# 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 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, 0, implicit $exec S_ENDPGM 0 ...