shylie/llvm-project
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/fold-operands-frame-index.mir
Changpeng Fang 32161e9de3
[AMDGPU] Do not fold an immediate into instructions with frame indexes (#151263) 
Do not fold an immediate into an instruction that already has a frame
index operand. A frame index could possibly turn out to be another immediate.

Fixes: SWDEV-536263

---------

Co-authored-by: Matt Arsenault <arsenm2@gmail.com>
2025-08-06 11:47:37 -07:00

678 lines
25 KiB
YAML
Raw Permalink Blame History

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5
# RUN: llc -mtriple=amdgcn -mcpu=gfx900 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX9 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1030 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX10 %s
# RUN: llc -mtriple=amdgcn -mcpu=gfx1200 -mattr=+wavefrontsize64 -verify-machineinstrs -run-pass=si-fold-operands %s -o - | FileCheck -check-prefixes=CHECK,GFX12 %s
---
name: fold_frame_index__s_add_i32__fi_const
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_const
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 128, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_I32 %0, 128, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__const_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__const_fi
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 128, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_I32 128, %0, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__materializedconst_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__materializedconst_fi
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 256, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 256
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_materializedconst_0
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_materializedconst_0
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 256
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, [[S_MOV_B32_]], implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_MOV_B32 256
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_materializedconst_1
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_materializedconst_1
; CHECK: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 256, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 256
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__reg_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: fold_frame_index__s_add_i32__reg_fi
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr4
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = COPY $sgpr4
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %0, %1, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_i32__fi_reg
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr4
; CHECK-LABEL: name: fold_frame_index__s_add_i32__fi_reg
; CHECK: liveins: $sgpr4
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr4
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, [[COPY]], implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = COPY $sgpr4
%1:sreg_32 = S_MOV_B32 %stack.0
%2:sreg_32 = S_ADD_I32 %1, %0, implicit-def $scc
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e32__const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e32__const_v_fi
; CHECK: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 128, %stack.0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e32 128, %0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e32__materialized_v_const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e32__materialized_v_const_v_fi
; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 128, implicit $exec
; CHECK-NEXT: [[V_ADD_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e32 %stack.0, [[V_MOV_B32_e32_]], implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_MOV_B32_e32 128, implicit $exec
%2:vgpr_32 = V_ADD_U32_e32 %1, %0, implicit $exec
$sgpr4 = COPY %2
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e64__imm_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e64__imm_v_fi
; CHECK: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 64, %stack.0, 0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e64 64, %0, 0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_u32_e64___v_fi_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_u32_e64___v_fi_imm
; CHECK: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 64, 0, implicit $exec
; CHECK-NEXT: $sgpr4 = COPY [[V_ADD_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_U32_e64 %0, 64, 0, implicit $exec
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__v_add_co_u32_e32__const_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e32__const_v_fi
; CHECK: [[V_ADD_CO_U32_e32_:%[0-9]+]]:vgpr_32 = V_ADD_CO_U32_e32 128, %stack.0, implicit-def $vcc, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e32_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32 = V_ADD_CO_U32_e32 128, %0, implicit-def $vcc, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: fold_frame_index__v_add_co_u32_e64__v_fi_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__v_fi_imm
; CHECK: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64 = V_ADD_CO_U32_e64 %stack.0, 64, 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32, %2:sreg_64 = V_ADD_CO_U32_e64 %0, 64, 0, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: fold_frame_index__v_add_co_u32_e64__imm_v_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__v_add_co_u32_e64__imm_v_fi
; CHECK: [[V_ADD_CO_U32_e64_:%[0-9]+]]:vgpr_32, [[V_ADD_CO_U32_e64_1:%[0-9]+]]:sreg_64 = V_ADD_CO_U32_e64 64, %stack.0, 0, implicit $exec
; CHECK-NEXT: $vgpr0 = COPY [[V_ADD_CO_U32_e64_]]
; CHECK-NEXT: SI_RETURN implicit $vgpr0
%0:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%1:vgpr_32, %2:sreg_64 = V_ADD_CO_U32_e64 64, %0, 0, implicit $exec
$vgpr0 = COPY %1
SI_RETURN implicit $vgpr0
...
