# RUN: llc -march=amdgcn -mcpu=gfx902 -verify-machineinstrs -run-pass=si-form-memory-clauses %s -o - | FileCheck -check-prefix=GCN %s
# GCN-LABEL: {{^}}name: vector_clause{{$}}
# GCN: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
# GCN-NEXT: %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
# GCN-NEXT: KILL %0{{$}}
# GCN-NEXT: %5:vreg_64 = IMPLICIT_DEF
# GCN-NEXT: GLOBAL_STORE_DWORDX4 %5, %1, 0, 0, implicit $exec
---
name: vector_clause
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
%5:vreg_64 = IMPLICIT_DEF
GLOBAL_STORE_DWORDX4 %5, %1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %5, %2, 16, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %5, %3, 32, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %5, %4, 48, 0, implicit $exec
...
# This would be a valid soft clause, but there's no need for a KILL
# since the pointer uses are live beyond the end the clause.
# GCN-LABEL: {{^}}name: vector_clause_no_kill{{$}}
# GCN: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
# GCN-NEXT: %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, implicit $exec
---
name: vector_clause_no_kill
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %3, 32, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %4, 48, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: subreg_full{{$}}
# GCN: undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
# GCN-NEXT: %1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
# GCN-NEXT: %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
# GCN-NEXT: KILL %0.sub2_sub3{{$}}
# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, implicit $exec
---
name: subreg_full
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_128 }
- { id: 1, class: vreg_128 }
body: |
bb.0:
%0 = IMPLICIT_DEF
undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
%1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
%1.sub2:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
%1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: subreg_part{{$}}
# GCN: undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
# GCN-NEXT: %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
# GCN-NEXT: KILL %0.sub2_sub3{{$}}
# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, implicit $exec
---
name: subreg_part
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_128 }
- { id: 1, class: vreg_128 }
body: |
bb.0:
%0 = IMPLICIT_DEF
undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
%1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
%1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0.sub0_sub1, %1, 0, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: dead{{$}}
# GCN: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
# GCN-NEXT: KILL %0{{$}}
---
name: dead
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vreg_128 }
- { id: 2, class: vreg_128 }
- { id: 3, class: vreg_128 }
- { id: 4, class: vreg_128 }
body: |
bb.0:
%0 = IMPLICIT_DEF
dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: subreg_dead{{$}}
# GCN: undef %2.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, implicit $exec
# GCN-NEXT: dead %2.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, implicit $exec
# GCN-NEXT: KILL %0{{$}}
# GCN-NEXT: GLOBAL_STORE_DWORD %1, %2.sub0, 0, 0, implicit $exec
---
name: subreg_dead
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_64 = IMPLICIT_DEF
undef %2.sub0:vreg_64 = GLOBAL_LOAD_DWORD %0, 16, 0, implicit $exec
dead %2.sub1:vreg_64 = GLOBAL_LOAD_DWORD %0, 32, 0, implicit $exec
GLOBAL_STORE_DWORD %1, %2.sub0, 0, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: kill{{$}}
# GCN: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
# GCN-NEXT: KILL %0{{$}}
---
name: kill
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_64 = IMPLICIT_DEF
%2:vreg_64 = IMPLICIT_DEF
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 killed %1, 16, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %2, %3, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %2, %4, 16, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: indirect{{$}}
# GCN: %1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, implicit $exec
# GCN-NEXT: %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
---
name: indirect
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vreg_64 }
- { id: 2, class: vreg_128 }
- { id: 3, class: vreg_128 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1:vreg_64 = GLOBAL_LOAD_DWORDX2 %0, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 0, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %2, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %3, 16, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: stack{{$}}
# GCN: %0:vreg_64 = IMPLICIT_DEF
# GCN-NEXT: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, implicit $exec
# GCN-NEXT: GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, implicit $exec
---
name: stack
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vreg_128 }
- { id: 2, class: vreg_128 }
stack:
