diff --git a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
index b49c5a997af78..e204d6ba356b8 100644
--- a/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/AMDGPU/SILoadStoreOptimizer.cpp
@@ -87,6 +87,8 @@ enum InstClassEnum {
   GLOBAL_STORE_SADDR,
   FLAT_LOAD,
   FLAT_STORE,
+  FLAT_LOAD_SADDR,
+  FLAT_STORE_SADDR,
   GLOBAL_LOAD, // GLOBAL_LOAD/GLOBAL_STORE are never used as the InstClass of
   GLOBAL_STORE // any CombineInfo, they are only ever returned by
                // getCommonInstClass.
@@ -354,6 +356,8 @@ static unsigned getOpcodeWidth(const MachineInstr &MI, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORD_SADDR:
   case AMDGPU::FLAT_LOAD_DWORD:
   case AMDGPU::FLAT_STORE_DWORD:
+  case AMDGPU::FLAT_LOAD_DWORD_SADDR:
+  case AMDGPU::FLAT_STORE_DWORD_SADDR:
     return 1;
   case AMDGPU::S_BUFFER_LOAD_DWORDX2_IMM:
   case AMDGPU::S_BUFFER_LOAD_DWORDX2_SGPR_IMM:
@@ -367,6 +371,8 @@ static unsigned getOpcodeWidth(const MachineInstr &MI, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX2_SADDR:
   case AMDGPU::FLAT_LOAD_DWORDX2:
   case AMDGPU::FLAT_STORE_DWORDX2:
+  case AMDGPU::FLAT_LOAD_DWORDX2_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX2_SADDR:
     return 2;
   case AMDGPU::S_BUFFER_LOAD_DWORDX3_IMM:
   case AMDGPU::S_BUFFER_LOAD_DWORDX3_SGPR_IMM:
@@ -380,6 +386,8 @@ static unsigned getOpcodeWidth(const MachineInstr &MI, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX3_SADDR:
   case AMDGPU::FLAT_LOAD_DWORDX3:
   case AMDGPU::FLAT_STORE_DWORDX3:
+  case AMDGPU::FLAT_LOAD_DWORDX3_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX3_SADDR:
     return 3;
   case AMDGPU::S_BUFFER_LOAD_DWORDX4_IMM:
   case AMDGPU::S_BUFFER_LOAD_DWORDX4_SGPR_IMM:
@@ -393,6 +401,8 @@ static unsigned getOpcodeWidth(const MachineInstr &MI, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX4_SADDR:
   case AMDGPU::FLAT_LOAD_DWORDX4:
   case AMDGPU::FLAT_STORE_DWORDX4:
+  case AMDGPU::FLAT_LOAD_DWORDX4_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX4_SADDR:
     return 4;
   case AMDGPU::S_BUFFER_LOAD_DWORDX8_IMM:
   case AMDGPU::S_BUFFER_LOAD_DWORDX8_SGPR_IMM:
@@ -575,6 +585,16 @@ static InstClassEnum getInstClass(unsigned Opc, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX3_SADDR:
   case AMDGPU::GLOBAL_STORE_DWORDX4_SADDR:
     return GLOBAL_STORE_SADDR;
+  case AMDGPU::FLAT_LOAD_DWORD_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX2_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX3_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX4_SADDR:
+    return FLAT_LOAD_SADDR;
+  case AMDGPU::FLAT_STORE_DWORD_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX2_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX3_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX4_SADDR:
+    return FLAT_STORE_SADDR;
   }
 }
 
@@ -661,6 +681,16 @@ static unsigned getInstSubclass(unsigned Opc, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX3_SADDR:
   case AMDGPU::GLOBAL_STORE_DWORDX4_SADDR:
     return AMDGPU::GLOBAL_STORE_DWORD_SADDR;
+  case AMDGPU::FLAT_LOAD_DWORD_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX2_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX3_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX4_SADDR:
+    return AMDGPU::FLAT_LOAD_DWORD_SADDR;
+  case AMDGPU::FLAT_STORE_DWORD_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX2_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX3_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX4_SADDR:
+    return AMDGPU::FLAT_STORE_DWORD_SADDR;
   }
 }
 
@@ -776,6 +806,14 @@ static AddressRegs getRegs(unsigned Opc, const SIInstrInfo &TII) {
   case AMDGPU::GLOBAL_STORE_DWORDX2_SADDR:
   case AMDGPU::GLOBAL_STORE_DWORDX3_SADDR:
