diff --git a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp index 0edcb38137c1..86bd1a2c7fef 100644 --- a/llvm/lib/Target/AMDGPU/SIISelLowering.cpp +++ b/llvm/lib/Target/AMDGPU/SIISelLowering.cpp @@ -8552,7 +8552,7 @@ SDValue SITargetLowering::performSHLPtrCombine(SDNode *N, EVT VT = N->getValueType(0); SDValue ShlX = DAG.getNode(ISD::SHL, SL, VT, N0.getOperand(0), N1); - SDValue COffset = DAG.getConstant(Offset, SL, MVT::i32); + SDValue COffset = DAG.getConstant(Offset, SL, VT); SDNodeFlags Flags; Flags.setNoUnsignedWrap(N->getFlags().hasNoUnsignedWrap() && diff --git a/llvm/test/CodeGen/AMDGPU/shl_add_ptr_global.ll b/llvm/test/CodeGen/AMDGPU/shl_add_ptr_global.ll new file mode 100644 index 000000000000..2260de0b74f3 --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/shl_add_ptr_global.ll @@ -0,0 +1,21 @@ +; RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -enable-var-scope -check-prefixes=GCN,GFX9 %s + +; GCN-LABEL: {{^}}shl_base_global_ptr: +; GCN: v_add_co_u32_e32 v[[EXTRA_LO:[0-9]+]], vcc, 0x80, v4 +; GCN: v_addc_co_u32_e32 v[[EXTRA_HI:[0-9]+]], vcc, 0, v5, vcc +; GCN: v_lshlrev_b64 v{{\[}}[[LO:[0-9]+]]:[[HI:[0-9]+]]{{\]}}, 2, v[4:5] +; GCN: v_mov_b32_e32 [[THREE:v[0-9]+]], 3 +; GCN: global_atomic_and v{{\[}}[[LO]]:[[HI]]{{\]}}, [[THREE]], off offset:512 +; GCN: global_store_dwordx2 v{{\[[0-9]+:[0-9]+\]}}, v{{\[}}[[EXTRA_LO]]:[[EXTRA_HI]]{{\]}} +define void @shl_base_global_ptr(i32 addrspace(1)* %out, i64 addrspace(1)* %extra.use, [512 x i32] addrspace(1)* %ptr) #0 { + %arrayidx0 = getelementptr inbounds [512 x i32], [512 x i32] addrspace(1)* %ptr, i64 0, i64 32 + %cast = ptrtoint i32 addrspace(1)* %arrayidx0 to i64 + %shl = shl i64 %cast, 2 + %castback = inttoptr i64 %shl to i32 addrspace(1)* + %val = atomicrmw and i32 addrspace(1)* %castback, i32 3 seq_cst + store volatile i64 %cast, i64 addrspace(1)* %extra.use, align 4 + ret void +} + +attributes #0 = { nounwind } +attributes #1 = { nounwind readnone }