- { id: 0, type: default, offset: 0, size: 64, alignment: 8 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %stack.0, 16, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %1, 0, 0, implicit $exec
GLOBAL_STORE_DWORDX4 %0, %2, 16, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: overflow_counter{{$}}
# GCN: dead %2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec
# GCN-NEXT: dead %3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec
# GCN-NEXT: dead %4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, implicit $exec
# GCN-NEXT: dead %5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, implicit $exec
# GCN-NEXT: dead %6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, implicit $exec
# GCN-NEXT: dead %7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, implicit $exec
# GCN-NEXT: dead %8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, implicit $exec
# GCN-NEXT: dead %9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, implicit $exec
# GCN-NEXT: dead %10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, implicit $exec
# GCN-NEXT: dead %11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, implicit $exec
# GCN-NEXT: dead %12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, implicit $exec
# GCN-NEXT: dead %13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, implicit $exec
# GCN-NEXT: dead %14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, implicit $exec
# GCN-NEXT: dead %15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, implicit $exec
# GCN-NEXT: dead %16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, implicit $exec
# GCN-NEXT: KILL %0{{$}}
# GCN-NEXT: dead %17:vgpr_32 = GLOBAL_LOAD_DWORD %1, 60, 0, implicit $exec
# GCN-NEXT: dead %18:vgpr_32 = GLOBAL_LOAD_DWORD %1, 64, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
---
name: overflow_counter
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_64 = IMPLICIT_DEF
%2:vgpr_32 = GLOBAL_LOAD_DWORD %0, 0, 0, implicit $exec
%3:vgpr_32 = GLOBAL_LOAD_DWORD %0, 4, 0, implicit $exec
%4:vgpr_32 = GLOBAL_LOAD_DWORD %0, 8, 0, implicit $exec
%5:vgpr_32 = GLOBAL_LOAD_DWORD %0, 12, 0, implicit $exec
%6:vgpr_32 = GLOBAL_LOAD_DWORD %0, 16, 0, implicit $exec
%7:vgpr_32 = GLOBAL_LOAD_DWORD %0, 20, 0, implicit $exec
%8:vgpr_32 = GLOBAL_LOAD_DWORD %0, 24, 0, implicit $exec
%9:vgpr_32 = GLOBAL_LOAD_DWORD %0, 28, 0, implicit $exec
%10:vgpr_32 = GLOBAL_LOAD_DWORD %0, 32, 0, implicit $exec
%11:vgpr_32 = GLOBAL_LOAD_DWORD %0, 36, 0, implicit $exec
%12:vgpr_32 = GLOBAL_LOAD_DWORD %0, 40, 0, implicit $exec
%13:vgpr_32 = GLOBAL_LOAD_DWORD %0, 44, 0, implicit $exec
%14:vgpr_32 = GLOBAL_LOAD_DWORD %0, 48, 0, implicit $exec
%15:vgpr_32 = GLOBAL_LOAD_DWORD %0, 52, 0, implicit $exec
%16:vgpr_32 = GLOBAL_LOAD_DWORD %0, 56, 0, implicit $exec
%17:vgpr_32 = GLOBAL_LOAD_DWORD %1, 60, 0, implicit $exec
%18:vgpr_32 = GLOBAL_LOAD_DWORD %1, 64, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: reg_pressure{{$}}
# GCN: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
# GCN-NEXT: dead %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
# GCN-NEXT: dead %6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, implicit $exec
# GCN-NEXT: KILL %0{{$}}
# GCN-NEXT: dead %7:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 80, 0, implicit $exec
# GCN-NEXT: dead %8:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 96, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
---
name: reg_pressure
tracksRegLiveness: true
body: |
bb.0:
%0:vreg_64 = IMPLICIT_DEF
%1:vreg_64 = IMPLICIT_DEF
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
%5:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 48, 0, implicit $exec
%6:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 64, 0, implicit $exec
%7:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 80, 0, implicit $exec
%8:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 96, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: image_clause{{$}}
# GCN: %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
# GCN-NEXT: %4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
# GCN-NEXT: %5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
# GCN-NEXT: KILL undef %2:sgpr_128{{$}}
# GCN-NEXT: IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec
---
name: image_clause
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: sgpr_256 }
- { id: 2, class: sgpr_128 }
- { id: 3, class: vreg_128 }
- { id: 4, class: vreg_128 }
- { id: 5, class: vreg_128 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1 = IMPLICIT_DEF
%3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load (s128))
%4:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load (s128))
%5:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, undef %2:sgpr_128, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load (s128))
IMAGE_STORE_V4_V2 %3, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store (s128))
IMAGE_STORE_V4_V2 %4, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store (s128))
IMAGE_STORE_V4_V2 %5, %0, %1, 15, -1, 0, 0, 0, 0, 0, 0, implicit $exec :: (store (s128))
...
