|
|
# RUN: llc -march=amdgcn -mcpu=gfx900 -start-before=twoaddressinstruction %s -o - | FileCheck %s -check-prefix=GCN
|
|
|
|
|
|
# Wait to sxpand SI_INDIRECT sequences that use VGPR indexing until after
|
|
|
# register allocation. We don’t want to reschedule the mode switching or to
|
|
|
# have any instructions inserted within the sequence. The Two-Address
|
|
|
# instruction pass could insert bad copies here if it is expanded too early.
|
|
|
|
|
|
---
|
|
|
# GCN-LABEL: expand_si_indirect
|
|
|
# GCN: s_set_gpr_idx_on
|
|
|
# GCN-NEXT: v_mov_b32_e32
|
|
|
# GCN-NEXT: s_set_gpr_idx_off
|
|
|
|
|
|
# GCN: s_set_gpr_idx_on
|
|
|
# GCN-NEXT: v_mov_b32_e32
|
|
|
# GCN-NOT: v_mov_b32_e32
|
|
|
# GCN-NEXT: s_set_gpr_idx_off
|
|
|
|
|
|
name: expand_si_indirect
|
|
|
tracksRegLiveness: true
|
|
|
body: |
|
|
|
bb.0.entry:
|
|
|
liveins: $sgpr0_sgpr1
|
|
|
|
|
|
%0:sgpr_64 = COPY killed $sgpr0_sgpr1
|
|
|
%1:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
|
|
|
%2:sreg_64_xexec = S_LOAD_DWORDX2_IMM %0(p4), 36, 0, 0
|
|
|
%3:sreg_32_xm0_xexec = S_LOAD_DWORD_IMM killed %0(p4), 44, 0, 0
|
|
|
%4:sreg_32 = S_ADD_I32 %3, 1, implicit-def dead $scc
|
|
|
%5:vgpr_32 = V_MOV_B32_e32 1065353216, implicit $exec
|
|
|
%6:vgpr_32 = V_MOV_B32_e32 1073741824, implicit $exec
|
|
|
%7:vgpr_32 = V_MOV_B32_e32 1077936128, implicit $exec
|
|
|
%8:vgpr_32 = V_MOV_B32_e32 1082130432, implicit $exec
|
|
|
%9:vgpr_32 = V_MOV_B32_e32 1084227584, implicit $exec
|
|
|
%10:vgpr_32 = V_MOV_B32_e32 1086324736, implicit $exec
|
|
|
%11:vgpr_32 = V_MOV_B32_e32 1088421888, implicit $exec
|
|
|
%12:vgpr_32 = V_MOV_B32_e32 1090519040, implicit $exec
|
|
|
%13:vgpr_32 = V_MOV_B32_e32 1091567616, implicit $exec
|
|
|
%14:vgpr_32 = V_MOV_B32_e32 1092616192, implicit $exec
|
|
|
%15:vgpr_32 = V_MOV_B32_e32 1093664768, implicit $exec
|
|
|
%16:vgpr_32 = V_MOV_B32_e32 1094713344, implicit $exec
|
|
|
%17:vgpr_32 = V_MOV_B32_e32 1095761920, implicit $exec
|
|
|
%18:vgpr_32 = V_MOV_B32_e32 1096810496, implicit $exec
|
|
|
%19:vgpr_32 = V_MOV_B32_e32 1097859072, implicit $exec
|
|
|
%20:vgpr_32 = V_MOV_B32_e32 1098907648, implicit $exec
|
|
|
%21:vreg_512 = REG_SEQUENCE killed %5, %subreg.sub0, killed %6, %subreg.sub1, killed %7, %subreg.sub2, killed %8, %subreg.sub3, killed %9, %subreg.sub4, killed %10, %subreg.sub5, killed %11, %subreg.sub6, killed %12, %subreg.sub7, killed %13, %subreg.sub8, killed %14, %subreg.sub9, killed %15, %subreg.sub10, killed %16, %subreg.sub11, killed %17, %subreg.sub12, killed %18, %subreg.sub13, killed %19, %subreg.sub14, killed %20, %subreg.sub15
|
|
|
%22:vgpr_32 = V_MOV_B32_e32 1099431936, implicit $exec
|
|
|
%23:vreg_512 = V_INDIRECT_REG_WRITE_GPR_IDX_B32_V16 killed %21, %22, killed %4, 3, implicit-def $m0, implicit $m0, implicit $exec
|
|
|
%24:sreg_32 = S_ADD_I32 killed %3, 2, implicit-def dead $scc
|
|
|
%25:vreg_512 = V_INDIRECT_REG_WRITE_GPR_IDX_B32_V16 %23, killed %22, killed %24, 3, implicit-def $m0, implicit $m0, implicit $exec
