maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

AMDGPU: Do not fold clamp instructions when sources are different 

Patch by hakzsam (Samuel Pitoiset)

llvm-svn: 314951
This commit is contained in:
Matt Arsenault 2017-10-05 00:13:17 +00:00
parent 89937534b2
commit aafff87dda
2 changed files with 23 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
llvm/lib/Target/AMDGPU/SIFoldOperands.cpp
View File

@ -737,6 +737,7 @@ const MachineOperand *SIFoldOperands::isClamp(const MachineInstr &MI) const {
const MachineOperand *Src0 = TII->getNamedOperand(MI, AMDGPU::OpName::src0); const MachineOperand *Src0 = TII->getNamedOperand(MI, AMDGPU::OpName::src0);
const MachineOperand *Src1 = TII->getNamedOperand(MI, AMDGPU::OpName::src1); const MachineOperand *Src1 = TII->getNamedOperand(MI, AMDGPU::OpName::src1);
if (!Src0->isReg() || !Src1->isReg() || if (!Src0->isReg() || !Src1->isReg() ||
Src0->getReg() != Src1->getReg() ||
Src0->getSubReg() != Src1->getSubReg() || Src0->getSubReg() != Src1->getSubReg() ||
Src0->getSubReg() != AMDGPU::NoSubRegister) Src0->getSubReg() != AMDGPU::NoSubRegister)
return nullptr; return nullptr;

22
llvm/test/CodeGen/AMDGPU/clamp.ll
View File

@ -663,6 +663,28 @@ define amdgpu_kernel void @v_clamp_v2f16_shuffle(<2 x half> addrspace(1)* %out,
ret void ret void
} }
; GCN-LABEL: {{^}}v_clamp_diff_source_f32:
; GCN: v_add_f32_e32 [[A:v[0-9]+]]
; GCN: v_add_f32_e32 [[B:v[0-9]+]]
; GCN: v_max_f32_e64 v{{[0-9]+}}, [[A]], [[B]] clamp{{$}}
define amdgpu_kernel void @v_clamp_diff_source_f32(float addrspace(1)* %out, float addrspace(1)* %aptr) #0
{
%gep0 = getelementptr float, float addrspace(1)* %aptr, i32 0
%gep1 = getelementptr float, float addrspace(1)* %aptr, i32 1
%gep2 = getelementptr float, float addrspace(1)* %aptr, i32 2
%l0 = load float, float addrspace(1)* %gep0
%l1 = load float, float addrspace(1)* %gep1
%l2 = load float, float addrspace(1)* %gep2
%a = fadd nsz float %l0, %l1
%b = fadd nsz float %l0, %l2
%res = call nsz float @llvm.maxnum.f32(float %a, float %b)
%max = call nsz float @llvm.maxnum.f32(float %res, float 0.0)
%min = call nsz float @llvm.minnum.f32(float %max, float 1.0)
%out.gep = getelementptr float, float addrspace(1)* %out, i32 3
store float %min, float addrspace(1)* %out.gep
ret void
}
declare i32 @llvm.amdgcn.workitem.id.x() #1 declare i32 @llvm.amdgcn.workitem.id.x() #1
declare float @llvm.fabs.f32(float) #1 declare float @llvm.fabs.f32(float) #1
declare float @llvm.minnum.f32(float, float) #1 declare float @llvm.minnum.f32(float, float) #1