llvm/llvm/test/CodeGen/AMDGPU/GlobalISel/inst-select-fract.f64.mir

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn -mcpu=gfx1010 -enable-unsafe-fp-math -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s -check-prefix=GFX10
# RUN: llc -mtriple=amdgcn -mcpu=gfx1100 -enable-unsafe-fp-math -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s -check-prefix=GFX11

---
name:            fract_f64_neg
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.1:
    liveins: $sgpr0_sgpr1

    ; GFX10-LABEL: name: fract_f64_neg
    ; GFX10: liveins: $sgpr0_sgpr1
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
    ; GFX10-NEXT: early-clobber %3:sgpr_128 = S_LOAD_DWORDX4_IMM_ec [[COPY]], 36, 0 :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_64 = COPY %3.sub0_sub1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_64 = COPY %3.sub2_sub3
    ; GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0 :: (load (s64), addrspace 1)
    ; GFX10-NEXT: [[S_MOV_B:%[0-9]+]]:sreg_64 = S_MOV_B64_IMM_PSEUDO -9223372036854775808
    ; GFX10-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[S_MOV_B]]
    ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
    ; GFX10-NEXT: [[V_ADD_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[COPY3]], 1, [[COPY4]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[V_FLOOR_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_FLOOR_F64_e64 0, [[V_ADD_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[V_ADD_F64_e64_1:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[V_ADD_F64_e64_]], 1, [[V_FLOOR_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec_xnull = COPY [[COPY1]]
    ; GFX10-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    ; GFX10-NEXT: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], [[V_ADD_F64_e64_1]], [[COPY5]], 0, 0, implicit $exec :: (store (s64), addrspace 1)
    ; GFX10-NEXT: S_ENDPGM 0
    ;
    ; GFX11-LABEL: name: fract_f64_neg
    ; GFX11: liveins: $sgpr0_sgpr1
    ; GFX11-NEXT: {{  $}}
    ; GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
    ; GFX11-NEXT: [[S_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_LOAD_DWORDX4_IMM [[COPY]], 36, 0 :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    ; GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub0_sub1
    ; GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub2_sub3
    ; GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0 :: (load (s64), addrspace 1)
    ; GFX11-NEXT: [[S_MOV_B:%[0-9]+]]:sreg_64 = S_MOV_B64_IMM_PSEUDO -9223372036854775808
    ; GFX11-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[S_MOV_B]]
    ; GFX11-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
    ; GFX11-NEXT: [[V_ADD_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[COPY3]], 1, [[COPY4]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[V_FLOOR_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_FLOOR_F64_e64 0, [[V_ADD_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[V_ADD_F64_e64_1:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[V_ADD_F64_e64_]], 1, [[V_FLOOR_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec_xnull = COPY [[COPY1]]
    ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    ; GFX11-NEXT: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], [[V_ADD_F64_e64_1]], [[COPY5]], 0, 0, implicit $exec :: (store (s64), addrspace 1)
    ; GFX11-NEXT: S_ENDPGM 0
    %2:sgpr(p4) = COPY $sgpr0_sgpr1
    %7:sgpr(s64) = G_CONSTANT i64 36
    %8:sgpr(p4) = G_PTR_ADD %2, %7(s64)
    %9:sgpr(<2 x s64>) = G_LOAD %8(p4) :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    %10:sgpr(s64), %13:sgpr(s64) = G_UNMERGE_VALUES %9(<2 x s64>)
    %15:sgpr(p1) = G_INTTOPTR %13(s64)
    %18:sgpr(s64) = G_LOAD %15(p1) :: (load (s64), addrspace 1)
    %19:sgpr(s64) = G_FCONSTANT double -0.000000e+00
    %24:sgpr(s64) = G_FNEG %18
    %25:vgpr(s64) = COPY %19(s64)
    %26:vgpr(s64) = COPY %24(s64)
    %20:vgpr(s64) = G_FADD %25, %26
    %21:vgpr(s64) = G_FFLOOR %20
    %23:vgpr(s64) = G_FNEG %21
    %22:vgpr(s64) = G_FADD %20, %23
    %12:sgpr(p1) = G_INTTOPTR %10(s64)
    %27:vgpr(p1) = COPY %12(p1)
    G_STORE %22(s64), %27(p1) :: (store (s64), addrspace 1)
    S_ENDPGM 0
...

