[AMDGPU][GISel] Fix MMO for raw/struct buffer access with non-constant offset

Codegen for the raw/struct buffer access intrinsics would update the
offset in the MMO to reflect the combined offset, if it was known to be
constant. If the combined offset was not known to be constant, or if
there was an index, it would set the offset in the MMO to 0. This is
unsafe because it makes it look like the access does not alias with
another access with a fixed non-zero offset.

Fix these cases by setting the pointer in the MMO to null, to reflect
the fact that we do not have any known IR value pointer + constant
offset for the access.

D106284 did this for SelectionDAG. This is the corresponding fix for
GlobalISel.

Differential Revision: https://reviews.llvm.org/D106451

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.cpp

@@ -3650,20 +3650,18 @@ bool AMDGPULegalizerInfo::legalizeIsAddrSpace(MachineInstr &MI,
 // (the offset that is excluded from bounds checking and swizzling, to go in
 // the instruction's soffset field).  This function takes the first kind of
 // offset and figures out how to split it between voffset and immoffset.
-std::tuple<Register, unsigned, unsigned>
+std::pair<Register, unsigned>
 AMDGPULegalizerInfo::splitBufferOffsets(MachineIRBuilder &B,
                                         Register OrigOffset) const {
   const unsigned MaxImm = 4095;
   Register BaseReg;
-  unsigned TotalConstOffset;
+  unsigned ImmOffset;
   const LLT S32 = LLT::scalar(32);
   MachineRegisterInfo &MRI = *B.getMRI();
 
-  std::tie(BaseReg, TotalConstOffset) =
+  std::tie(BaseReg, ImmOffset) =
       AMDGPU::getBaseWithConstantOffset(MRI, OrigOffset);
 
-  unsigned ImmOffset = TotalConstOffset;
-
   // If BaseReg is a pointer, convert it to int.
   if (MRI.getType(BaseReg).isPointer())
     BaseReg = B.buildPtrToInt(MRI.getType(OrigOffset), BaseReg).getReg(0);
@@ -3694,7 +3692,32 @@ AMDGPULegalizerInfo::splitBufferOffsets(MachineIRBuilder &B,
   if (!BaseReg)
     BaseReg = B.buildConstant(S32, 0).getReg(0);
 
-  return std::make_tuple(BaseReg, ImmOffset, TotalConstOffset);
+  return std::make_pair(BaseReg, ImmOffset);
+}
+
+/// Update \p MMO based on the offset inputs to a raw/struct buffer intrinsic.
+void AMDGPULegalizerInfo::updateBufferMMO(MachineMemOperand *MMO,
+                                          Register VOffset, Register SOffset,
+                                          unsigned ImmOffset, Register VIndex,
+                                          MachineRegisterInfo &MRI) const {
+  Optional<ValueAndVReg> MaybeVOffsetVal =
+      getConstantVRegValWithLookThrough(VOffset, MRI);
+  Optional<ValueAndVReg> MaybeSOffsetVal =
+      getConstantVRegValWithLookThrough(SOffset, MRI);
+  Optional<ValueAndVReg> MaybeVIndexVal =
+      getConstantVRegValWithLookThrough(VIndex, MRI);
+  // If the combined VOffset + SOffset + ImmOffset + strided VIndex is constant,
+  // update the MMO with that offset. The stride is unknown so we can only do
+  // this if VIndex is constant 0.
+  if (MaybeVOffsetVal && MaybeSOffsetVal && MaybeVIndexVal &&
+      MaybeVIndexVal->Value == 0) {
+    uint64_t TotalOffset = MaybeVOffsetVal->Value.getZExtValue() +
+                           MaybeSOffsetVal->Value.getZExtValue() + ImmOffset;
+    MMO->setOffset(TotalOffset);
+  } else {
+    // We don't have a constant combined offset to use in the MMO. Give up.
+    MMO->setValue((Value *)nullptr);
+  }
 }
 
 /// Handle register layout difference for f16 images for some subtargets.
@@ -3798,7 +3821,6 @@ bool AMDGPULegalizerInfo::legalizeBufferStore(MachineInstr &MI,
   const int MemSize = MMO->getSize();
 
   unsigned ImmOffset;
-  unsigned TotalOffset;
 
   // The typed intrinsics add an immediate after the registers.
   const unsigned NumVIndexOps = IsTyped ? 8 : 7;
@@ -3810,6 +3832,8 @@ bool AMDGPULegalizerInfo::legalizeBufferStore(MachineInstr &MI,
   if (HasVIndex) {
     VIndex = MI.getOperand(3).getReg();
     OpOffset = 1;
+  } else {
+    VIndex = B.buildConstant(S32, 0).getReg(0);
   }
 
   Register VOffset = MI.getOperand(3 + OpOffset).getReg();
@@ -3823,9 +3847,8 @@ bool AMDGPULegalizerInfo::legalizeBufferStore(MachineInstr &MI,
 
   unsigned AuxiliaryData = MI.getOperand(5 + OpOffset).getImm();
 
-  std::tie(VOffset, ImmOffset, TotalOffset) = splitBufferOffsets(B, VOffset);
-  if (TotalOffset != 0)
-    MMO = B.getMF().getMachineMemOperand(MMO, TotalOffset, MemSize);
+  std::tie(VOffset, ImmOffset) = splitBufferOffsets(B, VOffset);
+  updateBufferMMO(MMO, VOffset, SOffset, ImmOffset, VIndex, MRI);
 
   unsigned Opc;
   if (IsTyped) {
@@ -3848,9 +3871,6 @@ bool AMDGPULegalizerInfo::legalizeBufferStore(MachineInstr &MI,
     }
   }
 
-  if (!VIndex)
-    VIndex = B.buildConstant(S32, 0).getReg(0);
-
   auto MIB = B.buildInstr(Opc)
     .addUse(VData)              // vdata
     .addUse(RSrc)               // rsrc
@@ -3893,6 +3913,8 @@ bool AMDGPULegalizerInfo::legalizeBufferLoad(MachineInstr &MI,
   if (HasVIndex) {
     VIndex = MI.getOperand(3).getReg();
     OpOffset = 1;
+  } else {
+    VIndex = B.buildConstant(S32, 0).getReg(0);
   }
 
   Register VOffset = MI.getOperand(3 + OpOffset).getReg();
@@ -3906,16 +3928,14 @@ bool AMDGPULegalizerInfo::legalizeBufferLoad(MachineInstr &MI,
 
   unsigned AuxiliaryData = MI.getOperand(5 + OpOffset).getImm();
   unsigned ImmOffset;
-  unsigned TotalOffset;
 
   LLT Ty = MRI.getType(Dst);
   LLT EltTy = Ty.getScalarType();
   const bool IsD16 = IsFormat && (EltTy.getSizeInBits() == 16);
   const bool Unpacked = ST.hasUnpackedD16VMem();
 
-  std::tie(VOffset, ImmOffset, TotalOffset) = splitBufferOffsets(B, VOffset);
-  if (TotalOffset != 0)
-    MMO = B.getMF().getMachineMemOperand(MMO, TotalOffset, MemTy);
+  std::tie(VOffset, ImmOffset) = splitBufferOffsets(B, VOffset);
+  updateBufferMMO(MMO, VOffset, SOffset, ImmOffset, VIndex, MRI);
 
   unsigned Opc;
 
@@ -3952,9 +3972,6 @@ bool AMDGPULegalizerInfo::legalizeBufferLoad(MachineInstr &MI,
   else
     LoadDstReg = Dst;
 
-  if (!VIndex)
-    VIndex = B.buildConstant(S32, 0).getReg(0);
-
   auto MIB = B.buildInstr(Opc)
     .addDef(LoadDstReg)         // vdata
     .addUse(RSrc)               // rsrc
@@ -4095,6 +4112,8 @@ bool AMDGPULegalizerInfo::legalizeBufferAtomic(MachineInstr &MI,
   if (HasVIndex) {
     VIndex = MI.getOperand(4 + OpOffset).getReg();
     ++OpOffset;
+  } else {
+    VIndex = B.buildConstant(LLT::scalar(32), 0).getReg(0);
   }
 
   Register VOffset = MI.getOperand(4 + OpOffset).getReg();
@@ -4104,13 +4123,8 @@ bool AMDGPULegalizerInfo::legalizeBufferAtomic(MachineInstr &MI,
   MachineMemOperand *MMO = *MI.memoperands_begin();
 
   unsigned ImmOffset;
-  unsigned TotalOffset;
-  std::tie(VOffset, ImmOffset, TotalOffset) = splitBufferOffsets(B, VOffset);
-  if (TotalOffset != 0)
-    MMO = B.getMF().getMachineMemOperand(MMO, TotalOffset, MMO->getSize());
-
-  if (!VIndex)
-    VIndex = B.buildConstant(LLT::scalar(32), 0).getReg(0);
+  std::tie(VOffset, ImmOffset) = splitBufferOffsets(B, VOffset);
+  updateBufferMMO(MMO, VOffset, SOffset, ImmOffset, VIndex, *B.getMRI());
 
   auto MIB = B.buildInstr(getBufferAtomicPseudo(IID));
 

llvm/lib/Target/AMDGPU/AMDGPULegalizerInfo.h

@@ -142,8 +142,11 @@ public:
   bool legalizeIsAddrSpace(MachineInstr &MI, MachineRegisterInfo &MRI,
                            MachineIRBuilder &B, unsigned AddrSpace) const;
 
-  std::tuple<Register, unsigned, unsigned>
-  splitBufferOffsets(MachineIRBuilder &B, Register OrigOffset) const;
+  std::pair<Register, unsigned> splitBufferOffsets(MachineIRBuilder &B,
+                                                   Register OrigOffset) const;
+  void updateBufferMMO(MachineMemOperand *MMO, Register VOffset,
+                       Register SOffset, unsigned ImmOffset, Register VIndex,
+                       MachineRegisterInfo &MRI) const;
 
   Register handleD16VData(MachineIRBuilder &B, MachineRegisterInfo &MRI,
                           Register Reg, bool ImageStore = false) const;

llvm/test/CodeGen/AMDGPU/GlobalISel/buffer-schedule.ll

@@ -1,10 +1,8 @@
 ; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx900 -verify-machineinstrs < %s | FileCheck -check-prefixes=GCN %s
 
-; FIXME: the first load and store should not be reordered because they might
-; alias depending on the value of %off
 ; GCN-LABEL: {{^}}test1:
-; GCN: buffer_load_dword
 ; GCN: buffer_store_dword
+; GCN: buffer_load_dword
 ; GCN: buffer_store_dword
 define amdgpu_cs void @test1(<4 x i32> inreg %buf, i32 %off) {
 .entry:

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.add.ll

@@ -14,7 +14,7 @@ define amdgpu_ps float @raw_buffer_atomic_add_i32__vgpr_val__sgpr_rsrc__vgpr_vof
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_OFFEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -34,7 +34,7 @@ define amdgpu_ps float @raw_buffer_atomic_add_i32_noret__vgpr_val__sgpr_rsrc__vg
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_OFFEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -56,7 +56,7 @@ define amdgpu_ps <2 x float> @raw_buffer_atomic_add_i64__vgpr_val__sgpr_rsrc__vg
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY4]], %subreg.sub2, [[COPY5]], %subreg.sub3
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_OFFEN_RTN [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_OFFEN_RTN [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64), align 1, addrspace 4)
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN]].sub0
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY8]]
@@ -81,7 +81,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_i64_noret__vgpr_val__sgpr_rsrc__vgp
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY4]], %subreg.sub2, [[COPY5]], %subreg.sub3
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_OFFEN_RTN [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_OFFEN_RTN [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %ret = call i64 @llvm.amdgcn.raw.buffer.atomic.add.i64(i64 %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -121,7 +121,7 @@ define amdgpu_ps float @raw_buffer_atomic_add_i32__sgpr_val__vgpr_rsrc__sgpr_vof
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -170,7 +170,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_i32_noret__sgpr_val__vgpr_rsrc__sgp
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -195,7 +195,7 @@ define amdgpu_ps float @raw_buffer_atomic_add_i32__vgpr_val__sgpr_rsrc__vgpr_vof
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_OFFEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095
@@ -217,7 +217,7 @@ define amdgpu_ps float @raw_buffer_atomic_add_i32__vgpr_val__sgpr_rsrc__vgpr_vof
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_OFFEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.raw.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 2)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.cmpswap.ll

@@ -16,7 +16,7 @@ define amdgpu_ps float @raw_buffer_atomic_cmpswap_i32__vgpr_val__vgpr_cmp__sgpr_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN]].sub0
   ; CHECK:   $vgpr0 = COPY [[COPY8]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
@@ -40,7 +40,7 @@ define amdgpu_ps void @raw_buffer_atomic_cmpswap_i32_noret__vgpr_val__vgpr_cmp__
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN]].sub0
   ; CHECK:   S_ENDPGM 0
   %ret = call i32 @llvm.amdgcn.raw.buffer.atomic.cmpswap.i32(i32 %val, i32 %cmp, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -84,7 +84,7 @@ define amdgpu_ps float @raw_buffer_atomic_cmpswap_i32__sgpr_val__sgpr_cmp__vgpr_
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY9]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE4]], [[COPY10]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE4]], [[COPY10]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY13:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN]].sub0
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
@@ -137,7 +137,7 @@ define amdgpu_ps void @raw_buffer_atomic_cmpswap_i32_noret__sgpr_val__sgpr_cmp__
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY9]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE4]], [[COPY10]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE4]], [[COPY10]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY13:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN]].sub0
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
@@ -165,7 +165,7 @@ define amdgpu_ps float @raw_buffer_atomic_cmpswap_i32__vgpr_val__vgpr_cmp__sgpr_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_OFFEN_RTN]].sub0
   ; CHECK:   $vgpr0 = COPY [[COPY8]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.atomic.fadd.ll

@@ -15,7 +15,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -28,7 +28,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -46,7 +46,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset_plus4095__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -59,7 +59,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -77,7 +77,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX908:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset_4095__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -89,7 +89,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX90A:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
   ret void
@@ -107,7 +107,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__0_v
   ; GFX908:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__0_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -119,7 +119,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__0_v
   ; GFX90A:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 0, i32 %soffset, i32 0)
   ret void
@@ -159,7 +159,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__sgp
   ; GFX908:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; GFX908:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; GFX908:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX908:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX908:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -200,7 +200,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__sgp
   ; GFX90A:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; GFX90A:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; GFX90A:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX90A:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX90A:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -245,7 +245,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__0_v
   ; GFX908:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; GFX908:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; GFX908:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFSET [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX908:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX908:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -284,7 +284,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__0_v
   ; GFX90A:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; GFX90A:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; GFX90A:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFSET_RTN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX90A:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX90A:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -309,7 +309,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset_voffset_add4095
   ; GFX90A: bb.1 (%ir-block.0):
@@ -322,7 +322,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %voffset = add i32 %voffset.base, 4095
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -342,7 +342,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc
   ; GFX90A: bb.1 (%ir-block.0):
@@ -355,7 +355,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgp
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.raw.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 2)
   ret void
@@ -373,7 +373,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__v
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_OFFEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -386,7 +386,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__v
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_OFFEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_OFFEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -403,7 +403,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__0
   ; GFX908:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_OFFSET [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__0_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -415,7 +415,7 @@ define amdgpu_ps void @raw_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__0
   ; GFX90A:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_OFFSET_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_OFFSET_RTN [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call <2 x half> @llvm.amdgcn.raw.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 0, i32 %soffset, i32 0)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.format.f16.ll

@@ -14,7 +14,7 @@ define amdgpu_ps half @raw_buffer_load_format_f16__sgpr_rsrc__vgpr_voffset__sgpr
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: raw_buffer_load_format_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
@@ -27,7 +27,7 @@ define amdgpu_ps half @raw_buffer_load_format_f16__sgpr_rsrc__vgpr_voffset__sgpr
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.buffer.load.format.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -45,7 +45,7 @@ define amdgpu_ps <2 x half> @raw_buffer_load_format_v2f16__sgpr_rsrc__vgpr_voffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: raw_buffer_load_format_v2f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
@@ -58,7 +58,7 @@ define amdgpu_ps <2 x half> @raw_buffer_load_format_v2f16__sgpr_rsrc__vgpr_voffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN]].sub0
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN]].sub1
   ; UNPACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
@@ -93,7 +93,7 @@ define amdgpu_ps <4 x half> @raw_buffer_load_format_v4f16__sgpr_rsrc__vgpr_voffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub0
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub1
   ; PACKED:   $vgpr0 = COPY [[COPY6]]
@@ -109,7 +109,7 @@ define amdgpu_ps <4 x half> @raw_buffer_load_format_v4f16__sgpr_rsrc__vgpr_voffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub0
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub1
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub2
@@ -169,7 +169,7 @@ define amdgpu_ps half @raw_buffer_load_format_f16__vgpr_rsrc__sgpr_voffset__vgpr
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -209,7 +209,7 @@ define amdgpu_ps half @raw_buffer_load_format_f16__vgpr_rsrc__sgpr_voffset__vgpr
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -234,7 +234,7 @@ define amdgpu_ps <4 x half> @raw_buffer_load_format_v4f16__sgpr_rsrc__vgpr_voffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub0
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub1
   ; PACKED:   $vgpr0 = COPY [[COPY6]]
@@ -250,7 +250,7 @@ define amdgpu_ps <4 x half> @raw_buffer_load_format_v4f16__sgpr_rsrc__vgpr_voffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub0
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub1
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub2

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.format.ll

@@ -13,7 +13,7 @@ define amdgpu_ps float @raw_buffer_load_format_f32__sgpr_rsrc__vgpr_voffset__sgp
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.format.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -31,7 +31,7 @@ define amdgpu_ps <2 x float> @raw_buffer_load_format_v2f32__sgpr_rsrc__vgpr_voff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XY_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XY_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XY_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XY_OFFEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY6]]
@@ -52,7 +52,7 @@ define amdgpu_ps <3 x float> @raw_buffer_load_format_v3f32__sgpr_rsrc__vgpr_voff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZ_OFFEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_FORMAT_XYZ_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZ_OFFEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_FORMAT_XYZ_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub2
@@ -75,7 +75,7 @@ define amdgpu_ps <4 x float> @raw_buffer_load_format_v4f32__sgpr_rsrc__vgpr_voff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub2
@@ -121,7 +121,7 @@ define amdgpu_ps float @raw_buffer_load_format_f32__vgpr_rsrc__sgpr_voffset__vgp
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -146,7 +146,7 @@ define amdgpu_ps <4 x float> @raw_buffer_load_format_v4f32__sgpr_rsrc__vgpr_voff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub2

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.load.ll

@@ -14,7 +14,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -34,7 +34,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__sgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr7
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[COPY4]]
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -69,7 +69,7 @@ define amdgpu_ps float @raw_buffer_load_f32__vgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -114,7 +114,7 @@ define amdgpu_ps float @raw_buffer_load_f32__vgpr_rsrc__vgpr_voffset__vgpr_soffs
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -140,7 +140,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 1)
@@ -159,7 +159,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 2, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 2, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 2)
@@ -178,7 +178,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 4, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 4, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 4)
@@ -197,7 +197,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 6, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 6, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 6)
@@ -216,7 +216,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 5, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 5, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 5)
@@ -235,7 +235,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 7, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 7, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 7)
@@ -254,7 +254,7 @@ define amdgpu_ps <2 x float> @raw_buffer_load_v2f32__sgpr_rsrc__vgpr_voffset__sg
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORDX2_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX2_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_OFFEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY6]]
@@ -275,7 +275,7 @@ define amdgpu_ps <3 x float> @raw_buffer_load_v3f32__sgpr_rsrc__vgpr_voffset__sg
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORDX3_OFFEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_DWORDX3_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX3_OFFEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_DWORDX3_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_OFFEN]].sub2
@@ -298,7 +298,7 @@ define amdgpu_ps <4 x float> @raw_buffer_load_v4f32__sgpr_rsrc__vgpr_voffset__sg
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORDX4_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_DWORDX4_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX4_OFFEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_DWORDX4_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_OFFEN]].sub2
@@ -323,7 +323,7 @@ define amdgpu_ps half @raw_buffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffse
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_USHORT_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.buffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -341,7 +341,7 @@ define amdgpu_ps <2 x half> @raw_buffer_load_v2f16__sgpr_rsrc__vgpr_voffset__sgp
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call <2 x half> @llvm.amdgcn.raw.buffer.load.v2f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -365,7 +365,7 @@ define amdgpu_ps <4 x half> @raw_buffer_load_v4f16__sgpr_rsrc__vgpr_voffset__sgp
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORDX2_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX2_OFFEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_OFFEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY6]]
@@ -386,7 +386,7 @@ define amdgpu_ps float @raw_buffer_load_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffse
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8) from custom "BufferResource", addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8), addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_UBYTE_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call i8 @llvm.amdgcn.raw.buffer.load.i8(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -406,7 +406,7 @@ define amdgpu_ps float @raw_buffer_load_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffse
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8) from custom "BufferResource", addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8), addrspace 4)
   ; CHECK:   [[V_BFE_I32_e64_:%[0-9]+]]:vgpr_32 = V_BFE_I32_e64 [[BUFFER_LOAD_UBYTE_OFFEN]], 0, 8, implicit $exec
   ; CHECK:   $vgpr0 = COPY [[V_BFE_I32_e64_]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
@@ -444,7 +444,7 @@ define amdgpu_ps half @raw_buffer_load_f16__vgpr_rsrc__vgpr_voffset__sgpr_soffse
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_USHORT_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -486,7 +486,7 @@ define amdgpu_ps float @raw_buffer_load_i8__vgpr_rsrc__vgpr_voffset__sgpr_soffse
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8) from custom "BufferResource", addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_UBYTE_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8), addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -512,7 +512,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vdpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFSET:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET [[REG_SEQUENCE]], [[COPY4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFSET:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET [[REG_SEQUENCE]], [[COPY4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFSET]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %soffset, i32 0)
@@ -529,7 +529,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY3:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFSET:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET [[REG_SEQUENCE]], [[COPY4]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFSET:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET [[REG_SEQUENCE]], [[COPY4]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFSET]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
@@ -548,7 +548,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY5]], [[REG_SEQUENCE]], [[COPY4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY5]], [[REG_SEQUENCE]], [[COPY4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 4096, i32 %soffset, i32 0)
@@ -566,7 +566,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 16, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 16, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 16, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 16
@@ -585,7 +585,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095
@@ -607,7 +607,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   %10:vgpr_32, dead %15:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY4]], [[COPY6]], 0, implicit $exec
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %10, [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %10, [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4096
@@ -626,7 +626,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
@@ -644,7 +644,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
@@ -664,7 +664,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 16
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY5]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %soffset = add i32 %soffset.base, 16
@@ -685,7 +685,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY5]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %soffset = add i32 %soffset.base, 4095
@@ -706,7 +706,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY5]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %soffset = add i32 %soffset.base, 4096
@@ -744,7 +744,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN [[COPY4]], [[REG_SEQUENCE3]], [[S_ADD_I32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -774,7 +774,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr2
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK:   %13:vgpr_32, dead %35:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY4]], [[COPY6]], 0, implicit $exec
+  ; CHECK:   %14:vgpr_32, dead %35:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY4]], [[COPY6]], 0, implicit $exec
   ; CHECK:   [[COPY7:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
   ; CHECK:   [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
@@ -790,7 +790,7 @@ define amdgpu_ps float @raw_buffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %13, [[REG_SEQUENCE3]], [[COPY5]], 904, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 5000, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_OFFEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_OFFEN %14, [[REG_SEQUENCE3]], [[COPY5]], 904, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.format.f16.ll

@@ -14,7 +14,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_f16
   ; PACKED: bb.1 (%ir-block.0):
@@ -27,7 +27,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -44,7 +44,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_409
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_4095__sgpr_soffset_f16
   ; PACKED: bb.1 (%ir-block.0):
@@ -56,7 +56,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_409
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.f16(half %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
   ret void
@@ -78,7 +78,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY7]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16
   ; PACKED: bb.1 (%ir-block.0):
@@ -91,7 +91,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -116,7 +116,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY9]], [[COPY5]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY5]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v4f16
   ; PACKED: bb.1 (%ir-block.0):
@@ -131,7 +131,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; PACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -173,7 +173,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY11]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -211,7 +211,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY9]], implicit $exec
   ; PACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -240,7 +240,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY6]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4095
   ; PACKED: bb.1 (%ir-block.0):
@@ -253,7 +253,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
   ret void
@@ -275,7 +275,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY6]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_soffset4096
   ; PACKED: bb.1 (%ir-block.0):
@@ -288,7 +288,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
   ret void
@@ -310,7 +310,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY7]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_16
   ; PACKED: bb.1 (%ir-block.0):
@@ -323,7 +323,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 16
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -346,7 +346,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY7]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4095
   ; PACKED: bb.1 (%ir-block.0):
@@ -359,7 +359,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -385,7 +385,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_1]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY4]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr_soffset_v2f16_voffset_add_4096
   ; PACKED: bb.1 (%ir-block.0):
@@ -401,7 +401,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; PACKED:   %11:vgpr_32, dead %15:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4096
   call void @llvm.amdgcn.raw.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -448,7 +448,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; UNPACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY12]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -489,7 +489,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; PACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY10]], implicit $exec
   ; PACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.format.f32.ll

@@ -14,7 +14,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -31,7 +31,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__voffset_409
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.f32(float %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
   ret void
@@ -51,7 +51,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -72,7 +72,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_96 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZ_OFFEN_exact [[REG_SEQUENCE1]], [[COPY7]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZ_OFFEN_exact [[REG_SEQUENCE1]], [[COPY7]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -94,7 +94,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
   ; CHECK:   [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -132,7 +132,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY11]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -159,7 +159,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
   ret void
@@ -179,7 +179,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
   ret void
@@ -199,7 +199,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 16
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -220,7 +220,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -244,7 +244,7 @@ define amdgpu_ps void @raw_buffer_store_format__sgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   %13:vgpr_32, dead %17:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY6]], [[COPY8]], 0, implicit $exec
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s64) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE1]], %13, [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4096
   call void @llvm.amdgcn.raw.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -288,7 +288,7 @@ define amdgpu_ps void @raw_buffer_store_format__vgpr_rsrc__vgpr_val__vgpr_voffse
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY12]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %15, [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s128) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE1]], %15, [[REG_SEQUENCE4]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.buffer.store.ll

@@ -15,7 +15,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -36,7 +36,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__sgpr_val__sgpr_voffset__sgpr
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr8
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[COPY4]]
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[COPY5]]
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY7]], [[COPY8]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY7]], [[COPY8]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -71,7 +71,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -103,7 +103,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__vgpr
   ; CHECK:   successors: %bb.3(0x40000000), %bb.2(0x40000000)
   ; CHECK:   [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_]], [[COPY6]], implicit $exec
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[V_READFIRSTLANE_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[V_READFIRSTLANE_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[V_CMP_EQ_U32_e64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -148,7 +148,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__vgpr_voffset__vgpr
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -173,7 +173,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 1)
   ret void
@@ -191,7 +191,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 2)
   ret void
@@ -209,7 +209,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 3)
   ret void
@@ -227,7 +227,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 4, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 4, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 4)
   ret void
@@ -245,7 +245,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 6, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 6, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 6)
   ret void
@@ -263,7 +263,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 5, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 5, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 5)
   ret void
@@ -281,7 +281,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 7, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 7, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 7)
   ret void
@@ -301,7 +301,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -322,7 +322,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_96 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORDX3_OFFEN_exact [[REG_SEQUENCE1]], [[COPY7]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX3_OFFEN_exact [[REG_SEQUENCE1]], [[COPY7]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -344,7 +344,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
   ; CHECK:   [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORDX4_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX4_OFFEN_exact [[REG_SEQUENCE1]], [[COPY8]], [[REG_SEQUENCE]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -362,7 +362,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_BYTE_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; CHECK:   BUFFER_STORE_BYTE_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %val.trunc = trunc i32 %val to i8
   call void @llvm.amdgcn.raw.buffer.store.i8(i8 %val.trunc, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -381,7 +381,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_SHORT_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_SHORT_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %val.trunc = trunc i32 %val to i16
   call void @llvm.amdgcn.raw.buffer.store.i16(i16 %val.trunc, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -400,7 +400,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_SHORT_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_SHORT_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -418,7 +418,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -438,7 +438,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -474,7 +474,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE3]], [[COPY9]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX2_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE4]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -498,7 +498,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__sgpr_soffset_f32_v
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFSET_exact [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 0)
   ret void
@@ -517,7 +517,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__sgpr_soffset_f32_v
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 4096, i32 %soffset, i32 0)
   ret void
@@ -535,7 +535,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 16
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -554,7 +554,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -576,7 +576,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   %11:vgpr_32, dead %15:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4096
   call void @llvm.amdgcn.raw.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -595,7 +595,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 0)
   ret void
@@ -613,7 +613,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 0)
   ret void
@@ -631,7 +631,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 16
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -650,7 +650,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -672,7 +672,7 @@ define amdgpu_ps void @raw_buffer_store__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   %11:vgpr_32, dead %15:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %11, [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4096
   call void @llvm.amdgcn.raw.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset.add, i32 %soffset, i32 0)
@@ -695,7 +695,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr2
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK:   %13:vgpr_32, dead %33:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
+  ; CHECK:   %14:vgpr_32, dead %33:sreg_64_xexec = V_ADD_CO_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
   ; CHECK:   [[COPY8:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub0_sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]].sub2_sub3
   ; CHECK:   [[S_MOV_B64_term:%[0-9]+]]:sreg_64_xexec = S_MOV_B64_term $exec
@@ -711,7 +711,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY9]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %13, [[REG_SEQUENCE3]], [[COPY6]], 904, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 5000, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], %14, [[REG_SEQUENCE3]], [[COPY6]], 904, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -755,7 +755,7 @@ define amdgpu_ps void @raw_buffer_store__vgpr_rsrc__vgpr_val__5000_voffset__sgpr
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY6]], [[REG_SEQUENCE3]], [[COPY5]], 904, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 5000, align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_OFFEN_exact [[COPY4]], [[COPY6]], [[REG_SEQUENCE3]], [[COPY5]], 904, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.load.f16.ll

@@ -13,7 +13,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
@@ -26,7 +26,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.tbuffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -44,7 +44,7 @@ define amdgpu_ps <2 x half> @raw_tbuffer_load_v2f16__sgpr_rsrc__vgpr_voffset__sg
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN]].sub0
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_OFFEN]].sub1
   ; UNPACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
@@ -68,7 +68,7 @@ define amdgpu_ps <2 x half> @raw_tbuffer_load_v2f16__sgpr_rsrc__vgpr_voffset__sg
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call <2 x half> @llvm.amdgcn.raw.tbuffer.load.v2f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -92,7 +92,7 @@ define amdgpu_ps <4 x half> @raw_tbuffer_load_v4f16__sgpr_rsrc__vgpr_voffset__sg
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub0
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub1
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_OFFEN]].sub2
@@ -126,7 +126,7 @@ define amdgpu_ps <4 x half> @raw_tbuffer_load_v4f16__sgpr_rsrc__vgpr_voffset__sg
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub0
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_OFFEN]].sub1
   ; PACKED:   $vgpr0 = COPY [[COPY6]]
@@ -167,7 +167,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__vgpr_rsrc__sgpr_voffset__vgpr_soffs
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -207,7 +207,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__vgpr_rsrc__sgpr_voffset__vgpr_soffs
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -232,7 +232,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_glc
@@ -245,7 +245,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.tbuffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 1)
@@ -263,7 +263,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc
@@ -276,7 +276,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.tbuffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 2)
@@ -294,7 +294,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc_glc
@@ -307,7 +307,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.tbuffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 3)
@@ -325,7 +325,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; UNPACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; UNPACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_OFFEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_dlc
@@ -338,7 +338,7 @@ define amdgpu_ps half @raw_tbuffer_load_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; PACKED:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; PACKED:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_OFFEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.raw.tbuffer.load.f16(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 4)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.load.ll

@@ -12,7 +12,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.tbuffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -30,7 +30,7 @@ define amdgpu_ps <2 x float> @raw_tbuffer_load_v2f32__sgpr_rsrc__vgpr_voffset__s
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XY_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XY_OFFEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_OFFEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY6]]
@@ -51,7 +51,7 @@ define amdgpu_ps <3 x float> @raw_tbuffer_load_v3f32__sgpr_rsrc__vgpr_voffset__s
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZ_OFFEN:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZ_OFFEN:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_OFFEN]].sub2
@@ -74,7 +74,7 @@ define amdgpu_ps <4 x float> @raw_tbuffer_load_v4f32__sgpr_rsrc__vgpr_voffset__s
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_OFFEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub0
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub1
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_OFFEN]].sub2
@@ -119,7 +119,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__vgpr_rsrc__sgpr_voffset__vgpr_soff
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY5]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY5]], implicit $exec
   ; CHECK:   [[S_AND_B32_1:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U32_e64_]], [[S_AND_B32_]], implicit-def $scc
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY6]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -144,7 +144,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.tbuffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 1)
@@ -162,7 +162,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.tbuffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 2)
@@ -180,7 +180,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.tbuffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 3)
@@ -198,7 +198,7 @@ define amdgpu_ps float @raw_tbuffer_load_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1, [[COPY2]], %subreg.sub2, [[COPY3]], %subreg.sub3
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr_32 = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_OFFEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_OFFEN [[COPY4]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_OFFEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.tbuffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 4)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.f16.ll

@@ -14,7 +14,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -27,7 +27,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -49,7 +49,7 @@ define amdgpu_ps void @raw_tbuffer_store_v2f16__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY7]], [[COPY]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_XY_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_v2f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -62,7 +62,7 @@ define amdgpu_ps void @raw_tbuffer_store_v2f16__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_XY_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -93,7 +93,7 @@ define amdgpu_ps void @raw_tbuffer_store_v4f16__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; UNPACKED:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY9]], [[COPY1]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY1]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_XYZW_gfx80_OFFEN_exact [[REG_SEQUENCE1]], [[COPY6]], [[REG_SEQUENCE]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_v4f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -108,7 +108,7 @@ define amdgpu_ps void @raw_tbuffer_store_v4f16__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY4]], %subreg.sub2, [[COPY5]], %subreg.sub3
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; PACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_XYZW_OFFEN_exact [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -143,7 +143,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -179,7 +179,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; PACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -224,7 +224,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__vgpr_voffset__vgpr_soff
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -263,7 +263,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__vgpr_voffset__vgpr_soff
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -309,7 +309,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__sgpr_voffset__vgpr_soff
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -349,7 +349,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__vgpr_rsrc__sgpr_voffset__vgpr_soff
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -374,7 +374,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_glc
   ; PACKED: bb.1 (%ir-block.0):
@@ -387,7 +387,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 1)
   ret void
@@ -405,7 +405,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc
   ; PACKED: bb.1 (%ir-block.0):
@@ -418,7 +418,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 2)
   ret void
@@ -436,7 +436,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc_glc
   ; PACKED: bb.1 (%ir-block.0):
@@ -449,7 +449,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 3)
   ret void
@@ -467,7 +467,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_D16_X_gfx80_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soffset_dlc
   ; PACKED: bb.1 (%ir-block.0):
@@ -480,7 +480,7 @@ define amdgpu_ps void @raw_tbuffer_store_f16__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_D16_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f16(half %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 4)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.i8.ll

@@ -14,7 +14,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: raw_tbuffer_store_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -27,7 +27,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__sgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.i8(i8 %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
   ret void
@@ -62,7 +62,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; UNPACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -98,7 +98,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__vgpr_voffset__sgpr_soffs
   ; PACKED:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; PACKED:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -143,7 +143,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__vgpr_voffset__vgpr_soffs
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -182,7 +182,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__vgpr_voffset__vgpr_soffs
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -228,7 +228,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__sgpr_voffset__vgpr_soffs
   ; UNPACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; UNPACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -268,7 +268,7 @@ define amdgpu_ps void @raw_tbuffer_store_i8__vgpr_rsrc__sgpr_voffset__vgpr_soffs
   ; PACKED:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; PACKED:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.raw.tbuffer.store.ll

@@ -14,7 +14,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -35,7 +35,7 @@ define amdgpu_ps void @raw_tbuffer_store_v2f32__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY2]], %subreg.sub0, [[COPY3]], %subreg.sub1, [[COPY4]], %subreg.sub2, [[COPY5]], %subreg.sub3
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_XY_OFFEN_exact [[REG_SEQUENCE]], [[COPY6]], [[REG_SEQUENCE1]], [[COPY7]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -57,7 +57,7 @@ define amdgpu_ps void @raw_tbuffer_store_v3f32__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY3]], %subreg.sub0, [[COPY4]], %subreg.sub1, [[COPY5]], %subreg.sub2, [[COPY6]], %subreg.sub3
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_XYZ_OFFEN_exact [[REG_SEQUENCE]], [[COPY7]], [[REG_SEQUENCE1]], [[COPY8]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_XYZ_OFFEN_exact [[REG_SEQUENCE]], [[COPY7]], [[REG_SEQUENCE1]], [[COPY8]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -80,7 +80,7 @@ define amdgpu_ps void @raw_tbuffer_store_v4f32__sgpr_rsrc__vgpr_voffset__sgpr_so
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1, [[COPY6]], %subreg.sub2, [[COPY7]], %subreg.sub3
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
   ; CHECK:   [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE]], [[COPY8]], [[REG_SEQUENCE1]], [[COPY9]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_XYZW_OFFEN_exact [[REG_SEQUENCE]], [[COPY8]], [[REG_SEQUENCE1]], [[COPY9]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 0)
   ret void
@@ -100,7 +100,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__sgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr7
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[COPY5]]
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
   ret void
@@ -135,7 +135,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__vgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; CHECK:   [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 1, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[COPY6]], 0, 94, 1, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -180,7 +180,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__vgpr_rsrc__vgpr_voffset__vgpr_soff
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B32_1:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U32_e64_]], [[S_AND_B32_]], implicit-def $scc
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -226,7 +226,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__vgpr_rsrc__sgpr_voffset__vgpr_soff
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B32_1:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U32_e64_]], [[S_AND_B32_]], implicit-def $scc
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY7]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -252,7 +252,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 1, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 1)
   ret void
@@ -271,7 +271,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 2, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 2)
   ret void
@@ -290,7 +290,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 3, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 3)
   ret void
@@ -309,7 +309,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 4, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 78, i32 4)
   ret void
@@ -328,7 +328,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vdpr_voffset__sgpr_soff
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 0, i32 %soffset, i32 94, i32 0)
   ret void
@@ -345,7 +345,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY4:%[0-9]+]]:sreg_32 = COPY $sgpr5
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFSET_exact [[COPY]], [[REG_SEQUENCE]], [[COPY5]], 4095, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 4095, i32 %soffset, i32 94, i32 0)
   ret void
@@ -364,7 +364,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY5:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY6]], [[REG_SEQUENCE]], [[COPY5]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 4096, i32 %soffset, i32 94, i32 0)
   ret void
@@ -382,7 +382,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 16, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 16, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset = add i32 %voffset.base, 16
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -401,7 +401,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset = add i32 %voffset.base, 4095
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -423,7 +423,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[COPY5]], [[COPY7]], 0, implicit $exec
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[V_ADD_U32_e64_]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 4096, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[V_ADD_U32_e64_]], [[REG_SEQUENCE]], [[COPY6]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %voffset = add i32 %voffset.base, 4096
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -442,7 +442,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 4095, i32 94, i32 0)
   ret void
@@ -460,7 +460,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 4096, i32 94, i32 0)
   ret void
@@ -480,7 +480,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 16
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY6]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %soffset = add i32 %soffset.base, 16
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -501,7 +501,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4095
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY6]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %soffset = add i32 %soffset.base, 4095
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -522,7 +522,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 4096
   ; CHECK:   [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY6]], [[S_MOV_B32_]], implicit-def $scc
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %soffset = add i32 %soffset.base, 4096
   call void @llvm.amdgcn.raw.tbuffer.store.f32(float %val, <4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 94, i32 0)
@@ -560,7 +560,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY8]], implicit $exec
   ; CHECK:   [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[COPY5]], [[REG_SEQUENCE3]], [[S_ADD_I32_]], 0, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -606,7 +606,7 @@ define amdgpu_ps void @raw_tbuffer_store_f32__sgpr_rsrc__vgpr_voffset__sgpr_soff
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_32_xm0_xexec = V_CMP_EQ_U64_e64 [[REG_SEQUENCE2]], [[COPY9]], implicit $exec
   ; CHECK:   [[S_AND_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_B32 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE3:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[V_READFIRSTLANE_B32_]], %subreg.sub0, [[V_READFIRSTLANE_B32_1]], %subreg.sub1, [[V_READFIRSTLANE_B32_2]], %subreg.sub2, [[V_READFIRSTLANE_B32_3]], %subreg.sub3
-  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[V_ADD_U32_e64_]], [[REG_SEQUENCE3]], [[COPY6]], 904, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource" + 5000, align 1, addrspace 4)
+  ; CHECK:   TBUFFER_STORE_FORMAT_X_OFFEN_exact [[COPY]], [[V_ADD_U32_e64_]], [[REG_SEQUENCE3]], [[COPY6]], 904, 94, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B32_:%[0-9]+]]:sreg_32_xm0_xexec = S_AND_SAVEEXEC_B32 killed [[S_AND_B32_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec_lo = S_XOR_B32_term $exec_lo, [[S_AND_SAVEEXEC_B32_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.add.ll

