[llvm-branch-commits] [llvm] AMDGPU: Handle folding frame indexes into s_add_i32 (PR #101694)
Matt Arsenault via llvm-branch-commits
llvm-branch-commits at lists.llvm.org
Mon Aug 5 02:01:07 PDT 2024
================
@@ -0,0 +1,930 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx700 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=MUBUFW64 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx803 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=MUBUFW64 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx900 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=MUBUFW64 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx90a -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=MUBUFW64 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1010 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=MUBUFW32 %s
+
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx940 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=FLATSCRW64 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1100 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=FLATSCRW32 %s
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx1200 -verify-machineinstrs -run-pass=prologepilog %s -o - | FileCheck -check-prefix=FLATSCRW32 %s
+
+---
+name: s_add_i32__inline_imm__fi_offset0
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__inline_imm__fi_offset0
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 12, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__inline_imm__fi_offset0
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 12, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__inline_imm__fi_offset0
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__inline_imm__fi_offset0
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 12, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 12, %stack.0, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__fi_offset0__inline_imm
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 32, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__inline_imm
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 12, $sgpr7, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__inline_imm
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 12, $sgpr7, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__inline_imm
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__fi_offset0__inline_imm
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 12, $sgpr32, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 %stack.0, 12, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__inline_imm___fi_offset_inline_imm
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 16, alignment: 16 }
+ - { id: 1, size: 24, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 28, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 28, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 28, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__inline_imm___fi_offset_inline_imm
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 28, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 12, %stack.1, implicit-def $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__literal__fi_offset0
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__literal__fi_offset0
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 68, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__literal__fi_offset0
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 68, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__literal__fi_offset0
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__literal__fi_offset0
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 68, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 68, %stack.0, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__fi_offset0__literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__literal
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 68, $sgpr7, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__literal
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 68, $sgpr7, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__literal
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__fi_offset0__literal
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 68, $sgpr32, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 %stack.0, 68, implicit-def $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__literal__fi_offset96
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 24, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__literal__fi_offset96
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 164, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__literal__fi_offset96
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 164, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__literal__fi_offset96
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 $sgpr32, 164, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__literal__fi_offset96
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 $sgpr32, 164, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ renamable $sgpr7 = S_ADD_I32 68, %stack.1, implicit-def $scc
+ SI_RETURN implicit $sgpr7, implicit $scc
+
+...
+
+---
+name: s_add_i32____fi_offset96__literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 128, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32____fi_offset96__literal
+ ; MUBUFW64: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 164, $sgpr7, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32____fi_offset96__literal
+ ; MUBUFW32: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 164, $sgpr7, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32____fi_offset96__literal
+ ; FLATSCRW64: renamable $sgpr7 = S_ADD_I32 164, $sgpr32, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32____fi_offset96__literal
+ ; FLATSCRW32: renamable $sgpr7 = S_ADD_I32 164, $sgpr32, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ renamable $sgpr7 = S_ADD_I32 %stack.1, 68, implicit-def $scc
+ SI_RETURN implicit $sgpr7, implicit $scc
+
+...
+
+---
+name: s_add_i32__sgpr__fi_offset0
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_offset0
+ ; MUBUFW64: liveins: $sgpr8
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_offset0
+ ; MUBUFW32: liveins: $sgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_offset0
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_offset0
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.0, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__fi_offset0__sgpr
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 128, alignment: 16 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUFW64-LABEL: name: s_add_i32__fi_offset0__sgpr
+ ; MUBUFW64: liveins: $sgpr8
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__fi_offset0__sgpr
+ ; MUBUFW32: liveins: $sgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__fi_offset0__sgpr
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__fi_offset0__sgpr
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 %stack.0, $sgpr8, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__sgpr__fi_literal_offset
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 80, alignment: 16 }
+ - { id: 1, size: 48, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUFW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset
+ ; MUBUFW64: liveins: $sgpr8
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset
+ ; MUBUFW32: liveins: $sgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__sgpr__fi_literal_offset
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__sgpr__fi_literal_offset
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, 80, implicit-def dead $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 $sgpr8, %stack.1, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+
+...