|
|
|
%26:vgpr_32 = COPY %23.sub15
|
|
|
%27:vgpr_32 = COPY %23.sub14
|
|
|
%28:vgpr_32 = COPY %23.sub13
|
|
|
%29:vgpr_32 = COPY %23.sub12
|
|
|
%30:vreg_128 = REG_SEQUENCE killed %29, %subreg.sub0, killed %28, %subreg.sub1, killed %27, %subreg.sub2, killed %26, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %30, %2, 48, 0, 0, 0, implicit $exec
|
|
|
%31:vgpr_32 = COPY %23.sub11
|
|
|
%32:vgpr_32 = COPY %23.sub10
|
|
|
%33:vgpr_32 = COPY %23.sub9
|
|
|
%34:vgpr_32 = COPY %23.sub8
|
|
|
%35:vreg_128 = REG_SEQUENCE killed %34, %subreg.sub0, killed %33, %subreg.sub1, killed %32, %subreg.sub2, killed %31, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %35, %2, 32, 0, 0, 0, implicit $exec
|
|
|
%36:vgpr_32 = COPY %23.sub7
|
|
|
%37:vgpr_32 = COPY %23.sub6
|
|
|
%38:vgpr_32 = COPY %23.sub5
|
|
|
%39:vgpr_32 = COPY %23.sub4
|
|
|
%40:vreg_128 = REG_SEQUENCE killed %39, %subreg.sub0, killed %38, %subreg.sub1, killed %37, %subreg.sub2, killed %36, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %40, %2, 16, 0, 0, 0, implicit $exec
|
|
|
%41:vgpr_32 = COPY %23.sub3
|
|
|
%42:vgpr_32 = COPY %23.sub2
|
|
|
%43:vgpr_32 = COPY %23.sub1
|
|
|
%44:vgpr_32 = COPY killed %23.sub0
|
|
|
%45:vreg_128 = REG_SEQUENCE killed %44, %subreg.sub0, killed %43, %subreg.sub1, killed %42, %subreg.sub2, killed %41, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %45, %2, 0, 0, 0, 0, implicit $exec
|
|
|
%46:vgpr_32 = COPY %25.sub15
|
|
|
%47:vgpr_32 = COPY %25.sub14
|
|
|
%48:vgpr_32 = COPY %25.sub13
|
|
|
%49:vgpr_32 = COPY %25.sub12
|
|
|
%50:vreg_128 = REG_SEQUENCE killed %49, %subreg.sub0, killed %48, %subreg.sub1, killed %47, %subreg.sub2, killed %46, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %50, %2, 112, 0, 0, 0, implicit $exec
|
|
|
%51:vgpr_32 = COPY %25.sub11
|
|
|
%52:vgpr_32 = COPY %25.sub10
|
|
|
%53:vgpr_32 = COPY %25.sub9
|
|
|
%54:vgpr_32 = COPY %25.sub8
|
|
|
%55:vreg_128 = REG_SEQUENCE killed %54, %subreg.sub0, killed %53, %subreg.sub1, killed %52, %subreg.sub2, killed %51, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %55, %2, 96, 0, 0, 0, implicit $exec
|
|
|
%56:vgpr_32 = COPY %25.sub7
|
|
|
%57:vgpr_32 = COPY %25.sub6
|
|
|
%58:vgpr_32 = COPY %25.sub5
|
|
|
%59:vgpr_32 = COPY %25.sub4
|
|
|
%60:vreg_128 = REG_SEQUENCE killed %59, %subreg.sub0, killed %58, %subreg.sub1, killed %57, %subreg.sub2, killed %56, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR %1, killed %60, %2, 80, 0, 0, 0, implicit $exec
|
|
|
%61:vgpr_32 = COPY %25.sub3
|
|
|
%62:vgpr_32 = COPY %25.sub2
|
|
|
%63:vgpr_32 = COPY %25.sub1
|
|
|
%64:vgpr_32 = COPY killed %25.sub0
|
|
|
%65:vreg_128 = REG_SEQUENCE killed %64, %subreg.sub0, killed %63, %subreg.sub1, killed %62, %subreg.sub2, killed %61, %subreg.sub3
|
|
|
GLOBAL_STORE_DWORDX4_SADDR killed %1, killed %65, killed %2, 64, 0, 0, 0, implicit $exec
|
|
|
S_ENDPGM 0
|
|
|
|
|
|
...
|
|
|
|