   case AMDGPU::GLOBAL_STORE_DWORDX4_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORD_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX2_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX3_SADDR:
+  case AMDGPU::FLAT_LOAD_DWORDX4_SADDR:
+  case AMDGPU::FLAT_STORE_DWORD_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX2_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX3_SADDR:
+  case AMDGPU::FLAT_STORE_DWORDX4_SADDR:
     Result.SAddr = true;
     [[fallthrough]];
   case AMDGPU::GLOBAL_LOAD_DWORD:
@@ -1875,6 +1913,28 @@ unsigned SILoadStoreOptimizer::getNewOpcode(const CombineInfo &CI,
     case 4:
       return AMDGPU::FLAT_STORE_DWORDX4;
     }
+  case FLAT_LOAD_SADDR:
+    switch (Width) {
+    default:
+      return 0;
+    case 2:
+      return AMDGPU::FLAT_LOAD_DWORDX2_SADDR;
+    case 3:
+      return AMDGPU::FLAT_LOAD_DWORDX3_SADDR;
+    case 4:
+      return AMDGPU::FLAT_LOAD_DWORDX4_SADDR;
+    }
+  case FLAT_STORE_SADDR:
+    switch (Width) {
+    default:
+      return 0;
+    case 2:
+      return AMDGPU::FLAT_STORE_DWORDX2_SADDR;
+    case 3:
+      return AMDGPU::FLAT_STORE_DWORDX3_SADDR;
+    case 4:
+      return AMDGPU::FLAT_STORE_DWORDX4_SADDR;
+    }
   case MIMG:
     assert(((unsigned)llvm::popcount(CI.DMask | Paired.DMask) == Width) &&
            "No overlaps");
@@ -2508,12 +2568,14 @@ SILoadStoreOptimizer::optimizeInstsWithSameBaseAddr(
       OptimizeListAgain |= CI.Width + Paired.Width < 4;
       break;
     case FLAT_LOAD:
+    case FLAT_LOAD_SADDR:
     case GLOBAL_LOAD:
     case GLOBAL_LOAD_SADDR:
       NewMI = mergeFlatLoadPair(CI, Paired, Where->I);
       OptimizeListAgain |= CI.Width + Paired.Width < 4;
       break;
     case FLAT_STORE:
+    case FLAT_STORE_SADDR:
     case GLOBAL_STORE:
     case GLOBAL_STORE_SADDR:
       NewMI = mergeFlatStorePair(CI, Paired, Where->I);
diff --git a/llvm/test/CodeGen/AMDGPU/merge-flat-saddr-load-store.mir b/llvm/test/CodeGen/AMDGPU/merge-flat-saddr-load-store.mir
new file mode 100644
index 0000000000000..1c133c6114ec2
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/merge-flat-saddr-load-store.mir
@@ -0,0 +1,338 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1250 -run-pass=si-load-store-opt -o - %s | FileCheck -check-prefix=GCN %s
+
+---
+name:            merge_flat_load_dword_saddr_2
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_load_dword_saddr_2
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX2_SADDR:%[0-9]+]]:vreg_64_align2 = FLAT_LOAD_DWORDX2_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr :: (load (s64) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY [[FLAT_LOAD_DWORDX2_SADDR]].sub0
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[FLAT_LOAD_DWORDX2_SADDR]].sub1
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY]], implicit [[COPY1]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3
+...
+
+---
+name:            merge_flat_load_dword_saddr_3
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_load_dword_saddr_3
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX3_SADDR:%[0-9]+]]:vreg_96_align2 = FLAT_LOAD_DWORDX3_SADDR [[DEF]], [[DEF1]], 0, 1, implicit $exec, implicit $flat_scr :: (load (s96) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY [[FLAT_LOAD_DWORDX3_SADDR]].sub0_sub1
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[FLAT_LOAD_DWORDX3_SADDR]].sub2
+    ; GCN-NEXT: [[COPY2:%[0-9]+]]:vgpr_32 = COPY [[COPY]].sub0
+    ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY killed [[COPY]].sub1
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY2]], implicit [[COPY3]], implicit [[COPY1]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 0, 1, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 4, 1, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %4:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 8, 1, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3, implicit %4
+...
