| # NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py |
| # RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=gfx908 -start-before=greedy,1 -stop-after=prologepilog -verify-machineinstrs -verify-regalloc -o - %s | FileCheck --check-prefixes=GCN %s |
| |
| # The VGPR pair spilled and restored around the callsite is used in the next basic block. |
| # |
| # AMDGPU target spill hooks storeRegToStackSlot/loadRegFromStackSlot handle the register spills via |
| # spill pseudos to insert a single instruction per spill to tackle the limitation during inline spiller |
| # that incorrectly updates the Liveintervals in case of a spill lowered into multiple instructions. |
| # AV spills were handled earlier by converting them into equivalent VGPR spills by adding appropriate copies. |
| # The multiple instructions (a copy + vgpr spill pseudo) introduced an incorrect liverange that caused a |
| # crash during RA. It is fixed by introducing AV* spill pseudos to ensure a single instruction per spill and |
| # the test started compiling successfully. |
| |
| --- |
| name: test_av_spill_cross_bb_usage |
| tracksRegLiveness: true |
| stack: |
| - { id: 0, name: '', type: spill-slot, offset: 0, size: 4, alignment: 4 } |
| machineFunctionInfo: |
| scratchRSrcReg: $sgpr0_sgpr1_sgpr2_sgpr3 |
| stackPtrOffsetReg: '$sgpr32' |
| body: | |
| ; GCN-LABEL: name: test_av_spill_cross_bb_usage |
| ; GCN: bb.0: |
| ; GCN-NEXT: successors: %bb.2(0x40000000), %bb.1(0x40000000) |
| ; GCN-NEXT: liveins: $sgpr30, $sgpr31, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr40, $vgpr41, $vgpr42, $vgpr43, $vgpr44, $vgpr45, $vgpr46, $vgpr56, $vgpr57, $vgpr58, $vgpr59, $vgpr60, $vgpr61, $sgpr30_sgpr31 |
| ; GCN-NEXT: {{ $}} |
| ; GCN-NEXT: $sgpr4_sgpr5 = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET $vgpr40, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 68, 0, 0, implicit $exec :: (store (s32) into %stack.3, addrspace 5) |
| ; GCN-NEXT: $exec = S_MOV_B64 killed $sgpr4_sgpr5 |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr41, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 44, 0, 0, implicit $exec :: (store (s32) into %stack.4, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr42, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 40, 0, 0, implicit $exec :: (store (s32) into %stack.5, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr43, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 36, 0, 0, implicit $exec :: (store (s32) into %stack.6, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr44, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 32, 0, 0, implicit $exec :: (store (s32) into %stack.7, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr45, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 28, 0, 0, implicit $exec :: (store (s32) into %stack.8, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr46, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 24, 0, 0, implicit $exec :: (store (s32) into %stack.9, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr56, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 20, 0, 0, implicit $exec :: (store (s32) into %stack.10, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr57, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 16, 0, 0, implicit $exec :: (store (s32) into %stack.11, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr58, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 12, 0, 0, implicit $exec :: (store (s32) into %stack.12, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr59, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 8, 0, 0, implicit $exec :: (store (s32) into %stack.13, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr60, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 4, 0, 0, implicit $exec :: (store (s32) into %stack.14, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr61, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: (store (s32) into %stack.15, addrspace 5) |
| ; GCN-NEXT: renamable $vgpr44 = COPY $vgpr13, implicit $exec |
