AMDGPU: Add kernarg.segment.ptr intrinsic

[• tstellarAMD]

LGTM.

[arsenm]

r268105

include/llvm/IR/IntrinsicsAMDGPU.td

 def int_amdgcn_dispatch_ptr :
   GCCBuiltin<"__builtin_amdgcn_dispatch_ptr">,
   Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [], [IntrNoMem]>;
 
 def int_amdgcn_queue_ptr :
   GCCBuiltin<"__builtin_amdgcn_queue_ptr">,
   Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [], [IntrNoMem]>;
 
+def int_amdgcn_kernarg_segment_ptr :
+  GCCBuiltin<"__builtin_amdgcn_kernarg_segment_ptr">,
+  Intrinsic<[LLVMQualPointerType<llvm_i8_ty, 2>], [], [IntrNoMem]>;
+
 // __builtin_amdgcn_interp_p1 <i>, <attr_chan>, <attr>, <m0>
 def int_amdgcn_interp_p1 :
   GCCBuiltin<"__builtin_amdgcn_interp_p1">,
   Intrinsic<[llvm_float_ty],
             [llvm_i32_ty, llvm_i32_ty, llvm_i32_ty, llvm_i32_ty],
             [IntrNoMem]>;  // This intrinsic reads from lds, but the memory
                            // values are constant, so it behaves like IntrNoMem.
 

lib/Target/AMDGPU/SIISelLowering.cpp

if (!Subtarget->isAmdHsaOS()) {
       return DAG.getUNDEF(VT);
     }
 
     auto Reg = IntrinsicID == Intrinsic::amdgcn_dispatch_ptr ?
       SIRegisterInfo::DISPATCH_PTR : SIRegisterInfo::QUEUE_PTR;
     return CreateLiveInRegister(DAG, &AMDGPU::SReg_64RegClass,
                                 TRI->getPreloadedValue(MF, Reg), VT);
   }
+  case Intrinsic::amdgcn_kernarg_segment_ptr: {
+    unsigned Reg
+      = TRI->getPreloadedValue(MF, SIRegisterInfo::KERNARG_SEGMENT_PTR);
+    return CreateLiveInRegister(DAG, &AMDGPU::SReg_64RegClass, Reg, VT);
+  }
   case Intrinsic::amdgcn_rcp:
     return DAG.getNode(AMDGPUISD::RCP, DL, VT, Op.getOperand(1));
   case Intrinsic::amdgcn_rsq:
   case AMDGPUIntrinsic::AMDGPU_rsq: // Legacy name
     return DAG.getNode(AMDGPUISD::RSQ, DL, VT, Op.getOperand(1));
   case Intrinsic::amdgcn_rsq_clamp:
   case AMDGPUIntrinsic::AMDGPU_rsq_clamped: { // Legacy name
     if (Subtarget->getGeneration() < AMDGPUSubtarget::VOLCANIC_ISLANDS)

test/CodeGen/AMDGPU/llvm.amdgcn.kernarg.segment.ptr.ll

+; RUN: llc -mtriple=amdgcn--amdhsa -mcpu=kaveri -verify-machineinstrs < %s | FileCheck -check-prefix=HSA -check-prefix=ALL %s
+; RUN: llc -mtriple=amdgcn-mesa-mesa3d -verify-machineinstrs < %s | FileCheck -check-prefix=MESA -check-prefix=ALL %s
+
+; ALL-LABEL: {{^}}test:
+; HSA: enable_sgpr_kernarg_segment_ptr = 1
+; HSA: s_load_dword s{{[0-9]+}}, s[4:5], 0xa
+
+; MESA: s_load_dword s{{[0-9]+}}, s[0:1], 0xa
+define void @test(i32 addrspace(1)* %out) #1 {
+  %kernarg.segment.ptr = call noalias i8 addrspace(2)* @llvm.amdgcn.kernarg.segment.ptr()
+  %header.ptr = bitcast i8 addrspace(2)* %kernarg.segment.ptr to i32 addrspace(2)*
+  %gep = getelementptr i32, i32 addrspace(2)* %header.ptr, i64 10
+  %value = load i32, i32 addrspace(2)* %gep
+  store i32 %value, i32 addrspace(1)* %out
+  ret void
+}
+
+declare i8 addrspace(2)* @llvm.amdgcn.kernarg.segment.ptr() #0
+
+attributes #0 = { nounwind readnone }
+attributes #1 = { nounwind }