maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.workgroup.id.ll

107 lines
4.4 KiB
LLVM
Raw Normal View History

AMDGPU: Enable code object v3 for AMDHSA only Differential Revision: https://reviews.llvm.org/D54186 llvm-svn: 346923
2018-11-15 10:32:43 +08:00
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-code-object-v3 -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=CI-HSA %s
; RUN: llc -march=amdgcn -mtriple=amdgcn-unknown-amdhsa -mattr=-code-object-v3 -mcpu=carrizo -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=CO-V2 -check-prefix=VI-HSA %s
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=UNKNOWN-OS -check-prefix=SI-MESA %s
; RUN: llc -march=amdgcn -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefix=ALL -check-prefix=UNKNOWN-OS -check-prefix=VI-MESA %s
AMDGPU: Enable code object v3 for AMDHSA only Differential Revision: https://reviews.llvm.org/D54186 llvm-svn: 346923
2018-11-15 10:32:43 +08:00
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mattr=-code-object-v3 -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,SI-MESA %s
; RUN: llc -mtriple=amdgcn-unknown-mesa3d -mattr=-code-object-v3 -mcpu=tonga -verify-machineinstrs < %s | FileCheck -check-prefixes=ALL,CO-V2,VI-MESA %s
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
declare i32 @llvm.amdgcn.workgroup.id.x() #0
declare i32 @llvm.amdgcn.workgroup.id.y() #0
declare i32 @llvm.amdgcn.workgroup.id.z() #0
; ALL-LABEL {{^}}test_workgroup_id_x:
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: .amd_kernel_code_t
; CO-V2: user_sgpr_count = 6
; CO-V2: enable_sgpr_workgroup_id_x = 1
; CO-V2: enable_sgpr_workgroup_id_y = 0
; CO-V2: enable_sgpr_workgroup_id_z = 0
; CO-V2: enable_sgpr_workgroup_info = 0
; CO-V2: enable_vgpr_workitem_id = 0
; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
; CO-V2: .end_amd_kernel_code_t
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s2{{$}}
; CO-V2: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s6{{$}}
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
[AMDGPU] Assembler: Swap operands of flat_store instructions to match AMD assembler Historically, AMD internal sp3 assembler has flat_store* addr, data format. To match existing code and to enable reuse, change LLVM definitions to match. Also update MC and CodeGen tests. Differential Revision: http://reviews.llvm.org/D16927 Patch by: Nikolay Haustov llvm-svn: 260694
2016-02-13 01:57:54 +08:00
; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_workgroup_id_x(i32 addrspace(1)* %out) #1 {
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
%id = call i32 @llvm.amdgcn.workgroup.id.x()
store i32 %id, i32 addrspace(1)* %out
ret void
}
; ALL-LABEL {{^}}test_workgroup_id_y:
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: user_sgpr_count = 6
; CO-V2: enable_sgpr_workgroup_id_x = 1
; CO-V2: enable_sgpr_workgroup_id_y = 1
; CO-V2: enable_sgpr_workgroup_id_z = 0
; CO-V2: enable_sgpr_workgroup_info = 0
; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
[AMDGPU] Assembler: Swap operands of flat_store instructions to match AMD assembler Historically, AMD internal sp3 assembler has flat_store* addr, data format. To match existing code and to enable reuse, change LLVM definitions to match. Also update MC and CodeGen tests. Differential Revision: http://reviews.llvm.org/D16927 Patch by: Nikolay Haustov llvm-svn: 260694
2016-02-13 01:57:54 +08:00
; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 1
; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 0
; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_workgroup_id_y(i32 addrspace(1)* %out) #1 {
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
%id = call i32 @llvm.amdgcn.workgroup.id.y()
store i32 %id, i32 addrspace(1)* %out
ret void
}
; ALL-LABEL {{^}}test_workgroup_id_z:
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: user_sgpr_count = 6
; CO-V2: enable_sgpr_workgroup_id_x = 1
; CO-V2: enable_sgpr_workgroup_id_y = 0
; CO-V2: enable_sgpr_workgroup_id_z = 1
; CO-V2: enable_sgpr_workgroup_info = 0
; CO-V2: enable_vgpr_workitem_id = 0
; CO-V2: enable_sgpr_private_segment_buffer = 1
; CO-V2: enable_sgpr_dispatch_ptr = 0
; CO-V2: enable_sgpr_queue_ptr = 0
; CO-V2: enable_sgpr_kernarg_segment_ptr = 1
; CO-V2: enable_sgpr_dispatch_id = 0
; CO-V2: enable_sgpr_flat_scratch_init = 0
; CO-V2: enable_sgpr_private_segment_size = 0
; CO-V2: enable_sgpr_grid_workgroup_count_x = 0
; CO-V2: enable_sgpr_grid_workgroup_count_y = 0
; CO-V2: enable_sgpr_grid_workgroup_count_z = 0
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; UNKNOWN-OS: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s3{{$}}
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
; HSA: v_mov_b32_e32 [[VCOPY:v[0-9]+]], s7{{$}}
[AMDGPU] Assembler: Swap operands of flat_store instructions to match AMD assembler Historically, AMD internal sp3 assembler has flat_store* addr, data format. To match existing code and to enable reuse, change LLVM definitions to match. Also update MC and CodeGen tests. Differential Revision: http://reviews.llvm.org/D16927 Patch by: Nikolay Haustov llvm-svn: 260694
2016-02-13 01:57:54 +08:00
; ALL: {{buffer|flat}}_store_dword {{.*}}[[VCOPY]]
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
AMDGPU/SI: Add support for triples with the mesa3d operating system Summary: mesa3d will use the same kernel calling convention as amdhsa, but it will handle everything else like the default 'unknown' OS type. Reviewers: arsenm Subscribers: arsenm, llvm-commits, kzhuravl Differential Revision: https://reviews.llvm.org/D22783 llvm-svn: 281779
2016-09-17 05:34:26 +08:00
; CO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 6
; ALL-NOCO-V2: COMPUTE_PGM_RSRC2:USER_SGPR: 2
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
; ALL: COMPUTE_PGM_RSRC2:TGID_X_EN: 1
; ALL: COMPUTE_PGM_RSRC2:TGID_Y_EN: 0
; ALL: COMPUTE_PGM_RSRC2:TGID_Z_EN: 1
; ALL: COMPUTE_PGM_RSRC2:TIDIG_COMP_CNT: 0
AMDGPU: Mark all unspecified CC functions in tests as amdgpu_kernel Currently the default C calling convention functions are treated the same as compute kernels. Make this explicit so the default calling convention can be changed to a non-kernel. Converted with perl -pi -e 's/define void/define amdgpu_kernel void/' on the relevant test directories (and undoing in one place that actually wanted a non-kernel). llvm-svn: 298444
2017-03-22 05:39:51 +08:00
define amdgpu_kernel void @test_workgroup_id_z(i32 addrspace(1)* %out) #1 {
AMDGPU: Add new amdgcn workitem intrinsics These use the correct prefix and follow the HSA naming convention rather than the config register option names. llvm-svn: 259293
2016-01-30 12:25:19 +08:00
%id = call i32 @llvm.amdgcn.workgroup.id.z()
store i32 %id, i32 addrspace(1)* %out
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }