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.rsq.legacy.ll

40 lines
1.4 KiB
LLVM
Raw Normal View History

AMDGPU: Fold more custom nodes to undef This will help sneak undefs past GVN into the DAG for some tests. Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors. llvm-svn: 273181
2016-06-21 02:33:56 +08:00
; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=SI -check-prefix=FUNC %s
declare float @llvm.amdgcn.rsq.legacy(float) #0
; FUNC-LABEL: {{^}}rsq_legacy_f32:
; SI: v_rsq_legacy_f32_e32 {{v[0-9]+}}, {{s[0-9]+}}
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 @rsq_legacy_f32(float addrspace(1)* %out, float %src) #1 {
AMDGPU: Fold more custom nodes to undef This will help sneak undefs past GVN into the DAG for some tests. Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors. llvm-svn: 273181
2016-06-21 02:33:56 +08:00
%rsq = call float @llvm.amdgcn.rsq.legacy(float %src) #0
store float %rsq, float addrspace(1)* %out, align 4
ret void
}
; TODO: Really these should be constant folded
; FUNC-LABEL: {{^}}rsq_legacy_f32_constant_4.0
; SI: v_rsq_legacy_f32_e32 {{v[0-9]+}}, 4.0
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 @rsq_legacy_f32_constant_4.0(float addrspace(1)* %out) #1 {
AMDGPU: Fold more custom nodes to undef This will help sneak undefs past GVN into the DAG for some tests. Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors. llvm-svn: 273181
2016-06-21 02:33:56 +08:00
%rsq = call float @llvm.amdgcn.rsq.legacy(float 4.0) #0
store float %rsq, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}rsq_legacy_f32_constant_100.0
; SI: v_rsq_legacy_f32_e32 {{v[0-9]+}}, 0x42c80000
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 @rsq_legacy_f32_constant_100.0(float addrspace(1)* %out) #1 {
AMDGPU: Fold more custom nodes to undef This will help sneak undefs past GVN into the DAG for some tests. Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors. llvm-svn: 273181
2016-06-21 02:33:56 +08:00
%rsq = call float @llvm.amdgcn.rsq.legacy(float 100.0) #0
store float %rsq, float addrspace(1)* %out, align 4
ret void
}
; FUNC-LABEL: {{^}}rsq_legacy_undef_f32:
; SI-NOT: v_rsq_legacy_f32
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 @rsq_legacy_undef_f32(float addrspace(1)* %out) #1 {
AMDGPU: Fold more custom nodes to undef This will help sneak undefs past GVN into the DAG for some tests. Also add missing intrinsic for rsq_legacy, even though the node was already selected to the instruction. Also start passing the debug location to intrinsic errors. llvm-svn: 273181
2016-06-21 02:33:56 +08:00
%rsq = call float @llvm.amdgcn.rsq.legacy(float undef)
store float %rsq, float addrspace(1)* %out, align 4
ret void
}
attributes #0 = { nounwind readnone }
attributes #1 = { nounwind }