---
name:            fract_f64_neg_abs
legalized:       true
regBankSelected: true
tracksRegLiveness: true

body: |
  bb.1:
    liveins: $sgpr0_sgpr1

    ; GFX10-LABEL: name: fract_f64_neg_abs
    ; GFX10: liveins: $sgpr0_sgpr1
    ; GFX10-NEXT: {{  $}}
    ; GFX10-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
    ; GFX10-NEXT: early-clobber %3:sgpr_128 = S_LOAD_DWORDX4_IMM_ec [[COPY]], 36, 0 :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    ; GFX10-NEXT: [[COPY1:%[0-9]+]]:sreg_64 = COPY %3.sub0_sub1
    ; GFX10-NEXT: [[COPY2:%[0-9]+]]:sreg_64 = COPY %3.sub2_sub3
    ; GFX10-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0 :: (load (s64), addrspace 1)
    ; GFX10-NEXT: [[S_MOV_B:%[0-9]+]]:sreg_64 = S_MOV_B64_IMM_PSEUDO -9223372036854775808
    ; GFX10-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[S_MOV_B]]
    ; GFX10-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
    ; GFX10-NEXT: [[V_ADD_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[COPY3]], 3, [[COPY4]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[V_FLOOR_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_FLOOR_F64_e64 0, [[V_ADD_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[V_ADD_F64_e64_1:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[V_ADD_F64_e64_]], 1, [[V_FLOOR_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX10-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec_xnull = COPY [[COPY1]]
    ; GFX10-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    ; GFX10-NEXT: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], [[V_ADD_F64_e64_1]], [[COPY5]], 0, 0, implicit $exec :: (store (s64), addrspace 1)
    ; GFX10-NEXT: S_ENDPGM 0
    ;
    ; GFX11-LABEL: name: fract_f64_neg_abs
    ; GFX11: liveins: $sgpr0_sgpr1
    ; GFX11-NEXT: {{  $}}
    ; GFX11-NEXT: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
    ; GFX11-NEXT: [[S_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_LOAD_DWORDX4_IMM [[COPY]], 36, 0 :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    ; GFX11-NEXT: [[COPY1:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub0_sub1
    ; GFX11-NEXT: [[COPY2:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub2_sub3
    ; GFX11-NEXT: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0 :: (load (s64), addrspace 1)
    ; GFX11-NEXT: [[S_MOV_B:%[0-9]+]]:sreg_64 = S_MOV_B64_IMM_PSEUDO -9223372036854775808
    ; GFX11-NEXT: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[S_MOV_B]]
    ; GFX11-NEXT: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
    ; GFX11-NEXT: [[V_ADD_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[COPY3]], 3, [[COPY4]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[V_FLOOR_F64_e64_:%[0-9]+]]:vreg_64 = nofpexcept V_FLOOR_F64_e64 0, [[V_ADD_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[V_ADD_F64_e64_1:%[0-9]+]]:vreg_64 = nofpexcept V_ADD_F64_e64 0, [[V_ADD_F64_e64_]], 1, [[V_FLOOR_F64_e64_]], 0, 0, implicit $mode, implicit $exec
    ; GFX11-NEXT: [[COPY5:%[0-9]+]]:sreg_64_xexec_xnull = COPY [[COPY1]]
    ; GFX11-NEXT: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
    ; GFX11-NEXT: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], [[V_ADD_F64_e64_1]], [[COPY5]], 0, 0, implicit $exec :: (store (s64), addrspace 1)
    ; GFX11-NEXT: S_ENDPGM 0
    %2:sgpr(p4) = COPY $sgpr0_sgpr1
    %7:sgpr(s64) = G_CONSTANT i64 36
    %8:sgpr(p4) = G_PTR_ADD %2, %7(s64)
    %9:sgpr(<2 x s64>) = G_LOAD %8(p4) :: (dereferenceable invariant load (<2 x s64>), align 4, addrspace 4)
    %10:sgpr(s64), %13:sgpr(s64) = G_UNMERGE_VALUES %9(<2 x s64>)
    %15:sgpr(p1) = G_INTTOPTR %13(s64)
    %18:sgpr(s64) = G_LOAD %15(p1) :: (load (s64), addrspace 1)
    %19:sgpr(s64) = G_FABS %18
    %20:sgpr(s64) = G_FCONSTANT double -0.000000e+00
    %25:sgpr(s64) = G_FNEG %19
    %26:vgpr(s64) = COPY %20(s64)
    %27:vgpr(s64) = COPY %25(s64)
    %21:vgpr(s64) = G_FADD %26, %27
    %22:vgpr(s64) = G_FFLOOR %21
    %24:vgpr(s64) = G_FNEG %22
    %23:vgpr(s64) = G_FADD %21, %24
    %12:sgpr(p1) = G_INTTOPTR %10(s64)
    %28:vgpr(p1) = COPY %12(p1)
    G_STORE %23(s64), %28(p1) :: (store (s64), addrspace 1)
    S_ENDPGM 0
...