spill 16 with scratch load/store

Author: broxigarchen

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

@@ -1580,6 +1580,8 @@ static unsigned getSGPRSpillSaveOpcode(unsigned Size) {
 
 static unsigned getVGPRSpillSaveOpcode(unsigned Size) {
   switch (Size) {
+  case 2:
+    return AMDGPU::SI_SPILL_V16_SAVE;
   case 4:
     return AMDGPU::SI_SPILL_V32_SAVE;
   case 8:
@@ -1807,6 +1809,8 @@ static unsigned getSGPRSpillRestoreOpcode(unsigned Size) {
 
 static unsigned getVGPRSpillRestoreOpcode(unsigned Size) {
   switch (Size) {
+  case 2:
+    return AMDGPU::SI_SPILL_V16_RESTORE;
   case 4:
     return AMDGPU::SI_SPILL_V32_RESTORE;
   case 8:

llvm/lib/Target/AMDGPU/SIInstructions.td

@@ -1002,6 +1002,7 @@ multiclass SI_SPILL_VGPR <RegisterClass vgpr_class, bit UsesTmp = 0> {
   } // End UseNamedOperandTable = 1, Spill = 1, VALU = 1, SchedRW = [WriteVMEM]
 }
 
+defm SI_SPILL_V16  : SI_SPILL_VGPR <VGPR_16>;
 defm SI_SPILL_V32  : SI_SPILL_VGPR <VGPR_32>;
 defm SI_SPILL_V64  : SI_SPILL_VGPR <VReg_64>;
 defm SI_SPILL_V96  : SI_SPILL_VGPR <VReg_96>;

llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp

@@ -1280,6 +1280,8 @@ static unsigned getNumSubRegsForSpillOp(unsigned Op) {
   case AMDGPU::SI_SPILL_WWM_V32_RESTORE:
   case AMDGPU::SI_SPILL_WWM_AV32_SAVE:
   case AMDGPU::SI_SPILL_WWM_AV32_RESTORE:
+  case AMDGPU::SI_SPILL_V16_SAVE:
+  case AMDGPU::SI_SPILL_V16_RESTORE:
     return 1;
   default: llvm_unreachable("Invalid spill opcode");
   }
@@ -2347,6 +2349,7 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
     case AMDGPU::SI_SPILL_V96_SAVE:
     case AMDGPU::SI_SPILL_V64_SAVE:
     case AMDGPU::SI_SPILL_V32_SAVE:
+    case AMDGPU::SI_SPILL_V16_SAVE:
     case AMDGPU::SI_SPILL_A1024_SAVE:
     case AMDGPU::SI_SPILL_A512_SAVE:
     case AMDGPU::SI_SPILL_A384_SAVE:
@@ -2387,8 +2390,14 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
       assert(TII->getNamedOperand(*MI, AMDGPU::OpName::soffset)->getReg() ==
              MFI->getStackPtrOffsetReg());
 
-      unsigned Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_STORE_DWORD_SADDR
-                                            : AMDGPU::BUFFER_STORE_DWORD_OFFSET;
+      unsigned Opc;
+      if (MI->getOpcode() == AMDGPU::SI_SPILL_V16_SAVE) {
+        Opc = AMDGPU::SCRATCH_STORE_SHORT_SADDR_t16;
+      } else {
+        Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_STORE_DWORD_SADDR
+                                     : AMDGPU::BUFFER_STORE_DWORD_OFFSET;
+      }
+
       auto *MBB = MI->getParent();
       bool IsWWMRegSpill = TII->isWWMRegSpillOpcode(MI->getOpcode());
       if (IsWWMRegSpill) {
@@ -2406,6 +2415,7 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
       MI->eraseFromParent();
       return true;
     }
+    case AMDGPU::SI_SPILL_V16_RESTORE:
     case AMDGPU::SI_SPILL_V32_RESTORE:
     case AMDGPU::SI_SPILL_V64_RESTORE:
     case AMDGPU::SI_SPILL_V96_RESTORE:
@@ -2455,8 +2465,13 @@ bool SIRegisterInfo::eliminateFrameIndex(MachineBasicBlock::iterator MI,
       assert(TII->getNamedOperand(*MI, AMDGPU::OpName::soffset)->getReg() ==
              MFI->getStackPtrOffsetReg());
 
-      unsigned Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_LOAD_DWORD_SADDR
-                                            : AMDGPU::BUFFER_LOAD_DWORD_OFFSET;
+      unsigned Opc;
+      if (MI->getOpcode() == AMDGPU::SI_SPILL_V16_RESTORE) {
+        Opc = AMDGPU::SCRATCH_LOAD_SHORT_D16_SADDR_t16;
+      } else {
+        Opc = ST.enableFlatScratch() ? AMDGPU::SCRATCH_LOAD_DWORD_SADDR
+                                     : AMDGPU::BUFFER_LOAD_DWORD_OFFSET;
+      }
       auto *MBB = MI->getParent();
       bool IsWWMRegSpill = TII->isWWMRegSpillOpcode(MI->getOpcode());
       if (IsWWMRegSpill) {

llvm/lib/Target/AMDGPU/Utils/AMDGPUBaseInfo.cpp

@@ -2483,6 +2483,8 @@ bool isSISrcInlinableOperand(const MCInstrDesc &Desc, unsigned OpNo) {
 // (move from MC* level to Target* level). Return size in bits.
 unsigned getRegBitWidth(unsigned RCID) {
   switch (RCID) {
+  case AMDGPU::VGPR_16RegClassID:
+  case AMDGPU::VGPR_16_Lo128RegClassID:
   case AMDGPU::SGPR_LO16RegClassID:
   case AMDGPU::AGPR_LO16RegClassID:
     return 16;