Index: include/llvm/IR/IntrinsicsAMDGPU.td =================================================================== --- include/llvm/IR/IntrinsicsAMDGPU.td +++ include/llvm/IR/IntrinsicsAMDGPU.td @@ -566,6 +566,16 @@ [IntrReadMem, IntrSpeculatable] >; +// int_amdgcn_s_getpc is provided to allow a specific style of position +// independent code to determine the high part of its address when it is +// known (through convention) that the code and any data of interest does +// not cross a 4Gb address boundary. Use for any other purpose may not +// produce the desired results as optimizations may cause code movement, +// especially as we explicitly use IntrNoMem to allow optimizations. +def int_amdgcn_s_getpc : + GCCBuiltin<"__builtin_amdgcn_s_getpc">, + Intrinsic<[llvm_i64_ty], [], [IntrNoMem, IntrSpeculatable]>; + // __builtin_amdgcn_interp_mov , , , // param values: 0 = P10, 1 = P20, 2 = P0 def int_amdgcn_interp_mov : Index: lib/Target/AMDGPU/SOPInstructions.td =================================================================== --- lib/Target/AMDGPU/SOPInstructions.td +++ lib/Target/AMDGPU/SOPInstructions.td @@ -185,6 +185,11 @@ def S_BITSET1_B32 : SOP1_32 <"s_bitset1_b32">; def S_BITSET1_B64 : SOP1_64_32 <"s_bitset1_b64">; def S_GETPC_B64 : SOP1_64_0 <"s_getpc_b64">; +def : Pat < + (int_amdgcn_s_getpc), + (S_GETPC_B64) +>; + let isTerminator = 1, isBarrier = 1, isBranch = 1, isIndirectBranch = 1 in { Index: test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll =================================================================== --- /dev/null +++ test/CodeGen/AMDGPU/llvm.amdgcn.s.getpc.ll @@ -0,0 +1,15 @@ +; RUN: llc -march=amdgcn -verify-machineinstrs < %s | FileCheck -check-prefix=GCN %s + +declare i64 @llvm.amdgcn.s.getpc() #0 + +; GCN-LABEL: {{^}}test_s_getpc: +; GCN: s_load_dwordx2 +; GCN-DAG: s_getpc_b64 s{{\[[0-9]+:[0-9]+\]}} +; GCN: buffer_store_dwordx2 +define void @test_s_getpc(i64 addrspace(1)* %out) #0 { + %tmp = call i64 @llvm.amdgcn.s.getpc() #1 + store volatile i64 %tmp, i64 addrspace(1)* %out, align 8 + ret void +} + +attributes #0 = { nounwind readnone speculatable }