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

553 lines
16 KiB
YAML

# RUN: llc -march=amdgcn -verify-machineinstrs -run-pass si-optimize-exec-masking -o - %s | FileCheck %s
--- |
define amdgpu_kernel void @optimize_if_and_saveexec_xor(i32 %z, i32 %v) {
main_body:
br i1 undef, 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
ret void
}
define amdgpu_kernel void @optimize_if_and_saveexec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_or_saveexec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_and_saveexec_xor_valu_middle(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if: ; preds = %main_body
br label %end
end: ; preds = %if, %main_body
ret void
}
define amdgpu_kernel void @optimize_if_and_saveexec_xor_wrong_reg(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_and_saveexec_xor_modify_copy_to_exec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_and_saveexec_xor_live_out_setexec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_unknown_saveexec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_andn2_saveexec(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @optimize_if_andn2_saveexec_no_commute(i32 %z, i32 %v) {
main_body:
br i1 undef, label %if, label %end
if:
br label %end
end:
ret void
}
define amdgpu_kernel void @if_and_xor_read_exec_copy_subreg() {
main_body:
br i1 undef, label %if, label %end
if: ; preds = %main_body
br label %end
end: ; preds = %if, %main_body
ret void
}
...
---
# 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 $scc
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec{{$}}
# CHECK: $sgpr0_sgpr1 = S_AND_SAVEEXEC_B64 $vcc, implicit-def $exec, implicit-def $scc, implicit $exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_or_saveexec{{$}}
# CHECK: $sgpr0_sgpr1 = S_OR_SAVEEXEC_B64 $vcc, implicit-def $exec, implicit-def $scc, implicit $exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_or_saveexec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# 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, 0, implicit $exec
# CHECK-NEXT: $sgpr0_sgpr1 = S_XOR_B64 $sgpr2_sgpr3, killed $sgpr0_sgpr1, implicit-def $scc
# CHECK-NEXT: $exec = COPY killed $sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor_valu_middle
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, 0, implicit $exec
$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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_wrong_reg{{$}}
# 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, implicit $exec
name: optimize_if_and_saveexec_xor_wrong_reg
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
liveins: $sgpr0_sgpr1 , $sgpr4_sgpr5_sgpr6_sgpr7
$vgpr0 = BUFFER_LOAD_DWORD_OFFSET $sgpr4_sgpr5_sgpr6_sgpr7, 0, 0, 0, 0, 0, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_modify_copy_to_exec{{$}}
# 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, implicit $exec
name: optimize_if_and_saveexec_xor_modify_copy_to_exec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_and_saveexec_xor_live_out_setexec{{$}}
# 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 $sgpr2_sgpr3
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_and_saveexec_xor_live_out_setexec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
# CHECK-LABEL: name: optimize_if_unknown_saveexec{{$}}
# 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, implicit $exec
name: optimize_if_unknown_saveexec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_andn2_saveexec{{$}}
# CHECK: $sgpr0_sgpr1 = S_ANDN2_SAVEEXEC_B64 $vcc, implicit-def $exec, implicit-def $scc, implicit $exec
# CHECK-NEXT: SI_MASK_BRANCH
name: optimize_if_andn2_saveexec
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# CHECK-LABEL: name: optimize_if_andn2_saveexec_no_commute{{$}}
# 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, implicit $exec
name: optimize_if_andn2_saveexec_no_commute
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...
---
# A read from exec copy subreg prevents optimization
# CHECK-LABEL: name: if_and_xor_read_exec_copy_subreg{{$}}
# CHECK: $sgpr0_sgpr1 = COPY $exec
# CHECK-NEXT: $sgpr4 = S_MOV_B32 $sgpr1
name: if_and_xor_read_exec_copy_subreg
liveins:
- { reg: '$vgpr0' }
body: |
bb.0.main_body:
liveins: $vgpr0
$sgpr0_sgpr1 = COPY $exec
$sgpr4 = S_MOV_B32 $sgpr1
$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, implicit $exec
S_BRANCH %bb.1
bb.1.if:
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, 0, implicit $exec
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, 0, implicit $exec
S_ENDPGM 0
...