llvm-project/llvm/test/CodeGen/AMDGPU/optimize-if-exec-masking.mir

756 lines
22 KiB
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-optimize-exec-masking -o - %s | FileCheck %s
--- |
target datalayout = "e-p:32:32-p1:64:64-p2:64:64-p3:32:32-p4:64:64-p5:32:32-i64:64-v16:16-v24:32-v32:32-v48:64-v96:128-v192:256-v256:256-v512:512-v1024:1024-v2048:2048-n32:64"
define void @optimize_if_and_saveexec_xor(i32 %z, i32 %v) #0 {
main_body:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%cc = icmp eq i32 %id, 0
%0 = call { i1, i64 } @llvm.amdgcn.if(i1 %cc)
%1 = extractvalue { i1, i64 } %0, 0
%2 = extractvalue { i1, i64 } %0, 1
br i1 %1, label %if, label %end
if: ; preds = %main_body
%v.if = load volatile i32, i32 addrspace(1)* undef
br label %end
end: ; preds = %if, %main_body
%r = phi i32 [ 4, %main_body ], [ %v.if, %if ]
call void @llvm.amdgcn.end.cf(i64 %2)
store i32 %r, i32 addrspace(1)* undef
ret void
}
define void @optimize_if_and_saveexec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_or_saveexec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_and_saveexec_xor_valu_middle(i32 %z, i32 %v) #0 {
main_body:
%id = call i32 @llvm.amdgcn.workitem.id.x()
%cc = icmp eq i32 %id, 0
%0 = call { i1, i64 } @llvm.amdgcn.if(i1 %cc)
%1 = extractvalue { i1, i64 } %0, 0
%2 = extractvalue { i1, i64 } %0, 1
store i32 %id, i32 addrspace(1)* undef
br i1 %1, label %if, label %end
if: ; preds = %main_body
%v.if = load volatile i32, i32 addrspace(1)* undef
br label %end
end: ; preds = %if, %main_body
%r = phi i32 [ 4, %main_body ], [ %v.if, %if ]
call void @llvm.amdgcn.end.cf(i64 %2)
store i32 %r, i32 addrspace(1)* undef
ret void
}
define void @optimize_if_and_saveexec_xor_wrong_reg(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_and_saveexec_xor_modify_copy_to_exec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_and_saveexec_xor_live_out_setexec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_unknown_saveexec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_andn2_saveexec(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define void @optimize_if_andn2_saveexec_no_commute(i32 %z, i32 %v) #0 {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
; Function Attrs: nounwind readnone
declare i32 @llvm.amdgcn.workitem.id.x() #1
declare { i1, i64 } @llvm.amdgcn.if(i1)
declare void @llvm.amdgcn.end.cf(i64)
attributes #0 = { nounwind }
attributes #1 = { nounwind readnone }
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor{{$}}
# CHECK: %sgpr0_sgpr1 = S_AND_SAVEEXEC_B64 %vcc, implicit-def %exec, implicit-def %scc, implicit %exec
# CHECK-NEXT: %sgpr0_sgpr1 = S_XOR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec{{$}}
# CHECK: %sgpr0_sgpr1 = S_AND_SAVEEXEC_B64 %vcc, implicit-def %exec, implicit-def %scc, implicit %exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_or_saveexec{{$}}
# CHECK: %sgpr0_sgpr1 = S_OR_SAVEEXEC_B64 %vcc, implicit-def %exec, implicit-def %scc, implicit %exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_or_saveexec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_OR_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_valu_middle
# CHECK: %sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
# CHECK-NEXT: BUFFER_STORE_DWORD_OFFSET %vgpr0, undef %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
# CHECK-NEXT: %sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: %exec = COPY killed %sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor_valu_middle
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
BUFFER_STORE_DWORD_OFFSET %vgpr0, undef %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
%sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_wrong_reg{{$}}
# CHECK: %sgpr0_sgpr1 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
# CHECK-NEXT: %sgpr0_sgpr1 = S_XOR_B64 undef %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: %exec = COPY %sgpr0_sgpr1
# CHECK-NEXT: SI_MASK_BRANCH %bb.2.end, implicit %exec
name: optimize_if_and_saveexec_xor_wrong_reg
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr6 = S_MOV_B32 -1
%sgpr7 = S_MOV_B32 61440
