[AMDGPU][LIT] Added a MIR LIT showing the SGPR spills

This MIR test case is added to seek the consumption of VGPR lanes
being used for SGPR spills during si-lower-sgpr-spills pass of
AMDGPU pass pipeline. Basically, in this pass, stack slots are
mapped to available VGPR lanes for spilling purpose, thus ending
the need for stack slots.

In current scenarion, each new SGPR spill goes into new VGPR lanes
as, being mapped from its distinct stack slots assigned during SGPR
allocation pass. It can be clearly seen in the added test case.

Author: vg0204

llvm/test/CodeGen/AMDGPU/si-lower-sgpr-spills-vgpr-lanes-usage.mir

@@ -0,0 +1,231 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 -verify-machineinstrs -stress-regalloc=3 -start-before=greedy -stop-after=si-lower-sgpr-spills -o - %s | FileCheck -check-prefix=SGPR_SPILLED %s
+
+# This file contains 3 test cases to observe the optimal stack slot usage for SGPR spills utilizing Stack Slot Coloring pass.
+# @stack-slot-share-equal-sized-spills : In this, the stack slot indices is shared among the spill stack objects of equal size.
+# @stack-slot-share-unequal-sized-spills-with-large-spill-first AND
+# @stack-slot-share-unequal-sized-spills-with-small-spill-first :
+# In the remaining 2 test cases mentioned in just above 2 lines, the stack slot indices is shared among the spill stack objects of
+# unequal size, with spill slot having the size of the largest of the stack objects sharing the common stack indices.
+
+--- |
+  define void @stack-slot-share-equal-sized-spills(ptr addrspace(1) nocapture readnone %arg, ptr addrspace(1) noalias %arg1) {
+  bb:
+    %tmp = load i32, ptr addrspace(1) null, align 4
+    call void @func(i32 undef)
+    call void @func(i32 %tmp)
+    unreachable
+  }
+
+  define void @stack-slot-share-unequal-sized-spills-with-large-spill-first(ptr addrspace(1) nocapture readnone %arg, ptr addrspace(1) noalias %arg1) {
+  bb:
+    %tmp = load i32, ptr addrspace(1) null, align 4
+    call void @func(i32 undef)
+    call void @func(i32 %tmp)
+    unreachable
+  }
+
+  define void @stack-slot-share-unequal-sized-spills-with-small-spill-first(ptr addrspace(1) nocapture readnone %arg, ptr addrspace(1) noalias %arg1) {
+  bb:
+    %tmp = load i32, ptr addrspace(1) null, align 4
+    call void @func(i32 undef)
+    call void @func(i32 %tmp)
+    unreachable
+  }
+
+  declare void @func(i32)
+...
+
+---
+name:            stack-slot-share-equal-sized-spills
+tracksRegLiveness: true
+frameInfo:
+  adjustsStack:    true
+  hasCalls:        true
+machineFunctionInfo:
+  scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
+  frameOffsetReg: $sgpr32
+  stackPtrOffsetReg: $sgpr32
+body:             |
+  bb.0:
+    ; SGPR_SPILLED-LABEL: name: stack-slot-share-equal-sized-spills
+    ; SGPR_SPILLED: liveins: $sgpr30, $sgpr31, $vgpr62
+    ; SGPR_SPILLED-NEXT: {{  $}}
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr30, 0, $vgpr62
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr31, 1, $vgpr62
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 0, [[DEF]]
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr0, 1, [[DEF]], implicit-def $sgpr0_sgpr1, implicit $sgpr0_sgpr1
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr1, 2, [[DEF]], implicit $sgpr0_sgpr1
+    ; SGPR_SPILLED-NEXT: [[DEF1:%[0-9]+]]:vreg_64 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr
+    ; SGPR_SPILLED-NEXT: renamable $sgpr4_sgpr5 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr4, 3, [[DEF]], implicit-def $sgpr4_sgpr5, implicit $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR killed $sgpr5, 4, [[DEF]], implicit killed $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 4
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit undef $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 0
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 5, [[DEF]]
+    ; SGPR_SPILLED-NEXT: $sgpr0 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 1, implicit-def $sgpr0_sgpr1
+    ; SGPR_SPILLED-NEXT: $sgpr1 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 2
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr2, 6, [[DEF]], implicit-def $sgpr2_sgpr3, implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr3, 7, [[DEF]], implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $vgpr0 = COPY [[FLAT_LOAD_DWORD]]
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 4
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit killed $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 5
+    ; SGPR_SPILLED-NEXT: $sgpr2 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 6, implicit-def $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: $sgpr3 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 7
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    %0:sreg_32_xm0 = COPY $sgpr32
+    %5:sreg_64 = COPY $sgpr0_sgpr1
+    %1:vreg_64 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, implicit $exec, implicit $flat_scr
+    %3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit undef $vgpr0
+    $sgpr32 = COPY %0
+    %4:sreg_32_xm0 = COPY $sgpr32
+    $sgpr0_sgpr1 = COPY %5
+    %6:sreg_64 = COPY $sgpr2_sgpr3
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    $vgpr0 = COPY %2
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit killed $vgpr0
+    $sgpr32 = COPY %4
+    $sgpr2_sgpr3 = COPY %6
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+...
+
+---
+name:            stack-slot-share-unequal-sized-spills-with-large-spill-first
+tracksRegLiveness: true
+frameInfo:
+  adjustsStack:    true
+  hasCalls:        true
+machineFunctionInfo:
+  scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
+  frameOffsetReg: $sgpr32
+  stackPtrOffsetReg: $sgpr32
+body:             |
+  bb.0:
+    ; SGPR_SPILLED-LABEL: name: stack-slot-share-unequal-sized-spills-with-large-spill-first