+
+---
+name:            merge_flat_load_dword_saddr_4
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_load_dword_saddr_4
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_128_align2 = FLAT_LOAD_DWORDX4_SADDR [[DEF]], [[DEF1]], 0, 2, implicit $exec, implicit $flat_scr :: (load (s128) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_96_align2 = COPY [[FLAT_LOAD_DWORDX4_SADDR]].sub0_sub1_sub2
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[FLAT_LOAD_DWORDX4_SADDR]].sub3
+    ; GCN-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY [[COPY]].sub0_sub1
+    ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY killed [[COPY]].sub2
+    ; GCN-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY2]].sub0
+    ; GCN-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[COPY2]].sub1
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY4]], implicit [[COPY5]], implicit [[COPY3]], implicit [[COPY1]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 0, 2, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 4, 2, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %4:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 8, 2, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %5:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 12, 2, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3, implicit %4, implicit %5
+...
+
+---
+name:            merge_flat_load_dword_saddr_6
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_load_dword_saddr_6
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_128_align2 = FLAT_LOAD_DWORDX4_SADDR [[DEF]], [[DEF1]], 4, 3, implicit $exec, implicit $flat_scr :: (load (s128) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_96_align2 = COPY [[FLAT_LOAD_DWORDX4_SADDR]].sub0_sub1_sub2
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY killed [[FLAT_LOAD_DWORDX4_SADDR]].sub3
+    ; GCN-NEXT: [[COPY2:%[0-9]+]]:vreg_64_align2 = COPY [[COPY]].sub0_sub1
+    ; GCN-NEXT: [[COPY3:%[0-9]+]]:vgpr_32 = COPY killed [[COPY]].sub2
+    ; GCN-NEXT: [[COPY4:%[0-9]+]]:vgpr_32 = COPY [[COPY2]].sub0
+    ; GCN-NEXT: [[COPY5:%[0-9]+]]:vgpr_32 = COPY killed [[COPY2]].sub1
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX2_SADDR:%[0-9]+]]:vreg_64_align2 = FLAT_LOAD_DWORDX2_SADDR [[DEF]], [[DEF1]], 20, 3, implicit $exec, implicit $flat_scr :: (load (s64) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY6:%[0-9]+]]:vgpr_32 = COPY [[FLAT_LOAD_DWORDX2_SADDR]].sub0
+    ; GCN-NEXT: [[COPY7:%[0-9]+]]:vgpr_32 = COPY killed [[FLAT_LOAD_DWORDX2_SADDR]].sub1
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY4]], implicit [[COPY5]], implicit [[COPY3]], implicit [[COPY1]], implicit [[COPY6]], implicit [[COPY7]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 4, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 8, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %4:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 12, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %5:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 16, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %6:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 20, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %7:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1, 24, 3, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3, implicit %4, implicit %5, implicit %6, implicit %7
+...
+
+---
+name:            merge_flat_load_dwordx2_saddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_load_dwordx2_saddr
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORDX4_SADDR:%[0-9]+]]:vreg_128_align2 = FLAT_LOAD_DWORDX4_SADDR [[DEF]], [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr :: (load (s128) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[COPY:%[0-9]+]]:vreg_64_align2 = COPY [[FLAT_LOAD_DWORDX4_SADDR]].sub0_sub1
+    ; GCN-NEXT: [[COPY1:%[0-9]+]]:vreg_64_align2 = COPY killed [[FLAT_LOAD_DWORDX4_SADDR]].sub2_sub3
+    ; GCN-NEXT: S_NOP 0, implicit [[COPY]], implicit [[COPY1]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vreg_64_align2 = FLAT_LOAD_DWORDX2_SADDR %0, %1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s64) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vreg_64_align2 = FLAT_LOAD_DWORDX2_SADDR %0, %1, 8, 0, implicit $exec, implicit $flat_scr :: (load (s64) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3
+...
