forked from OSchip/llvm-project
2353 lines
168 KiB
YAML
2353 lines
168 KiB
YAML
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=tahiti -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=SI %s
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer -global-isel-abort=0 %s -o - | FileCheck -check-prefix=VI %s
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX9 %s
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx900 -run-pass=legalizer -global-isel-abort=0 -enable-unsafe-fp-math -o - %s | FileCheck -check-prefix=GFX9-UNSAFE %s
|
|
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -run-pass=legalizer -global-isel-abort=0 -o - %s | FileCheck -check-prefix=GFX10 %s
|
|
|
|
---
|
|
name: test_fdiv_s16
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: true
|
|
fp32-output-denormals: true
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s16
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC]](s16)
|
|
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; VI-LABEL: name: test_fdiv_s16
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
|
; VI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; VI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; VI: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; VI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; VI: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC1]](s16), [[TRUNC]](s16)
|
|
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s16
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
|
; GFX9: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX9: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX9: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC1]](s16), [[TRUNC]](s16)
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s16
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC1]](s16)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[INT]]
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s16
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX10: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[COPY1]](s32)
|
|
; GFX10: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX10: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX10: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC1]](s16), [[TRUNC]](s16)
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX10: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(s16) = G_TRUNC %0
|
|
%3:_(s16) = G_TRUNC %1
|
|
%4:_(s16) = G_FDIV %2, %3
|
|
%5:_(s32) = G_ANYEXT %4
|
|
$vgpr0 = COPY %5
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s32_denorms_on
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: true
|
|
fp32-output-denormals: true
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s32_denorms_on
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; SI: $vgpr0 = COPY [[INT6]](s32)
|
|
; VI-LABEL: name: test_fdiv_s32_denorms_on
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; VI: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s32_denorms_on
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; GFX9: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s32_denorms_on
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[INT]]
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[FMUL]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s32_denorms_on
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; GFX10: $vgpr0 = COPY [[INT6]](s32)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(s32) = G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s32_denorms_off
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s32_denorms_off
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; SI: $vgpr0 = COPY [[INT6]](s32)
|
|
; VI-LABEL: name: test_fdiv_s32_denorms_off
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; VI: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s32_denorms_off
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; GFX9: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s32_denorms_off
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[INT]]
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[FMUL]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s32_denorms_off
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s32), [[COPY1]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: S_DENORM_MODE 15, implicit-def $mode, implicit $mode
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: S_DENORM_MODE 12, implicit-def $mode, implicit $mode
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY1]](s32), [[COPY]](s32)
|
|
; GFX10: $vgpr0 = COPY [[INT6]](s32)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(s32) = G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s32_denorms_off_arcp
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s32_denorms_off_arcp
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; SI: [[INT:%[0-9]+]]:_(s32) = arcp G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = arcp G_FMUL [[COPY]], [[INT]]
|
|
; SI: $vgpr0 = COPY [[FMUL]](s32)
|
|
; VI-LABEL: name: test_fdiv_s32_denorms_off_arcp
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; VI: [[INT:%[0-9]+]]:_(s32) = arcp G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = arcp G_FMUL [[COPY]], [[INT]]
|
|
; VI: $vgpr0 = COPY [[FMUL]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s32_denorms_off_arcp
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32) = arcp G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = arcp G_FMUL [[COPY]], [[INT]]
|
|
; GFX9: $vgpr0 = COPY [[FMUL]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s32_denorms_off_arcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = arcp G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = arcp G_FMUL [[COPY]], [[INT]]
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[FMUL]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s32_denorms_off_arcp
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32) = arcp G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s32)
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = arcp G_FMUL [[COPY]], [[INT]]
|
|
; GFX10: $vgpr0 = COPY [[FMUL]](s32)
|
|
%0:_(s32) = COPY $vgpr0
|
|
%1:_(s32) = COPY $vgpr1
|
|
%2:_(s32) = arcp G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s64
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
|
|
|
; SI-LABEL: name: test_fdiv_s64
|
|
; SI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; SI: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
|
; SI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 0
|
|
; SI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; SI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; SI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; SI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 1
|
|
; SI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
|
|
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
|
|
; SI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT]](s64)
|
|
; SI: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT3]](s64)
|
|
; SI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV1]](s32), [[UV7]]
|
|
; SI: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV3]](s32), [[UV5]]
|
|
; SI: [[XOR:%[0-9]+]]:_(s1) = G_XOR [[ICMP]], [[ICMP1]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[XOR]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY1]](s64), [[COPY]](s64)
|
|
; SI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; VI-LABEL: name: test_fdiv_s64
|
|
