diff options
Diffstat (limited to 'llvm/test/CodeGen/AMDGPU/spill-restore-partial-copy.mir')
| -rw-r--r-- | llvm/test/CodeGen/AMDGPU/spill-restore-partial-copy.mir | 324 |
1 files changed, 324 insertions, 0 deletions
diff --git a/llvm/test/CodeGen/AMDGPU/spill-restore-partial-copy.mir b/llvm/test/CodeGen/AMDGPU/spill-restore-partial-copy.mir new file mode 100644 index 0000000..bb87b6e --- /dev/null +++ b/llvm/test/CodeGen/AMDGPU/spill-restore-partial-copy.mir @@ -0,0 +1,324 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 5 +# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=gfx950 -run-pass prologepilog,machine-cp -o - %s | FileCheck -check-prefix=GFX950 %s + +--- | + define amdgpu_kernel void @full_copy() #0 { ret void } + + define amdgpu_kernel void @partial_copy() #0 { ret void } + + define amdgpu_kernel void @full_spill() #0 { ret void } + + attributes #0 = { "amdgpu-waves-per-eu"="8,8" } +... + +--- +name: full_copy +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 1, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 2, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 3, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 4, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 5, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 6, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } +machineFunctionInfo: + stackPtrOffsetReg: '$sgpr32' + hasSpilledVGPRs: true +body: | + bb.0: + ; GFX950-LABEL: name: full_copy + ; GFX950: liveins: $agpr6, $agpr7, $agpr8, $agpr9, $agpr10, $agpr11, $agpr12, $agpr13, $agpr14, $agpr15, $agpr16, $agpr17, $agpr18, $agpr19, $agpr20, $agpr21, $agpr22, $agpr23, $agpr24, $agpr25, $agpr26, $agpr27, $agpr28, $agpr29 + ; GFX950-NEXT: {{ $}} + ; GFX950-NEXT: renamable $agpr0_agpr1 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr6 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr3, implicit $exec, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr7 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr2, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr8 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr9 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit killed $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr10 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr7, implicit $exec, implicit-def $vgpr4_vgpr5_vgpr6_vgpr7, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr11 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr6, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr12 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr5, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr13 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr4, implicit $exec, implicit killed $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr14 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr11, implicit $exec, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr15 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr10, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr16 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr9, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr17 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr8, implicit $exec, implicit killed $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr18 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr15, implicit $exec, implicit-def $vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr19 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr14, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr20 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr13, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr21 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr12, implicit $exec, implicit killed $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr22 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr19, implicit $exec, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr23 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr18, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr24 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr17, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr25 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr16, implicit $exec, implicit killed $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr26 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr23, implicit $exec, implicit-def $vgpr20_vgpr21_vgpr22_vgpr23, implicit $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: $agpr27 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr22, implicit $exec, implicit $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: $agpr28 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr21, implicit $exec, implicit $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: $agpr29 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr20, implicit $exec, implicit killed $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: $vgpr0 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr5 = COPY $agpr6, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr7, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr8, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr9, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr10, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr11, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr12, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr13, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr14, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr15, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr16, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr17, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr18, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr19, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr20, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr21, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr22, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr23, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr24, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr25, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr26, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr27, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr28, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr29, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + ; GFX950-NEXT: S_ENDPGM 0 + renamable $agpr0_agpr1 = IMPLICIT_DEF + renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + SI_SPILL_AV128_SAVE killed $vgpr0_vgpr1_vgpr2_vgpr3, %stack.0, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.0, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr4_vgpr5_vgpr6_vgpr7, %stack.1, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.1, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr8_vgpr9_vgpr10_vgpr11, %stack.2, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.2, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr12_vgpr13_vgpr14_vgpr15, %stack.3, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.3, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr16_vgpr17_vgpr18_vgpr19, %stack.4, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.4, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr20_vgpr21_vgpr22_vgpr23, %stack.5, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.5, align 4, addrspace 5) + $vgpr0 = IMPLICIT_DEF + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.0, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.1, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.1, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.3, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.3, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.5, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.5, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + S_ENDPGM 0 +... + + +# We need to add implicit operand as well as implicit-def operand to the scratch_load, otherwise, MachineCopyPropagation will think the preceeding copies are dead, and will delete them. + +--- +name: partial_copy +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 1, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 2, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 3, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 4, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 5, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 6, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } +machineFunctionInfo: + stackPtrOffsetReg: '$sgpr32' + hasSpilledVGPRs: true +body: | + bb.0: + ; GFX950-LABEL: name: partial_copy + ; GFX950: liveins: $agpr6, $agpr7, $agpr8, $agpr9, $agpr10, $agpr11, $agpr12, $agpr13, $agpr14, $agpr15, $agpr16, $agpr17, $agpr18, $agpr19, $agpr20, $agpr21, $agpr22, $agpr23, $agpr24, $agpr25, $agpr26, $agpr27 + ; GFX950-NEXT: {{ $}} + ; GFX950-NEXT: renamable $agpr0_agpr1 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $agpr28_agpr29_agpr30_agpr31 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr6 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr3, implicit $exec, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr7 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr2, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr8 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr9 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit killed $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr10 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr7, implicit $exec, implicit-def $vgpr4_vgpr5_vgpr6_vgpr7, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr11 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr6, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr12 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr5, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr13 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr4, implicit $exec, implicit killed $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr14 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr11, implicit $exec, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr15 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr10, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr16 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr9, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr17 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr8, implicit $exec, implicit killed $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr18 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr15, implicit $exec, implicit-def $vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr19 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr14, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr20 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr13, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr21 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr12, implicit $exec, implicit killed $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr22 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr19, implicit $exec, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr23 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr18, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr24 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr17, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr25 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr16, implicit $exec, implicit killed $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr26 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr23, implicit $exec, implicit-def $vgpr20_vgpr21_vgpr22_vgpr23, implicit $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: $agpr27 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr22, implicit $exec, implicit $vgpr20_vgpr21_vgpr22_vgpr23 + ; GFX950-NEXT: SCRATCH_STORE_DWORDX2_SADDR killed $vgpr20_vgpr21, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr, implicit killed $vgpr20_vgpr21_vgpr22_vgpr23 :: (store (s64) into %stack.5, align 4, addrspace 5) + ; GFX950-NEXT: $vgpr0 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr5 = COPY $agpr6, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr7, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr8, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr9, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr10, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr11, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr12, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr13, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr14, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr15, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr16, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr17, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr18, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr19, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr20, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr21, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr22, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr23, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr24, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr25, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr26, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr27, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2_agpr3 = SCRATCH_LOAD_DWORDX2_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr, implicit-def $agpr2_agpr3_agpr4_agpr5, implicit $agpr2_agpr3_agpr4_agpr5 :: (load (s64) from %stack.5, align 4, addrspace 5) + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + ; GFX950-NEXT: S_ENDPGM 0 + renamable $agpr0_agpr1 = IMPLICIT_DEF + renamable $agpr28_agpr29_agpr30_agpr31 = IMPLICIT_DEF + renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + SI_SPILL_AV128_SAVE killed $vgpr0_vgpr1_vgpr2_vgpr3, %stack.0, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.0, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr4_vgpr5_vgpr6_vgpr7, %stack.1, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.1, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr8_vgpr9_vgpr10_vgpr11, %stack.2, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.2, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr12_vgpr13_vgpr14_vgpr15, %stack.3, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.3, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr16_vgpr17_vgpr18_vgpr19, %stack.4, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.4, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr20_vgpr21_vgpr22_vgpr23, %stack.5, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.5, align 4, addrspace 5) + $vgpr0 = IMPLICIT_DEF + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.0, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.1, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.1, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.3, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.3, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.5, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.5, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + S_ENDPGM 0 +... + +# Since there are no preceeding copies , we do not need to add implicit operand, as the implicit-def operand does not clobber. + +--- +name: full_spill +tracksRegLiveness: true +stack: + - { id: 0, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 1, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 2, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 3, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 4, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 5, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } + - { id: 6, name: '', type: spill-slot, offset: 0, size: 16, alignment: 4 } +machineFunctionInfo: + stackPtrOffsetReg: '$sgpr32' + hasSpilledVGPRs: true +body: | + bb.0: + ; GFX950-LABEL: name: full_spill + ; GFX950: liveins: $agpr6, $agpr7, $agpr8, $agpr9, $agpr10, $agpr11, $agpr12, $agpr13, $agpr14, $agpr15, $agpr16, $agpr17, $agpr18, $agpr19, $agpr20, $agpr21, $agpr22, $agpr23, $agpr24, $agpr25 + ; GFX950-NEXT: {{ $}} + ; GFX950-NEXT: renamable $agpr0_agpr1 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $agpr26_agpr27 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $agpr28_agpr29_agpr30_agpr31 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + ; GFX950-NEXT: renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr6 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr3, implicit $exec, implicit-def $vgpr0_vgpr1_vgpr2_vgpr3, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr7 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr2, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr8 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr1, implicit $exec, implicit $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr9 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr0, implicit $exec, implicit killed $vgpr0_vgpr1_vgpr2_vgpr3 + ; GFX950-NEXT: $agpr10 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr7, implicit $exec, implicit-def $vgpr4_vgpr5_vgpr6_vgpr7, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr11 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr6, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr12 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr5, implicit $exec, implicit $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr13 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr4, implicit $exec, implicit killed $vgpr4_vgpr5_vgpr6_vgpr7 + ; GFX950-NEXT: $agpr14 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr11, implicit $exec, implicit-def $vgpr8_vgpr9_vgpr10_vgpr11, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr15 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr10, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr16 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr9, implicit $exec, implicit $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr17 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr8, implicit $exec, implicit killed $vgpr8_vgpr9_vgpr10_vgpr11 + ; GFX950-NEXT: $agpr18 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr15, implicit $exec, implicit-def $vgpr12_vgpr13_vgpr14_vgpr15, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr19 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr14, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr20 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr13, implicit $exec, implicit $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr21 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr12, implicit $exec, implicit killed $vgpr12_vgpr13_vgpr14_vgpr15 + ; GFX950-NEXT: $agpr22 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr19, implicit $exec, implicit-def $vgpr16_vgpr17_vgpr18_vgpr19, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr23 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr18, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr24 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr17, implicit $exec, implicit $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: $agpr25 = V_ACCVGPR_WRITE_B32_e64 killed $vgpr16, implicit $exec, implicit killed $vgpr16_vgpr17_vgpr18_vgpr19 + ; GFX950-NEXT: SCRATCH_STORE_DWORDX4_SADDR killed $vgpr20_vgpr21_vgpr22_vgpr23, $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: (store (s128) into %stack.5, align 4, addrspace 5) + ; GFX950-NEXT: $vgpr0 = IMPLICIT_DEF + ; GFX950-NEXT: $agpr5 = COPY $agpr6, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr7, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr8, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr9, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr10, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr11, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr12, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr13, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr14, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr15, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr16, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr17, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr18, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr19, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr20, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr21, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + ; GFX950-NEXT: $agpr5 = COPY $agpr22, implicit-def $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr4 = COPY $agpr23, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr3 = COPY $agpr24, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: $agpr2 = COPY $agpr25, implicit $agpr2_agpr3_agpr4_agpr5 + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + ; GFX950-NEXT: $agpr2_agpr3_agpr4_agpr5 = SCRATCH_LOAD_DWORDX4_SADDR $sgpr32, 0, 0, implicit $exec, implicit $flat_scr :: (load (s128) from %stack.5, align 4, addrspace 5) + ; GFX950-NEXT: DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + ; GFX950-NEXT: S_ENDPGM 0 + renamable $agpr0_agpr1 = IMPLICIT_DEF + renamable $agpr26_agpr27 = IMPLICIT_DEF + renamable $agpr28_agpr29_agpr30_agpr31 = IMPLICIT_DEF + renamable $vgpr0_vgpr1_vgpr2_vgpr3_vgpr4_vgpr5_vgpr6_vgpr7_vgpr8_vgpr9_vgpr10_vgpr11_vgpr12_vgpr13_vgpr14_vgpr15 = IMPLICIT_DEF + renamable $vgpr16_vgpr17_vgpr18_vgpr19_vgpr20_vgpr21_vgpr22_vgpr23_vgpr24_vgpr25_vgpr26_vgpr27 = IMPLICIT_DEF + SI_SPILL_AV128_SAVE killed $vgpr0_vgpr1_vgpr2_vgpr3, %stack.0, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.0, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr4_vgpr5_vgpr6_vgpr7, %stack.1, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.1, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr8_vgpr9_vgpr10_vgpr11, %stack.2, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.2, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr12_vgpr13_vgpr14_vgpr15, %stack.3, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.3, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr16_vgpr17_vgpr18_vgpr19, %stack.4, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.4, align 4, addrspace 5) + SI_SPILL_AV128_SAVE killed $vgpr20_vgpr21_vgpr22_vgpr23, %stack.5, $sgpr32, 0, implicit $exec :: (store (s128) into %stack.5, align 4, addrspace 5) + $vgpr0 = IMPLICIT_DEF + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.0, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.0, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 0, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.1, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.1, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 1024, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.2, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.2, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 2048, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.3, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.3, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 3072, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.4, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.4, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 4096, 0, implicit $exec + renamable $agpr2_agpr3_agpr4_agpr5 = SI_SPILL_AV128_RESTORE %stack.5, $sgpr32, 0, implicit $exec :: (load (s128) from %stack.5, align 4, addrspace 5) + DS_WRITE_B128_gfx9 renamable $vgpr0, killed renamable $agpr2_agpr3_agpr4_agpr5, 5120, 0, implicit $exec + S_ENDPGM 0 +... |