| ; GCN-NEXT: renamable $vgpr43 = COPY $vgpr12, implicit $exec |
| ; GCN-NEXT: S_CBRANCH_SCC1 %bb.2, implicit undef $scc |
| ; GCN-NEXT: S_BRANCH %bb.1 |
| ; GCN-NEXT: {{ $}} |
| ; GCN-NEXT: bb.1: |
| ; GCN-NEXT: successors: %bb.2(0x80000000) |
| ; GCN-NEXT: liveins: $exec:0x000000000000000F, $sgpr30, $sgpr31, $vgpr0:0x0000000000000003, $vgpr1:0x0000000000000003, $vgpr2:0x0000000000000003, $vgpr3:0x0000000000000003, $vgpr4:0x0000000000000003, $vgpr5:0x0000000000000003, $vgpr6:0x0000000000000003, $vgpr7:0x0000000000000003, $vgpr8:0x0000000000000003, $vgpr9:0x0000000000000003, $vgpr40, $sgpr30_sgpr31, $vgpr10_vgpr11:0x000000000000000F, $vgpr41_vgpr42:0x000000000000000F, $vgpr43_vgpr44:0x000000000000000F, $vgpr45_vgpr46:0x000000000000000F, $vgpr56_vgpr57:0x000000000000000F, $vgpr58_vgpr59:0x000000000000000F, $vgpr60_vgpr61:0x000000000000000F |
| ; GCN-NEXT: {{ $}} |
| ; GCN-NEXT: renamable $vgpr57 = COPY $vgpr9, implicit $exec |
| ; GCN-NEXT: renamable $vgpr56 = COPY $vgpr8, implicit $exec |
| ; GCN-NEXT: renamable $vgpr59 = COPY $vgpr7, implicit $exec |
| ; GCN-NEXT: renamable $vgpr58 = COPY $vgpr6, implicit $exec |
| ; GCN-NEXT: renamable $vgpr61 = COPY $vgpr5, implicit $exec |
| ; GCN-NEXT: renamable $vgpr60 = COPY $vgpr4, implicit $exec |
| ; GCN-NEXT: renamable $vgpr42 = COPY $vgpr3, implicit $exec |
| ; GCN-NEXT: renamable $vgpr41 = COPY $vgpr2, implicit $exec |
| ; GCN-NEXT: renamable $vgpr46 = COPY $vgpr1, implicit $exec |
| ; GCN-NEXT: renamable $vgpr45 = COPY $vgpr0, implicit $exec |
| ; GCN-NEXT: renamable $sgpr16_sgpr17 = IMPLICIT_DEF |
| ; GCN-NEXT: $vgpr40 = V_WRITELANE_B32 $sgpr30, 0, $vgpr40, implicit-def $sgpr30_sgpr31, implicit $sgpr30_sgpr31 |
| ; GCN-NEXT: $vgpr40 = V_WRITELANE_B32 $sgpr31, 1, $vgpr40, implicit $sgpr30_sgpr31 |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr10, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 52, 0, 0, implicit $exec, implicit-def $vgpr10_vgpr11, implicit $vgpr10_vgpr11 :: (store (s32) into %stack.1, addrspace 5) |
| ; GCN-NEXT: BUFFER_STORE_DWORD_OFFSET killed $vgpr11, $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 56, 0, 0, implicit $exec, implicit killed $vgpr10_vgpr11 :: (store (s32) into %stack.1 + 4, addrspace 5) |
| ; GCN-NEXT: dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu, implicit-def dead $vgpr0 |
| ; GCN-NEXT: $vgpr14 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 60, 0, 0, implicit $exec, implicit-def $vgpr14_vgpr15 :: (load (s32) from %stack.2, addrspace 5) |
| ; GCN-NEXT: $vgpr15 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 64, 0, 0, implicit $exec, implicit-def $vgpr14_vgpr15 :: (load (s32) from %stack.2 + 4, addrspace 5) |
| ; GCN-NEXT: renamable $vgpr0_vgpr1 = nofpexcept V_FMA_F64_e64 0, killed $vgpr45_vgpr46, 0, killed $vgpr41_vgpr42, 0, killed $vgpr60_vgpr61, 0, 0, implicit $mode, implicit $exec |
| ; GCN-NEXT: FLAT_STORE_DWORDX2 killed renamable $vgpr58_vgpr59, killed renamable $vgpr0_vgpr1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| ; GCN-NEXT: $vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 52, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.1, addrspace 5) |
| ; GCN-NEXT: $vgpr1 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 56, 0, 0, implicit $exec, implicit-def $vgpr0_vgpr1 :: (load (s32) from %stack.1 + 4, addrspace 5) |
| ; GCN-NEXT: FLAT_STORE_DWORDX2 killed renamable $vgpr0_vgpr1, killed renamable $vgpr56_vgpr57, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| ; GCN-NEXT: {{ $}} |
| ; GCN-NEXT: bb.2: |
| ; GCN-NEXT: liveins: $vgpr40, $vgpr14_vgpr15:0x000000000000000F, $vgpr43_vgpr44:0x000000000000000F |
| ; GCN-NEXT: {{ $}} |
| ; GCN-NEXT: renamable $vgpr0_vgpr1 = V_MOV_B64_PSEUDO 0, implicit $exec |
| ; GCN-NEXT: FLAT_STORE_DWORDX2 undef renamable $vgpr0_vgpr1, killed renamable $vgpr43_vgpr44, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| ; GCN-NEXT: FLAT_STORE_DWORDX2 killed renamable $vgpr0_vgpr1, killed renamable $vgpr14_vgpr15, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| ; GCN-NEXT: $vgpr61 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 0, 0, 0, implicit $exec :: (load (s32) from %stack.15, addrspace 5) |
