[AMDGPU][True16][CodeGen] S_PACK_XX_B32_B16 lowering for true16 mode (#162389)

S_PACK_XX_B32_B16 requires special lowering for true16 mode when it's
being lowered to VALU in fix-sgpr-copy pass.

Added test cases in fix-sgpr-copies-f16-true16.mir

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

@@ -9072,6 +9072,67 @@ void SIInstrInfo::movePackToVALU(SIInstrWorklist &Worklist,
   MachineOperand &Src1 = Inst.getOperand(2);
   const DebugLoc &DL = Inst.getDebugLoc();
 
+  if (ST.useRealTrue16Insts()) {
+    Register SrcReg0, SrcReg1;
+    if (!Src0.isReg() || !RI.isVGPR(MRI, Src0.getReg())) {
+      SrcReg0 = MRI.createVirtualRegister(&AMDGPU::VGPR_32RegClass);
+      BuildMI(*MBB, Inst, DL, get(AMDGPU::V_MOV_B32_e32), SrcReg0).add(Src0);
+    } else {
+      SrcReg0 = Src0.getReg();
+    }
+
+    if (!Src1.isReg() || !RI.isVGPR(MRI, Src1.getReg())) {
+      SrcReg1 = MRI.createVirtualRegister(&AMDGPU::VGPR_32RegClass);
+      BuildMI(*MBB, Inst, DL, get(AMDGPU::V_MOV_B32_e32), SrcReg1).add(Src1);
+    } else {
+      SrcReg1 = Src1.getReg();
+    }
+
+    bool isSrc0Reg16 = MRI.constrainRegClass(SrcReg0, &AMDGPU::VGPR_16RegClass);
+    bool isSrc1Reg16 = MRI.constrainRegClass(SrcReg1, &AMDGPU::VGPR_16RegClass);
+
+    auto NewMI = BuildMI(*MBB, Inst, DL, get(AMDGPU::REG_SEQUENCE), ResultReg);
+    switch (Inst.getOpcode()) {
+    case AMDGPU::S_PACK_LL_B32_B16:
+      NewMI
+          .addReg(SrcReg0, 0,
+                  isSrc0Reg16 ? AMDGPU::NoSubRegister : AMDGPU::lo16)
+          .addImm(AMDGPU::lo16)
+          .addReg(SrcReg1, 0,
+                  isSrc1Reg16 ? AMDGPU::NoSubRegister : AMDGPU::lo16)
+          .addImm(AMDGPU::hi16);
+      break;
+    case AMDGPU::S_PACK_LH_B32_B16:
+      NewMI
+          .addReg(SrcReg0, 0,
+                  isSrc0Reg16 ? AMDGPU::NoSubRegister : AMDGPU::lo16)
+          .addImm(AMDGPU::lo16)
+          .addReg(SrcReg1, 0, AMDGPU::hi16)
+          .addImm(AMDGPU::hi16);
+      break;
+    case AMDGPU::S_PACK_HL_B32_B16:
+      NewMI.addReg(SrcReg0, 0, AMDGPU::hi16)
+          .addImm(AMDGPU::lo16)
+          .addReg(SrcReg1, 0,
+                  isSrc1Reg16 ? AMDGPU::NoSubRegister : AMDGPU::lo16)
+          .addImm(AMDGPU::hi16);
+      break;
+    case AMDGPU::S_PACK_HH_B32_B16:
+      NewMI.addReg(SrcReg0, 0, AMDGPU::hi16)
+          .addImm(AMDGPU::lo16)
+          .addReg(SrcReg1, 0, AMDGPU::hi16)
+          .addImm(AMDGPU::hi16);
+      break;
+    default:
+      llvm_unreachable("unhandled s_pack_* instruction");
+    }
+
+    MachineOperand &Dest = Inst.getOperand(0);
+    MRI.replaceRegWith(Dest.getReg(), ResultReg);
+    addUsersToMoveToVALUWorklist(ResultReg, MRI, Worklist);
+    return;
+  }
+
   switch (Inst.getOpcode()) {
   case AMDGPU::S_PACK_LL_B32_B16: {
     Register ImmReg = MRI.createVirtualRegister(&AMDGPU::VGPR_32RegClass);

llvm/test/CodeGen/AMDGPU/add.v2i16.ll

@@ -780,7 +780,7 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i64(ptr addrspace(1) %out,
 ; GFX11-TRUE16-NEXT:    s_load_b128 s[0:3], s[4:5], 0x24
 ; GFX11-TRUE16-NEXT:    s_load_b64 s[4:5], s[4:5], 0x34
 ; GFX11-TRUE16-NEXT:    v_and_b32_e32 v0, 0x3ff, v0
-; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v2.l, 0
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v2.h, 0
 ; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2)
 ; GFX11-TRUE16-NEXT:    v_lshlrev_b32_e32 v0, 2, v0
 ; GFX11-TRUE16-NEXT:    s_waitcnt lgkmcnt(0)
@@ -790,11 +790,9 @@ define amdgpu_kernel void @v_test_add_v2i16_zext_to_v2i64(ptr addrspace(1) %out,
 ; GFX11-TRUE16-NEXT:    s_waitcnt vmcnt(0)
 ; GFX11-TRUE16-NEXT:    v_pk_add_u16 v0, v1, v0
 ; GFX11-TRUE16-NEXT:    v_mov_b32_e32 v1, 0
-; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_2)
-; GFX11-TRUE16-NEXT:    v_lshrrev_b32_e32 v3, 16, v0
-; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v0.h, v2.l
-; GFX11-TRUE16-NEXT:    v_lshl_or_b32 v2, v2, 16, v3
-; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_4)
+; GFX11-TRUE16-NEXT:    s_delay_alu instid0(VALU_DEP_2) | instskip(SKIP_1) | instid1(VALU_DEP_3)
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v2.l, v0.h
+; GFX11-TRUE16-NEXT:    v_mov_b16_e32 v0.h, v2.h
 ; GFX11-TRUE16-NEXT:    v_mov_b32_e32 v3, v1
 ; GFX11-TRUE16-NEXT:    global_store_b128 v1, v[0:3], s[0:1]
 ; GFX11-TRUE16-NEXT:    s_endpgm