 v1, s1
|
|
; HSA-TRAP-GFX803-V4-NEXT: flat_store_dword v[0:1], v2
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX803-V4-NEXT: flat_store_dword v[0:1], v3
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX803-V4-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX900-V2-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-TRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-TRAP-GFX900-V2-NEXT: workitem_vgpr_count = 3
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-TRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-TRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-TRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-TRAP-GFX900-V2-NEXT: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V2-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX900-V2-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX900-V3-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX900-V3: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V3-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX900-V3-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; HSA-TRAP-GFX900-V4-LABEL: debugtrap:
|
|
; HSA-TRAP-GFX900-V4: ; %bb.0:
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-TRAP-GFX900-V4-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_trap 3
|
|
; HSA-TRAP-GFX900-V4-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-TRAP-GFX900-V4-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V2-LABEL: debugtrap:
|
|
; HSA-NOTRAP-GFX900-V2: .amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_major = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_code_version_minor = 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_kind = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_major = 9
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_minor = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: amd_machine_version_stepping = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_entry_byte_offset = 256
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernel_code_prefetch_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_workitem_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_wavefront_sgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priority = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: float_mode = 240
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: priv = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_dx10_clamp = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ieee_mode = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wgp_mode = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_mem_ordered = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_fwd_progress = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_wave_byte_offset = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: user_sgpr_count = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_trap_handler = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_x = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_id_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_workgroup_info = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_vgpr_workitem_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception_msb = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: granulated_lds_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_exception = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_buffer = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_ptr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_queue_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_kernarg_segment_ptr = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_dispatch_id = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_flat_scratch_init = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_private_segment_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_x = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_y = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_sgpr_grid_workgroup_count_z = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_wavefront_size32 = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: enable_ordered_append_gds = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_element_size = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_ptr64 = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_dynamic_callstack = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_debug_enabled = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: is_xnack_enabled = 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_private_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_group_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: gds_segment_byte_size = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_byte_size = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workgroup_fbarrier_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_sgpr_count = 8
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: workitem_vgpr_count = 3
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_vgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_first = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: reserved_sgpr_count = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_wavefront_private_segment_offset_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: debug_private_segment_buffer_sgpr = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: kernarg_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: group_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: private_segment_alignment = 4
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: wavefront_size = 6
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: call_convention = -1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: runtime_loader_kernel_symbol = 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: .end_amd_kernel_code_t
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V2-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V3-LABEL: debugtrap:
|
|
; HSA-NOTRAP-GFX900-V3: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V3-NEXT: s_endpgm
|
|
;
|
|
; HSA-NOTRAP-GFX900-V4-LABEL: debugtrap:
|
|
; HSA-NOTRAP-GFX900-V4: ; %bb.0:
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_load_dwordx2 s[0:1], s[6:7], 0x0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v0, 0
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v1, 1
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: v_mov_b32_e32 v2, 2
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt lgkmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: global_store_dword v0, v1, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: global_store_dword v0, v2, s[0:1]
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_waitcnt vmcnt(0)
|
|
; HSA-NOTRAP-GFX900-V4-NEXT: s_endpgm
|
|
store volatile i32 1, i32 addrspace(1)* %arg0
|
|
call void @llvm.debugtrap()
|
|
store volatile i32 2, i32 addrspace(1)* %arg0
|
|
ret void
|
|
}
|
|
|
|
attributes #0 = { nounwind noreturn }
|
|
attributes #1 = { nounwind }
|