---
name: multi_use_scalar_fi__add_imm_add_inline_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr0, $sgpr1
; CHECK-LABEL: name: multi_use_scalar_fi__add_imm_add_inline_imm
; CHECK: liveins: $sgpr0, $sgpr1
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr0
; CHECK-NEXT: [[COPY1:%[0-9]+]]:sreg_32 = COPY $sgpr1
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.0
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[S_MOV_B32_]], 16380, implicit-def dead $scc
; CHECK-NEXT: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 %stack.0, 56, implicit-def dead $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: $sgpr5 = COPY [[S_ADD_I32_1]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4, implicit $sgpr5
%0:sreg_32 = COPY $sgpr0
%1:sreg_32 = COPY $sgpr1
%2:sreg_32 = S_MOV_B32 16380
%3:sreg_32 = S_MOV_B32 56
%4:sreg_32 = S_MOV_B32 %stack.0
%5:sreg_32 = S_ADD_I32 %4, killed %2, implicit-def dead $scc
%6:sreg_32 = S_ADD_I32 %4, killed %3, implicit-def dead $scc
$sgpr4 = COPY %5
$sgpr5 = COPY %6
SI_RETURN implicit $sgpr4, implicit $sgpr5
...
---
name: multi_add_use_vector_fi__add_imm_add_inline_imm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX9-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX9: liveins: $vgpr0, $vgpr1
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX9-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX9-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GFX9-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_MOV_B32_e32_]], killed [[COPY1]], 0, implicit $exec
; GFX9-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 [[V_MOV_B32_e32_]], 56, 0, implicit $exec
; GFX9-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX9-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX9-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
;
; GFX10-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX10: liveins: $vgpr0, $vgpr1
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX10-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX10-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, killed [[COPY1]], 0, implicit $exec
; GFX10-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 56, 0, implicit $exec
; GFX10-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX10-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX10-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
;
; GFX12-LABEL: name: multi_add_use_vector_fi__add_imm_add_inline_imm
; GFX12: liveins: $vgpr0, $vgpr1
; GFX12-NEXT: {{ $}}
; GFX12-NEXT: [[COPY:%[0-9]+]]:vgpr_32 = COPY $vgpr0
; GFX12-NEXT: [[COPY1:%[0-9]+]]:vgpr_32 = COPY $vgpr1
; GFX12-NEXT: [[V_ADD_U32_e64_:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, killed [[COPY1]], 0, implicit $exec
; GFX12-NEXT: [[V_ADD_U32_e64_1:%[0-9]+]]:vgpr_32 = V_ADD_U32_e64 %stack.0, 56, 0, implicit $exec
; GFX12-NEXT: $vgpr0 = COPY [[V_ADD_U32_e64_]]
; GFX12-NEXT: $vgpr1 = COPY [[V_ADD_U32_e64_1]]
; GFX12-NEXT: SI_RETURN implicit $vgpr0, implicit $vgpr1
%0:vgpr_32 = COPY $vgpr0
%1:vgpr_32 = COPY $vgpr1
%2:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%3:vgpr_32 = V_ADD_U32_e64 %2, killed %1, 0, implicit $exec
%4:vgpr_32 = V_MOV_B32_e32 999, implicit $exec
%5:vgpr_32 = COPY %3
%6:sreg_32 = S_MOV_B32 56
%7:vgpr_32 = V_ADD_U32_e64 %2, killed %6, 0, implicit $exec
%8:vgpr_32 = COPY %7
$vgpr0 = COPY %3
$vgpr1 = COPY %7
SI_RETURN implicit $vgpr0, implicit $vgpr1
...
---
name: fold_frame_index__through_reg_sequence_to_user_subreg
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
liveins: $sgpr8
; CHECK-LABEL: name: fold_frame_index__through_reg_sequence_to_user_subreg
; CHECK: liveins: $sgpr8
; CHECK-NEXT: {{ $}}
; CHECK-NEXT: [[COPY:%[0-9]+]]:sreg_32 = COPY $sgpr8
; CHECK-NEXT: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 123
; CHECK-NEXT: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.0
; CHECK-NEXT: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; CHECK-NEXT: [[S_ADD_I32_:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], %stack.0, implicit-def $scc
; CHECK-NEXT: [[S_ADD_I32_1:%[0-9]+]]:sreg_32 = S_ADD_I32 [[COPY]], 123, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_I32_]]
; CHECK-NEXT: $sgpr5 = COPY [[S_ADD_I32_1]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4, implicit $sgpr5
%0:sreg_32 = COPY $sgpr8
%1:sreg_32 = S_MOV_B32 123
%2:sreg_32 = S_MOV_B32 %stack.0
%3:sreg_64 = REG_SEQUENCE %1, %subreg.sub0, %2, %subreg.sub1
%4:sreg_32 = S_ADD_I32 %0, %3.sub1, implicit-def $scc
%5:sreg_32 = S_ADD_I32 %0, %3.sub0, implicit-def $scc
$sgpr4 = COPY %4
$sgpr5 = COPY %5
SI_RETURN implicit $sgpr4, implicit $sgpr5
...
