Index: llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
===================================================================
--- llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
+++ llvm/lib/Target/AMDGPU/SIRegisterInfo.cpp
@@ -697,8 +697,10 @@
   unsigned Opc = (IsStore ^ TRI->isVGPR(MRI, Reg)) ? AMDGPU::V_ACCVGPR_WRITE_B32
                                                    : AMDGPU::V_ACCVGPR_READ_B32;
 
-  return BuildMI(*MBB, MI, MI->getDebugLoc(), TII->get(Opc), Dst)
-           .addReg(Src, getKillRegState(IsKill));
+  auto MIB = BuildMI(*MBB, MI, MI->getDebugLoc(), TII->get(Opc), Dst)
+               .addReg(Src, getKillRegState(IsKill));
+  MIB->setAsmPrinterFlag(MachineInstr::ReloadReuse);
+  return MIB;
 }
 
 // This differs from buildSpillLoadStore by only scavenging a VGPR. It does not
@@ -870,10 +872,12 @@
           RS->setRegUsed(TmpReg);
         }
         if (IsStore) {
-          auto AccRead = BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_ACCVGPR_READ_B32), TmpReg)
+          auto AccRead = BuildMI(*MBB, MI, DL,
+                                 TII->get(AMDGPU::V_ACCVGPR_READ_B32), TmpReg)
             .addReg(SubReg, getKillRegState(IsKill));
           if (NeedSuperRegDef)
             AccRead.addReg(ValueReg, RegState::ImplicitDefine);
+          AccRead->setAsmPrinterFlag(MachineInstr::ReloadReuse);
         }
         SubReg = TmpReg;
       }
@@ -907,10 +911,12 @@
       if (!IsAGPR && NeedSuperRegDef)
         MIB.addReg(ValueReg, RegState::ImplicitDefine);
 
-      if (!IsStore && TmpReg != AMDGPU::NoRegister)
+      if (!IsStore && TmpReg != AMDGPU::NoRegister) {
         MIB = BuildMI(*MBB, MI, DL, TII->get(AMDGPU::V_ACCVGPR_WRITE_B32),
                       FinalReg)
           .addReg(TmpReg, RegState::Kill);
+        MIB->setAsmPrinterFlag(MachineInstr::ReloadReuse);
+      }
     } else {
       if (NeedSuperRegDef)
         MIB.addReg(ValueReg, RegState::ImplicitDefine);
Index: llvm/test/CodeGen/AMDGPU/spill-agpr.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/spill-agpr.ll
+++ llvm/test/CodeGen/AMDGPU/spill-agpr.ll
@@ -5,10 +5,10 @@
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; A2V-NOT:    SCRATCH_RSRC
-; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a0
+; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a0 ; Reload Reuse
 ; A2M:        buffer_store_dword v[[VSPILL]], off, s[{{[0-9:]+}}], 0 offset:[[FI:[0-9]+]] ; 4-byte Folded Spill
 ; A2M:        buffer_load_dword v[[VSPILL:[0-9]+]], off, s[{{[0-9:]+}}], 0 offset:[[FI]] ; 4-byte Folded Reload
-; GFX908:     v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]]
+; GFX908:     v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]] ; Reload Reuse
 ; A2V:        ScratchSize: 0
 define amdgpu_kernel void @max_24regs_32a_used(<16 x float> addrspace(1)* %arg, float addrspace(1)* %out) #0 {
 bb:
@@ -34,10 +34,10 @@
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; A2V-NOT:    SCRATCH_RSRC
-; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a{{[0-9]+}}
+; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a{{[0-9]+}} ; Reload Reuse
 ; A2M:        buffer_store_dword v[[VSPILL]], off, s[{{[0-9:]+}}], 0 offset:[[FI:[0-9]+]] ; 4-byte Folded Spill
 ; A2M:        buffer_load_dword v[[VSPILL:[0-9]+]], off, s[{{[0-9:]+}}], 0 offset:[[FI]] ; 4-byte Folded Reload
-; A2V:        v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]]
+; A2V:        v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]] ; Reload Reuse
 ; A2V:        ScratchSize: 0
 define amdgpu_kernel void @max_12regs_13a_used(i32 %cond, <4 x float> addrspace(1)* %arg, <4 x float> addrspace(1)* %out) #2 {
 bb:
@@ -55,8 +55,7 @@
 st:
   %gep1 = getelementptr <4 x float>, <4 x float> addrspace(1)* %out, i64 16
   %gep2 = getelementptr <4 x float>, <4 x float> addrspace(1)* %out, i64 32
-  store <4 x float> %mai.1, <4 x float> addrspace(1)* %gep1
-  store <4 x float> %mai.2, <4 x float> addrspace(1)* %gep2
+  call void asm sideeffect "", "a,a"(<4 x float> %mai.1, <4 x float> %mai.2)
   ret void
 }
 
