AMDGPU: Move MIMG MMO check to verifier

[arsenm]

f012c58abdb086ea093d48e7a705f98f9e9561c6

llvm/lib/Target/AMDGPU/MIMGInstructions.td

class MIMG_Base <dag outs, string dns = "">
   let mayLoad = 1;
   let mayStore = 0;
   let SchedRW = [WriteVMEM];
   let UseNamedOperandTable = 1;
   let hasSideEffects = 0; // XXX ????
 
   let DecoderNamespace = dns;
   let isAsmParserOnly = !if(!eq(dns,""), 1, 0);
-  let usesCustomInserter = 1;
 }
 
 class MIMG <dag outs, string dns = "">
   : MIMG_Base <outs, dns> {
 
   let hasPostISelHook = 1;
   let AsmMatchConverter = "cvtMIMG";
 

llvm/lib/Target/AMDGPU/SIISelLowering.cpp

 
 MachineBasicBlock *SITargetLowering::EmitInstrWithCustomInserter(
   MachineInstr &MI, MachineBasicBlock *BB) const {
 
   const SIInstrInfo *TII = getSubtarget()->getInstrInfo();
   MachineFunction *MF = BB->getParent();
   SIMachineFunctionInfo *MFI = MF->getInfo<SIMachineFunctionInfo>();
 
-  if (TII->isMIMG(MI)) {
-    if (MI.memoperands_empty() && MI.mayLoadOrStore()) {
-      report_fatal_error("missing mem operand from MIMG instruction");
-    }
-    // Add a memoperand for mimg instructions so that they aren't assumed to
-    // be ordered memory instuctions.
-
-    return BB;
-  }
-
   switch (MI.getOpcode()) {
   case AMDGPU::S_UADDO_PSEUDO:
   case AMDGPU::S_USUBO_PSEUDO: {
     const DebugLoc &DL = MI.getDebugLoc();
     MachineOperand &Dest0 = MI.getOperand(0);
     MachineOperand &Dest1 = MI.getOperand(1);
     MachineOperand &Src0 = MI.getOperand(2);
     MachineOperand &Src1 = MI.getOperand(3);

llvm/lib/Target/AMDGPU/SIInstrInfo.cpp

for (unsigned I = InlineAsm::MIOp_FirstOperand, E = MI.getNumOperands();
         ErrInfo = "inlineasm operand has incorrect register class.";
         return false;
       }
     }
 
     return true;
   }
 
+  if (isMIMG(MI) && MI.memoperands_empty() && MI.mayLoadOrStore()) {
+    ErrInfo = "missing memory operand from MIMG instruction.";
+    return false;
+  }
+
   // Make sure the register classes are correct.
   for (int i = 0, e = Desc.getNumOperands(); i != e; ++i) {
     if (MI.getOperand(i).isFPImm()) {
       ErrInfo = "FPImm Machine Operands are not supported. ISel should bitcast "
                 "all fp values to integers.";
       return false;
     }
 

llvm/test/CodeGen/AMDGPU/coalescer-subreg-join.mir

bb.0:
     %11.sub1 = COPY %1
     %11.sub2 = COPY %1
     %11.sub3 = COPY %1
     %11.sub4 = COPY %1
     %11.sub5 = COPY %1
     %11.sub6 = COPY %1
     %11.sub7 = COPY %1
     %11.sub8 = COPY %1
-    dead %18 = IMAGE_SAMPLE_C_D_O_V1_V16 %11, %3, %4, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
+    dead %18 = IMAGE_SAMPLE_C_D_O_V1_V16 %11, %3, %4, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (load 4)
     %20.sub1 = COPY %2
     %20.sub2 = COPY %2
     %20.sub3 = COPY %2
     %20.sub4 = COPY %2
     %20.sub5 = COPY %2
     %20.sub6 = COPY %2
     %20.sub7 = COPY %2
     %20.sub8 = COPY %2
-    dead %27 = IMAGE_SAMPLE_C_D_O_V1_V16 %20, %5, %6, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
+    dead %27 = IMAGE_SAMPLE_C_D_O_V1_V16 %20, %5, %6, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (load 4)
 
 ...

llvm/test/CodeGen/AMDGPU/memory_clause.mir

registers:
   - { id: 2, class: sgpr_128 }
   - { id: 3, class: vreg_128 }
   - { id: 4, class: vreg_128 }
   - { id: 5, class: vreg_128 }
 body:             |
   bb.0:
     %0 = IMPLICIT_DEF
     %1 = IMPLICIT_DEF
-    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    IMAGE_STORE_V4_V2 %4, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    IMAGE_STORE_V4_V2 %5, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+    %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+    %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+    IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
+    IMAGE_STORE_V4_V2 %4, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
+    IMAGE_STORE_V4_V2 %5, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
 ...
 
