forked from OSchip/llvm-project
250 lines
16 KiB
YAML
250 lines
16 KiB
YAML
# RUN: llc -march=amdgcn -mcpu=gfx900 -run-pass si-fixup-vector-isel -amdgpu-enable-global-sgpr-addr %s -o - | FileCheck -check-prefix=GCN %s
|
|
|
|
# Coverage tests for GLOBAL_* to their _SADDR equivalent.
|
|
|
|
# GCN-LABEL: name: global_load_store_atomics
|
|
# GCN: GLOBAL_LOAD_DWORD_SADDR
|
|
# GCN: GLOBAL_STORE_DWORD_SADDR
|
|
# GCN: GLOBAL_LOAD_DWORDX2_SADDR
|
|
# GCN: GLOBAL_STORE_DWORDX2_SADDR
|
|
# GCN: GLOBAL_LOAD_DWORDX3_SADDR
|
|
# GCN: GLOBAL_STORE_DWORDX3_SADDR
|
|
# GCN: GLOBAL_LOAD_DWORDX4_SADDR
|
|
# GCN: GLOBAL_STORE_DWORDX4_SADDR
|
|
# GCN: GLOBAL_LOAD_SSHORT_SADDR
|
|
# GCN: GLOBAL_STORE_SHORT_SADDR
|
|
# GCN: GLOBAL_LOAD_USHORT_SADDR
|
|
# GCN: GLOBAL_STORE_SHORT_SADDR
|
|
# GCN: GLOBAL_LOAD_UBYTE_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_SADDR
|
|
# GCN: GLOBAL_LOAD_SBYTE_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_SADDR
|
|
# GCN: GLOBAL_LOAD_SBYTE_D16_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_LOAD_UBYTE_D16_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_LOAD_SBYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_LOAD_UBYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_STORE_BYTE_D16_HI_SADDR
|
|
# GCN: GLOBAL_LOAD_SHORT_D16_HI_SADDR
|
|
# GCN: GLOBAL_STORE_SHORT_D16_HI_SADDR
|
|
# GCN: GLOBAL_LOAD_SHORT_D16_SADDR
|
|
# GCN: GLOBAL_STORE_SHORT_D16_HI_SADDR
|
|
|
|
# GCN: GLOBAL_ATOMIC_XOR_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_XOR_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SMIN_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SMIN_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_AND_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_AND_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SWAP_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SWAP_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SMAX_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SMAX_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_UMIN_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_UMIN_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_UMAX_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_UMAX_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_OR_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_OR_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_ADD_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_ADD_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SUB_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SUB_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_CMPSWAP_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_CMPSWAP_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_INC_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_INC_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_DEC_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_DEC_SADDR %
|
|
|
|
# GCN: GLOBAL_ATOMIC_OR_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_OR_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_XOR_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_XOR_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_AND_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_AND_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_ADD_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_ADD_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SUB_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SUB_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_DEC_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_DEC_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_INC_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_INC_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SMIN_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SMIN_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SWAP_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SWAP_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_SMAX_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_SMAX_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_UMIN_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_UMIN_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_UMAX_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_UMAX_X2_SADDR %
|
|
# GCN: GLOBAL_ATOMIC_CMPSWAP_X2_SADDR_RTN
|
|
# GCN: GLOBAL_ATOMIC_CMPSWAP_X2_SADDR %
|
|
|
|
name: global_load_store_atomics
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $sgpr0_sgpr1
|
|
|
|
%1:sgpr_64 = COPY $sgpr0_sgpr1
|
|
%0:vgpr_32 = COPY $vgpr0
|
|
%4:sreg_64_xexec = S_LOAD_DWORDX2_IMM %1, 36, 0, 0 :: (dereferenceable invariant load 8 )
|
|
%5:sreg_32_xm0 = S_MOV_B32 2
|
|
%6:vgpr_32 = V_LSHLREV_B32_e64 killed %5, %0, implicit $exec
|
|
%7:sreg_32_xm0 = S_MOV_B32 0
|
|
%15:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
%14:vreg_64 = REG_SEQUENCE killed %6, %subreg.sub0, killed %15, %subreg.sub1
|
|
%21:sgpr_32 = COPY %4.sub0
|
|
%22:vgpr_32 = COPY %14.sub0
|
|
%23:sgpr_32 = COPY %4.sub1
|
|
%24:vgpr_32 = COPY %14.sub1
|
|
%17:vgpr_32, %19:sreg_64_xexec = V_ADD_I32_e64 %21, %22, 0, implicit $exec
|
|
%25:vgpr_32 = COPY %23
|
|
%18:vgpr_32, dead %20:sreg_64_xexec = V_ADDC_U32_e64 %25, %24, killed %19, 0, implicit $exec
|
|
%16:vreg_64 = REG_SEQUENCE %17, %subreg.sub0, %18, %subreg.sub1
|
|
%11:vreg_64 = COPY %16
|
|
|
|
%10:vgpr_32 = GLOBAL_LOAD_DWORD %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_DWORD %11, %10, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%40:vreg_64 = GLOBAL_LOAD_DWORDX2 %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_DWORDX2 %11, %40, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%41:vreg_96 = GLOBAL_LOAD_DWORDX3 %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_DWORDX3 %11, %41, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%42:vreg_128 = GLOBAL_LOAD_DWORDX4 %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_DWORDX4 %11, %42, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%43:vgpr_32 = GLOBAL_LOAD_SSHORT %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_SHORT %11, %43, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%44:vgpr_32 = GLOBAL_LOAD_USHORT %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_SHORT %11, %44, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%45:vgpr_32 = GLOBAL_LOAD_UBYTE %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE %11, %45, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%46:vgpr_32 = GLOBAL_LOAD_SBYTE %11, 16, 0, 0, 0, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE %11, %46, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%47:vgpr_32 = GLOBAL_LOAD_SBYTE_D16 %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE_D16_HI %11, %47, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%48:vgpr_32 = GLOBAL_LOAD_UBYTE_D16 %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE_D16_HI %11, %48, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%49:vgpr_32 = GLOBAL_LOAD_SBYTE_D16_HI %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE_D16_HI %11, %49, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%50:vgpr_32 = GLOBAL_LOAD_UBYTE_D16_HI %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_BYTE_D16_HI %11, %50, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%51:vgpr_32 = GLOBAL_LOAD_SHORT_D16_HI %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_SHORT_D16_HI %11, %51, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