@@ -65,25 +64,20 @@
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; A2V-NOT:    SCRATCH_RSRC
 
-; A2V: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a{{[0-9]+}}
-; A2V: v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]]
+; A2V: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a{{[0-9]+}} ; Reload Reuse
+; A2V: v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]] ; Reload Reuse
 ; A2V: ScratchSize: 0
 
 ; A2M: buffer_store_dword v[[VSPILLSTORE:[0-9]+]], off, s[{{[0-9:]+}}], 0 offset:[[FI:[0-9]+]] ; 4-byte Folded Spill
 ; A2M: buffer_load_dword v[[VSPILL_RELOAD:[0-9]+]], off, s[{{[0-9:]+}}], 0 offset:[[FI]] ; 4-byte Folded Reload
-; A2M: v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL_RELOAD]]
+; A2M: v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL_RELOAD]] ; Reload Reuse
 define amdgpu_kernel void @max_10_vgprs_used_9a() #1 {
-  %v0 = load volatile i32, i32 addrspace(3)* undef
-  %v1 = load volatile i32, i32 addrspace(3)* undef
-  %v2 = load volatile i32, i32 addrspace(3)* undef
-  %v3 = load volatile i32, i32 addrspace(3)* undef
-  %v4 = load volatile i32, i32 addrspace(3)* undef
-  %v5 = load volatile i32, i32 addrspace(3)* undef
-  %v6 = load volatile i32, i32 addrspace(3)* undef
-  %v7 = load volatile i32, i32 addrspace(3)* undef
-  call void asm sideeffect "", "a,a,a,a,~{v0},~{v1},~{v2},~{v3},~{v4},~{v5},~{v6}"(i32 %v0, i32 %v1, i32 %v2, i32 %v3)
-  %v8 = load volatile i32, i32 addrspace(3)* undef
-  call void asm sideeffect "", "a,a,a,a,a"(i32 %v4, i32 %v5, i32 %v6, i32 %v7, i32 %v8)
+  %a1 = call <4 x i32> asm sideeffect "", "=a"()
+  %a2 = call <4 x i32> asm sideeffect "", "=a"()
+  %a3 = call i32 asm sideeffect "", "=a"()
+  %a4 = call <2 x i32> asm sideeffect "", "=a"()
+  call void asm sideeffect "", "a,a,a"(<4 x i32> %a1, <4 x i32> %a2, i32 %a3)
+  call void asm sideeffect "", "a"(<2 x i32> %a4)
   ret void
 }
 
@@ -91,10 +85,10 @@
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; A2M-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; A2V-NOT:    SCRATCH_RSRC
-; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a0
+; GFX908-DAG: v_accvgpr_read_b32 v[[VSPILL:[0-9]+]], a0 ; Reload Reuse
 ; A2M:        buffer_store_dword v[[VSPILL]], off, s[{{[0-9:]+}}], 0 offset:[[FI:[0-9]+]] ; 4-byte Folded Spill
 ; A2M:        buffer_load_dword v[[VSPILL:[0-9]+]], off, s[{{[0-9:]+}}], 0 offset:[[FI]] ; 4-byte Folded Reload
-; GFX908:     v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]]
+; GFX908:     v_accvgpr_write_b32 a{{[0-9]+}}, v[[VSPILL]] ; Reload Reuse
 ; A2V:        ScratchSize: 0
 define amdgpu_kernel void @max_32regs_mfma32(float addrspace(1)* %arg) #3 {
 bb:
@@ -115,6 +109,6 @@
 declare <32 x float> @llvm.amdgcn.mfma.f32.32x32x1f32(float, float, <32 x float>, i32, i32, i32)
 