 # GCN-LABEL: {{^}}name: mixed_clause{{$}}
 # GCN:      dead early-clobber %4:vreg_128, dead early-clobber %3:vreg_128, dead early-clobber %5:vgpr_32 = BUNDLE %0, %2, %1, implicit $exec {
 # GCN-NEXT:   dead %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
 # GCN-NEXT:   dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, 0, implicit $exec
 # GCN-NEXT:   dead %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, 0, 0, implicit $exec
 # GCN-NEXT: }
 
 ---
 name:            mixed_clause
 tracksRegLiveness: true
 registers:
   - { id: 0, class: vreg_64 }
   - { id: 1, class: sgpr_256 }
   - { id: 2, class: sgpr_128 }
   - { id: 3, class: vreg_128 }
   - { id: 4, class: vreg_128 }
   - { id: 5, class: vgpr_32 }
 body:             |
   bb.0:
     %0 = IMPLICIT_DEF
     %1 = IMPLICIT_DEF
     %2 = IMPLICIT_DEF
-    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
     %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, 0, 0, implicit $exec
     %5:vgpr_32 = BUFFER_LOAD_DWORD_ADDR64 %0, %2, 0, 0, 0, 0, 0, 0, 0, implicit $exec
 ...
 
 # GCN-LABEL: {{^}}name: atomic{{$}}
 # GCN:      %1:vgpr_32 = IMPLICIT_DEF
 # GCN-NEXT: dead %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr
 # GCN-NEXT: dead %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 0, implicit $exec, implicit $flat_scr

llvm/test/CodeGen/AMDGPU/merge-image-load.mir

body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 =COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vreg_128 = COPY %2
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_LOAD_V1_V4 %5:vreg_128, %3:sgpr_256, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    IMAGE_STORE_V4_V4 %4:vreg_128, %5:vreg_128, %3:sgpr_256, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    IMAGE_STORE_V4_V4 %4:vreg_128, %5:vreg_128, %3:sgpr_256, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
     %7:vreg_96 = IMAGE_LOAD_V3_V4 %5:vreg_128, %3:sgpr_256, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_load_dmask_overlapped_not_merged
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_LOAD_V1_V4 %5, %3, 4, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_LOAD_V3_V4 %5, %3, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
bb.0.entry:
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_LOAD_V1_V4 %5, %3, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
     %7:vreg_96 = IMAGE_LOAD_V3_V4 %5, %3, 7, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_load_mip_merged_v1v3
-# GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_LOAD_MIP_V4_V4 %5, %3, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4) 
+# GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_LOAD_MIP_V4_V4 %5, %3, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_load_mip_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0

llvm/test/CodeGen/AMDGPU/merge-image-sample.mir

body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 # GFX9-LABEL: name: image_sample_l_merged_v1v3_reversed
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub3
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub0_sub1_sub2
 
 name: image_sample_l_merged_v1v3_reversed
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_merged_v2v2
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_64 = COPY %8.sub0_sub1
 # GFX9: %{{[0-9]+}}:vreg_64 = COPY killed %8.sub2_sub3
 
 name: image_sample_l_merged_v2v2
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 3, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4)
-    %7:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 12, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4) 
+    %7:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 12, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_merged_v2v2_reversed
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_64 = COPY %8.sub2_sub3
 # GFX9: %{{[0-9]+}}:vreg_64 = COPY killed %8.sub0_sub1
 
 name: image_sample_l_merged_v2v2_reversed
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 12, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4)
-    %7:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 3, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4) 
+    %7:vreg_64 = IMAGE_SAMPLE_L_V2_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 3, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 8, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_merged_v3v1
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY %8.sub0_sub1_sub2
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY killed %8.sub3
 
 name: image_sample_l_merged_v3v1
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
-    %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4) 
+    %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_merged_v3v1_reversed
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY %8.sub1_sub2_sub3
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY killed %8.sub0
 
