[AMDGPU] New llvm.amdgcn.wave.id intrinsic

llvm/include/llvm/IR/IntrinsicsAMDGPU.td

@@ -2777,6 +2777,10 @@ class AMDGPULoadTr<LLVMType ptr_ty>:
 
 def int_amdgcn_global_load_tr : AMDGPULoadTr<global_ptr_ty>;
 
+// i32 @llvm.amdgcn.wave.id()
+def int_amdgcn_wave_id :
+  DefaultAttrsIntrinsic<[llvm_i32_ty], [], [IntrNoMem, IntrSpeculatable]>;
+
 //===----------------------------------------------------------------------===//
 // Deep learning intrinsics.
 //===----------------------------------------------------------------------===//

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp

@@ -6883,6 +6883,23 @@ bool AMDGPULegalizerInfo::legalizeStackSave(MachineInstr &MI,
   return true;
 }
 
+bool AMDGPULegalizerInfo::legalizeWaveID(MachineInstr &MI,
+                                         MachineIRBuilder &B) const {
+  // With architected SGPRs, waveIDinGroup is in TTMP8[29:25].
+  if (!ST.hasArchitectedSGPRs())
+    return false;
+  LLT S32 = LLT::scalar(32);
+  Register DstReg = MI.getOperand(0).getReg();
+  Register TTMP8 =
+      getFunctionLiveInPhysReg(B.getMF(), B.getTII(), AMDGPU::TTMP8,
+                               AMDGPU::SReg_32RegClass, B.getDebugLoc(), S32);
+  auto LSB = B.buildConstant(S32, 25);
+  auto Width = B.buildConstant(S32, 5);
+  B.buildUbfx(DstReg, TTMP8, LSB, Width);
+  MI.eraseFromParent();
+  return true;
+}
+
 bool AMDGPULegalizerInfo::legalizeIntrinsic(LegalizerHelper &Helper,
                                             MachineInstr &MI) const {
   MachineIRBuilder &B = Helper.MIRBuilder;
@@ -7005,6 +7022,8 @@ bool AMDGPULegalizerInfo::legalizeIntrinsic(LegalizerHelper &Helper,
   case Intrinsic::amdgcn_workgroup_id_z:
     return legalizePreloadedArgIntrin(MI, MRI, B,
                                       AMDGPUFunctionArgInfo::WORKGROUP_ID_Z);
+  case Intrinsic::amdgcn_wave_id:
+    return legalizeWaveID(MI, B);
   case Intrinsic::amdgcn_lds_kernel_id:
     return legalizePreloadedArgIntrin(MI, MRI, B,
                                       AMDGPUFunctionArgInfo::LDS_KERNEL_ID);

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h

@@ -212,6 +212,7 @@ class AMDGPULegalizerInfo final : public LegalizerInfo {
 
   bool legalizeFPTruncRound(MachineInstr &MI, MachineIRBuilder &B) const;
   bool legalizeStackSave(MachineInstr &MI, MachineIRBuilder &B) const;
+  bool legalizeWaveID(MachineInstr &MI, MachineIRBuilder &B) const;
 
   bool legalizeImageIntrinsic(
       MachineInstr &MI, MachineIRBuilder &B,

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

@@ -7920,6 +7920,18 @@ SDValue SITargetLowering::lowerSBuffer(EVT VT, SDLoc DL, SDValue Rsrc,
   return Loads[0];
 }
 
+SDValue SITargetLowering::lowerWaveID(SelectionDAG &DAG, SDValue Op) const {
+  // With architected SGPRs, waveIDinGroup is in TTMP8[29:25].
+  if (!Subtarget->hasArchitectedSGPRs())
+    return {};
+  SDLoc SL(Op);
+  MVT VT = MVT::i32;
+  SDValue TTMP8 = CreateLiveInRegister(DAG, &AMDGPU::SReg_32RegClass,
+                                       AMDGPU::TTMP8, VT, SL);
+  return DAG.getNode(AMDGPUISD::BFE_U32, SL, VT, TTMP8,
+                     DAG.getConstant(25, SL, VT), DAG.getConstant(5, SL, VT));
+}
+
 SDValue SITargetLowering::lowerWorkitemID(SelectionDAG &DAG, SDValue Op,
                                           unsigned Dim,
                                           const ArgDescriptor &Arg) const {
@@ -8090,6 +8102,8 @@ SDValue SITargetLowering::LowerINTRINSIC_WO_CHAIN(SDValue Op,
   case Intrinsic::amdgcn_workgroup_id_z:
     return getPreloadedValue(DAG, *MFI, VT,
                              AMDGPUFunctionArgInfo::WORKGROUP_ID_Z);
+  case Intrinsic::amdgcn_wave_id:
+    return lowerWaveID(DAG, Op);
   case Intrinsic::amdgcn_lds_kernel_id: {
     if (MFI->isEntryFunction())
       return getLDSKernelId(DAG, DL);

llvm/lib/Target/AMDGPU/SIISelLowering.h

@@ -80,6 +80,7 @@ class SITargetLowering final : public AMDGPUTargetLowering {
   SDValue lowerStructBufferAtomicIntrin(SDValue Op, SelectionDAG &DAG,
                                         unsigned NewOpcode) const;
 
