llvm-project/llvm/test/CodeGen/AMDGPU/constant-fold-imm-immreg.mir

886 lines
29 KiB
YAML

# RUN: llc -mtriple=amdgcn--amdhsa -mcpu=hawaii -verify-machineinstrs -run-pass si-fold-operands,dead-mi-elimination -o - %s | FileCheck -check-prefix=GCN %s
--- |
define amdgpu_kernel void @s_fold_and_imm_regimm_32(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
%and = and i32 %a, 1234567
store volatile i32 %and, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @v_fold_and_imm_regimm_32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i64 %idxprom
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i64 %idxprom
%a = load i32, i32 addrspace(1)* %gep.a
%and = and i32 %a, 1234567
store i32 %and, i32 addrspace(1)* %gep.out
ret void
}
define amdgpu_kernel void @s_fold_shl_imm_regimm_32(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
%shl = shl i32 %a, 12
store volatile i32 %shl, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @v_fold_shl_imm_regimm_32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i64 %idxprom
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i64 %idxprom
%a = load i32, i32 addrspace(1)* %gep.a
%shl = shl i32 %a, 12
store i32 %shl, i32 addrspace(1)* %gep.out
ret void
}
define amdgpu_kernel void @s_fold_ashr_imm_regimm_32(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
%ashr = ashr i32 %a, 12
store volatile i32 %ashr, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @v_fold_ashr_imm_regimm_32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i64 %idxprom
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i64 %idxprom
%a = load i32, i32 addrspace(1)* %gep.a
%ashr = ashr i32 %a, 12
store i32 %ashr, i32 addrspace(1)* %gep.out
ret void
}
define amdgpu_kernel void @s_fold_lshr_imm_regimm_32(i32 addrspace(1)* %out, i32 %a, i32 %b) #0 {
%lshr = lshr i32 %a, 12
store volatile i32 %lshr, i32 addrspace(1)* %out
ret void
}
define amdgpu_kernel void @v_fold_lshr_imm_regimm_32(i32 addrspace(1)* %out, i32 addrspace(1)* %aptr) #0 {
%tid = call i32 @llvm.amdgcn.workitem.id.x()
%idxprom = sext i32 %tid to i64
%gep.a = getelementptr i32, i32 addrspace(1)* %aptr, i64 %idxprom
%gep.out = getelementptr i32, i32 addrspace(1)* %out, i64 %idxprom
%a = load i32, i32 addrspace(1)* %gep.a
%lshr = lshr i32 %a, 12
store i32 %lshr, i32 addrspace(1)* %gep.out
ret void
}
define amdgpu_kernel void @undefined_vreg_operand() {
unreachable
}
declare i32 @llvm.amdgcn.workitem.id.x() #1
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
...
---
# GCN-LABEL: name: s_fold_and_imm_regimm_32{{$}}
# GCN: %10 = V_MOV_B32_e32 1543, implicit %exec
# GCN: BUFFER_STORE_DWORD_OFFSET killed %10,
name: s_fold_and_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_64_xexec }
- { id: 2, class: sreg_32_xm0 }
- { id: 3, class: sreg_32_xm0 }
- { id: 4, class: sreg_32_xm0 }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: sreg_128 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1
%0 = COPY %sgpr0_sgpr1
%1 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%2 = COPY %1.sub1
%3 = COPY %1.sub0
%4 = S_MOV_B32 61440
%5 = S_MOV_B32 -1
%6 = REG_SEQUENCE killed %2, 1, killed %3, 2, killed %4, 3, killed %5, 4
%7 = S_MOV_B32 1234567
%8 = S_MOV_B32 9999
%9 = S_AND_B32 killed %7, killed %8, implicit-def dead %scc
%10 = COPY %9
BUFFER_STORE_DWORD_OFFSET killed %10, killed %6, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out)
S_ENDPGM
...