| ; GCN-NEXT: $vgpr60 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 4, 0, 0, implicit $exec :: (load (s32) from %stack.14, addrspace 5) |
| ; GCN-NEXT: $vgpr59 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 8, 0, 0, implicit $exec :: (load (s32) from %stack.13, addrspace 5) |
| ; GCN-NEXT: $vgpr58 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 12, 0, 0, implicit $exec :: (load (s32) from %stack.12, addrspace 5) |
| ; GCN-NEXT: $vgpr57 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 16, 0, 0, implicit $exec :: (load (s32) from %stack.11, addrspace 5) |
| ; GCN-NEXT: $vgpr56 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 20, 0, 0, implicit $exec :: (load (s32) from %stack.10, addrspace 5) |
| ; GCN-NEXT: $vgpr46 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 24, 0, 0, implicit $exec :: (load (s32) from %stack.9, addrspace 5) |
| ; GCN-NEXT: $vgpr45 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 28, 0, 0, implicit $exec :: (load (s32) from %stack.8, addrspace 5) |
| ; GCN-NEXT: $vgpr44 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 32, 0, 0, implicit $exec :: (load (s32) from %stack.7, addrspace 5) |
| ; GCN-NEXT: $vgpr43 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 36, 0, 0, implicit $exec :: (load (s32) from %stack.6, addrspace 5) |
| ; GCN-NEXT: $vgpr42 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 40, 0, 0, implicit $exec :: (load (s32) from %stack.5, addrspace 5) |
| ; GCN-NEXT: $vgpr41 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 44, 0, 0, implicit $exec :: (load (s32) from %stack.4, addrspace 5) |
| ; GCN-NEXT: $sgpr4_sgpr5 = S_OR_SAVEEXEC_B64 -1, implicit-def $exec, implicit-def dead $scc, implicit $exec |
| ; GCN-NEXT: $vgpr40 = BUFFER_LOAD_DWORD_OFFSET $sgpr0_sgpr1_sgpr2_sgpr3, $sgpr32, 68, 0, 0, implicit $exec :: (load (s32) from %stack.3, addrspace 5) |
| ; GCN-NEXT: $exec = S_MOV_B64 killed $sgpr4_sgpr5 |
| ; GCN-NEXT: S_SETPC_B64_return undef $sgpr30_sgpr31 |
| bb.0: |
| liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8, $vgpr9, $vgpr10, $vgpr11, $vgpr12, $vgpr13, $vgpr14, $vgpr15, $vgpr40, $sgpr30, $sgpr31, $sgpr30_sgpr31 |
| |
| undef %0.sub1:vreg_64 = COPY $vgpr15 |
| %0.sub0:vreg_64 = COPY $vgpr14 |
| undef %1.sub1:vreg_64 = COPY $vgpr13 |
| %1.sub0:vreg_64 = COPY $vgpr12 |
| undef %2.sub1:vreg_64 = COPY $vgpr11 |
| %2.sub0:vreg_64 = COPY $vgpr10 |
| undef %3.sub1:vreg_64 = COPY $vgpr9 |
| %3.sub0:vreg_64 = COPY $vgpr8 |
| undef %4.sub1:vreg_64 = COPY $vgpr7 |
| %4.sub0:vreg_64 = COPY $vgpr6 |
| undef %5.sub1:vreg_64 = COPY $vgpr5 |
| %5.sub0:vreg_64 = COPY $vgpr4 |
| undef %6.sub1:vreg_64 = COPY $vgpr3 |
| %6.sub0:vreg_64 = COPY $vgpr2 |
| undef %7.sub1:vreg_64 = COPY $vgpr1 |
| %7.sub0:vreg_64 = COPY $vgpr0 |
| S_CBRANCH_SCC1 %bb.2, implicit undef $scc |
| S_BRANCH %bb.1 |
| |
| bb.1: |
| liveins: $vgpr40, $sgpr30, $sgpr31, $sgpr30_sgpr31 |
| |
| ADJCALLSTACKUP 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 |
| renamable $sgpr16_sgpr17 = IMPLICIT_DEF |
| $vgpr40 = V_WRITELANE_B32 $sgpr30, 0, $vgpr40, implicit-def $sgpr30_sgpr31, implicit $sgpr30_sgpr31 |
| $vgpr40 = V_WRITELANE_B32 killed $sgpr31, 1, $vgpr40, implicit killed $sgpr30_sgpr31 |
| dead $sgpr30_sgpr31 = SI_CALL killed renamable $sgpr16_sgpr17, 0, csr_amdgpu, implicit-def dead $vgpr0 |
| %8:vreg_64 = nofpexcept V_FMA_F64_e64 0, %7, 0, %6, 0, %5, 0, 0, implicit $mode, implicit $exec |
| ADJCALLSTACKDOWN 0, 0, implicit-def dead $scc, implicit-def $sgpr32, implicit $sgpr32 |
| FLAT_STORE_DWORDX2 %4, %8, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| FLAT_STORE_DWORDX2 %2, %3, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| |
| bb.2: |
| liveins: $vgpr40 |
| |
| %9:vreg_64 = V_MOV_B64_PSEUDO 0, implicit $exec |
| FLAT_STORE_DWORDX2 undef %10:vreg_64, %1, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| FLAT_STORE_DWORDX2 %9, %0, 0, 0, implicit $exec, implicit $flat_scr :: (store (s64)) |
| S_SETPC_B64_return undef $sgpr30_sgpr31 |
| ... |