; VI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; VI: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
|
; VI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 0
|
|
; VI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; VI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; VI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; VI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 1
|
|
; VI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY1]](s64), [[COPY]](s64)
|
|
; VI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-LABEL: name: test_fdiv_s64
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
|
; GFX9: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 0
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 1
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY1]](s64), [[COPY]](s64)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s64
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY1]](s64)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[COPY]], [[INT]]
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[FMUL]](s64)
|
|
; GFX10-LABEL: name: test_fdiv_s64
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
|
|
; GFX10: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 0
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[COPY]](s64), [[COPY1]](s64), 1
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY1]](s64), [[COPY]](s64)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
%0:_(s64) = COPY $vgpr0_vgpr1
|
|
%1:_(s64) = COPY $vgpr2_vgpr3
|
|
%2:_(s64) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v2s32
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
|
|
|
; SI-LABEL: name: test_fdiv_v2s32
|
|
; SI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; SI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; SI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; SI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; VI-LABEL: name: test_fdiv_v2s32
|
|
; VI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; VI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; VI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; VI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; VI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; VI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; VI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; VI: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; VI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; VI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; VI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; VI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; VI: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; VI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; VI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX9-LABEL: name: test_fdiv_v2s32
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; GFX9: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; GFX9: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; GFX9: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX9: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; GFX9: S_SETREG_IMM32_B32 3, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX9: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX9: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX9: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX9: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX9: S_SETREG_IMM32_B32 0, 2305, implicit-def $mode, implicit $mode
|
|
; GFX9: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX9: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v2s32
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX9-UNSAFE: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV2]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV3]](s32)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX10-LABEL: name: test_fdiv_v2s32
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX10: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: S_DENORM_MODE 15, implicit-def $mode, implicit $mode
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: S_DENORM_MODE 12, implicit-def $mode, implicit $mode
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; GFX10: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; GFX10: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; GFX10: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX10: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; GFX10: S_DENORM_MODE 15, implicit-def $mode, implicit $mode
|
|
; GFX10: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX10: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX10: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX10: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX10: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX10: S_DENORM_MODE 12, implicit-def $mode, implicit $mode
|
|
; GFX10: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX10: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
%2:_(<2 x s32>) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v2s32_flags
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
|
|
|
; SI-LABEL: name: test_fdiv_v2s32_flags
|
|
; SI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; SI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT7]]
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; SI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; VI-LABEL: name: test_fdiv_v2s32_flags
|
|
; VI: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; VI: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; VI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT]]
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; VI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; VI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; VI: [[INT11:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; VI: [[FNEG1:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT7]]
|
|
; VI: [[FMA5:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; VI: [[FMA6:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT9]], [[FMA6]]
|
|
; VI: [[FMA7:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; VI: [[FMA8:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; VI: [[FMA9:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; VI: [[INT12:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; VI: [[INT13:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; VI: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX9-LABEL: name: test_fdiv_v2s32_flags
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX9: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT]]
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; GFX9: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; GFX9: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; GFX9: [[INT11:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX9: [[FNEG1:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT7]]
|
|
; GFX9: [[FMA5:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX9: [[FMA6:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX9: [[FMA7:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX9: [[FMA8:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX9: [[FMA9:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX9: [[INT12:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX9: [[INT13:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v2s32_flags