 name: image_sample_l_merged_v3v1_reversed
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
-    %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4) 
+    %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_divided_merged
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 
 name: image_sample_l_divided_merged
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
     %7:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %8:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
-    %9:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %7:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %9:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %7:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
     %10:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
-    %11:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %11:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_divided_not_merged
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
 name: image_sample_l_divided_not_merged
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vreg_128 = COPY %2
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    IMAGE_STORE_V4_V4 %4:vreg_128, %5:vreg_128, %3:sgpr_256, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    IMAGE_STORE_V4_V4 %4:vreg_128, %5:vreg_128, %3:sgpr_256, 15, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
+    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_dmask_overlapped_not_merged
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 4, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
 name: image_sample_l_dmask_overlapped_not_merged
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 4, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_dmask_not_disjoint_not_merged
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 4, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 11, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
 name: image_sample_l_dmask_not_disjoint_not_merged
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 4, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 11, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 11, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_not_merged_0
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %6, %3, %2, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
 name: image_sample_l_not_merged_0
bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_128 = COPY $sgpr92_sgpr93_sgpr94_sgpr95
     %4:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %5:vgpr_32 = COPY %2.sub3
     %6:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %7:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %6, %4, %2, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %8:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %6, %4, %3, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %8:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %6, %4, %3, 7, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 # GFX9-LABEL: name: image_sample_l_not_merged_3
 # GFX9: %{{[0-9]+}}:vgpr_32 = IMAGE_SAMPLE_L_V1_V4 %5, %3, %2, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vreg_96 = IMAGE_SAMPLE_L_V3_V4 %5, %3, %2, 7, 1, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 
 name: image_sample_l_not_merged_3
body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_b_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_b_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_B_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_B_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_B_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_b_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_b_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_B_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_B_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_B_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_b_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_b_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_B_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_B_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_B_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_b_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_B_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_b_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_B_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_B_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_B_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cd_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cd_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CD_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CD_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CD_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cd_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cd_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CD_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CD_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CD_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cd_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cd_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CD_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CD_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CD_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cd_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CD_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cd_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CD_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CD_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CD_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_b_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_b_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_B_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_B_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_B_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_b_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_b_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_B_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_b_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_b_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_B_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_B_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_b_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_B_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_b_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_B_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_B_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_B_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cd_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cd_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CD_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CD_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CD_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cd_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cd_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CD_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cd_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cd_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CD_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CD_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cd_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CD_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cd_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CD_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CD_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CD_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_d_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_d_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_D_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_D_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_D_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_d_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_d_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_D_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_d_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_d_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_D_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_D_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_d_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_D_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_d_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_D_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_D_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_D_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_l_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_L_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_l_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_L_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_L_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_lz_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_LZ_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_lz_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_LZ_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_LZ_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_LZ_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_lz_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_LZ_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_lz_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_LZ_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_LZ_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_LZ_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_l_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_L_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_l_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_L_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_L_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_L_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_c_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_C_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_c_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_C_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_C_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_C_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_d_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_d_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_D_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_D_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_D_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_d_cl_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_CL_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_d_cl_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_D_CL_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_D_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_D_CL_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_d_cl_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_CL_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_d_cl_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_D_CL_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_D_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_D_CL_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_d_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_D_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_d_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_D_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_D_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_D_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_lz_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_LZ_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_lz_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_LZ_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_LZ_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_LZ_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_lz_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_LZ_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_lz_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_LZ_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_LZ_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_LZ_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_l_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_L_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_l_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_L_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_L_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_L_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---
 
 
 # GFX9-LABEL: name: image_sample_o_merged_v1v3
 # GFX9: %{{[0-9]+}}:vreg_128 = IMAGE_SAMPLE_O_V4_V4 %5, %3, %2, 15, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec, implicit $exec :: (dereferenceable load 16, align 4, addrspace 4)
 # GFX9: %{{[0-9]+}}:vgpr_32 = COPY %8.sub0
 # GFX9: %{{[0-9]+}}:vreg_96 = COPY killed %8.sub1_sub2_sub3
 
 name: image_sample_o_merged_v1v3
 body:             |
   bb.0.entry:
     %0:sgpr_64 = COPY $sgpr0_sgpr1
     %1:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0, 36, 0, 0
     %2:sgpr_128 = COPY $sgpr96_sgpr97_sgpr98_sgpr99
     %3:sgpr_256 = S_LOAD_DWORDX8_IMM %1, 208, 0, 0
     %4:vgpr_32 = COPY %2.sub3
     %5:vreg_128 = BUFFER_LOAD_DWORDX4_OFFSET %2:sgpr_128, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable invariant load 16)
     %6:vgpr_32 = IMAGE_SAMPLE_O_V1_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 1, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 4, addrspace 4)
-    %7:vreg_96 = IMAGE_SAMPLE_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4) 
+    %7:vreg_96 = IMAGE_SAMPLE_O_V3_V4 %5:vreg_128, %3:sgpr_256, %2:sgpr_128, 14, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (dereferenceable load 12, align 16, addrspace 4)
 ...
 ---

llvm/test/CodeGen/AMDGPU/nsa-vmem-hazard.mir

 # RUN: llc -march=amdgcn -mcpu=gfx1010 -verify-machineinstrs -run-pass post-RA-hazard-rec -o - %s | FileCheck -check-prefix=GCN %s
 