+    ; SGPR_SPILLED: liveins: $sgpr30, $sgpr31, $vgpr62
+    ; SGPR_SPILLED-NEXT: {{  $}}
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr30, 0, $vgpr62
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr31, 1, $vgpr62
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 0, [[DEF]]
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr2, 1, [[DEF]], implicit-def $sgpr2_sgpr3, implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr3, 2, [[DEF]], implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: [[DEF1:%[0-9]+]]:vreg_64 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr
+    ; SGPR_SPILLED-NEXT: renamable $sgpr4_sgpr5 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr4, 3, [[DEF]], implicit-def $sgpr4_sgpr5, implicit $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR killed $sgpr5, 4, [[DEF]], implicit killed $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 4
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit undef $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 0
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 5, [[DEF]]
+    ; SGPR_SPILLED-NEXT: $sgpr2 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 1, implicit-def $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: $sgpr3 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 2
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr2, 6, [[DEF]]
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $vgpr0 = COPY [[FLAT_LOAD_DWORD]]
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 4
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit killed $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 5
+    ; SGPR_SPILLED-NEXT: $sgpr2 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 6
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    %0:sreg_32_xm0 = COPY $sgpr32
+    %5:sreg_64 = COPY $sgpr2_sgpr3
+    %1:vreg_64 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, implicit $exec, implicit $flat_scr
+    %3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit undef $vgpr0
+    $sgpr32 = COPY %0
+    %4:sreg_32_xm0 = COPY $sgpr32
+    $sgpr2_sgpr3 = COPY %5
+    %6:sreg_32 = COPY $sgpr2
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    $vgpr0 = COPY %2
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit killed $vgpr0
+    $sgpr32 = COPY %4
+    $sgpr2 = COPY %6
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+...
+
+---
+name:            stack-slot-share-unequal-sized-spills-with-small-spill-first
+tracksRegLiveness: true
+frameInfo:
+  adjustsStack:    true
+  hasCalls:        true
+machineFunctionInfo:
+  scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3
+  frameOffsetReg: $sgpr32
+  stackPtrOffsetReg: $sgpr32
+body:             |
+  bb.0:
+    ; SGPR_SPILLED-LABEL: name: stack-slot-share-unequal-sized-spills-with-small-spill-first
+    ; SGPR_SPILLED: liveins: $sgpr30, $sgpr31, $vgpr62
+    ; SGPR_SPILLED-NEXT: {{  $}}
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr30, 0, $vgpr62
+    ; SGPR_SPILLED-NEXT: $vgpr62 = SI_SPILL_S32_TO_VGPR killed $sgpr31, 1, $vgpr62
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 0, [[DEF]]
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr0, 1, [[DEF]]
+    ; SGPR_SPILLED-NEXT: [[DEF1:%[0-9]+]]:vreg_64 = IMPLICIT_DEF
+    ; SGPR_SPILLED-NEXT: [[FLAT_LOAD_DWORD:%[0-9]+]]:vgpr_32 = FLAT_LOAD_DWORD [[DEF1]], 0, 0, implicit $exec, implicit $flat_scr
+    ; SGPR_SPILLED-NEXT: renamable $sgpr4_sgpr5 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr4, 2, [[DEF]], implicit-def $sgpr4_sgpr5, implicit $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR killed $sgpr5, 3, [[DEF]], implicit killed $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 2, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit undef $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 0
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr32, 4, [[DEF]]
+    ; SGPR_SPILLED-NEXT: $sgpr0 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 1
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr2, 5, [[DEF]], implicit-def $sgpr2_sgpr3, implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: [[DEF:%[0-9]+]]:vgpr_32 = SI_SPILL_S32_TO_VGPR $sgpr3, 6, [[DEF]], implicit $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ; SGPR_SPILLED-NEXT: $vgpr0 = COPY [[FLAT_LOAD_DWORD]]
+    ; SGPR_SPILLED-NEXT: $sgpr4 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 2, implicit-def $sgpr4_sgpr5
+    ; SGPR_SPILLED-NEXT: $sgpr5 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 3
+    ; SGPR_SPILLED-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr4_sgpr5, @func, csr_amdgpu, implicit killed $vgpr0
+    ; SGPR_SPILLED-NEXT: $sgpr32 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 4
+    ; SGPR_SPILLED-NEXT: $sgpr2 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 5, implicit-def $sgpr2_sgpr3
+    ; SGPR_SPILLED-NEXT: $sgpr3 = SI_RESTORE_S32_FROM_VGPR [[DEF]], 6
+    ; SGPR_SPILLED-NEXT: ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    %0:sreg_32_xm0 = COPY $sgpr32
+    %5:sreg_32 = COPY $sgpr0
+    %1:vreg_64 = IMPLICIT_DEF
+    %2:vgpr_32 = FLAT_LOAD_DWORD %1, 0, 0, implicit $exec, implicit $flat_scr
+    %3:sreg_64 = SI_PC_ADD_REL_OFFSET target-flags(amdgpu-rel32-lo) @func + 4, target-flags(amdgpu-rel32-hi) @func + 4, implicit-def dead $scc
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit undef $vgpr0
+    $sgpr32 = COPY %0
+    %4:sreg_32_xm0 = COPY $sgpr32
+    $sgpr0 = COPY %5
+    %6:sreg_64 = COPY $sgpr2_sgpr3
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    ADJCALLSTACKUP 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+    $vgpr0 = COPY %2
+    dead $sgpr30_sgpr31 = SI_CALL %3, @func, csr_amdgpu, implicit killed $vgpr0
+    $sgpr32 = COPY %4
+    $sgpr2_sgpr3 = COPY %6
+    ADJCALLSTACKDOWN 0, 0, implicit-def $scc, implicit-def $sgpr32, implicit $sgpr32, implicit $sgpr32
+...