 attributes #0 = { nounwind "amdgpu-num-vgpr"="24" }
-attributes #1 = { nounwind "amdgpu-num-vgpr"="8" }
+attributes #1 = { nounwind "amdgpu-num-vgpr"="10" }
 attributes #2 = { nounwind "amdgpu-num-vgpr"="12" }
 attributes #3 = { nounwind "amdgpu-num-vgpr"="32" }
Index: llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
===================================================================
--- llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
+++ llvm/test/CodeGen/AMDGPU/spill-vgpr-to-agpr.ll
@@ -5,15 +5,15 @@
 ; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; GFX900-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; GFX908-NOT: SCRATCH_RSRC
-; GFX908-DAG: v_accvgpr_write_b32 a0, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}}
+; GFX908-DAG: v_accvgpr_write_b32 a0, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}} ; Reload Reuse
 ; GFX900:     buffer_store_dword v{{[0-9]}},
 ; GFX900:     buffer_store_dword v{{[0-9]}},
 ; GFX900:     buffer_load_dword v{{[0-9]}},
 ; GFX900:     buffer_load_dword v{{[0-9]}},
 ; GFX908-NOT: buffer_
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a0
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a0 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1 ; Reload Reuse
 
 ; GCN:    NumVgprs: 10
 ; GFX900: ScratchSize: 12
@@ -59,10 +59,10 @@
 ; GCN-LABEL: {{^}}max_10_vgprs_used_9a:
 ; GFX908-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; GFX908-DAG: s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
-; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
+; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}} ; Reload Reuse
 ; GFX908:     buffer_store_dword v{{[0-9]}},
 ; GFX908-NOT: buffer_
-; GFX908:     v_accvgpr_read_b32 v{{[0-9]}}, a9
+; GFX908:     v_accvgpr_read_b32 v{{[0-9]}}, a9 ; Reload Reuse
 ; GFX908:     buffer_load_dword v{{[0-9]}},
 ; GFX908-NOT: buffer_
 
@@ -113,28 +113,28 @@
 ; GCN-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; GCN-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
 ; GFX908-DAG: v_accvgpr_write_b32 a0, 1
-; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a2, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a3, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a4, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a5, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a6, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a7, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a8, v{{[0-9]}}
-; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
+; GFX908-DAG: v_accvgpr_write_b32 a1, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a2, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a3, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a4, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a5, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a6, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a7, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a8, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}} ; Reload Reuse
 ; GFX900:     buffer_store_dword v{{[0-9]}},
 ; GCN-DAG:    buffer_store_dword v{{[0-9]}},
 ; GFX900:     buffer_load_dword v{{[0-9]}},
 ; GCN-DAG:    buffer_load_dword v{{[0-9]}},
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a2
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a3
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a4
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a5
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a6
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a7
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a8
-; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a9
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a1 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a2 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a3 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a4 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a5 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a6 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a7 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a8 ; Reload Reuse
+; GFX908-DAG: v_accvgpr_read_b32 v{{[0-9]}}, a9 ; Reload Reuse
 
 ; GCN:    NumVgprs: 10
 ; GFX900: ScratchSize: 44
@@ -166,8 +166,8 @@
 ; GCN-LABEL: {{^}}max_10_vgprs_spill_v32:
 ; GCN-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD0
 ; GCN-DAG:    s_mov_b32 s{{[0-9]+}}, SCRATCH_RSRC_DWORD1
-; GFX908-DAG: v_accvgpr_write_b32 a0,
-; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}}
+; GFX908-DAG: v_accvgpr_write_b32 a0, v{{[0-9]}} ; Reload Reuse
+; GFX908-DAG: v_accvgpr_write_b32 a9, v{{[0-9]}} ; Reload Reuse
 ; GCN-NOT:    a10
 ; GCN:        buffer_store_dword v{{[0-9]}},