llvm/test/CodeGen/AMDGPU/swdev502267-use-after-free-last-chance-recoloring-alloc-succeeds.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx942 -stress-regalloc=4 -verify-regalloc -start-before=greedy,2 -stop-after=virtregrewriter,2 -o - %s | FileCheck %s

# This testcase hit a situation where greedy would hit a use after
# free during last chance recoloring. This case successfully allocates
# after, but is extremely sensitive to the exact allocation ordering.

---
name:            swdev502267_use_after_free_last_chance_recoloring_alloc_succeeds
tracksRegLiveness: true
stack:
  - { id: 0, size: 16 }
machineFunctionInfo:
  scratchRSrcReg:  '$sgpr0_sgpr1_sgpr2_sgpr3'
  frameOffsetReg:  '$sgpr33'
  stackPtrOffsetReg: '$sgpr32'
body:             |
  ; CHECK-LABEL: name: swdev502267_use_after_free_last_chance_recoloring_alloc_succeeds
  ; CHECK: bb.0:
  ; CHECK-NEXT:   successors: %bb.2(0x40000000), %bb.1(0x40000000)
  ; CHECK-NEXT:   liveins: $vgpr0_vgpr1_vgpr2_vgpr3
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   renamable $vgpr4_vgpr5 = IMPLICIT_DEF
  ; CHECK-NEXT:   renamable $vgpr6_vgpr7_vgpr8_vgpr9 = GLOBAL_LOAD_DWORDX4 killed renamable $vgpr4_vgpr5, 0, 0, implicit $exec :: (volatile load (s128), addrspace 1)
  ; CHECK-NEXT:   renamable $vgpr4 = V_FMA_F32_e64 0, $vgpr6, 0, $vgpr6, 0, $vgpr3, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   renamable $vgpr5 = V_FMA_F32_e64 0, $vgpr7, 0, $vgpr7, 0, $vgpr2, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   SI_SPILL_AV128_SAVE $vgpr6_vgpr7_vgpr8_vgpr9, %stack.2, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr6 = V_FMA_F32_e64 0, killed $vgpr8, 0, $vgpr8, 0, $vgpr1, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   renamable $vgpr7 = IMPLICIT_DEF
  ; CHECK-NEXT:   S_CBRANCH_EXECZ %bb.2, implicit $exec
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.1:
  ; CHECK-NEXT:   successors: %bb.2(0x80000000)
  ; CHECK-NEXT:   liveins: $vgpr0_vgpr1_vgpr2_vgpr3:0x00000000000000FF, $vgpr4_vgpr5_vgpr6_vgpr7:0x00000000000000FF
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   SI_SPILL_AV128_SAVE killed $vgpr0_vgpr1_vgpr2_vgpr3, %stack.1, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.1, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr0_vgpr1_vgpr2_vgpr3 = SI_SPILL_V128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr0 = V_FMA_F32_e64 0, $vgpr6, 0, $vgpr6, 0, killed $vgpr2, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   SI_SPILL_V128_SAVE $vgpr4_vgpr5_vgpr6_vgpr7, %stack.4, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.4, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr0 = V_TRUNC_F32_e32 killed $vgpr0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   SI_SPILL_V32_SAVE killed $vgpr0, %stack.3, $sgpr32, 0, implicit $exec :: (store (s32) into %stack.3, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr0 = IMPLICIT_DEF
  ; CHECK-NEXT:   renamable $vgpr2_vgpr3_vgpr4_vgpr5 = SI_SPILL_V128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr5 = nofpexcept V_DIV_FIXUP_F32_e64 0, killed $vgpr0, 0, killed $vgpr7, 0, killed $vgpr5, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   renamable $vgpr0 = SI_SPILL_V32_RESTORE %stack.3, $sgpr32, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr9 = COPY killed renamable $vgpr5
  ; CHECK-NEXT:   renamable $vgpr4_vgpr5_vgpr6_vgpr7 = SI_SPILL_V128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr2_vgpr3_vgpr4_vgpr5 = SI_SPILL_V128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr8 = nofpexcept V_FMA_F32_e64 1, killed $vgpr0, 0, killed $vgpr6, 0, killed $vgpr4, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   renamable $vgpr2_vgpr3 = COPY killed renamable $vgpr8_vgpr9
  ; CHECK-NEXT:   renamable $vgpr0 = IMPLICIT_DEF
  ; CHECK-NEXT:   renamable $vgpr4_vgpr5_vgpr6_vgpr7 = SI_SPILL_V128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr6_vgpr7_vgpr8_vgpr9 = SI_SPILL_V128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr0 = nofpexcept V_DIV_FIXUP_F32_e64 0, killed $vgpr0, 0, killed $vgpr4, 0, killed $vgpr6, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   renamable $vgpr4_vgpr5_vgpr6_vgpr7 = SI_SPILL_V128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr6_vgpr7_vgpr8_vgpr9 = SI_SPILL_V128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5)
  ; CHECK-NEXT:   dead renamable $vgpr1 = V_FMA_F32_e64 0, killed $vgpr5, 0, $vgpr5, 0, killed $vgpr7, 0, 0, implicit $mode, implicit $exec
  ; CHECK-NEXT:   dead renamable $vgpr4_vgpr5_vgpr6_vgpr7 = SCRATCH_LOAD_DWORDX4_SADDR %stack.0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load (s128), addrspace 5)
  ; CHECK-NEXT:   renamable $vgpr4_vgpr5 = IMPLICIT_DEF
  ; CHECK-NEXT:   GLOBAL_STORE_DWORDX4 killed renamable $vgpr4_vgpr5, renamable $vgpr0_vgpr1_vgpr2_vgpr3, 0, 0, implicit $exec :: (volatile store (s128), addrspace 1)
  ; CHECK-NEXT:   renamable $vgpr0_vgpr1_vgpr2_vgpr3 = SI_SPILL_AV128_RESTORE %stack.1, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.1, align 4, addrspace 5)
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT: bb.2:
  ; CHECK-NEXT:   liveins: $vgpr0_vgpr1_vgpr2_vgpr3:0x00000000000000FF
  ; CHECK-NEXT: {{  $}}
  ; CHECK-NEXT:   SI_RETURN implicit $vgpr0_vgpr1_vgpr2_vgpr3
  bb.0:
    liveins: $vgpr0_vgpr1_vgpr2_vgpr3

