forked from OSchip/llvm-project
598 lines
21 KiB
YAML
598 lines
21 KiB
YAML
# RUN: llc -verify-machineinstrs -march=amdgcn -run-pass si-shrink-instructions -o - %s | FileCheck -check-prefix=GCN %s
|
|
# Check that add with carry out isn't incorrectly reduced to e32 when
|
|
# the carry out is a virtual register.
|
|
|
|
# TODO: We should run this test until the end of codegen to make sure
|
|
# that the post-RA run does manage to shrink it, but right now the
|
|
# resume crashes
|
|
|
|
--- |
|
|
define amdgpu_kernel void @shrink_add_vop3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = add i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @shrink_sub_vop3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = sub i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @shrink_subrev_vop3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = sub i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @check_addc_src2_vop3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = add i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @shrink_addc_vop3(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = add i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
define amdgpu_kernel void @shrink_addc_undef_vcc(i32 addrspace(1)* %out, i32 addrspace(1)* %in) #0 {
|
|
%tid = call i32 @llvm.amdgcn.workitem.id.x()
|
|
%tid.ext = sext i32 %tid to i64
|
|
%a.ptr = getelementptr inbounds i32, i32 addrspace(1)* %in, i64 %tid.ext
|
|
%b.ptr = getelementptr i32, i32 addrspace(1)* %a.ptr, i32 1
|
|
%out.gep = getelementptr i32, i32 addrspace(1)* %out, i64 %tid.ext
|
|
%a = load volatile i32, i32 addrspace(1)* %a.ptr
|
|
%b = load volatile i32, i32 addrspace(1)* %b.ptr
|
|
%result = add i32 %a, %b
|
|
store volatile i32 %result, i32 addrspace(1)* %out.gep
|
|
ret void
|
|
}
|
|
|
|
declare i32 @llvm.amdgcn.workitem.id.x() #1
|
|
|
|
attributes #0 = { nounwind }
|
|
attributes #1 = { nounwind readnone }
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: shrink_add_vop3{{$}}
|
|
# GCN: %29, %9 = V_ADD_I32_e64 %19, %17, implicit %exec
|
|
# GCN: %24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
name: shrink_add_vop3
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%29, %9 = V_ADD_I32_e64 %19, %17, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %24, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: shrink_sub_vop3{{$}}
|
|
# GCN: %29, %9 = V_SUB_I32_e64 %19, %17, implicit %exec
|
|
# GCN: %24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
|
|
name: shrink_sub_vop3
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%29, %9 = V_SUB_I32_e64 %19, %17, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %24, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: shrink_subrev_vop3{{$}}
|
|
# GCN: %29, %9 = V_SUBREV_I32_e64 %19, %17, implicit %exec
|
|
# GCN: %24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
|
|
name: shrink_subrev_vop3
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%29, %9 = V_SUBREV_I32_e64 %19, %17, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %9, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %29, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: check_addc_src2_vop3{{$}}
|
|
# GCN: %29, %vcc = V_ADDC_U32_e64 %19, %17, %9, implicit %exec
|
|
# GCN: %24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
name: check_addc_src2_vop3
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%9 = S_MOV_B64 0
|
|
%29, %vcc = V_ADDC_U32_e64 %19, %17, %9, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %24, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|
|
---
|
|
# GCN-LABEL: name: shrink_addc_vop3{{$}}
|
|
# GCN: %29 = V_ADDC_U32_e32 %17, %19, implicit-def %vcc, implicit %vcc, implicit %exec
|
|
# GCN %24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
|
|
name: shrink_addc_vop3
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%vcc = S_MOV_B64 0
|
|
%29, %vcc = V_ADDC_U32_e64 %19, %17, %vcc, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %24, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|
|
|
|
---
|
|
# GCN-LABEL: name: shrink_addc_undef_vcc{{$}}
|
|
# GCN: %29 = V_ADDC_U32_e32 %17, %19, implicit-def %vcc, implicit undef %vcc, implicit %exec
|
|
# GCN: %24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
name: shrink_addc_undef_vcc
|
|
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_64_xexec }
|
|
- { id: 6, class: sreg_32 }
|
|
- { id: 7, class: sreg_32 }
|
|
- { id: 8, class: sreg_32_xm0 }
|
|
- { id: 9, class: sreg_64 }
|
|
- { id: 10, class: sreg_32_xm0 }
|
|
- { id: 11, class: sreg_32_xm0 }
|
|
- { id: 12, class: sgpr_64 }
|
|
- { id: 13, class: sgpr_128 }
|
|
- { id: 14, class: sreg_32_xm0 }
|
|
- { id: 15, class: sreg_64 }
|
|
- { id: 16, class: sgpr_128 }
|
|
- { id: 17, class: vgpr_32 }
|
|
- { id: 18, class: vreg_64 }
|
|
- { id: 19, class: vgpr_32 }
|
|
- { id: 20, class: vreg_64 }
|
|
- { id: 21, class: sreg_32_xm0 }
|
|
- { id: 22, class: sreg_32 }
|
|
- { id: 23, class: sreg_32 }
|
|
- { id: 24, class: vgpr_32 }
|
|
- { id: 25, class: vreg_64 }
|
|
- { id: 26, class: vgpr_32 }
|
|
- { id: 27, class: vreg_64 }
|
|
- { id: 28, class: vreg_64 }
|
|
- { id: 29, 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, 9, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%5 = S_LOAD_DWORDX2_IMM %0, 11, 0 :: (non-temporal dereferenceable invariant load 8 from `i64 addrspace(2)* undef`)
|
|
%26 = V_ASHRREV_I32_e32 31, %3, implicit %exec
|
|
%27 = REG_SEQUENCE %3, 1, %26, 2
|
|
%10 = S_MOV_B32 61440
|
|
%11 = S_MOV_B32 0
|
|
%12 = REG_SEQUENCE killed %11, 1, killed %10, 2
|
|
%13 = REG_SEQUENCE killed %5, 17, %12, 18
|
|
%28 = V_LSHL_B64 killed %27, 2, implicit %exec
|
|
%16 = REG_SEQUENCE killed %4, 17, %12, 18
|
|
%17 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.a.ptr)
|
|
%19 = BUFFER_LOAD_DWORD_ADDR64 %28, %13, 0, 4, 0, 0, 0, implicit %exec :: (volatile load 4 from %ir.b.ptr)
|
|
%29, %vcc = V_ADDC_U32_e64 %19, %17, undef %vcc, implicit %exec
|
|
%24 = V_CNDMASK_B32_e64 0, 1, killed %vcc, implicit %exec
|
|
BUFFER_STORE_DWORD_ADDR64 %24, %28, killed %16, 0, 0, 0, 0, 0, implicit %exec :: (volatile store 4 into %ir.out.gep)
|
|
S_ENDPGM
|
|
|
|
...
|