%52:vgpr_32 = GLOBAL_LOAD_SHORT_D16 %11, 16, 0, 0, 0, %46, implicit $exec :: (load 4)
|
|
GLOBAL_STORE_SHORT_D16_HI %11, %52, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
|
|
%53:vgpr_32 = GLOBAL_ATOMIC_XOR_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %53, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_XOR %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%54:vgpr_32 = GLOBAL_ATOMIC_SMIN_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %54, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SMIN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%55:vgpr_32 = GLOBAL_ATOMIC_AND_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %55, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_AND %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%56:vgpr_32 = GLOBAL_ATOMIC_SWAP_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %56, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SWAP %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%57:vgpr_32 = GLOBAL_ATOMIC_SMAX_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %57, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SMAX %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%58:vgpr_32 = GLOBAL_ATOMIC_UMIN_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %58, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_UMIN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%59:vgpr_32 = GLOBAL_ATOMIC_UMAX_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %59, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_UMAX %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%60:vgpr_32 = GLOBAL_ATOMIC_OR_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %60, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_OR %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%61:vgpr_32 = GLOBAL_ATOMIC_ADD_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %61, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_ADD %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%62:vgpr_32 = GLOBAL_ATOMIC_SUB_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %62, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SUB %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%63:vgpr_32 = GLOBAL_ATOMIC_CMPSWAP_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %63, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_CMPSWAP %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%64:vgpr_32 = GLOBAL_ATOMIC_INC_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %64, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_INC %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%65:vgpr_32 = GLOBAL_ATOMIC_DEC_RTN %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORD %11, %65, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_DEC %11, %15, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%66:vreg_64 = GLOBAL_ATOMIC_OR_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %66, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_OR_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%67:vreg_64 = GLOBAL_ATOMIC_XOR_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %67, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_XOR_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%68:vreg_64 = GLOBAL_ATOMIC_AND_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %68, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_AND_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%69:vreg_64 = GLOBAL_ATOMIC_ADD_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %69, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_ADD_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%70:vreg_64 = GLOBAL_ATOMIC_SUB_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %70, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SUB_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%71:vreg_64 = GLOBAL_ATOMIC_DEC_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %71, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_DEC_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%72:vreg_64 = GLOBAL_ATOMIC_INC_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %72, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_INC_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%73:vreg_64 = GLOBAL_ATOMIC_SMIN_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %73, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SMIN_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%74:vreg_64 = GLOBAL_ATOMIC_SWAP_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %74, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SWAP_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%75:vreg_64 = GLOBAL_ATOMIC_SMAX_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %75, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_SMAX_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%76:vreg_64 = GLOBAL_ATOMIC_UMIN_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %76, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_UMIN_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%77:vreg_64 = GLOBAL_ATOMIC_UMAX_X2_RTN %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %77, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_UMAX_X2 %11, %16, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
%79:sgpr_128 = REG_SEQUENCE %4, %subreg.sub0, %4, %subreg.sub1, %4, %subreg.sub2, %4, %subreg.sub3
|
|
%80:vreg_128 = COPY %79
|
|
|
|
%78:vreg_64 = GLOBAL_ATOMIC_CMPSWAP_X2_RTN %11, %80, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
GLOBAL_STORE_DWORDX2 %11, %78, 0, 0, 0, 0, implicit $exec :: (volatile store 4 into `i32 addrspace(1)* undef`, addrspace 1)
|
|
GLOBAL_ATOMIC_CMPSWAP_X2 %11, %80, 16, 0, implicit $exec :: (volatile load store seq_cst 4, addrspace 1)
|
|
|
|
S_ENDPGM 0
|
|
...
|