name: fold_frame_index__s_add_u32__fi_const
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_u32__fi_const
; CHECK: [[S_ADD_U32_:%[0-9]+]]:sreg_32 = S_ADD_U32 %stack.0, 128, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_U32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_U32 %0, 128, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_u32__const_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_u32__const_fi
; CHECK: [[S_ADD_U32_:%[0-9]+]]:sreg_32 = S_ADD_U32 128, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_U32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_U32 128, %0, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_u32__fi_inlineimm
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_u32__fi_inlineimm
; CHECK: [[S_ADD_U32_:%[0-9]+]]:sreg_32 = S_ADD_U32 %stack.0, 16, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_U32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_U32 %0, 16, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: fold_frame_index__s_add_u32__inlineimm_fi
tracksRegLiveness: true
frameInfo:
maxAlignment: 4
localFrameSize: 16384
stack:
- { id: 0, size: 16384, alignment: 4, local-offset: 0 }
body: |
bb.0:
; CHECK-LABEL: name: fold_frame_index__s_add_u32__inlineimm_fi
; CHECK: [[S_ADD_U32_:%[0-9]+]]:sreg_32 = S_ADD_U32 16, %stack.0, implicit-def $scc
; CHECK-NEXT: $sgpr4 = COPY [[S_ADD_U32_]]
; CHECK-NEXT: SI_RETURN implicit $sgpr4
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_ADD_U32 16, %0, implicit-def $scc
$sgpr4 = COPY %1
SI_RETURN implicit $sgpr4
...
---
name: no_fold_literal_and_fi_s_or_b32
tracksRegLiveness: true
frameInfo:
maxAlignment: 16
localFrameSize: 8192
stack:
- { id: 0, size: 4096, alignment: 4, local-offset: 0 }
- { id: 1, size: 4096, alignment: 16, local-offset: 4096 }
body: |
bb.0:
; CHECK-LABEL: name: no_fold_literal_and_fi_s_or_b32
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.1
; CHECK-NEXT: [[S_AND_B32_:%[0-9]+]]:sreg_32 = S_AND_B32 killed [[S_MOV_B32_]], 12345, implicit-def dead $scc
; CHECK-NEXT: S_ENDPGM 0, implicit [[S_AND_B32_]]
%0:sreg_32 = S_MOV_B32 12345
%1:sreg_32 = S_MOV_B32 %stack.1
%2:sreg_32 = S_AND_B32 killed %1, killed %0, implicit-def dead $scc
S_ENDPGM 0, implicit %2
...
---
name: no_fold_literal_or_fi_s_or_b32
tracksRegLiveness: true
frameInfo:
maxAlignment: 16
localFrameSize: 8192
stack:
- { id: 0, size: 4096, alignment: 4, local-offset: 0 }
- { id: 1, size: 4096, alignment: 16, local-offset: 4096 }
body: |
bb.0:
; CHECK-LABEL: name: no_fold_literal_or_fi_s_or_b32
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.1
; CHECK-NEXT: [[S_OR_B32_:%[0-9]+]]:sreg_32 = S_OR_B32 killed [[S_MOV_B32_]], 12345, implicit-def dead $scc
; CHECK-NEXT: S_ENDPGM 0, implicit [[S_OR_B32_]]
%0:sreg_32 = S_MOV_B32 12345
%1:sreg_32 = S_MOV_B32 %stack.1
%2:sreg_32 = S_OR_B32 killed %1, killed %0, implicit-def dead $scc
S_ENDPGM 0, implicit %2
...
---
name: no_fold_literal_and_fi_s_mul_i32
tracksRegLiveness: true
frameInfo:
maxAlignment: 16
localFrameSize: 8192
stack:
- { id: 0, size: 4096, alignment: 4, local-offset: 0 }
- { id: 1, size: 4096, alignment: 16, local-offset: 4096 }
body: |
bb.0:
; CHECK-LABEL: name: no_fold_literal_and_fi_s_mul_i32
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.1
; CHECK-NEXT: [[S_MUL_I32_:%[0-9]+]]:sreg_32 = S_MUL_I32 killed [[S_MOV_B32_]], 12345, implicit-def dead $scc
; CHECK-NEXT: S_ENDPGM 0, implicit [[S_MUL_I32_]]
%0:sreg_32 = S_MOV_B32 12345
%1:sreg_32 = S_MOV_B32 %stack.1
%2:sreg_32 = S_MUL_I32 killed %1, killed %0, implicit-def dead $scc
S_ENDPGM 0, implicit %2
...