+
+---
+name:            no_merge_flat_load_dword_and_flat_load_dword_saddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_load_dword_and_flat_load_dword_saddr
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD_SADDR [[DEF]], [[DEF1]].sub0, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: S_NOP 0, implicit [[FLAT_LOAD_DWORD]], implicit [[FLAT_LOAD_DWORD_SADDR]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vreg_64_align2 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1.sub0, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3
+...
+
+---
+name:            no_merge_flat_load_dword_saddr_different_saddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_load_dword_saddr_different_saddr
+    ; GCN: [[DEF:%[0-9]+]]:sgpr_128 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD_SADDR [[DEF]].sub0_sub1, [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD_SADDR [[DEF]].sub2_sub3, [[DEF1]], 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: S_NOP 0, implicit [[FLAT_LOAD_DWORD_SADDR]], implicit [[FLAT_LOAD_DWORD_SADDR1]]
+    %0:sgpr_128 = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0.sub0_sub1, %1, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0.sub2_sub3, %1, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3
+...
+
+---
+name:            no_merge_flat_load_dword_saddr_different_vaddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_load_dword_saddr_different_vaddr
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD_SADDR:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD_SADDR [[DEF]], [[DEF1]].sub0, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: [[FLAT_LOAD_DWORD_SADDR1:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD_SADDR [[DEF]], [[DEF1]].sub1, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: S_NOP 0, implicit [[FLAT_LOAD_DWORD_SADDR]], implicit [[FLAT_LOAD_DWORD_SADDR1]]
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vreg_64_align2 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1.sub0, 0, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %3:vgpr_32 = FLAT_LOAD_DWORD_SADDR %0, %1.sub1, 4, 0, implicit $exec, implicit $flat_scr :: (load (s32) from `ptr addrspace(1) undef`, align 4, addrspace 1)
+    S_NOP 0, implicit %2, implicit %3
+...
+---
+name:            merge_flat_store_dword_saddr_2
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_store_dword_saddr_2
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[DEF2]], %subreg.sub0, [[DEF3]], %subreg.sub1
+    ; GCN-NEXT: FLAT_STORE_DWORDX2_SADDR [[DEF1]], killed [[REG_SEQUENCE]], [[DEF]], 0, 0, implicit $exec, implicit $flat_scr :: (store (s64) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1, %2, %0, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %3, %0, 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            merge_flat_store_dword_saddr_3
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_store_dword_saddr_3
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[DEF2]], %subreg.sub0, [[DEF3]], %subreg.sub1
+    ; GCN-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_96_align2 = REG_SEQUENCE killed [[REG_SEQUENCE]], %subreg.sub0_sub1, [[DEF4]], %subreg.sub2
+    ; GCN-NEXT: FLAT_STORE_DWORDX3_SADDR [[DEF1]], killed [[REG_SEQUENCE1]], [[DEF]], 4, 1, implicit $exec, implicit $flat_scr :: (store (s96) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    %4:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1, %2, %0, 4, 1, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %3, %0, 8, 1, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %4, %0, 12, 1, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            merge_flat_store_dword_saddr_4
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_store_dword_saddr_4
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF5:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[DEF2]], %subreg.sub0, [[DEF3]], %subreg.sub1
+    ; GCN-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_96_align2 = REG_SEQUENCE killed [[REG_SEQUENCE]], %subreg.sub0_sub1, [[DEF4]], %subreg.sub2
+    ; GCN-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:vreg_128_align2 = REG_SEQUENCE killed [[REG_SEQUENCE1]], %subreg.sub0_sub1_sub2, [[DEF5]], %subreg.sub3
+    ; GCN-NEXT: FLAT_STORE_DWORDX4_SADDR [[DEF1]], killed [[REG_SEQUENCE2]], [[DEF]], 4, 2, implicit $exec, implicit $flat_scr :: (store (s128) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    %4:vgpr_32 = IMPLICIT_DEF