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr0_sgpr1 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%sgpr0_sgpr1 = S_XOR_B64 undef %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term %sgpr0_sgpr1
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1 , %sgpr4_sgpr5_sgpr6_sgpr7
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1, %sgpr4_sgpr5_sgpr6_sgpr7
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_modify_copy_to_exec{{$}}
# CHECK: %sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
# CHECK-NEXT: %sgpr2_sgpr3 = S_OR_B64 killed %sgpr2_sgpr3, 1, implicit-def %scc
# CHECK-NEXT: %sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: %exec = COPY killed %sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH %bb.2.end, implicit %exec
name: optimize_if_and_saveexec_xor_modify_copy_to_exec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%sgpr2_sgpr3 = S_OR_B64 killed %sgpr2_sgpr3, 1, implicit-def %scc
%sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr0 = S_MOV_B32 0
%sgpr1 = S_MOV_B32 1
%sgpr2 = S_MOV_B32 -1
%sgpr3 = S_MOV_B32 61440
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_live_out_setexec{{$}}
# CHECK: %sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
# CHECK-NEXT: %sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: %exec = COPY %sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor_live_out_setexec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_AND_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%sgpr0_sgpr1 = S_XOR_B64 %sgpr2_sgpr3, killed %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1, %sgpr2_sgpr3
S_SLEEP 0, implicit %sgpr2_sgpr3
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
# CHECK-LABEL: name: optimize_if_unknown_saveexec{{$}}
# CHECK: %sgpr0_sgpr1 = COPY %exec
# CHECK: %sgpr2_sgpr3 = S_LSHR_B64 %sgpr0_sgpr1, killed %vcc_lo, implicit-def %scc
# CHECK-NEXT: %exec = COPY killed %sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH %bb.2.end, implicit %exec
name: optimize_if_unknown_saveexec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
frameInfo:
isFrameAddressTaken: false
isReturnAddressTaken: false
hasStackMap: false
hasPatchPoint: false
stackSize: 0
offsetAdjustment: 0
maxAlignment: 0
adjustsStack: false
hasCalls: false
maxCallFrameSize: 0
hasOpaqueSPAdjustment: false
hasVAStart: false
hasMustTailInVarArgFunc: false
body: |
bb.0.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_LSHR_B64 %sgpr0_sgpr1, killed %vcc_lo, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_andn2_saveexec{{$}}
# CHECK: %sgpr0_sgpr1 = S_ANDN2_SAVEEXEC_B64 %vcc, implicit-def %exec, implicit-def %scc, implicit %exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_andn2_saveexec
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_ANDN2_B64 %sgpr0_sgpr1, killed %vcc, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...
---
# CHECK-LABEL: name: optimize_if_andn2_saveexec_no_commute{{$}}
# CHECK: %sgpr2_sgpr3 = S_ANDN2_B64 killed %vcc, %sgpr0_sgpr1, implicit-def %scc
# CHECK-NEXT: %exec = COPY killed %sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH %bb.2.end, implicit %exec
name: optimize_if_andn2_saveexec_no_commute
alignment: 0
exposesReturnsTwice: false
legalized: false
regBankSelected: false
selected: false
tracksRegLiveness: true
liveins:
- { reg: '%vgpr0' }
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.main_body:
successors: %bb.1.if, %bb.2.end
liveins: %vgpr0
%sgpr0_sgpr1 = COPY %exec
%vcc = V_CMP_EQ_I32_e64 0, killed %vgpr0, implicit %exec
%vgpr0 = V_MOV_B32_e32 4, implicit %exec
%sgpr2_sgpr3 = S_ANDN2_B64 killed %vcc, %sgpr0_sgpr1, implicit-def %scc
%exec = S_MOV_B64_term killed %sgpr2_sgpr3
SI_MASK_BRANCH %bb.2.end, implicit %exec
S_BRANCH %bb.1.if
bb.1.if:
successors: %bb.2.end
liveins: %sgpr0_sgpr1
%sgpr7 = S_MOV_B32 61440
%sgpr6 = S_MOV_B32 -1
%vgpr0 = BUFFER_LOAD_DWORD_OFFSET %sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, implicit %exec :: (volatile load 4 from `i32 addrspace(1)* undef`)
bb.2.end:
liveins: %vgpr0, %sgpr0_sgpr1
%exec = S_OR_B64 %exec, killed %sgpr0_sgpr1, implicit-def %scc
%sgpr3 = S_MOV_B32 61440
%sgpr2 = S_MOV_B32 -1
BUFFER_STORE_DWORD_OFFSET killed %vgpr0, %sgpr0_sgpr1_sgpr2_sgpr3, 0, 0, 0, 0, 0, implicit %exec :: (store 4 into `i32 addrspace(1)* undef`)
S_ENDPGM
...