# GCN-LABEL: {{^}}name: mixed_clause{{$}}
# GCN: dead %3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: dead %5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
# GCN-NEXT: KILL %2{{$}}
# GCN-NEXT: KILL %0{{$}}
---
name: mixed_clause
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: sgpr_256 }
- { id: 2, class: sgpr_128 }
- { id: 3, class: vreg_128 }
- { id: 4, class: vreg_128 }
- { id: 5, class: vgpr_32 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1 = IMPLICIT_DEF
%2 = IMPLICIT_DEF
%3:vreg_128 = IMAGE_SAMPLE_LZ_V4_V2 %0, %1, %2, 15, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load (s128))
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%5:vgpr_32 = BUFFER_LOAD_DWORD_OFFSET %2, 0, 0, 0, 0, 0, implicit $exec
...
# GCN-LABEL: {{^}}name: atomic{{$}}
# GCN: %1:vgpr_32 = IMPLICIT_DEF
# GCN-NEXT: dead %2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 2, implicit $exec, implicit $flat_scr
# GCN-NEXT: dead %3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 2, implicit $exec, implicit $flat_scr
# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
# GCN-NEXT: FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
# GCN-NEXT: S_ENDPGM 0
---
name: atomic
tracksRegLiveness: true
registers:
- { id: 0, class: vreg_64 }
- { id: 1, class: vgpr_32 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: vgpr_32 }
body: |
bb.0:
%0 = IMPLICIT_DEF
%1 = IMPLICIT_DEF
%2:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 2, implicit $exec, implicit $flat_scr
%3:vgpr_32 = FLAT_ATOMIC_ADD_RTN %0, %1, 0, 2, implicit $exec, implicit $flat_scr
FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
FLAT_ATOMIC_ADD %0, %1, 0, 0, implicit $exec, implicit $flat_scr
S_ENDPGM 0
...
# One of the pointers has an additional use after the clause, but one
# doesn't. Only the final use should be killed.
# GCN-LABEL: {{^}}name: ptr_use_after_clause{{$}}
# GCN: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
# GCN-NEXT: dead %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 48, 0, implicit $exec
# GCN-NEXT: KILL %1{{$}}
# GCN-NEXT: S_NOP 0, implicit %0
---
name: ptr_use_after_clause
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
%0:vreg_64 = COPY $vgpr0_vgpr1
%1:vreg_64 = COPY $vgpr2_vgpr3
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 16, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 32, 0, implicit $exec
%5:vreg_128 = GLOBAL_LOAD_DWORDX4 %1, 48, 0, implicit $exec
S_NOP 0, implicit %0
...
# Only part of the register is really live past the clause.
# GCN-LABEL: {{^}}name: ptr_use_after_clause_subreg{{$}}
# GCN: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 48, 0, implicit $exec
# GCN-NEXT: KILL %0.sub2_sub3{{$}}
# GCN-NEXT: S_NOP 0, implicit %0.sub0_sub1{{$}}
---
name: ptr_use_after_clause_subreg
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
%0:vreg_128 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 48, 0, implicit $exec
S_NOP 0, implicit %0.sub0_sub1
...
# More complex situation where only some of the use subregisters live
# beyond the clause.
# GCN-LABEL: {{^}}name: ptr_use_after_clause_subreg_multi{{$}}
# GCN: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub3_sub4, 32, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub6_sub7, 48, 0, implicit $exec
# GCN-NEXT: KILL %0.sub2_sub3_sub4, %0.sub7{{$}}
# GCN-NEXT: S_NOP 0, implicit %0.sub0_sub1, implicit %0.sub5_sub6
---
name: ptr_use_after_clause_subreg_multi
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
%0:vreg_256 = COPY $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub3_sub4, 32, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub6_sub7, 48, 0, implicit $exec
S_NOP 0, implicit %0.sub0_sub1, implicit %0.sub5_sub6
...
# Have subranges, but none of them are killed
# GCN-LABEL: {{^}}name: no_killed_subranges{{$}}
# GCN: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
# GCN-NEXT: dead %3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
# GCN-NEXT: dead %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 48, 0, implicit $exec
# GCN-NEXT: S_NOP 0, implicit %0.sub0_sub1{{$}}
# GCN-NEXT: S_NOP 0, implicit %0.sub2_sub3{{$}}
---
name: no_killed_subranges
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
%0:vreg_128 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 16, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub2_sub3, 48, 0, implicit $exec
S_NOP 0, implicit %0.sub0_sub1
S_NOP 0, implicit %0.sub2_sub3
...
