diff --git a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
--- a/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ b/llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -2234,73 +2234,84 @@
         // Convert to a swizzled stack address by scaling by the wave size.
         //
         // In an entry function/kernel the offset is already swizzled.
-
+        bool IsSALU = TII->isSALU(*MI);
+        const TargetRegisterClass *RC = IsSALU ? &AMDGPU::SReg_32RegClass
+                                                   : &AMDGPU::VGPR_32RegClass;
         bool IsCopy = MI->getOpcode() == AMDGPU::V_MOV_B32_e32;
         Register ResultReg =
             IsCopy ? MI->getOperand(0).getReg()
-                   : RS->scavengeRegister(&AMDGPU::VGPR_32RegClass, MI, 0);
+                   : RS->scavengeRegister(RC, MI, 0);
 
         int64_t Offset = FrameInfo.getObjectOffset(Index);
         if (Offset == 0) {
+          unsigned OpCode =
+              IsSALU ? AMDGPU::S_LSHR_B32 : AMDGPU::V_LSHRREV_B32_e64;
           // XXX - This never happens because of emergency scavenging slot at 0?
-          BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_LSHRREV_B32_e64), ResultReg)
-            .addImm(ST.getWavefrontSizeLog2())
-            .addReg(FrameReg);
-        } else {
-          if (auto MIB = TII->getAddNoCarry(*MBB, MI, DL, ResultReg, *RS)) {
-            // Reuse ResultReg in intermediate step.
-            Register ScaledReg = ResultReg;
-
-            BuildMI(*MBB, *MIB, DL, TII->get(AMDGPU::V_LSHRREV_B32_e64),
-                    ScaledReg)
+          BuildMI(*MBB, MI, DL, TII->get(OpCode), ResultReg)
               .addImm(ST.getWavefrontSizeLog2())
               .addReg(FrameReg);
-
-            const bool IsVOP2 = MIB->getOpcode() == AMDGPU::V_ADD_U32_e32;
-
-            // TODO: Fold if use instruction is another add of a constant.
-            if (IsVOP2 || AMDGPU::isInlinableLiteral32(Offset, ST.hasInv2PiInlineImm())) {
-              // FIXME: This can fail
-              MIB.addImm(Offset);
-              MIB.addReg(ScaledReg, RegState::Kill);
-              if (!IsVOP2)
+        } else {
+          MachineInstrBuilder MIB;
+          if (!IsSALU) {
+            if (MIB = TII->getAddNoCarry(*MBB, MI, DL, ResultReg, *RS)) {
+              // Reuse ResultReg in intermediate step.
+              Register ScaledReg = ResultReg;
+
+              BuildMI(*MBB, *MIB, DL, TII->get(AMDGPU::V_LSHRREV_B32_e64),
+                      ScaledReg)
+                  .addImm(ST.getWavefrontSizeLog2())
+                  .addReg(FrameReg);
+
+              const bool IsVOP2 = MIB->getOpcode() == AMDGPU::V_ADD_U32_e32;
+
+              // TODO: Fold if use instruction is another add of a constant.
+              if (IsVOP2 || AMDGPU::isInlinableLiteral32(
+                                Offset, ST.hasInv2PiInlineImm())) {
+                // FIXME: This can fail
+                MIB.addImm(Offset);
+                MIB.addReg(ScaledReg, RegState::Kill);
+                if (!IsVOP2)
+                  MIB.addImm(0); // clamp bit
+              } else {
+                assert(MIB->getOpcode() == AMDGPU::V_ADD_CO_U32_e64 &&
+                       "Need to reuse carry out register");
+
+                // Use scavenged unused carry out as offset register.
+                Register ConstOffsetReg;
+                if (!isWave32)
+                  ConstOffsetReg = getSubReg(MIB.getReg(1), AMDGPU::sub0);
+                else
+                  ConstOffsetReg = MIB.getReg(1);
+
+                BuildMI(*MBB, *MIB, DL, TII->get(AMDGPU::S_MOV_B32),
+                        ConstOffsetReg)
+                    .addImm(Offset);
+                MIB.addReg(ConstOffsetReg, RegState::Kill);
+                MIB.addReg(ScaledReg, RegState::Kill);
                 MIB.addImm(0); // clamp bit
-            } else {
-              assert(MIB->getOpcode() == AMDGPU::V_ADD_CO_U32_e64 &&
-                     "Need to reuse carry out register");
-
-              // Use scavenged unused carry out as offset register.
-              Register ConstOffsetReg;
-              if (!isWave32)
-                ConstOffsetReg = getSubReg(MIB.getReg(1), AMDGPU::sub0);
-              else
-                ConstOffsetReg = MIB.getReg(1);
-
-              BuildMI(*MBB, *MIB, DL, TII->get(AMDGPU::S_MOV_B32), ConstOffsetReg)
-                .addImm(Offset);
-              MIB.addReg(ConstOffsetReg, RegState::Kill);
-              MIB.addReg(ScaledReg, RegState::Kill);
-              MIB.addImm(0); // clamp bit
+              }
             }
-          } else {
+          }
+          if (!MIB || IsSALU) {
             // We have to produce a carry out, and there isn't a free SGPR pair
             // for it. We can keep the whole computation on the SALU to avoid
             // clobbering an additional register at the cost of an extra mov.