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX9-UNSAFE: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV2]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV3]](s32)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[UV1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
; GFX10-LABEL: name: test_fdiv_v2s32_flags
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
|
|
; GFX10: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV2]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT]]
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV2]](s32), [[UV]](s32)
|
|
; GFX10: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 0
|
|
; GFX10: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV3]](s32), 1
|
|
; GFX10: [[INT11:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX10: [[FNEG1:%[0-9]+]]:_(s32) = nnan G_FNEG [[INT7]]
|
|
; GFX10: [[FMA5:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX10: [[FMA6:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = nnan G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX10: [[FMA7:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX10: [[FMA8:%[0-9]+]]:_(s32) = nnan G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX10: [[FMA9:%[0-9]+]]:_(s32) = nnan G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX10: [[INT12:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX10: [[INT13:%[0-9]+]]:_(s32) = nnan G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV3]](s32), [[UV1]](s32)
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
|
|
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
|
|
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
|
|
%2:_(<2 x s32>) = nnan G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v3s32
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5
|
|
|
|
; SI-LABEL: name: test_fdiv_v3s32
|
|
; SI: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
; SI: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
|
; SI: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV3]](s32), [[UV]](s32)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV4]](s32), [[UV1]](s32)
|
|
; SI: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 0
|
|
; SI: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 1
|
|
; SI: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; SI: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; SI: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C]]
|
|
; SI: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; SI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; SI: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; SI: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; SI: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; SI: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; SI: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[UV5]](s32), [[UV2]](s32)
|
|
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32), [[INT20]](s32)
|
|
; SI: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
|
; VI-LABEL: name: test_fdiv_v3s32
|
|
; VI: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
; VI: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
; VI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
|
; VI: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV3]](s32), [[UV]](s32)
|
|
; VI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 0
|
|
; VI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 1
|
|
; VI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; VI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; VI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; VI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; VI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; VI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; VI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; VI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; VI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV4]](s32), [[UV1]](s32)
|
|
; VI: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 0
|
|
; VI: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 1
|
|
; VI: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; VI: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; VI: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C]]
|
|
; VI: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; VI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; VI: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; VI: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; VI: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; VI: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; VI: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[UV5]](s32), [[UV2]](s32)
|
|
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32), [[INT20]](s32)
|
|
; VI: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX9-LABEL: name: test_fdiv_v3s32
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
; GFX9: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
|
; GFX9: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV3]](s32), [[UV]](s32)
|
|
; GFX9: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 0
|
|
; GFX9: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 1
|
|
; GFX9: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX9: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; GFX9: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX9: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX9: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX9: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX9: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX9: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX9: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV4]](s32), [[UV1]](s32)
|
|
; GFX9: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 0
|
|
; GFX9: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 1
|
|
; GFX9: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; GFX9: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; GFX9: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C]]
|
|
; GFX9: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; GFX9: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; GFX9: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; GFX9: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; GFX9: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; GFX9: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; GFX9: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[UV5]](s32), [[UV2]](s32)
|
|
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32), [[INT20]](s32)
|
|
; GFX9: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v3s32
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
|
; GFX9-UNSAFE: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV3]](s32)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV4]](s32)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV5]](s32)
|
|
; GFX9-UNSAFE: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[INT2]]
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMUL]](s32), [[FMUL1]](s32), [[FMUL2]](s32)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX10-LABEL: name: test_fdiv_v3s32
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
; GFX10: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
|
|
; GFX10: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s32), [[UV3]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[UV3]](s32), [[UV]](s32)
|
|
; GFX10: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 0
|
|
; GFX10: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s32), [[UV4]](s32), 1
