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.s.getreg.ll

28 lines
1.2 KiB
LLVM
Raw Normal View History

DAG: Ignore call site attributes when emitting target intrinsic A target intrinsic may be defined as possibly reading memory, but the call site may have additional knowledge that it doesn't read memory. The intrinsic lowering will expect the pessimistic assumption of the intrinsic definition, so the chain should still be used. llvm-svn: 287593
2016-11-22 06:56:42 +08:00
; RUN: llc -march=amdgcn -mcpu=tahiti -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=fiji -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s
AMDGPU/SI: Define S_GETREG Intrinsic Summary: Define s_getreg intrinsic to generate s_getreg instruction to read hardware registers. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17892 llvm-svn: 263124
2016-03-11 00:47:15 +08:00
DAG: Ignore call site attributes when emitting target intrinsic A target intrinsic may be defined as possibly reading memory, but the call site may have additional knowledge that it doesn't read memory. The intrinsic lowering will expect the pessimistic assumption of the intrinsic definition, so the chain should still be used. llvm-svn: 287593
2016-11-22 06:56:42 +08:00
; GCN-LABEL: {{^}}s_getreg_test:
; GCN: s_getreg_b32 s{{[0-9]+}}, hwreg(HW_REG_LDS_ALLOC, 8, 23)
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 @s_getreg_test(i32 addrspace(1)* %out) { ; simm16=45574 for lds size.
DAG: Ignore call site attributes when emitting target intrinsic A target intrinsic may be defined as possibly reading memory, but the call site may have additional knowledge that it doesn't read memory. The intrinsic lowering will expect the pessimistic assumption of the intrinsic definition, so the chain should still be used. llvm-svn: 287593
2016-11-22 06:56:42 +08:00
%lds_size_64dwords = call i32 @llvm.amdgcn.s.getreg(i32 45574)
%lds_size_bytes = shl i32 %lds_size_64dwords, 8
store i32 %lds_size_bytes, i32 addrspace(1)* %out
ret void
}
; Call site has additional readnone knowledge.
; GCN-LABEL: {{^}}readnone_s_getreg_test:
; GCN: s_getreg_b32 s{{[0-9]+}}, hwreg(HW_REG_LDS_ALLOC, 8, 23)
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 @readnone_s_getreg_test(i32 addrspace(1)* %out) { ; simm16=45574 for lds size.
DAG: Ignore call site attributes when emitting target intrinsic A target intrinsic may be defined as possibly reading memory, but the call site may have additional knowledge that it doesn't read memory. The intrinsic lowering will expect the pessimistic assumption of the intrinsic definition, so the chain should still be used. llvm-svn: 287593
2016-11-22 06:56:42 +08:00
%lds_size_64dwords = call i32 @llvm.amdgcn.s.getreg(i32 45574) #1
AMDGPU/SI: Define S_GETREG Intrinsic Summary: Define s_getreg intrinsic to generate s_getreg instruction to read hardware registers. Reviewers: tstellarAMD, arsenm Subscribers: llvm-commits, arsenm Differential Revision: http://reviews.llvm.org/D17892 llvm-svn: 263124
2016-03-11 00:47:15 +08:00
%lds_size_bytes = shl i32 %lds_size_64dwords, 8
store i32 %lds_size_bytes, i32 addrspace(1)* %out
ret void
}
declare i32 @llvm.amdgcn.s.getreg(i32) #0
DAG: Ignore call site attributes when emitting target intrinsic A target intrinsic may be defined as possibly reading memory, but the call site may have additional knowledge that it doesn't read memory. The intrinsic lowering will expect the pessimistic assumption of the intrinsic definition, so the chain should still be used. llvm-svn: 287593
2016-11-22 06:56:42 +08:00
attributes #0 = { nounwind readonly }
attributes #1 = { nounwind readnone }