 
             // We may have 1 free scratch SGPR even though a carry out is
             // unavailable. Only one additional mov is needed.
-            Register TmpScaledReg =
-                RS->scavengeRegister(&AMDGPU::SReg_32_XM0RegClass, MI, 0, false);
-            Register ScaledReg = TmpScaledReg.isValid() ? TmpScaledReg : FrameReg;
+            Register TmpScaledReg = RS->scavengeRegister(
+                &AMDGPU::SReg_32_XM0RegClass, MI, 0, false);
+            Register ScaledReg =
+                TmpScaledReg.isValid() ? TmpScaledReg : FrameReg;
 
             BuildMI(*MBB, MI, DL, TII->get(AMDGPU::S_LSHR_B32), ScaledReg)
-              .addReg(FrameReg)
-              .addImm(ST.getWavefrontSizeLog2());
+                .addReg(FrameReg)
+                .addImm(ST.getWavefrontSizeLog2());
             BuildMI(*MBB, MI, DL, TII->get(AMDGPU::S_ADD_I32), ScaledReg)
                 .addReg(ScaledReg, RegState::Kill)
                 .addImm(Offset);
             BuildMI(*MBB, MI, DL, TII->get(AMDGPU::COPY), ResultReg)
-              .addReg(ScaledReg, RegState::Kill);
+                .addReg(ScaledReg, RegState::Kill);
 
             // If there were truly no free SGPRs, we need to undo everything.
             if (!TmpScaledReg.isValid()) {
@@ -2308,8 +2319,8 @@
                   .addReg(ScaledReg, RegState::Kill)
                   .addImm(-Offset);
               BuildMI(*MBB, MI, DL, TII->get(AMDGPU::S_LSHL_B32), ScaledReg)
-                .addReg(FrameReg)
-                .addImm(ST.getWavefrontSizeLog2());
+                  .addReg(FrameReg)
+                  .addImm(ST.getWavefrontSizeLog2());
             }
           }
         }
diff --git a/llvm/test/CodeGen/AMDGPU/frame-index.mir b/llvm/test/CodeGen/AMDGPU/frame-index.mir
new file mode 100644
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/frame-index.mir
@@ -0,0 +1,118 @@
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=kaveri -mattr=-promote-alloca -amdgpu-sroa=0 -verify-machineinstrs -run-pass=prologepilog -o - %s | FileCheck -check-prefix=GCN %s
+
+--- |
+  
+  declare i32 @llvm.amdgcn.workitem.id.x() #0
+  
+  define void @func_add_constant_to_fi_divergent_i32() {
+    %alloca = alloca [2 x i32], align 4, addrspace(5)
+    %tid = call i32 @llvm.amdgcn.workitem.id.x()
+    %1 = getelementptr [2 x i32], [2 x i32] addrspace(5)* %alloca, i32 0, i32 %tid
+    %gep02 = getelementptr inbounds i32, i32 addrspace(5)* %1, i32 1
+    store volatile i32 addrspace(5)* %gep02, i32 addrspace(5)* addrspace(3)* undef, align 4
+    ret void
+  }
+  
+  define void @func_add_constant_to_fi_uniform_i32() {
+    %alloca = alloca [2 x i32], align 4, addrspace(5)
+    %gep0 = getelementptr inbounds [2 x i32], [2 x i32] addrspace(5)* %alloca, i32 0, i32 1
+    store volatile i32 addrspace(5)* %gep0, i32 addrspace(5)* addrspace(3)* undef, align 4
+    ret void
+  }
+  
+  define void @func_other_fi_user_non_inline_imm_offset_i32() {
+    %alloca0 = alloca [128 x i32], align 4, addrspace(5)
+    %alloca1 = alloca [8 x i32], align 4, addrspace(5)
+    %gep0 = getelementptr inbounds [128 x i32], [128 x i32] addrspace(5)* %alloca0, i32 0, i32 65
+    %gep11 = bitcast [8 x i32] addrspace(5)* %alloca1 to i32 addrspace(5)*
+    store volatile i32 7, i32 addrspace(5)* %gep0, align 4
+    %ptrtoint = ptrtoint i32 addrspace(5)* %gep11 to i32
+    %mul = mul i32 %ptrtoint, 9
+    store volatile i32 %mul, i32 addrspace(3)* undef, align 4
+    ret void
+  }
+  
+...