---
# GCN-LABEL: name: v_fold_and_imm_regimm_32{{$}}
# GCN: %9 = V_MOV_B32_e32 646, implicit %exec
# GCN: FLAT_STORE_DWORD %19, %9,
# GCN: %10 = V_MOV_B32_e32 646, implicit %exec
# GCN: FLAT_STORE_DWORD %19, %10
# GCN: %11 = V_MOV_B32_e32 646, implicit %exec
# GCN: FLAT_STORE_DWORD %19, %11,
# GCN: %12 = V_MOV_B32_e32 1234567, implicit %exec
# GCN: FLAT_STORE_DWORD %19, %12,
# GCN: %13 = V_MOV_B32_e32 63, implicit %exec
# GCN: FLAT_STORE_DWORD %19, %13,
name: v_fold_and_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 20, class: sreg_32_xm0 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vreg_64 }
- { id: 26, class: sreg_32_xm0 }
- { id: 27, class: vgpr_32 }
- { id: 28, class: vgpr_32 }
- { id: 29, class: vgpr_32 }
- { id: 30, class: vgpr_32 }
- { id: 31, class: vgpr_32 }
- { id: 32, class: vreg_64 }
- { id: 33, class: vreg_64 }
- { id: 34, class: vgpr_32 }
- { id: 35, class: vgpr_32 }
- { id: 36, class: vgpr_32 }
- { id: 37, class: vreg_64 }
- { id: 44, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%3' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%3 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%31 = V_ASHRREV_I32_e64 31, %3, implicit %exec
%32 = REG_SEQUENCE %3, 1, %31, 2
%33 = V_LSHLREV_B64 2, killed %32, implicit %exec
%20 = COPY %4.sub1
%44 = V_ADD_I32_e32 %4.sub0, %33.sub0, implicit-def %vcc, implicit %exec
%36 = COPY killed %20
%35 = V_ADDC_U32_e32 %33.sub1, %36, implicit-def %vcc, implicit %vcc, implicit %exec
%37 = REG_SEQUENCE %44, 1, killed %35, 2
%24 = V_MOV_B32_e32 982, implicit %exec
%26 = S_MOV_B32 1234567
%34 = V_MOV_B32_e32 63, implicit %exec
%27 = V_AND_B32_e64 %26, %24, implicit %exec
FLAT_STORE_DWORD %37, %27, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%28 = V_AND_B32_e64 %24, %26, implicit %exec
FLAT_STORE_DWORD %37, %28, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%29 = V_AND_B32_e32 %26, %24, implicit %exec
FLAT_STORE_DWORD %37, %29, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%30 = V_AND_B32_e64 %26, %26, implicit %exec
FLAT_STORE_DWORD %37, %30, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%31 = V_AND_B32_e64 %34, %34, implicit %exec
FLAT_STORE_DWORD %37, %31, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
S_ENDPGM
...
---
# GCN-LABEL: name: s_fold_shl_imm_regimm_32{{$}}
# GC1: %13 = V_MOV_B32_e32 4096, implicit %exec
# GCN: BUFFER_STORE_DWORD_OFFSET killed %13,
name: s_fold_shl_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: sgpr_32 }
- { id: 3, class: vgpr_32 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0_xexec }
- { id: 6, class: sreg_32_xm0 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: sreg_128 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sreg_32_xm0 }
- { id: 13, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_MOV_B32 1
%6 = COPY %4.sub1
%7 = COPY %4.sub0
%8 = S_MOV_B32 61440
%9 = S_MOV_B32 -1
%10 = REG_SEQUENCE killed %7, 1, killed %6, 2, killed %9, 3, killed %8, 4
%12 = S_LSHL_B32 killed %5, 12, implicit-def dead %scc
%13 = COPY %12
BUFFER_STORE_DWORD_OFFSET killed %13, killed %10, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out)
S_ENDPGM
...