# sub2 is undef at entry to the soft clause. It should not be have its
# live range extended.
# GCN-LABEL: name: no_killed_undef_subrange_use
# GCN: dead %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: dead %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
# GCN-NEXT: KILL %0.sub0_sub1{{$}}
# GCN-NEXT: %0.sub2:vreg_128 = V_MOV_B32_e32 0, implicit $exec
# GCN-NEXT: S_NOP 0, implicit %0.sub2
---
name: no_killed_undef_subrange_use
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1
undef %0.sub0_sub1:vreg_128 = COPY $vgpr0_vgpr1
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 0, 0, implicit $exec
%3:vreg_128 = GLOBAL_LOAD_DWORDX4 %0.sub0_sub1, 32, 0, implicit $exec
%0.sub2:vreg_128 = V_MOV_B32_e32 0, implicit $exec
S_NOP 0, implicit %0.sub2
...
# Make sure intervening implicit_defs are not treated as breaking the
# clause
#
# GCN-LABEL: {{^}}name: implicit_def_no_break{{$}}
# GCN: %1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
# GCN-NEXT: %2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
# GCN-NEXT: %3:vreg_64 = IMPLICIT_DEF
# GCN-NEXT: %4:vreg_128 = GLOBAL_LOAD_DWORDX4 %3, 32, 0, implicit $exec
# GCN-NEXT: %5:vreg_128 = GLOBAL_LOAD_DWORDX4 %3, 48, 0, implicit $exec
# GCN-NEXT: KILL %3{{$}}
# GCN-NEXT: KILL %0{{$}}
---
name: implicit_def_no_break
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1
%0:vreg_64 = COPY $vgpr0_vgpr1
%1:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 0, 0, implicit $exec
%2:vreg_128 = GLOBAL_LOAD_DWORDX4 %0, 16, 0, implicit $exec
%3:vreg_64 = IMPLICIT_DEF
%4:vreg_128 = GLOBAL_LOAD_DWORDX4 %3, 32, 0, implicit $exec
%5:vreg_128 = GLOBAL_LOAD_DWORDX4 %3, 48, 0, implicit $exec
S_NOP 0, implicit %1, implicit %2, implicit %4, implicit %5
...
# GCN-LABEL: {{^}}name: kill_part_subreg{{$}}
# GCN: undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
# GCN-NEXT: %1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
# GCN-NEXT: %1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
# GCN-NEXT: KILL %0.sub0_sub1_sub2, %0.sub3
---
name: kill_part_subreg
tracksRegLiveness: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3
%0:vreg_128 = COPY $vgpr0_vgpr1_vgpr2_vgpr3
undef %1.sub0:vreg_128 = GLOBAL_LOAD_DWORD %0.sub0_sub1, 0, 0, implicit $exec
%1.sub1:vreg_128 = GLOBAL_LOAD_DWORD %0.sub1_sub2, 16, 0, implicit $exec
%1.sub3:vreg_128 = GLOBAL_LOAD_DWORD %0.sub2_sub3, 32, 0, implicit $exec
S_NOP 0, implicit %1
...
# GCN-LABEL: {{^}}name: mem_clause_sreg256_used_stack{{$}}
# GCN: undef %0.sub7:sgpr_256 = S_LOAD_DWORD_IMM undef %1:sgpr_64(p4), 8, 0
# GCN-NEXT: dead %0.sub3:sgpr_256 = S_LOAD_DWORD_IMM undef %1:sgpr_64(p4), 24, 0
# GCN-NEXT: KILL undef %1
---
name: mem_clause_sreg256_used_stack
stack:
- { id: 0, type: default, offset: 0, size: 40, alignment: 8 }
machineFunctionInfo:
isEntryFunction: true
scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
stackPtrOffsetReg: '$sgpr32'
body: |
bb.0:
undef %0.sub7:sgpr_256 = S_LOAD_DWORD_IMM undef %1:sgpr_64(p4), 8, 0
%0.sub3:sgpr_256 = S_LOAD_DWORD_IMM undef %1:sgpr_64(p4), 24, 0
S_ENDPGM 0
...