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

104 lines
5.0 KiB
YAML

# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=amdgcn -mcpu=gfx1010 -enable-unsafe-fp-math -run-pass=instruction-select -verify-machineinstrs %s -o - | FileCheck %s
---
name: fract_f64_neg
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.1:
liveins: $sgpr0_sgpr1
; CHECK-LABEL: name: fract_f64_neg
; CHECK: liveins: $sgpr0_sgpr1
; CHECK: $vcc_hi = IMPLICIT_DEF
; CHECK: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
; CHECK: [[S_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_LOAD_DWORDX4_IMM [[COPY]], 36, 0, 0 :: (dereferenceable invariant load 16, align 4, addrspace 4)
; CHECK: [[COPY1:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub0_sub1
; CHECK: [[COPY2:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub2_sub3
; CHECK: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0, 0 :: (load 8, addrspace 1)
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
; CHECK: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 -2147483648
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; CHECK: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]]
; CHECK: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
; CHECK: %12:vreg_64 = nofpexcept V_ADD_F64 0, [[COPY3]], 1, [[COPY4]], 0, 0, implicit $mode, implicit $exec
; CHECK: %15:vreg_64 = nofpexcept V_FRACT_F64_e64 0, %12, 0, 0, implicit $mode, implicit $exec
; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], %15, [[COPY1]], 0, 0, 0, 0, implicit $exec :: (store 8, addrspace 1)
; CHECK: 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 16, align 4, addrspace 4)
%10:sgpr(s64) = G_EXTRACT %9(<2 x s64>), 0
%13:sgpr(s64) = G_EXTRACT %9(<2 x s64>), 64
%15:sgpr(p1) = G_INTTOPTR %13(s64)
%18:sgpr(s64) = G_LOAD %15(p1) :: (load 8, 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 8, addrspace 1)
S_ENDPGM 0
...
---
name: fract_f64_neg_abs
legalized: true
regBankSelected: true
tracksRegLiveness: true
body: |
bb.1:
liveins: $sgpr0_sgpr1
; CHECK-LABEL: name: fract_f64_neg_abs
; CHECK: liveins: $sgpr0_sgpr1
; CHECK: $vcc_hi = IMPLICIT_DEF
; CHECK: [[COPY:%[0-9]+]]:sreg_64 = COPY $sgpr0_sgpr1
; CHECK: [[S_LOAD_DWORDX4_IMM:%[0-9]+]]:sgpr_128 = S_LOAD_DWORDX4_IMM [[COPY]], 36, 0, 0 :: (dereferenceable invariant load 16, align 4, addrspace 4)
; CHECK: [[COPY1:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub0_sub1
; CHECK: [[COPY2:%[0-9]+]]:sreg_64 = COPY [[S_LOAD_DWORDX4_IMM]].sub2_sub3
; CHECK: [[S_LOAD_DWORDX2_IMM:%[0-9]+]]:sreg_64_xexec = S_LOAD_DWORDX2_IMM [[COPY2]], 0, 0, 0 :: (load 8, addrspace 1)
; CHECK: [[S_MOV_B32_:%[0-9]+]]:sreg_32 = S_MOV_B32 0
; CHECK: [[S_MOV_B32_1:%[0-9]+]]:sreg_32 = S_MOV_B32 -2147483648
; CHECK: [[REG_SEQUENCE:%[0-9]+]]:sreg_64 = REG_SEQUENCE [[S_MOV_B32_]], %subreg.sub0, [[S_MOV_B32_1]], %subreg.sub1
; CHECK: [[COPY3:%[0-9]+]]:vreg_64 = COPY [[REG_SEQUENCE]]
; CHECK: [[COPY4:%[0-9]+]]:vreg_64 = COPY [[S_LOAD_DWORDX2_IMM]]
; CHECK: %13:vreg_64 = nofpexcept V_ADD_F64 0, [[COPY3]], 3, [[COPY4]], 0, 0, implicit $mode, implicit $exec
; CHECK: %16:vreg_64 = nofpexcept V_FRACT_F64_e64 0, %13, 0, 0, implicit $mode, implicit $exec
; CHECK: [[V_MOV_B32_e32_:%[0-9]+]]:vgpr_32 = V_MOV_B32_e32 0, implicit $exec
; CHECK: GLOBAL_STORE_DWORDX2_SADDR [[V_MOV_B32_e32_]], %16, [[COPY1]], 0, 0, 0, 0, implicit $exec :: (store 8, addrspace 1)
; CHECK: 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 16, align 4, addrspace 4)
%10:sgpr(s64) = G_EXTRACT %9(<2 x s64>), 0
%13:sgpr(s64) = G_EXTRACT %9(<2 x s64>), 64
%15:sgpr(p1) = G_INTTOPTR %13(s64)
%18:sgpr(s64) = G_LOAD %15(p1) :: (load 8, 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 8, addrspace 1)
S_ENDPGM 0
...