@@ -16,7 +16,7 @@ define amdgpu_ps float @struct_buffer_atomic_add_i32__vgpr_val__sgpr_rsrc__vgpr_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_BOTHEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -38,7 +38,7 @@ define amdgpu_ps float @struct_buffer_atomic_add_i32_noret__vgpr_val__sgpr_rsrc_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_BOTHEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -62,7 +62,7 @@ define amdgpu_ps <2 x float> @struct_buffer_atomic_add_i64__vgpr_val__sgpr_rsrc_
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64), align 1, addrspace 4)
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN]].sub0
   ; CHECK:   [[COPY10:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY9]]
@@ -89,7 +89,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_i64_noret__vgpr_val__sgpr_rsrc__
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_ADD_X2_BOTHEN_RTN [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s64), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %ret = call i64 @llvm.amdgcn.struct.buffer.atomic.add.i64(i64 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -132,7 +132,7 @@ define amdgpu_ps float @struct_buffer_atomic_add_i32__sgpr_val__vgpr_rsrc__sgpr_
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -184,7 +184,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_i32_noret__sgpr_val__vgpr_rsrc__
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -212,7 +212,7 @@ define amdgpu_ps float @struct_buffer_atomic_add_i32__vgpr_val__sgpr_rsrc__vgpr_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_ADD_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_ATOMIC_ADD_BOTHEN_RTN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %ret = call i32 @llvm.amdgcn.struct.buffer.atomic.add.i32(i32 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 2)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.cmpswap.ll

@@ -19,7 +19,7 @@ define amdgpu_ps float @struct_buffer_atomic_cmpswap_i32__vgpr_val__vgpr_cmp__sg
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN]].sub0
   ; CHECK:   $vgpr0 = COPY [[COPY9]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
@@ -45,7 +45,7 @@ define amdgpu_ps void @struct_buffer_atomic_cmpswap_noret_i32__vgpr_val__vgpr_cm
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN]].sub0
   ; CHECK:   S_ENDPGM 0
   %ret = call i32 @llvm.amdgcn.struct.buffer.atomic.cmpswap.i32(i32 %val, i32 %cmp, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -92,7 +92,7 @@ define amdgpu_ps float @struct_buffer_atomic_cmpswap_i32__sgpr_val__sgpr_cmp__vg
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY11]], %subreg.sub0, [[COPY12]], %subreg.sub1
   ; CHECK:   [[REG_SEQUENCE5:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY15:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN]].sub0
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
@@ -148,7 +148,7 @@ define amdgpu_ps void @struct_buffer_atomic_cmpswap_i32_noret__sgpr_val__sgpr_cm
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY11]], %subreg.sub0, [[COPY12]], %subreg.sub1
   ; CHECK:   [[REG_SEQUENCE5:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY15:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN]].sub0
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
@@ -178,7 +178,7 @@ define amdgpu_ps float @struct_buffer_atomic_cmpswap_i32__vgpr_val__vgpr_cmp__sg
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[COPY1]], %subreg.sub1
-  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN:%[0-9]+]]:vreg_64 = BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY8]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_ATOMIC_CMPSWAP_BOTHEN_RTN]].sub0
   ; CHECK:   $vgpr0 = COPY [[COPY9]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.atomic.fadd.ll

@@ -17,7 +17,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX908:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX908:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -32,7 +32,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX90A:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX90A:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -52,7 +52,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX908:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX908:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset_plus4095__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -67,7 +67,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX90A:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX90A:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %voffset.add = add i32 %voffset, 4095
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset.add, i32 %soffset, i32 0)
@@ -86,7 +86,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__4095_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -99,7 +99,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 4095, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 4095, i32 %soffset, i32 0)
   ret void
@@ -118,7 +118,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__0_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -131,7 +131,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 %soffset, i32 0)
   ret void
@@ -174,7 +174,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__
   ; GFX908:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; GFX908:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; GFX908:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX908:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX908:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -218,7 +218,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__
   ; GFX90A:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; GFX90A:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; GFX90A:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX90A:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX90A:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -265,7 +265,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__
   ; GFX908:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; GFX908:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; GFX908:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX908:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX908:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -306,7 +306,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__sgpr_val__vgpr_rsrc__
   ; GFX90A:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0 = V_READFIRSTLANE_B32 [[COPY6]], implicit $exec
   ; GFX90A:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; GFX90A:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY7]], [[COPY8]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 1, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; GFX90A:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; GFX90A:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -334,7 +334,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX908:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX908:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset_slc
   ; GFX90A: bb.1 (%ir-block.0):
@@ -349,7 +349,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX90A:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX90A:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 2)
   ret void
@@ -367,7 +367,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_ADD_F32_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 2, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__0_voffset__sgpr_soffset_slc
   ; GFX90A: bb.1 (%ir-block.0):
@@ -380,7 +380,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_f32_noret__vgpr_val__sgpr_rsrc__
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_ADD_F32_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_ADD_F32_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 3, implicit $exec :: (volatile dereferenceable load store (s32), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call float @llvm.amdgcn.struct.buffer.atomic.fadd.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 %soffset, i32 2)
   ret void
@@ -400,7 +400,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc
   ; GFX908:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX908:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX908:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_BOTHEN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__vgpr_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -415,7 +415,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc
   ; GFX90A:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; GFX90A:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; GFX90A:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_BOTHEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_BOTHEN_RTN [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call <2 x half> @llvm.amdgcn.struct.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -433,7 +433,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc
   ; GFX908:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX908:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX908:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX908:   BUFFER_ATOMIC_PK_ADD_F16_IDXEN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX908:   S_ENDPGM 0
   ; GFX90A-LABEL: name: struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc__0_voffset__sgpr_soffset
   ; GFX90A: bb.1 (%ir-block.0):
@@ -446,7 +446,7 @@ define amdgpu_ps void @struct_buffer_atomic_add_v2f16_noret__vgpr_val__sgpr_rsrc
   ; GFX90A:   [[REG_SEQUENCE:%[0-9]+]]:sgpr_128 = REG_SEQUENCE [[COPY1]], %subreg.sub0, [[COPY2]], %subreg.sub1, [[COPY3]], %subreg.sub2, [[COPY4]], %subreg.sub3
   ; GFX90A:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; GFX90A:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
-  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>) on custom "BufferResource", align 1, addrspace 4)
+  ; GFX90A:   [[BUFFER_ATOMIC_PK_ADD_F16_IDXEN_RTN:%[0-9]+]]:vgpr_32 = BUFFER_ATOMIC_PK_ADD_F16_IDXEN_RTN [[COPY]], [[COPY5]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, implicit $exec :: (volatile dereferenceable load store (<2 x s16>), align 1, addrspace 4)
   ; GFX90A:   S_ENDPGM 0
   %ret = call <2 x half> @llvm.amdgcn.struct.buffer.atomic.fadd.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 0, i32 %soffset, i32 0)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.format.f16.ll

@@ -15,7 +15,7 @@ define amdgpu_ps half @struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vg
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
@@ -30,7 +30,7 @@ define amdgpu_ps half @struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vg
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.struct.buffer.load.format.f16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -50,7 +50,7 @@ define amdgpu_ps <2 x half> @struct_buffer_load_format_v2f16__sgpr_rsrc__vgpr_vi
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN]].sub0
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN]].sub1
   ; UNPACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
@@ -76,7 +76,7 @@ define amdgpu_ps <2 x half> @struct_buffer_load_format_v2f16__sgpr_rsrc__vgpr_vi
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XY_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_XY_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call <2 x half> @llvm.amdgcn.struct.buffer.load.format.v2f16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -102,7 +102,7 @@ define amdgpu_ps <4 x half> @struct_buffer_load_format_v4f16__sgpr_rsrc__vgpr_vi
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub0
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub1
   ; UNPACKED:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub2
@@ -138,7 +138,7 @@ define amdgpu_ps <4 x half> @struct_buffer_load_format_v4f16__sgpr_rsrc__vgpr_vi
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN]].sub0
   ; PACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN]].sub1
   ; PACKED:   $vgpr0 = COPY [[COPY7]]
@@ -183,7 +183,7 @@ define amdgpu_ps <4 x half> @struct_buffer_load_format_v4f16__vpr_rsrc__sgpr_vin
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -247,7 +247,7 @@ define amdgpu_ps <4 x half> @struct_buffer_load_format_v4f16__vpr_rsrc__sgpr_vin
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -277,7 +277,7 @@ define amdgpu_ps half @struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vg
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset_voffsset_add_4095
@@ -292,7 +292,7 @@ define amdgpu_ps half @struct_buffer_load_format_f16__sgpr_rsrc__vgpr_vindex__vg
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095
@@ -313,7 +313,7 @@ define amdgpu_ps half @struct_buffer_load_format_i16__sgpr_rsrc__vgpr_vindex__vg
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; PACKED-LABEL: name: struct_buffer_load_format_i16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
@@ -328,7 +328,7 @@ define amdgpu_ps half @struct_buffer_load_format_i16__sgpr_rsrc__vgpr_vindex__vg
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call i16 @llvm.amdgcn.struct.buffer.load.format.i16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.format.ll