+    %5:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1, %2, %0, 4, 2, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %3, %0, 8, 2, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %4, %0, 12, 2, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %5, %0, 16, 2, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            merge_flat_store_dword_saddr_6
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: merge_flat_store_dword_saddr_6
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF4:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF5:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF6:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF7:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[REG_SEQUENCE:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[DEF2]], %subreg.sub0, [[DEF3]], %subreg.sub1
+    ; GCN-NEXT: [[REG_SEQUENCE1:%[0-9]+]]:vreg_96_align2 = REG_SEQUENCE killed [[REG_SEQUENCE]], %subreg.sub0_sub1, [[DEF4]], %subreg.sub2
+    ; GCN-NEXT: [[REG_SEQUENCE2:%[0-9]+]]:vreg_128_align2 = REG_SEQUENCE killed [[REG_SEQUENCE1]], %subreg.sub0_sub1_sub2, [[DEF5]], %subreg.sub3
+    ; GCN-NEXT: FLAT_STORE_DWORDX4_SADDR [[DEF1]], killed [[REG_SEQUENCE2]], [[DEF]], 4, 3, implicit $exec, implicit $flat_scr :: (store (s128) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    ; GCN-NEXT: [[REG_SEQUENCE3:%[0-9]+]]:vreg_64_align2 = REG_SEQUENCE [[DEF6]], %subreg.sub0, [[DEF7]], %subreg.sub1
+    ; GCN-NEXT: FLAT_STORE_DWORDX2_SADDR [[DEF1]], killed [[REG_SEQUENCE3]], [[DEF]], 20, 3, implicit $exec, implicit $flat_scr :: (store (s64) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    %4:vgpr_32 = IMPLICIT_DEF
+    %5:vgpr_32 = IMPLICIT_DEF
+    %6:vgpr_32 = IMPLICIT_DEF
+    %7:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1, %2, %0, 4, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %3, %0, 8, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %4, %0, 12, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %5, %0, 16, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %6, %0, 20, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %7, %0, 24, 3, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            no_merge_flat_store_dword_saddr_with_flat_store_dword
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_store_dword_saddr_with_flat_store_dword
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: FLAT_STORE_DWORD_SADDR [[DEF1]].sub0, [[DEF2]], [[DEF]], 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: FLAT_STORE_DWORD [[DEF1]], [[DEF3]], 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vreg_64_align2 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1.sub0, %2, %0, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD %1, %3, 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            no_merge_flat_store_dword_saddr_different_vaddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_store_dword_saddr_different_vaddr
+    ; GCN: [[DEF:%[0-9]+]]:sreg_64_xexec_xnull = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vreg_64_align2 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: FLAT_STORE_DWORD_SADDR [[DEF1]].sub0, [[DEF2]], [[DEF]], 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: FLAT_STORE_DWORD_SADDR [[DEF1]].sub1, [[DEF3]], [[DEF]], 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    %0:sreg_64_xexec_xnull = IMPLICIT_DEF
+    %1:vreg_64_align2 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1.sub0, %2, %0, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1.sub1, %3, %0, 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...
+
+---
+name:            no_merge_flat_store_dword_saddr_different_saddr
+body:             |
+  bb.0.entry:
+
+    ; GCN-LABEL: name: no_merge_flat_store_dword_saddr_different_saddr
+    ; GCN: [[DEF:%[0-9]+]]:sgpr_128 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF1:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF2:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: [[DEF3:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; GCN-NEXT: FLAT_STORE_DWORD_SADDR [[DEF1]], [[DEF2]], [[DEF]].sub0_sub1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    ; GCN-NEXT: FLAT_STORE_DWORD_SADDR [[DEF1]], [[DEF3]], [[DEF]].sub2_sub3, 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, addrspace 1)
+    %0:sgpr_128 = IMPLICIT_DEF
+    %1:vgpr_32 = IMPLICIT_DEF
+    %2:vgpr_32 = IMPLICIT_DEF
+    %3:vgpr_32 = IMPLICIT_DEF
+    FLAT_STORE_DWORD_SADDR %1, %2, %0.sub0_sub1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+    FLAT_STORE_DWORD_SADDR %1, %3, %0.sub2_sub3, 4, 0, implicit $exec, implicit $flat_scr :: (store (s32) into `ptr addrspace(1) undef`, align 4, addrspace 1)
+...