+
+---
+name: s_add_i32__fi_literal_offset__sgpr
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 80, alignment: 16 }
+ - { id: 1, size: 48, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+body: |
+ bb.0:
+ liveins: $sgpr8
+ ; MUBUFW64-LABEL: name: s_add_i32__fi_literal_offset__sgpr
+ ; MUBUFW64: liveins: $sgpr8
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 6, implicit-def dead $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__fi_literal_offset__sgpr
+ ; MUBUFW32: liveins: $sgpr8
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_LSHR_B32 $sgpr32, 5, implicit-def dead $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr7, $sgpr8, implicit-def $scc
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__fi_literal_offset__sgpr
+ ; FLATSCRW64: liveins: $sgpr8
+ ; FLATSCRW64-NEXT: {{ $}}
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW64-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__fi_literal_offset__sgpr
+ ; FLATSCRW32: liveins: $sgpr8
+ ; FLATSCRW32-NEXT: {{ $}}
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 $sgpr32, $sgpr8, implicit-def $scc
+ ; FLATSCRW32-NEXT: renamable $sgpr7 = S_ADD_I32 80, $sgpr7, implicit-def $scc
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7, implicit $scc
+ renamable $sgpr7 = S_ADD_I32 %stack.1, $sgpr8, implicit-def $scc
+ SI_RETURN implicit $sgpr7, implicit $scc
+
+...
+
+---
+name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 128, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: renamable $sgpr7 = S_MOV_B32 164
+ ; MUBUFW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; MUBUFW32-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; MUBUFW32: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: {{ $}}
+ ; MUBUFW32-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: $sgpr1 = S_ADDC_U32 $sgpr1, 0, implicit-def dead $scc, implicit $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW32-NEXT: renamable $sgpr7 = S_MOV_B32 164
+ ; MUBUFW32-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW64-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; FLATSCRW64: renamable $sgpr7 = S_MOV_B32 164
+ ; FLATSCRW64-NEXT: SI_RETURN implicit $sgpr7
+ ;
+ ; FLATSCRW32-LABEL: name: s_add_i32__kernel__literal__fi_offset96__offset_literal
+ ; FLATSCRW32: renamable $sgpr7 = S_MOV_B32 164
+ ; FLATSCRW32-NEXT: SI_RETURN implicit $sgpr7
+ renamable $sgpr7 = S_ADD_I32 68, %stack.1, implicit-def dead $scc
+ SI_RETURN implicit $sgpr7
+...
+
+---
+name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+tracksRegLiveness: true
+stack:
+ - { id: 0, size: 96, alignment: 16 }
+ - { id: 1, size: 128, alignment: 4 }
+machineFunctionInfo:
+ scratchRSrcReg: '$sgpr0_sgpr1_sgpr2_sgpr3'
+ frameOffsetReg: '$sgpr33'
+ stackPtrOffsetReg: '$sgpr32'
+ isEntryFunction: true
+body: |
+ bb.0:
+ ; MUBUFW64-LABEL: name: s_add_i32__kernel__fi_offset96__offset_literal__literal
+ ; MUBUFW64: liveins: $sgpr0_sgpr1_sgpr2_sgpr3
+ ; MUBUFW64-NEXT: {{ $}}
+ ; MUBUFW64-NEXT: $sgpr0 = S_ADD_U32 $sgpr0, $noreg, implicit-def $scc, implicit-def $sgpr0_sgpr1_sgpr2_sgpr3
----------------
arsenm wrote:
The required flat scratch init register is missing from the MIR. It doesn't matter for the purposes of the test (for the 64-bit add to increment the SRD)
https://github.com/llvm/llvm-project/pull/101694
More information about the llvm-branch-commits
mailing list