---
# GCN-LABEL: name: v_fold_shl_imm_regimm_32{{$}}
# GCN: %11 = V_MOV_B32_e32 40955904, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %11,
# GCN: %12 = V_MOV_B32_e32 24, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %12,
# GCN: %13 = V_MOV_B32_e32 4096, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %13,
# GCN: %14 = V_MOV_B32_e32 24, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %14,
# GCN: %15 = V_MOV_B32_e32 0, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %15,
# GCN: %22 = V_MOV_B32_e32 4096, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %22,
# GCN: %23 = V_MOV_B32_e32 1, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %23,
# GCN: %25 = V_MOV_B32_e32 2, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %25,
# GCN: %26 = V_MOV_B32_e32 7927808, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %26,
# GCN: %28 = V_MOV_B32_e32 -8, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %28,
name: v_fold_shl_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: sreg_64_xexec }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: vgpr_32 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_64 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: vgpr_32 }
- { id: 11, class: vgpr_32 }
- { id: 12, class: vgpr_32 }
- { id: 13, class: vgpr_32 }
- { id: 14, class: vgpr_32 }
- { id: 15, class: vgpr_32 }
- { id: 16, class: vreg_64 }
- { id: 17, class: vreg_64 }
- { id: 18, class: vgpr_32 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vreg_64 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vgpr_32 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vgpr_32 }
- { id: 26, class: vgpr_32 }
- { id: 27, class: sreg_32_xm0 }
- { id: 28, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%2' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%2 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%3 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%15 = V_ASHRREV_I32_e64 31, %2, implicit %exec
%16 = REG_SEQUENCE %2, 1, %15, 2
%17 = V_LSHLREV_B64 2, killed %16, implicit %exec
%9 = COPY %3.sub1
%21 = V_ADD_I32_e32 %3.sub0, %17.sub0, implicit-def %vcc, implicit %exec
%19 = COPY killed %9
%18 = V_ADDC_U32_e32 %17.sub1, %19, implicit-def %vcc, implicit %vcc, implicit %exec
%20 = REG_SEQUENCE %21, 1, killed %18, 2
%10 = V_MOV_B32_e32 9999, implicit %exec
%24 = V_MOV_B32_e32 3871, implicit %exec
%6 = V_MOV_B32_e32 1, implicit %exec
%7 = S_MOV_B32 1
%27 = S_MOV_B32 -4
%11 = V_LSHLREV_B32_e64 12, %10, implicit %exec
FLAT_STORE_DWORD %20, %11, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%12 = V_LSHLREV_B32_e64 %7, 12, implicit %exec
FLAT_STORE_DWORD %20, %12, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%13 = V_LSHL_B32_e64 %7, 12, implicit %exec
FLAT_STORE_DWORD %20, %13, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%14 = V_LSHL_B32_e64 12, %7, implicit %exec
FLAT_STORE_DWORD %20, %14, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%15 = V_LSHL_B32_e64 12, %24, implicit %exec
FLAT_STORE_DWORD %20, %15, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%22 = V_LSHL_B32_e64 %6, 12, implicit %exec
FLAT_STORE_DWORD %20, %22, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%23 = V_LSHL_B32_e64 %6, 32, implicit %exec
FLAT_STORE_DWORD %20, %23, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%25 = V_LSHL_B32_e32 %6, %6, implicit %exec
FLAT_STORE_DWORD %20, %25, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%26 = V_LSHLREV_B32_e32 11, %24, implicit %exec
FLAT_STORE_DWORD %20, %26, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%28 = V_LSHL_B32_e32 %27, %6, implicit %exec
FLAT_STORE_DWORD %20, %28, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
S_ENDPGM
...
---
# GCN-LABEL: name: s_fold_ashr_imm_regimm_32{{$}}
# GCN: %11 = V_MOV_B32_e32 243, implicit %exec
# GCN: BUFFER_STORE_DWORD_OFFSET killed %11, killed %8,
name: s_fold_ashr_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0_xexec }
- { id: 6, class: sreg_32_xm0 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: sreg_128 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sreg_32_xm0 }
- { id: 13, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_MOV_B32 999123
%6 = COPY %4.sub1
%7 = COPY %4.sub0
%8 = S_MOV_B32 61440
%9 = S_MOV_B32 -1
%10 = REG_SEQUENCE killed %7, 1, killed %6, 2, killed %9, 3, killed %8, 4
%12 = S_ASHR_I32 killed %5, 12, implicit-def dead %scc
%13 = COPY %12
BUFFER_STORE_DWORD_OFFSET killed %13, killed %10, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out)
S_ENDPGM
...