 # GCN-LABEL: name: hazard_image_sample_d_buf_off6
 # GCN:      IMAGE_SAMPLE
 # GCN-NEXT: S_NOP 0
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
 ---
 name:            hazard_image_sample_d_buf_off6
 body:            |
   bb.0:
-    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec  :: (load 16)
     $vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
 ...
 
 # GCN-LABEL: name: no_hazard_image_sample_d_buf_off1
 # GCN:      IMAGE_SAMPLE
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
 ---
 name:            no_hazard_image_sample_d_buf_off1
 body:            |
   bb.0:
-    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec  :: (load 16)
     $vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 1, 0, 0, 0, 0, 0, implicit $exec
 ...
 
 # GCN-LABEL: name: no_hazard_image_sample_d_buf_far
 # GCN:      IMAGE_SAMPLE
 # GCN-NEXT: V_NOP_e32
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
 ---
 name:            no_hazard_image_sample_d_buf_far
 body:            |
   bb.0:
-    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 undef $vgpr3, undef $vgpr8, undef $vgpr7, undef $vgpr5, undef $vgpr4, undef $vgpr6, undef $vgpr0, undef $vgpr2, undef $vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec  :: (load 16)
     V_NOP_e32 implicit $exec
     $vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
 ...
 
 # Non-NSA
 # GCN-LABEL: name: no_hazard_image_sample_v4_v2_buf_off6
 # GCN:      IMAGE_SAMPLE
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
 ---
 name:            no_hazard_image_sample_v4_v2_buf_off6
 body:            |
   bb.0:
-    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V2_gfx10 undef $vgpr1_vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V2_gfx10 undef $vgpr1_vgpr2, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec  :: (load 16)
     $vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
 ...
 
 # Less than 4 dwords
 # GCN-LABEL: name: no_hazard_image_sample_v4_v3_buf_off6
 # GCN:      IMAGE_SAMPLE
 # GCN-NEXT: BUFFER_LOAD_DWORD_OFFSET
 ---
 name:            no_hazard_image_sample_v4_v3_buf_off6
 body:            |
   bb.0:
-    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V3_nsa_gfx10 undef $vgpr1, undef $vgpr2, undef $vgpr0, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr0_vgpr1_vgpr2_vgpr3 = IMAGE_SAMPLE_V4_V3_nsa_gfx10 undef $vgpr1, undef $vgpr2, undef $vgpr0, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, undef $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
     $vgpr1 = BUFFER_LOAD_DWORD_OFFSET undef $sgpr0_sgpr1_sgpr2_sgpr3, undef $sgpr4, 6, 0, 0, 0, 0, 0, implicit $exec
 ...

llvm/test/CodeGen/AMDGPU/postra-bundle-memops.mir

bb.0:
     DS_WRITE_B32_gfx9 $vgpr0, $vgpr3, 4, 0, implicit killed $m0, implicit $exec
     S_NOP 0
     $sgpr2 = S_LOAD_DWORD_IMM undef $sgpr0_sgpr1, 0, 0, 0
     $sgpr3 = S_LOAD_DWORD_SGPR undef $sgpr0_sgpr1, undef $sgpr10, 0, 0
     $vgpr2 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, undef $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr2, 0, 0, 0, 0, 0, 0, implicit $exec
     $vgpr3 = BUFFER_LOAD_DWORD_OFFEN $vgpr1, undef $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr2, 0, 0, 0, 0, 0, 0, implicit $exec
     BUFFER_STORE_DWORD_ADDR64 $vgpr0, $vgpr2_vgpr3,  undef $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, 0, implicit $exec
     BUFFER_STORE_DWORD_ADDR64 $vgpr0, $vgpr2_vgpr3,  undef $sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    $vgpr2 = IMAGE_LOAD_V1_V4 undef $vgpr4_vgpr5_vgpr6_vgpr7, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    $vgpr3 = IMAGE_LOAD_V1_V4 undef $vgpr4_vgpr5_vgpr6_vgpr7, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    IMAGE_STORE_V4_V2 undef $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr0_vgpr1, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec
-    IMAGE_STORE_V4_V2 undef $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr0_vgpr1, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr2 = IMAGE_LOAD_V1_V4 undef $vgpr4_vgpr5_vgpr6_vgpr7, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4)
+    $vgpr3 = IMAGE_LOAD_V1_V4 undef $vgpr4_vgpr5_vgpr6_vgpr7, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 4)
+    IMAGE_STORE_V4_V2 undef $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr0_vgpr1, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
+    IMAGE_STORE_V4_V2 undef $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr0_vgpr1, undef $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
     S_NOP 0
     $sgpr64_sgpr65_sgpr66_sgpr67_sgpr68_sgpr69_sgpr70_sgpr71 = S_LOAD_DWORDX8_IMM undef $sgpr10_sgpr11, 464, 0, 0
     $sgpr68_sgpr69_sgpr70_sgpr71_sgpr72_sgpr73_sgpr74_sgpr75 = S_LOAD_DWORDX8_IMM undef $sgpr10_sgpr11, 128, 0, 0
     S_NOP 0
     $vgpr2 = DS_READ_B32_gfx9 $vgpr0, 0, 0, implicit $exec
     $vgpr3 = DS_READ_B32_gfx9 $vgpr1, 0, 0, implicit $exec
 ...