@@ -15,7 +15,7 @@ define amdgpu_ps float @struct_buffer_load_format_f32__sgpr_rsrc__vgpr_vindex__v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.format.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -35,7 +35,7 @@ define amdgpu_ps <2 x float> @struct_buffer_load_format_v2f32__sgpr_rsrc__vgpr_v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XY_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XY_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_FORMAT_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XY_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XY_BOTHEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY7]]
@@ -58,7 +58,7 @@ define amdgpu_ps <3 x float> @struct_buffer_load_format_v3f32__sgpr_rsrc__vgpr_v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZ_BOTHEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_FORMAT_XYZ_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZ_BOTHEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_FORMAT_XYZ_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub2
@@ -83,7 +83,7 @@ define amdgpu_ps <4 x float> @struct_buffer_load_format_v4f32__sgpr_rsrc__vgpr_v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub2
@@ -132,7 +132,7 @@ define amdgpu_ps <4 x float> @struct_buffer_load_format_v4f32__vpr_rsrc__sgpr_vi
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -166,7 +166,7 @@ define amdgpu_ps float @struct_buffer_load_format_f32__sgpr_rsrc__vgpr_vindex__v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095
@@ -187,7 +187,7 @@ define amdgpu_ps float @struct_buffer_load_format_i32__sgpr_rsrc__vgpr_vindex__v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call i32 @llvm.amdgcn.struct.buffer.load.format.i32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.load.ll

@@ -16,7 +16,7 @@ define amdgpu_ps float @struct_buffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -37,7 +37,7 @@ define amdgpu_ps <2 x float> @struct_buffer_load_v2f32__sgpr_rsrc__vgpr_vindex__
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORDX2_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX2_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_BOTHEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY7]]
@@ -61,7 +61,7 @@ define amdgpu_ps <3 x float> @struct_buffer_load_v3f32__sgpr_rsrc__vgpr_vindex__
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORDX3_BOTHEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_DWORDX3_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX3_BOTHEN:%[0-9]+]]:vreg_96 = BUFFER_LOAD_DWORDX3_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX3_BOTHEN]].sub2
@@ -87,7 +87,7 @@ define amdgpu_ps <4 x float> @struct_buffer_load_v4f32__sgpr_rsrc__vgpr_vindex__
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORDX4_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_DWORDX4_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX4_BOTHEN:%[0-9]+]]:vreg_128 = BUFFER_LOAD_DWORDX4_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX4_BOTHEN]].sub2
@@ -116,7 +116,7 @@ define amdgpu_ps float @struct_buffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY4]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %voffset, i32 %soffset, i32 0)
@@ -137,7 +137,7 @@ define amdgpu_ps float @struct_buffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095
@@ -158,7 +158,7 @@ define amdgpu_ps float @struct_buffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 64
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[S_MOV_B32_]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 64, i32 0)
@@ -200,7 +200,7 @@ define amdgpu_ps float @struct_buffer_load_f32__vgpr_rsrc__sgpr_vindex__sgpr_vof
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -227,7 +227,7 @@ define amdgpu_ps float @struct_buffer_load_i8_zext__sgpr_rsrc__vgpr_vindex__vgpr
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_UBYTE_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8) from custom "BufferResource", addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_UBYTE_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8), addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_UBYTE_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call i8 @llvm.amdgcn.struct.buffer.load.i8(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -249,7 +249,7 @@ define amdgpu_ps float @struct_buffer_load_i8_sext__sgpr_rsrc__vgpr_vindex__vgpr
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_UBYTE_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8) from custom "BufferResource", addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_UBYTE_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_UBYTE_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s8), addrspace 4)
   ; CHECK:   [[V_BFE_I32_e64_:%[0-9]+]]:vgpr_32 = V_BFE_I32_e64 [[BUFFER_LOAD_UBYTE_BOTHEN]], 0, 8, implicit $exec
   ; CHECK:   $vgpr0 = COPY [[V_BFE_I32_e64_]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
@@ -272,7 +272,7 @@ define amdgpu_ps float @struct_buffer_load_i16_zext__sgpr_rsrc__vgpr_vindex__vgp
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_USHORT_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call i16 @llvm.amdgcn.struct.buffer.load.i16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -294,7 +294,7 @@ define amdgpu_ps float @struct_buffer_load_i16_sext__sgpr_rsrc__vgpr_vindex__vgp
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; CHECK:   [[V_BFE_I32_e64_:%[0-9]+]]:vgpr_32 = V_BFE_I32_e64 [[BUFFER_LOAD_USHORT_BOTHEN]], 0, 16, implicit $exec
   ; CHECK:   $vgpr0 = COPY [[V_BFE_I32_e64_]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
@@ -318,7 +318,7 @@ define amdgpu_ps half @struct_buffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_voff
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_USHORT_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_USHORT_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_USHORT_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.struct.buffer.load.f16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -339,7 +339,7 @@ define amdgpu_ps <2 x half> @struct_buffer_load_v2f16__sgpr_rsrc__vgpr_vindex__v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call <2 x half> @llvm.amdgcn.struct.buffer.load.v2f16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -366,7 +366,7 @@ define amdgpu_ps <4 x half> @struct_buffer_load_v4f16__sgpr_rsrc__vgpr_vindex__v
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORDX2_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORDX2_BOTHEN:%[0-9]+]]:vreg_64 = BUFFER_LOAD_DWORDX2_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[BUFFER_LOAD_DWORDX2_BOTHEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY7]]
@@ -390,7 +390,7 @@ define amdgpu_ps float @struct_buffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[BUFFER_LOAD_DWORD_BOTHEN:%[0-9]+]]:vgpr_32 = BUFFER_LOAD_DWORD_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 1, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[BUFFER_LOAD_DWORD_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 1)

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.format.f16.ll

@@ -16,7 +16,7 @@ define amdgpu_ps void @struct_buffer_store_format_f16__vgpr_val__sgpr_rsrc__vgpr
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; UNPACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: struct_buffer_store_format_f16__vgpr_val__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -31,7 +31,7 @@ define amdgpu_ps void @struct_buffer_store_format_f16__vgpr_val__sgpr_rsrc__vgpr
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; PACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.f16(half %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -55,7 +55,7 @@ define amdgpu_ps void @struct_buffer_store_format_v2f16__vgpr_val__sgpr_rsrc__vg
   ; UNPACKED:   [[V_LSHRREV_B32_e64_:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY8]], [[COPY]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1
   ; UNPACKED:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_BOTHEN_exact [[REG_SEQUENCE1]], [[REG_SEQUENCE2]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XY_gfx80_BOTHEN_exact [[REG_SEQUENCE1]], [[REG_SEQUENCE2]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: struct_buffer_store_format_v2f16__vgpr_val__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -70,7 +70,7 @@ define amdgpu_ps void @struct_buffer_store_format_v2f16__vgpr_val__sgpr_rsrc__vg
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; PACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XY_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -103,7 +103,7 @@ define amdgpu_ps void @struct_buffer_store_format_v4f16__vgpr_val__sgpr_rsrc__vg
   ; UNPACKED:   [[V_LSHRREV_B32_e64_1:%[0-9]+]]:vgpr_32 = V_LSHRREV_B32_e64 [[COPY10]], [[COPY1]], implicit $exec
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_128 = REG_SEQUENCE [[COPY]], %subreg.sub0, [[V_LSHRREV_B32_e64_]], %subreg.sub1, [[COPY1]], %subreg.sub2, [[V_LSHRREV_B32_e64_1]], %subreg.sub3
   ; UNPACKED:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_BOTHEN_exact [[REG_SEQUENCE1]], [[REG_SEQUENCE2]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_XYZW_gfx80_BOTHEN_exact [[REG_SEQUENCE1]], [[REG_SEQUENCE2]], [[REG_SEQUENCE]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: struct_buffer_store_format_v4f16__vgpr_val__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -120,7 +120,7 @@ define amdgpu_ps void @struct_buffer_store_format_v4f16__vgpr_val__sgpr_rsrc__vg
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; PACKED:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_XYZW_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -162,7 +162,7 @@ define amdgpu_ps void @struct_buffer_store_format_f16__sgpr_val__vgpr_rsrc__sgpr
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -206,7 +206,7 @@ define amdgpu_ps void @struct_buffer_store_format_f16__sgpr_val__vgpr_rsrc__sgpr
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -233,7 +233,7 @@ define amdgpu_ps void @struct_buffer_store_format_i16__vgpr_val__sgpr_rsrc__vgpr
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; UNPACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   BUFFER_STORE_FORMAT_D16_X_gfx80_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; UNPACKED:   S_ENDPGM 0
   ; PACKED-LABEL: name: struct_buffer_store_format_i16__vgpr_val__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
   ; PACKED: bb.1 (%ir-block.0):
@@ -248,7 +248,7 @@ define amdgpu_ps void @struct_buffer_store_format_i16__vgpr_val__sgpr_rsrc__vgpr
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; PACKED:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   BUFFER_STORE_FORMAT_D16_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; PACKED:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.i16(i16 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.format.f32.ll