+# GCN-LABEL: name: func_add_constant_to_fi_divergent_i32{{$}}
+# GCN: $vgpr1 = V_LSHRREV_B32_e64 6, $sgpr32
+# GCN: $vgpr0 = V_ADD_CO_U32_e32 killed $vgpr1, killed $vgpr0
+---
+name: func_add_constant_to_fi_divergent_i32
+tracksRegLiveness: true
+stack:
+  - { id: 0, name: alloca, type: default, offset: 0, size: 8, alignment: 4, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      local-offset: 0, debug-info-variable: '', debug-info-expression: '', 
+      debug-info-location: '' }
+machineFunctionInfo:
+  stackPtrOffsetReg: '$sgpr32'
+
+body:             |
+  bb.0 (%ir-block.0):
+    liveins: $vgpr31, $sgpr30_sgpr31
+  
+    renamable $vgpr0 = V_AND_B32_e32 1023, killed $vgpr31, implicit $exec
+    renamable $vgpr0 = V_LSHLREV_B32_e32 2, killed $vgpr0, implicit $exec
+    renamable $vgpr0 = V_ADD_CO_U32_e32 %stack.0.alloca, killed $vgpr0, implicit-def dead $vcc, implicit $exec
+    renamable $vgpr0, dead renamable $vcc = nuw V_ADD_CO_U32_e64 4, killed $vgpr0, 0, implicit $exec
+    $m0 = S_MOV_B32 -1
+    DS_WRITE_B32 undef renamable $vgpr0, killed renamable $vgpr0, 0, 0, implicit $m0, implicit $exec :: (volatile store (s32) into `i32 addrspace(5)* addrspace(3)* undef`, addrspace 3)
+    S_SETPC_B64_return killed renamable $sgpr30_sgpr31
+
+...
+# GCN-LABEL: name: func_add_constant_to_fi_uniform_i32{{$}}
+# GCN: $vcc_hi = S_LSHR_B32 6, $sgpr32, implicit-def $scc
+# GCN: $sgpr4 = nuw S_ADD_I32 killed $vcc_hi, 4
+---
+name: func_add_constant_to_fi_uniform_i32
+tracksRegLiveness: true
+stack:
+  - { id: 0, name: alloca, type: default, offset: 0, size: 8, alignment: 4, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      local-offset: 0, debug-info-variable: '', debug-info-expression: '', 
+      debug-info-location: '' }
+machineFunctionInfo:
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0 (%ir-block.0):
+    liveins: $sgpr30_sgpr31
+  
+    renamable $sgpr4 = nuw S_ADD_I32 %stack.0.alloca, 4, implicit-def dead $scc
+    renamable $vgpr0 = COPY killed renamable $sgpr4, implicit $exec
+    $m0 = S_MOV_B32 -1
+    DS_WRITE_B32 undef renamable $vgpr0, killed renamable $vgpr0, 0, 0, implicit $m0, implicit $exec :: (volatile store (s32) into `i32 addrspace(5)* addrspace(3)* undef`, addrspace 3)
+    S_SETPC_B64_return killed renamable $sgpr30_sgpr31
+
+...
+# GCN-LABEL: name: func_other_fi_user_non_inline_imm_offset_i32
+# GCN: $vcc_hi = S_LSHR_B32 $sgpr32, 6
+# GCN: $vcc_hi = S_ADD_I32 killed $vcc_hi, 512
+# GCN: $sgpr4 = S_MUL_I32 killed $vcc_hi, 9
+---
+name: func_other_fi_user_non_inline_imm_offset_i32
+tracksRegLiveness: true
+stack:
+  - { id: 0, name: alloca0, type: default, offset: 0, size: 512, alignment: 4, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      local-offset: 0, debug-info-variable: '', debug-info-expression: '', 
+      debug-info-location: '' }
+  - { id: 1, name: alloca1, type: default, offset: 0, size: 32, alignment: 4, 
+      stack-id: default, callee-saved-register: '', callee-saved-restored: true, 
+      local-offset: 512, debug-info-variable: '', debug-info-expression: '', 
+      debug-info-location: '' }
+machineFunctionInfo:
+  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
+  stackPtrOffsetReg: '$sgpr32'
+body:             |
+  bb.0 (%ir-block.0):
+    liveins: $sgpr30_sgpr31
+  
+    renamable $vgpr0 = V_MOV_B32_e32 7, implicit $exec
+    BUFFER_STORE_DWORD_OFFEN killed renamable $vgpr0, %stack.0.alloca0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 260, 0, 0, 0, implicit $exec :: (volatile store (s32) into %ir.gep0, addrspace 5)
+    renamable $sgpr4 = S_MUL_I32 %stack.1.alloca1, 9
+    renamable $vgpr0 = COPY killed renamable $sgpr4, implicit $exec
+    $m0 = S_MOV_B32 -1
+    DS_WRITE_B32 undef renamable $vgpr0, killed renamable $vgpr0, 0, 0, implicit $m0, implicit $exec :: (volatile store (s32) into `i32 addrspace(3)* undef`, addrspace 3)
+    S_SETPC_B64_return killed renamable $sgpr30_sgpr31
+
+...