# GCN-LABEL: name: v_fold_ashr_imm_regimm_32{{$}}
# GCN: %11 = V_MOV_B32_e32 3903258, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %11,
# GCN: %12 = V_MOV_B32_e32 62452139, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %12,
# GCN: %13 = V_MOV_B32_e32 1678031, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %13,
# GCN: %14 = V_MOV_B32_e32 3, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %14,
# GCN: %15 = V_MOV_B32_e32 -1, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %15,
# GCN: %22 = V_MOV_B32_e32 62500, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %22,
# GCN: %23 = V_MOV_B32_e32 500000, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %23,
# GCN: %25 = V_MOV_B32_e32 1920, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %25,
# GCN: %26 = V_MOV_B32_e32 487907, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %26,
# GCN: %28 = V_MOV_B32_e32 -1, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %28,
name: v_fold_ashr_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: sreg_64_xexec }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: vgpr_32 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: vgpr_32 }
- { id: 11, class: vgpr_32 }
- { id: 12, class: vgpr_32 }
- { id: 13, class: vgpr_32 }
- { id: 14, class: vgpr_32 }
- { id: 15, class: vgpr_32 }
- { id: 16, class: vreg_64 }
- { id: 17, class: vreg_64 }
- { id: 18, class: vgpr_32 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vreg_64 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vgpr_32 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vgpr_32 }
- { id: 26, class: vgpr_32 }
- { id: 27, class: sreg_32_xm0 }
- { id: 28, class: vgpr_32 }
- { id: 32, class: sreg_32_xm0 }
- { id: 33, class: sreg_32_xm0 }
- { id: 34, class: vgpr_32 }
- { id: 35, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%2' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%2 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%3 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%15 = V_ASHRREV_I32_e64 31, %2, implicit %exec
%16 = REG_SEQUENCE %2, 1, %15, 2
%17 = V_LSHLREV_B64 2, killed %16, implicit %exec
%9 = COPY %3.sub1
%21 = V_ADD_I32_e32 %3.sub0, %17.sub0, implicit-def %vcc, implicit %exec
%19 = COPY killed %9
%18 = V_ADDC_U32_e32 %17.sub1, %19, implicit-def %vcc, implicit %vcc, implicit %exec
%20 = REG_SEQUENCE %21, 1, killed %18, 2
%10 = V_MOV_B32_e32 999234234, implicit %exec
%24 = V_MOV_B32_e32 3871, implicit %exec
%6 = V_MOV_B32_e32 1000000, implicit %exec
%7 = S_MOV_B32 13424252
%8 = S_MOV_B32 4
%27 = S_MOV_B32 -4
%32 = S_MOV_B32 1
%33 = S_MOV_B32 3841
%34 = V_MOV_B32_e32 3841, implicit %exec
%35 = V_MOV_B32_e32 2, implicit %exec
%11 = V_ASHRREV_I32_e64 8, %10, implicit %exec
FLAT_STORE_DWORD %20, %11, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%12 = V_ASHRREV_I32_e64 %8, %10, implicit %exec
FLAT_STORE_DWORD %20, %12, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%13 = V_ASHR_I32_e64 %7, 3, implicit %exec
FLAT_STORE_DWORD %20, %13, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%14 = V_ASHR_I32_e64 7, %32, implicit %exec
FLAT_STORE_DWORD %20, %14, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%15 = V_ASHR_I32_e64 %27, %24, implicit %exec
FLAT_STORE_DWORD %20, %15, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%22 = V_ASHR_I32_e64 %6, 4, implicit %exec
FLAT_STORE_DWORD %20, %22, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%23 = V_ASHR_I32_e64 %6, %33, implicit %exec
FLAT_STORE_DWORD %20, %23, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%25 = V_ASHR_I32_e32 %34, %34, implicit %exec
FLAT_STORE_DWORD %20, %25, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%26 = V_ASHRREV_I32_e32 11, %10, implicit %exec
FLAT_STORE_DWORD %20, %26, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%28 = V_ASHR_I32_e32 %27, %35, implicit %exec
FLAT_STORE_DWORD %20, %28, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
S_ENDPGM
...