---
name: no_fold_multiple_fi_s_cselect_b32
tracksRegLiveness: true
stack:
- { id: 0, size: 64, alignment: 4 }
- { id: 1, size: 32, alignment: 4 }
body: |
bb.0:
; CHECK-LABEL: name: no_fold_multiple_fi_s_cselect_b32
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 %stack.1
; CHECK-NEXT: [[S_CSELECT_B32_:%[0-9]+]]:sreg_32 = S_CSELECT_B32 killed [[S_MOV_B32_]], %stack.0, implicit undef $scc
; CHECK-NEXT: S_ENDPGM 0, implicit [[S_CSELECT_B32_]]
%0:sreg_32 = S_MOV_B32 %stack.0
%1:sreg_32 = S_MOV_B32 %stack.1
%2:sreg_32 = S_CSELECT_B32 killed %1, killed %0, implicit undef $scc
S_ENDPGM 0, implicit %2
...
---
name: no_fold_multiple_fi_v_cndmask_b32_e64
tracksRegLiveness: true
stack:
- { id: 0, size: 64, alignment: 4 }
- { id: 1, size: 32, alignment: 4 }
body: |
bb.0:
liveins: $sgpr8_sgpr9
; GFX9-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e64
; GFX9: liveins: $sgpr8_sgpr9
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: [[COPY:%[0-9]+]]:sreg_64_xexec = COPY $sgpr8_sgpr9
; GFX9-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GFX9-NEXT: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX9-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, killed [[V_MOV_B32_e32_]], 0, killed [[V_MOV_B32_e32_1]], [[COPY]], implicit $exec
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e64_]]
;
; GFX10-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e64
; GFX10: liveins: $sgpr8_sgpr9
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64_xexec = COPY $sgpr8_sgpr9
; GFX10-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX10-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, %stack.0, 0, killed [[V_MOV_B32_e32_]], [[COPY]], implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e64_]]
;
; GFX12-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e64
; GFX12: liveins: $sgpr8_sgpr9
; GFX12-NEXT: {{ $}}
; GFX12-NEXT: [[COPY:%[0-9]+]]:sreg_64_xexec = COPY $sgpr8_sgpr9
; GFX12-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX12-NEXT: [[V_CNDMASK_B32_e64_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e64 0, %stack.0, 0, killed [[V_MOV_B32_e32_]], [[COPY]], implicit $exec
; GFX12-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e64_]]
%0:sreg_64_xexec = COPY $sgpr8_sgpr9
%1:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%2:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
%3:vgpr_32 = V_CNDMASK_B32_e64 0, killed %1, 0, killed %2, %0, implicit $exec
S_ENDPGM 0, implicit %3
...
---
name: no_fold_multiple_fi_v_cndmask_b32_e32
tracksRegLiveness: true
stack:
- { id: 0, size: 64, alignment: 4 }
- { id: 1, size: 32, alignment: 4 }
body: |
bb.0:
liveins: $sgpr8_sgpr9
; GFX9-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e32
; GFX9: liveins: $sgpr8_sgpr9
; GFX9-NEXT: {{ $}}
; GFX9-NEXT: $vcc = COPY $sgpr8_sgpr9
; GFX9-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
; GFX9-NEXT: [[V_MOV_B32_e32_1:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX9-NEXT: [[V_CNDMASK_B32_e32_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e32 killed [[V_MOV_B32_e32_]], killed [[V_MOV_B32_e32_1]], implicit $vcc, implicit $exec
; GFX9-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e32_]]
;
; GFX10-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e32
; GFX10: liveins: $sgpr8_sgpr9
; GFX10-NEXT: {{ $}}
; GFX10-NEXT: $vcc = COPY $sgpr8_sgpr9
; GFX10-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX10-NEXT: [[V_CNDMASK_B32_e32_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e32 %stack.0, killed [[V_MOV_B32_e32_]], implicit $vcc, implicit $exec
; GFX10-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e32_]]
;
; GFX12-LABEL: name: no_fold_multiple_fi_v_cndmask_b32_e32
; GFX12: liveins: $sgpr8_sgpr9
; GFX12-NEXT: {{ $}}
; GFX12-NEXT: $vcc = COPY $sgpr8_sgpr9
; GFX12-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
; GFX12-NEXT: [[V_CNDMASK_B32_e32_:%[0-9]+]]:vgpr_32 = V_CNDMASK_B32_e32 %stack.0, killed [[V_MOV_B32_e32_]], implicit $vcc, implicit $exec
; GFX12-NEXT: S_ENDPGM 0, implicit [[V_CNDMASK_B32_e32_]]
$vcc = COPY $sgpr8_sgpr9
%1:vgpr_32 = V_MOV_B32_e32 %stack.0, implicit $exec
%2:vgpr_32 = V_MOV_B32_e32 %stack.1, implicit $exec
%3:vgpr_32 = V_CNDMASK_B32_e32 killed %1, killed %2, implicit $vcc, implicit $exec
S_ENDPGM 0, implicit %3
...
Reference in New Issue View Git Blame Copy Permalink