    %0:vreg_128_align2 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
    %1:vreg_64_align2 = IMPLICIT_DEF
    %2:vgpr_32 = IMPLICIT_DEF
    %3:vreg_128_align2 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, implicit $exec :: (volatile load (s128), addrspace 1)
    undef %4.sub0:vreg_128_align2 = V_FMA_F32_e64 0, %3.sub0, 0, %3.sub0, 0, %0.sub3, 0, 0, implicit $mode, implicit $exec
    %4.sub1:vreg_128_align2 = V_FMA_F32_e64 0, %3.sub1, 0, %3.sub1, 0, %0.sub2, 0, 0, implicit $mode, implicit $exec
    %4.sub2:vreg_128_align2 = V_FMA_F32_e64 0, %3.sub2, 0, %3.sub2, 0, %0.sub1, 0, 0, implicit $mode, implicit $exec
    %4.sub3:vreg_128_align2 = IMPLICIT_DEF
    S_CBRANCH_EXECZ %bb.2, implicit $exec

  bb.1:
    %5:vgpr_32 = V_FMA_F32_e64 0, %4.sub2, 0, %4.sub2, 0, %3.sub2, 0, 0, implicit $mode, implicit $exec
    %6:vgpr_32 = V_TRUNC_F32_e32 %5, implicit $mode, implicit $exec
    undef %7.sub3:vreg_128_align2 = nofpexcept V_DIV_FIXUP_F32_e64 0, %2, 0, %4.sub3, 0, %3.sub3, 0, 0, implicit $mode, implicit $exec
    %7.sub2:vreg_128_align2 = nofpexcept V_FMA_F32_e64 1, %6, 0, %4.sub2, 0, %3.sub2, 0, 0, implicit $mode, implicit $exec
    %7.sub0:vreg_128_align2 = nofpexcept V_DIV_FIXUP_F32_e64 0, %2, 0, %4.sub0, 0, %3.sub0, 0, 0, implicit $mode, implicit $exec
    %8:vgpr_32 = V_FMA_F32_e64 0, %4.sub1, 0, %4.sub1, 0, %3.sub1, 0, 0, implicit $mode, implicit $exec
    %9:vreg_128_align2 = SCRATCH_LOAD_DWORDX4_SADDR %stack.0, 0, 0, implicit $exec, implicit $flat_scr :: (volatile load (s128), addrspace 5)
    GLOBAL_STORE_DWORDX4 %1, %7, 0, 0, implicit $exec :: (volatile store (s128), addrspace 1)

  bb.2:
    $vgpr0_vgpr1_vgpr2_vgpr3 = COPY %0
    SI_RETURN implicit $vgpr0_vgpr1_vgpr2_vgpr3

...