+  SDValue lowerWaveID(SelectionDAG &DAG, SDValue Op) const;
   SDValue lowerWorkitemID(SelectionDAG &DAG, SDValue Op, unsigned Dim,
                           const ArgDescriptor &ArgDesc) const;
 

llvm/test/CodeGen/AMDGPU/llvm.amdgcn.wave.id.ll

@@ -0,0 +1,61 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py UTC_ARGS: --version 4
+; RUN: not --crash llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -global-isel=0 -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=GFX9-SDAG-ERR %s
+; RUN: not --crash llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -global-isel=1 -verify-machineinstrs < %s 2>&1 | FileCheck -check-prefix=GFX9-GISEL-ERR %s
+; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -mattr=+architected-sgprs -global-isel=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -mattr=+architected-sgprs -global-isel=1 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX9 %s
+; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -global-isel=0 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX12 %s
+; RUN: llc -mtriple=amdgcn-amd-amdpal -mcpu=gfx1200 -global-isel=1 -verify-machineinstrs < %s | FileCheck -check-prefix=GFX12 %s
+
+; GFX9-SDAG-ERR: LLVM ERROR: Cannot select: intrinsic %llvm.amdgcn.wave.id
+; GFX9-GISEL-ERR: LLVM ERROR: unable to legalize instruction: {{.*}} = G_INTRINSIC intrinsic(@llvm.amdgcn.wave.id)
+
+define amdgpu_cs void @test_wave_id(ptr addrspace(1) %out) {
+; GFX9-LABEL: test_wave_id:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_bfe_u32 s0, ttmp8, 0x50019
+; GFX9-NEXT:    v_mov_b32_e32 v2, s0
+; GFX9-NEXT:    global_store_dword v[0:1], v2, off
+; GFX9-NEXT:    s_endpgm
+;
+; GFX12-LABEL: test_wave_id:
+; GFX12:       ; %bb.0:
+; GFX12-NEXT:    s_bfe_u32 s0, ttmp8, 0x50019
+; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
+; GFX12-NEXT:    v_mov_b32_e32 v2, s0
+; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
+; GFX12-NEXT:    s_nop 0
+; GFX12-NEXT:    s_sendmsg sendmsg(MSG_DEALLOC_VGPRS)
+; GFX12-NEXT:    s_endpgm
+  %waveid = call i32 @llvm.amdgcn.wave.id()
+  store i32 %waveid, ptr addrspace(1) %out
+  ret void
+}
+
+define amdgpu_gfx void @test_wave_id_callable(ptr addrspace(1) %out) {
+; GFX9-LABEL: test_wave_id_callable:
+; GFX9:       ; %bb.0:
+; GFX9-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX9-NEXT:    s_bfe_u32 s34, ttmp8, 0x50019
+; GFX9-NEXT:    v_mov_b32_e32 v2, s34
+; GFX9-NEXT:    global_store_dword v[0:1], v2, off
+; GFX9-NEXT:    s_waitcnt vmcnt(0)
+; GFX9-NEXT:    s_setpc_b64 s[30:31]
+;
+; GFX12-LABEL: test_wave_id_callable:
+; GFX12:       ; %bb.0:
+; GFX12-NEXT:    s_wait_loadcnt_dscnt 0x0
+; GFX12-NEXT:    s_wait_expcnt 0x0
+; GFX12-NEXT:    s_wait_samplecnt 0x0
+; GFX12-NEXT:    s_wait_bvhcnt 0x0
+; GFX12-NEXT:    s_wait_kmcnt 0x0
+; GFX12-NEXT:    s_bfe_u32 s0, ttmp8, 0x50019
+; GFX12-NEXT:    s_delay_alu instid0(SALU_CYCLE_1)
+; GFX12-NEXT:    v_mov_b32_e32 v2, s0
+; GFX12-NEXT:    global_store_b32 v[0:1], v2, off
+; GFX12-NEXT:    s_setpc_b64 s[30:31]
+  %waveid = call i32 @llvm.amdgcn.wave.id()
+  store i32 %waveid, ptr addrspace(1) %out
+  ret void
+}
+
+declare i32 @llvm.amdgcn.wave.id()