---
# GCN-LABEL: name: s_fold_lshr_imm_regimm_32{{$}}
# GCN: %11 = V_MOV_B32_e32 1048332, implicit %exec
# GCN: BUFFER_STORE_DWORD_OFFSET killed %11, killed %8,
name: s_fold_lshr_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0_xexec }
- { id: 6, class: sreg_32_xm0 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: sreg_128 }
- { id: 11, class: sreg_32_xm0 }
- { id: 12, class: sreg_32_xm0 }
- { id: 13, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1
%0 = COPY %sgpr0_sgpr1
%4 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%5 = S_MOV_B32 -999123
%6 = COPY %4.sub1
%7 = COPY %4.sub0
%8 = S_MOV_B32 61440
%9 = S_MOV_B32 -1
%10 = REG_SEQUENCE killed %7, 1, killed %6, 2, killed %9, 3, killed %8, 4
%12 = S_LSHR_B32 killed %5, 12, implicit-def dead %scc
%13 = COPY %12
BUFFER_STORE_DWORD_OFFSET killed %13, killed %10, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out)
S_ENDPGM
...
---
# GCN-LABEL: name: v_fold_lshr_imm_regimm_32{{$}}
# GCN: %11 = V_MOV_B32_e32 3903258, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %11,
# GCN: %12 = V_MOV_B32_e32 62452139, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %12,
# GCN: %13 = V_MOV_B32_e32 1678031, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %13,
# GCN: %14 = V_MOV_B32_e32 3, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %14,
# GCN: %15 = V_MOV_B32_e32 1, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %15,
# GCN: %22 = V_MOV_B32_e32 62500, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %22,
# GCN: %23 = V_MOV_B32_e32 500000, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %23,
# GCN: %25 = V_MOV_B32_e32 1920, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %25,
# GCN: %26 = V_MOV_B32_e32 487907, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %26,
# GCN: %28 = V_MOV_B32_e32 1073741823, implicit %exec
# GCN: FLAT_STORE_DWORD %20, %28,
name: v_fold_lshr_imm_regimm_32
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
registers:
- { id: 0, class: sgpr_64 }
- { id: 1, class: sreg_32_xm0 }
- { id: 2, class: vgpr_32 }
- { id: 3, class: sreg_64_xexec }
- { id: 4, class: sreg_64_xexec }
- { id: 5, class: sreg_32_xm0 }
- { id: 6, class: vgpr_32 }
- { id: 7, class: sreg_32_xm0 }
- { id: 8, class: sreg_32_xm0 }
- { id: 9, class: sreg_32_xm0 }
- { id: 10, class: vgpr_32 }
- { id: 11, class: vgpr_32 }
- { id: 12, class: vgpr_32 }
- { id: 13, class: vgpr_32 }
- { id: 14, class: vgpr_32 }
- { id: 15, class: vgpr_32 }
- { id: 16, class: vreg_64 }
- { id: 17, class: vreg_64 }
- { id: 18, class: vgpr_32 }
- { id: 19, class: vgpr_32 }
- { id: 20, class: vreg_64 }
- { id: 21, class: vgpr_32 }
- { id: 22, class: vgpr_32 }
- { id: 23, class: vgpr_32 }
- { id: 24, class: vgpr_32 }
- { id: 25, class: vgpr_32 }
- { id: 26, class: vgpr_32 }
- { id: 27, class: sreg_32_xm0 }
- { id: 28, class: vgpr_32 }
- { id: 32, class: sreg_32_xm0 }
- { id: 33, class: sreg_32_xm0 }
- { id: 34, class: vgpr_32 }
- { id: 35, class: vgpr_32 }
liveins:
