From 3c07c813c059408b8ba3c307b747a202e4104128 Mon Sep 17 00:00:00 2001 From: Matt Arsenault Date: Fri, 22 Jul 2016 17:01:33 +0000 Subject: [PATCH] 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. llvm-svn: 276438 --- llvm/lib/Target/AMDGPU/SIISelLowering.cpp | 6 +++--- llvm/test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll | 17 +++++++++++++++-- 2 files changed, 18 insertions(+), 5 deletions(-) diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp index 5033374..55f1cab 100644 --- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp +++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp @@ -1433,9 +1433,9 @@ MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter( MachineFunction *MF = BB->getParent(); SIMachineFunctionInfo *MFI = MF->getInfo(); DebugLoc DL = MI.getDebugLoc(); - BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOVK_I32)) - .addOperand(MI.getOperand(0)) - .addImm(MFI->LDSSize); + BuildMI(*BB, MI, DL, TII->get(AMDGPU::S_MOV_B32)) + .addOperand(MI.getOperand(0)) + .addImm(MFI->LDSSize); MI.eraseFromParent(); return BB; } diff --git a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll index 9090b08..6014e2e 100644 --- a/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll +++ b/llvm/test/CodeGen/AMDGPU/llvm.amdgcn.groupstaticsize.ll @@ -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 -- 2.7.4