@@ -15,7 +15,7 @@ define amdgpu_ps void @struct_buffer_store_format_f32__vgpr_val__sgpr_rsrc__vgpr
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -37,7 +37,7 @@ define amdgpu_ps void @struct_buffer_store_format_v2f32__vgpr_val__sgpr_rsrc__vg
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_XY_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XY_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -60,7 +60,7 @@ define amdgpu_ps void @struct_buffer_store_format_v3f32__vgpr_val__sgpr_rsrc__vg
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
   ; CHECK:   [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZ_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZ_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -84,7 +84,7 @@ define amdgpu_ps void @struct_buffer_store_format_v4f32__vgpr_val__sgpr_rsrc__vg
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY $vgpr5
   ; CHECK:   [[COPY10:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY9]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY10]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_XYZW_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY10]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -126,7 +126,7 @@ define amdgpu_ps void @struct_buffer_store_format_f32__sgpr_val__vgpr_rsrc__sgpr
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY7]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY9]], %subreg.sub0, [[COPY10]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY8]], [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -153,7 +153,7 @@ define amdgpu_ps void @struct_buffer_store_format_i32__vgpr_val__sgpr_rsrc__vgpr
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_FORMAT_X_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.format.i32(i32 %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.buffer.store.ll

@@ -17,7 +17,7 @@ define amdgpu_ps void @struct_buffer_store_f32_sgpr_rsrc__vgpr_val__vgpr_vindex_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -39,7 +39,7 @@ define amdgpu_ps void @struct_buffer_store_v2f32_sgpr_rsrc__vgpr_val__vgpr_vinde
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORDX2_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX2_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.v2f32(<2 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -62,7 +62,7 @@ define amdgpu_ps void @struct_buffer_store_v3f32_sgpr_rsrc__vgpr_val__vgpr_vinde
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY $vgpr4
   ; CHECK:   [[COPY9:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORDX3_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX3_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY9]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.v3f32(<3 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -86,7 +86,7 @@ define amdgpu_ps void @struct_buffer_store_v4f32_sgpr_rsrc__vgpr_val__vgpr_vinde
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY $vgpr5
   ; CHECK:   [[COPY10:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY8]], %subreg.sub0, [[COPY9]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORDX4_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY10]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX4_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY10]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.v4f32(<4 x float> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -132,7 +132,7 @@ define amdgpu_ps void @struct_buffer_store_v4f32_vgpr_rsrc__sgpr_val__sgpr_vinde
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY10]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE5:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY12]], %subreg.sub0, [[COPY13]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORDX4_BOTHEN_exact [[COPY11]], [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX4_BOTHEN_exact [[COPY11]], [[REG_SEQUENCE5]], [[REG_SEQUENCE4]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -159,7 +159,7 @@ define amdgpu_ps void @struct_buffer_store_i8_sgpr_rsrc__vgpr_val__vgpr_vindex__
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_BYTE_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s8) into custom "BufferResource", addrspace 4)
+  ; CHECK:   BUFFER_STORE_BYTE_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s8), addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %val.trunc = trunc i32 %val to i8
   call void @llvm.amdgcn.struct.buffer.store.i8(i8 %val.trunc, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -180,7 +180,7 @@ define amdgpu_ps void @struct_buffer_store_i16_sgpr_rsrc__vgpr_val__vgpr_vindex_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_SHORT_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_SHORT_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (s16), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   %val.trunc = trunc i32 %val to i16
   call void @llvm.amdgcn.struct.buffer.store.i16(i16 %val.trunc, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -201,7 +201,7 @@ define amdgpu_ps void @struct_buffer_store_f32_sgpr_rsrc__vgpr_val__vgpr_vindex_
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, 0, 0, implicit $exec :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 1, 0, 0, implicit $exec :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 1)
   ret void
@@ -221,7 +221,7 @@ define amdgpu_ps void @struct_buffer_store_v2f16_sgpr_rsrc__vgpr_val__vgpr_vinde
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY5]], %subreg.sub0, [[COPY6]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORD_BOTHEN_exact [[COPY]], [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY7]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<2 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.v2f16(<2 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -249,7 +249,7 @@ define amdgpu_ps void @struct_buffer_store_v4f16_sgpr_rsrc__vgpr_val__vgpr_vinde
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY $vgpr3
   ; CHECK:   [[COPY8:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE2:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY7]], %subreg.sub1
-  ; CHECK:   BUFFER_STORE_DWORDX2_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   BUFFER_STORE_DWORDX2_BOTHEN_exact [[REG_SEQUENCE]], [[REG_SEQUENCE2]], [[REG_SEQUENCE1]], [[COPY8]], 0, 0, 0, 0, implicit $exec :: (dereferenceable store (<4 x s16>), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.v4f16(<4 x half> %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.tbuffer.load.f16.ll

@@ -16,7 +16,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
@@ -31,7 +31,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.struct.tbuffer.load.f16(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -51,7 +51,7 @@ define amdgpu_ps <2 x half> @struct_tbuffer_load_v2f16__sgpr_rsrc__vgpr_vindex__
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: struct_tbuffer_load_v2f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset
@@ -66,7 +66,7 @@ define amdgpu_ps <2 x half> @struct_tbuffer_load_v2f16__sgpr_rsrc__vgpr_vindex__
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN]].sub0
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XY_gfx80_BOTHEN]].sub1
   ; UNPACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 65535
@@ -103,7 +103,7 @@ define amdgpu_ps <4 x half> @struct_tbuffer_load_v4f16__sgpr_rsrc__vgpr_vindex__
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN]].sub0
   ; PACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN]].sub1
   ; PACKED:   $vgpr0 = COPY [[COPY7]]
@@ -121,7 +121,7 @@ define amdgpu_ps <4 x half> @struct_tbuffer_load_v4f16__sgpr_rsrc__vgpr_vindex__
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub0
   ; UNPACKED:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub1
   ; UNPACKED:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN]].sub2
@@ -163,7 +163,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; PACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
   ; PACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY4]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset_vindex0
@@ -179,7 +179,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; UNPACKED:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
   ; UNPACKED:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY4]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call half @llvm.amdgcn.struct.tbuffer.load.f16(<4 x i32> %rsrc, i32 0, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -220,7 +220,7 @@ define amdgpu_ps <4 x half> @struct_tbuffer_load_v4f16__vgpr_rsrc__sgpr_vindex__
   ; PACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; PACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; PACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_D16_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; PACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; PACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; PACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -266,7 +266,7 @@ define amdgpu_ps <4 x half> @struct_tbuffer_load_v4f16__vgpr_rsrc__sgpr_vindex__
   ; UNPACKED:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; UNPACKED:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; UNPACKED:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>) from custom "BufferResource", align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_D16_XYZW_gfx80_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s16>), align 1, addrspace 4)
   ; UNPACKED:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; UNPACKED:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; UNPACKED:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -314,7 +314,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; PACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; PACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; PACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; PACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; PACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_BOTHEN]]
   ; PACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   ; UNPACKED-LABEL: name: struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_voffset__sgpr_soffset_voffset_add4095
@@ -329,7 +329,7 @@ define amdgpu_ps half @struct_tbuffer_load_f16__sgpr_rsrc__vgpr_vindex__vgpr_vof
   ; UNPACKED:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; UNPACKED:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; UNPACKED:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; UNPACKED:   [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s16), align 1, addrspace 4)
   ; UNPACKED:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_D16_X_gfx80_BOTHEN]]
   ; UNPACKED:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095

llvm/test/CodeGen/AMDGPU/GlobalISel/llvm.amdgcn.struct.tbuffer.load.ll

@@ -15,7 +15,7 @@ define amdgpu_ps float @struct_tbuffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vo
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.tbuffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -35,7 +35,7 @@ define amdgpu_ps <2 x float> @struct_tbuffer_load_v2f32__sgpr_rsrc__vgpr_vindex_
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XY_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XY_BOTHEN:%[0-9]+]]:vreg_64 = TBUFFER_LOAD_FORMAT_XY_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<2 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XY_BOTHEN]].sub1
   ; CHECK:   $vgpr0 = COPY [[COPY7]]
@@ -58,7 +58,7 @@ define amdgpu_ps <3 x float> @struct_tbuffer_load_v3f32__sgpr_rsrc__vgpr_vindex_
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZ_BOTHEN:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZ_BOTHEN:%[0-9]+]]:vreg_96 = TBUFFER_LOAD_FORMAT_XYZ_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<3 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZ_BOTHEN]].sub2
@@ -83,7 +83,7 @@ define amdgpu_ps <4 x float> @struct_tbuffer_load_v4f32__sgpr_rsrc__vgpr_vindex_
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub0
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub1
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr_32 = COPY [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN]].sub2
@@ -111,7 +111,7 @@ define amdgpu_ps float @struct_tbuffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vo
   ; CHECK:   [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[S_MOV_B32_]]
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY6]], %subreg.sub0, [[COPY4]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY5]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.tbuffer.load.f32(<4 x i32> %rsrc, i32 0, i32 %voffset, i32 %soffset, i32 78, i32 0)
@@ -152,7 +152,7 @@ define amdgpu_ps <4 x float> @struct_tbuffer_load_v4f32__vgpr_rsrc__sgpr_vindex_
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]], [[COPY6]], implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
   ; CHECK:   [[REG_SEQUENCE4:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY7]], %subreg.sub0, [[COPY8]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_XYZW_BOTHEN:%[0-9]+]]:vreg_128 = TBUFFER_LOAD_FORMAT_XYZW_BOTHEN [[REG_SEQUENCE4]], [[REG_SEQUENCE3]], [[V_READFIRSTLANE_B32_4]], 0, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (<4 x s32>), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -186,7 +186,7 @@ define amdgpu_ps float @struct_tbuffer_load_f32__sgpr_rsrc__vgpr_vindex__vgpr_vo
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr_32 = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sreg_32 = COPY $sgpr6
   ; CHECK:   [[REG_SEQUENCE1:%[0-9]+]]:vreg_64 = REG_SEQUENCE [[COPY4]], %subreg.sub0, [[COPY5]], %subreg.sub1
-  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32) from custom "BufferResource" + 4095, align 1, addrspace 4)
+  ; CHECK:   [[TBUFFER_LOAD_FORMAT_X_BOTHEN:%[0-9]+]]:vgpr_32 = TBUFFER_LOAD_FORMAT_X_BOTHEN [[REG_SEQUENCE1]], [[REG_SEQUENCE]], [[COPY6]], 4095, 78, 0, 0, 0, implicit $exec :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[TBUFFER_LOAD_FORMAT_X_BOTHEN]]
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %voffset = add i32 %voffset.base, 4095

llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.raw.buffer.load.ll

@@ -16,7 +16,7 @@ define amdgpu_ps float @raw_buffer_load__sgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[COPY5:%[0-9]+]]:sgpr(s32) = COPY $sgpr6
   ; CHECK:   [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 0
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[AMDGPU_BUFFER_LOAD]](s32)
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -38,7 +38,7 @@ define amdgpu_ps float @raw_buffer_load__sgpr_rsrc__sgpr_val__sgpr_voffset__sgpr
   ; CHECK:   [[C:%[0-9]+]]:sgpr(s32) = G_CONSTANT i32 0
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr(s32) = COPY [[C]](s32)
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr(s32) = COPY [[COPY4]](s32)
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY7]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY7]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[AMDGPU_BUFFER_LOAD]](s32)
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.raw.buffer.load.f32(<4 x i32> %rsrc, i32 %voffset, i32 %soffset, i32 0)
@@ -78,7 +78,7 @@ define amdgpu_ps float @raw_buffer_load__vgpr_rsrc__vgpr_val__vgpr_voffset__sgpr
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[MV1]](s64), [[UV1]](s64), implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:sgpr(<4 x s32>) = G_BUILD_VECTOR [[V_READFIRSTLANE_B32_]](s32), [[V_READFIRSTLANE_B32_1]](s32), [[V_READFIRSTLANE_B32_2]](s32), [[V_READFIRSTLANE_B32_3]](s32)
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[COPY5]], 0, 0, 0 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -116,7 +116,7 @@ define amdgpu_ps float @raw_buffer_load__sgpr_rsrc__vgpr_val__vgpr_voffset__vgpr
   ; CHECK:   [[PHI1:%[0-9]+]]:vgpr(s32) = G_PHI [[DEF]](s32), %bb.1, %9(s32), %bb.2
   ; CHECK:   [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY5]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_]](s32), [[COPY5]](s32), implicit $exec
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[V_READFIRSTLANE_B32_]], 0, 0, 0 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[V_READFIRSTLANE_B32_]], 0, 0, 0 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[V_CMP_EQ_U32_e64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -166,7 +166,7 @@ define amdgpu_ps float @raw_buffer_load__vgpr_rsrc__vgpr_val__vgpr_voffset__vgpr
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY5]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]](s32), [[COPY5]](s32), implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY6]](s32), [[COPY4]], [[V_READFIRSTLANE_B32_4]], 0, 0, 0 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.struct.buffer.load.ll

@@ -15,7 +15,7 @@ define amdgpu_ps float @struct_buffer_load__sgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[COPY4:%[0-9]+]]:vgpr(s32) = COPY $vgpr0
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:sgpr(s32) = COPY $sgpr6
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[AMDGPU_BUFFER_LOAD]](s32)
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -37,7 +37,7 @@ define amdgpu_ps float @struct_buffer_load__sgpr_rsrc__sgpr_val__sgpr_vindex__sg
   ; CHECK:   [[COPY6:%[0-9]+]]:sgpr(s32) = COPY $sgpr8
   ; CHECK:   [[COPY7:%[0-9]+]]:vgpr(s32) = COPY [[COPY4]](s32)
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr(s32) = COPY [[COPY5]](s32)
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY7]](s32), [[COPY8]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY7]](s32), [[COPY8]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   $vgpr0 = COPY [[AMDGPU_BUFFER_LOAD]](s32)
   ; CHECK:   SI_RETURN_TO_EPILOG implicit $vgpr0
   %val = call float @llvm.amdgcn.struct.buffer.load.f32(<4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
@@ -76,7 +76,7 @@ define amdgpu_ps float @struct_buffer_load__vgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[MV1]](s64), [[UV1]](s64), implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:sgpr(<4 x s32>) = G_BUILD_VECTOR [[V_READFIRSTLANE_B32_]](s32), [[V_READFIRSTLANE_B32_1]](s32), [[V_READFIRSTLANE_B32_2]](s32), [[V_READFIRSTLANE_B32_3]](s32)
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[COPY6]], 0, 0, -1 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -113,7 +113,7 @@ define amdgpu_ps float @struct_buffer_load__sgpr_rsrc__vgpr_val__vgpr_vindex_vgp
   ; CHECK:   [[PHI1:%[0-9]+]]:vgpr(s32) = G_PHI [[DEF]](s32), %bb.1, %10(s32), %bb.2
   ; CHECK:   [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY6]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_]](s32), [[COPY6]](s32), implicit $exec
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[V_READFIRSTLANE_B32_]], 0, 0, -1 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[V_READFIRSTLANE_B32_]], 0, 0, -1 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[V_CMP_EQ_U32_e64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -162,7 +162,7 @@ define amdgpu_ps float @struct_buffer_load__vgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY6]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]](s32), [[COPY6]](s32), implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[V_READFIRSTLANE_B32_4]], 0, 0, -1 :: (dereferenceable load (s32) from custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   [[AMDGPU_BUFFER_LOAD:%[0-9]+]]:vgpr(s32) = G_AMDGPU_BUFFER_LOAD [[BUILD_VECTOR1]](<4 x s32>), [[COPY4]](s32), [[COPY5]], [[V_READFIRSTLANE_B32_4]], 0, 0, -1 :: (dereferenceable load (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec

llvm/test/CodeGen/AMDGPU/GlobalISel/regbankselect-amdgcn.struct.buffer.store.ll

@@ -16,7 +16,7 @@ define amdgpu_ps void @struct_buffer_store__sgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[COPY5:%[0-9]+]]:vgpr(s32) = COPY $vgpr1
   ; CHECK:   [[COPY6:%[0-9]+]]:vgpr(s32) = COPY $vgpr2
   ; CHECK:   [[COPY7:%[0-9]+]]:sgpr(s32) = COPY $sgpr6
-  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -39,7 +39,7 @@ define amdgpu_ps void @struct_buffer_store__sgpr_rsrc__sgpr_val__sgpr_vindex__sg
   ; CHECK:   [[COPY8:%[0-9]+]]:vgpr(s32) = COPY [[COPY4]](s32)
   ; CHECK:   [[COPY9:%[0-9]+]]:vgpr(s32) = COPY [[COPY5]](s32)
   ; CHECK:   [[COPY10:%[0-9]+]]:vgpr(s32) = COPY [[COPY6]](s32)
-  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY8]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY9]](s32), [[COPY10]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY8]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY9]](s32), [[COPY10]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   S_ENDPGM 0
   call void @llvm.amdgcn.struct.buffer.store.f32(float %val, <4 x i32> %rsrc, i32 %vindex, i32 %voffset, i32 %soffset, i32 0)
   ret void
@@ -76,7 +76,7 @@ define amdgpu_ps void @struct_buffer_store__vgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[V_CMP_EQ_U64_e64_1:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U64_e64 [[MV1]](s64), [[UV1]](s64), implicit $exec
   ; CHECK:   [[S_AND_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U64_e64_1]], [[V_CMP_EQ_U64_e64_]], implicit-def $scc
   ; CHECK:   [[BUILD_VECTOR1:%[0-9]+]]:sgpr(<4 x s32>) = G_BUILD_VECTOR [[V_READFIRSTLANE_B32_]](s32), [[V_READFIRSTLANE_B32_1]](s32), [[V_READFIRSTLANE_B32_2]](s32), [[V_READFIRSTLANE_B32_3]](s32)
-  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR1]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR1]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[COPY7]], 0, 0, -1 :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -111,7 +111,7 @@ define amdgpu_ps void @struct_buffer_store__sgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[PHI:%[0-9]+]]:sreg_64_xexec = PHI [[DEF]], %bb.1, %14, %bb.2
   ; CHECK:   [[V_READFIRSTLANE_B32_:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY7]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_]](s32), [[COPY7]](s32), implicit $exec
-  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[V_READFIRSTLANE_B32_]], 0, 0, -1 :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[V_READFIRSTLANE_B32_]], 0, 0, -1 :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[V_CMP_EQ_U32_e64_]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec
@@ -158,7 +158,7 @@ define amdgpu_ps void @struct_buffer_store__vgpr_rsrc__vgpr_val__vgpr_vindex__vg
   ; CHECK:   [[V_READFIRSTLANE_B32_4:%[0-9]+]]:sreg_32_xm0(s32) = V_READFIRSTLANE_B32 [[COPY7]](s32), implicit $exec
   ; CHECK:   [[V_CMP_EQ_U32_e64_:%[0-9]+]]:sreg_64_xexec = V_CMP_EQ_U32_e64 [[V_READFIRSTLANE_B32_4]](s32), [[COPY7]](s32), implicit $exec
   ; CHECK:   [[S_AND_B64_1:%[0-9]+]]:sreg_64_xexec = S_AND_B64 [[V_CMP_EQ_U32_e64_]], [[S_AND_B64_]], implicit-def $scc
-  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR1]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[V_READFIRSTLANE_B32_4]], 0, 0, -1 :: (dereferenceable store (s32) into custom "BufferResource", align 1, addrspace 4)
+  ; CHECK:   G_AMDGPU_BUFFER_STORE [[COPY4]](s32), [[BUILD_VECTOR1]](<4 x s32>), [[COPY5]](s32), [[COPY6]], [[V_READFIRSTLANE_B32_4]], 0, 0, -1 :: (dereferenceable store (s32), align 1, addrspace 4)
   ; CHECK:   [[S_AND_SAVEEXEC_B64_:%[0-9]+]]:sreg_64_xexec = S_AND_SAVEEXEC_B64 killed [[S_AND_B64_1]], implicit-def $exec, implicit-def $scc, implicit $exec
   ; CHECK:   $exec = S_XOR_B64_term $exec, [[S_AND_SAVEEXEC_B64_]], implicit-def $scc
   ; CHECK:   S_CBRANCH_EXECNZ %bb.2, implicit $exec