- { reg: '%sgpr0_sgpr1', virtual-reg: '%0' }
- { reg: '%vgpr0', virtual-reg: '%2' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0 (%ir-block.0):
liveins: %sgpr0_sgpr1, %vgpr0
%2 = COPY %vgpr0
%0 = COPY %sgpr0_sgpr1
%3 = S_LOAD_DWORDX2_IMM %0, 36, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
%15 = V_ASHRREV_I32_e64 31, %2, implicit %exec
%16 = REG_SEQUENCE %2, 1, %15, 2
%17 = V_LSHLREV_B64 2, killed %16, implicit %exec
%9 = COPY %3.sub1
%21 = V_ADD_I32_e32 %3.sub0, %17.sub0, implicit-def %vcc, implicit %exec
%19 = COPY killed %9
%18 = V_ADDC_U32_e32 %17.sub1, %19, implicit-def %vcc, implicit %vcc, implicit %exec
%20 = REG_SEQUENCE %21, 1, killed %18, 2
%10 = V_MOV_B32_e32 999234234, implicit %exec
%24 = V_MOV_B32_e32 3871, implicit %exec
%6 = V_MOV_B32_e32 1000000, implicit %exec
%7 = S_MOV_B32 13424252
%8 = S_MOV_B32 4
%27 = S_MOV_B32 -4
%32 = S_MOV_B32 1
%33 = S_MOV_B32 3841
%34 = V_MOV_B32_e32 3841, implicit %exec
%35 = V_MOV_B32_e32 2, implicit %exec
%11 = V_LSHRREV_B32_e64 8, %10, implicit %exec
FLAT_STORE_DWORD %20, %11, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%12 = V_LSHRREV_B32_e64 %8, %10, implicit %exec
FLAT_STORE_DWORD %20, %12, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%13 = V_LSHR_B32_e64 %7, 3, implicit %exec
FLAT_STORE_DWORD %20, %13, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%14 = V_LSHR_B32_e64 7, %32, implicit %exec
FLAT_STORE_DWORD %20, %14, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%15 = V_LSHR_B32_e64 %27, %24, implicit %exec
FLAT_STORE_DWORD %20, %15, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%22 = V_LSHR_B32_e64 %6, 4, implicit %exec
FLAT_STORE_DWORD %20, %22, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%23 = V_LSHR_B32_e64 %6, %33, implicit %exec
FLAT_STORE_DWORD %20, %23, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%25 = V_LSHR_B32_e32 %34, %34, implicit %exec
FLAT_STORE_DWORD %20, %25, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%26 = V_LSHRREV_B32_e32 11, %10, implicit %exec
FLAT_STORE_DWORD %20, %26, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
%28 = V_LSHR_B32_e32 %27, %35, implicit %exec
FLAT_STORE_DWORD %20, %28, 0, 0, 0, implicit %exec, implicit %flat_scr :: (volatile store 4 into %ir.gep.out)
S_ENDPGM
...
---
# There is only an undef use operand for %1, so there is no
# corresponding defining instruction
# GCN-LABEL: name: undefined_vreg_operand{{$}}
# GCN: bb.0
# GCN-NEXT: FLAT_STORE_DWORD undef %3, undef %1,
# GCN-NEXT: S_ENDPGM
name: undefined_vreg_operand
tracksRegLiveness: true
registers:
- { id: 0, class: vgpr_32, preferred-register: '' }
- { id: 1, class: vgpr_32, preferred-register: '' }
- { id: 2, class: vgpr_32, preferred-register: '' }
- { id: 3, class: vreg_64, preferred-register: '' }
body: |
bb.0:
%0 = V_MOV_B32_e32 0, implicit %exec
%2 = V_XOR_B32_e64 killed %0, undef %1, implicit %exec
FLAT_STORE_DWORD undef %3, %2, 0, 0, 0, implicit %exec, implicit %flat_scr
S_ENDPGM
...