AMDGPU: Fix groupstaticsize for large LDS

The size can exceed s_movk_i32's limit, and we don't
want to use it this early since it inhibits optimizations.

This should probably be merged to the release branch.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@276438 91177308-0d34-0410-b5e6-96231b3b80d8
This commit is contained in:
Matt Arsenault 2016-07-22 17:01:33 +00:00
parent 30f0e3e4be
commit 9da217ee1e
2 changed files with 18 additions and 5 deletions

View File

@ -1433,7 +1433,7 @@ MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter(
MachineFunction *MF = BB->getParent();
SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
DebugLoc DL = MI.getDebugLoc();
BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOVK_I32))
BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOV_B32))
.addOperand(MI.getOperand(0))
.addImm(MFI->LDSSize);
MI.eraseFromParent();

View File

@ -5,8 +5,10 @@
@lds0 = addrspace(3) global [512 x float] undef, align 4
@lds1 = addrspace(3) global [256 x float] undef, align 4
@large = addrspace(3) global [4096 x i32] undef, align 4
; CHECK-LABEL: {{^}}groupstaticsize_test0:
; CHECK: s_movk_i32 s{{[0-9]+}}, 0x800
; CHECK: v_mov_b32_e32 v{{[0-9]+}}, 0x800{{$}}
define void @groupstaticsize_test0(float addrspace(1)* %out, i32 addrspace(1)* %lds_size) #0 {
%tid.x = tail call i32 @llvm.amdgcn.workitem.id.x() #1
%idx.0 = add nsw i32 %tid.x, 64
@ -20,7 +22,7 @@ define void @groupstaticsize_test0(float addrspace(1)* %out, i32 addrspace(1)* %
}
; CHECK-LABEL: {{^}}groupstaticsize_test1:
; CHECK: s_movk_i32 s{{[0-9]+}}, 0xc00
; CHECK: v_mov_b32_e32 v{{[0-9]+}}, 0xc00{{$}}
define void @groupstaticsize_test1(float addrspace(1)* %out, i32 %cond, i32 addrspace(1)* %lds_size) {
entry:
%static_lds_size = call i32 @llvm.amdgcn.groupstaticsize() #1
@ -46,6 +48,17 @@ endif: ; preds = %else, %if
ret void
}
; Exceeds 16-bit simm limit of s_movk_i32
; CHECK-LABEL: {{^}}large_groupstaticsize:
; CHECK: v_mov_b32_e32 [[REG:v[0-9]+]], 0x4000{{$}}
define void @large_groupstaticsize(i32 addrspace(1)* %size, i32 %idx) #0 {
%gep = getelementptr inbounds [4096 x i32], [4096 x i32] addrspace(3)* @large, i32 0, i32 %idx
store volatile i32 0, i32 addrspace(3)* %gep
%static_lds_size = call i32 @llvm.amdgcn.groupstaticsize()
store i32 %static_lds_size, i32 addrspace(1)* %size
ret void
}
declare i32 @llvm.amdgcn.groupstaticsize() #1
declare i32 @llvm.amdgcn.workitem.id.x() #1