llvm/test/CodeGen/AMDGPU/waitcnt-preexisting.mir

bb.0:
     renamable $vgpr2_vgpr3 = DS_READ2_B32 renamable $vgpr13, 2, 3, 0, implicit $m0, implicit $exec
     renamable $vgpr1 = V_ADD_U32_e32 1, killed $vgpr1, implicit $exec
     renamable $vgpr1 = V_MAX_U32_e32 killed $vgpr0, killed $vgpr1, implicit $exec
     renamable $vgpr1 = V_MAX_U32_e32 killed $vgpr2, killed $vgpr1, implicit $exec
     renamable $vgpr1 = V_MAX_U32_e32 killed $vgpr3, killed $vgpr1, implicit $exec
     $vgpr0 = V_MOV_B32_e32 $vgpr1, implicit $exec, implicit $exec
     $vgpr2 = V_MOV_B32_e32 $vgpr1, implicit $exec, implicit $exec
     $vgpr3 = V_MOV_B32_e32 $vgpr1, implicit $exec, implicit $exec
-    IMAGE_STORE_V4_V2 killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, killed renamable $vgpr0_vgpr1, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec
+    IMAGE_STORE_V4_V2 killed renamable $vgpr0_vgpr1_vgpr2_vgpr3, killed renamable $vgpr0_vgpr1, killed renamable $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 15, -1, 1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store 16)
     S_ENDPGM 0
 ...

llvm/test/CodeGen/AMDGPU/waitcnt-vmem-waw.mir

 body: |
   bb.0:
     liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
     ; GFX9-LABEL: name: gather_gather
     ; GFX9: liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
     ; GFX9: S_WAITCNT 0
     ; GFX9: $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr0_vgpr1_vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
     ; GFX9: $vgpr13_vgpr14_vgpr15_vgpr16 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr0_vgpr1_vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    $vgpr13_vgpr14_vgpr15_vgpr16 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec
+    $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr0_vgpr1_vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+    $vgpr13_vgpr14_vgpr15_vgpr16 = IMAGE_GATHER4_LZ_O_V4_V3 $vgpr3_vgpr4_vgpr5, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 0, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
 ...
 
 # Image load vs image sample. Waitcnt required because they are not guaranteed
 # to write their results in order, despite both using the s_waitcnt vmcnt
 # counter.
 ---
 name: nosampler_sampler
 tracksRegLiveness: true
 body: |
   bb.0:
     liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0_vgpr1_vgpr2_vgpr3
     ; GFX9-LABEL: name: nosampler_sampler
     ; GFX9: liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0_vgpr1_vgpr2_vgpr3
     ; GFX9: S_WAITCNT 0
     ; GFX9: $vgpr4 = IMAGE_LOAD_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
     ; GFX9: S_WAITCNT 3952
     ; GFX9: $vgpr4 = IMAGE_SAMPLE_L_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
-    $vgpr4 = IMAGE_LOAD_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec
-    $vgpr4 = IMAGE_SAMPLE_L_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec
+    $vgpr4 = IMAGE_LOAD_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, 2, -1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+    $vgpr4 = IMAGE_SAMPLE_L_V1_V4 $vgpr0_vgpr1_vgpr2_vgpr3, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 8, 0, 0, 0, 0, 0, 0, -1, 0, implicit $exec :: (load 16)
 ...