|
|
; GFX10: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; GFX10: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; GFX10: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C]]
|
|
; GFX10: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; GFX10: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; GFX10: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; GFX10: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; GFX10: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; GFX10: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[UV4]](s32), [[UV1]](s32)
|
|
; GFX10: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 0
|
|
; GFX10: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV2]](s32), [[UV5]](s32), 1
|
|
; GFX10: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; GFX10: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; GFX10: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C]]
|
|
; GFX10: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; GFX10: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; GFX10: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; GFX10: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; GFX10: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; GFX10: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; GFX10: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[UV5]](s32), [[UV2]](s32)
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[INT6]](s32), [[INT13]](s32), [[INT20]](s32)
|
|
; GFX10: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
|
|
%0:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
|
|
%1:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
|
|
%2:_(<3 x s32>) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1_vgpr2 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v2s64
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7
|
|
|
|
; SI-LABEL: name: test_fdiv_v2s64
|
|
; SI: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
; SI: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
; SI: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
|
; SI: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
|
; SI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 0
|
|
; SI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; SI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; SI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; SI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 1
|
|
; SI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; SI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV]](s64)
|
|
; SI: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV2]](s64)
|
|
; SI: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT]](s64)
|
|
; SI: [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT3]](s64)
|
|
; SI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV5]](s32), [[UV11]]
|
|
; SI: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV7]](s32), [[UV9]]
|
|
; SI: [[XOR:%[0-9]+]]:_(s1) = G_XOR [[ICMP]], [[ICMP1]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[XOR]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[UV2]](s64), [[UV]](s64)
|
|
; SI: [[INT7:%[0-9]+]]:_(s64), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 0
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s64) = G_FNEG [[INT7]]
|
|
; SI: [[INT9:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s64)
|
|
; SI: [[FMA5:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[INT9]], [[C]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s64) = G_FMA [[INT9]], [[FMA5]], [[INT9]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMA6]], [[C]]
|
|
; SI: [[INT10:%[0-9]+]]:_(s64), [[INT11:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 1
|
|
; SI: [[FMA8:%[0-9]+]]:_(s64) = G_FMA [[FMA6]], [[FMA7]], [[FMA6]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[INT10]], [[FMA8]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMUL1]], [[INT10]]
|
|
; SI: [[UV12:%[0-9]+]]:_(s32), [[UV13:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV1]](s64)
|
|
; SI: [[UV14:%[0-9]+]]:_(s32), [[UV15:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[UV3]](s64)
|
|
; SI: [[UV16:%[0-9]+]]:_(s32), [[UV17:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT7]](s64)
|
|
; SI: [[UV18:%[0-9]+]]:_(s32), [[UV19:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT10]](s64)
|
|
; SI: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV13]](s32), [[UV19]]
|
|
; SI: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV15]](s32), [[UV17]]
|
|
; SI: [[XOR1:%[0-9]+]]:_(s1) = G_XOR [[ICMP2]], [[ICMP3]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s64), [[FMA8]](s64), [[FMUL1]](s64), [[XOR1]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s64), [[UV3]](s64), [[UV1]](s64)
|
|
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[INT6]](s64), [[INT13]](s64)
|
|
; SI: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
|
; VI-LABEL: name: test_fdiv_v2s64
|
|
; VI: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
; VI: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
; VI: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
|
; VI: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
|
; VI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 0
|
|
; VI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; VI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; VI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; VI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 1
|
|
; VI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[UV2]](s64), [[UV]](s64)
|
|
; VI: [[INT7:%[0-9]+]]:_(s64), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 0
|
|
; VI: [[FNEG1:%[0-9]+]]:_(s64) = G_FNEG [[INT7]]
|
|
; VI: [[INT9:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s64)
|
|
; VI: [[FMA5:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[INT9]], [[C]]
|
|
; VI: [[FMA6:%[0-9]+]]:_(s64) = G_FMA [[INT9]], [[FMA5]], [[INT9]]
|
|
; VI: [[FMA7:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMA6]], [[C]]
|
|
; VI: [[INT10:%[0-9]+]]:_(s64), [[INT11:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 1
|
|
; VI: [[FMA8:%[0-9]+]]:_(s64) = G_FMA [[FMA6]], [[FMA7]], [[FMA6]]
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[INT10]], [[FMA8]]
|
|
; VI: [[FMA9:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMUL1]], [[INT10]]
|
|
; VI: [[INT12:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s64), [[FMA8]](s64), [[FMUL1]](s64), [[INT11]](s1)
|
|
; VI: [[INT13:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s64), [[UV3]](s64), [[UV1]](s64)
|
|
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[INT6]](s64), [[INT13]](s64)
|
|
; VI: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
|
; GFX9-LABEL: name: test_fdiv_v2s64
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
; GFX9: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
|
; GFX9: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
|
; GFX9: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 0
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 1
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[UV2]](s64), [[UV]](s64)
|
|
; GFX9: [[INT7:%[0-9]+]]:_(s64), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 0
|
|
; GFX9: [[FNEG1:%[0-9]+]]:_(s64) = G_FNEG [[INT7]]
|
|
; GFX9: [[INT9:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s64)
|
|
; GFX9: [[FMA5:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[INT9]], [[C]]
|
|
; GFX9: [[FMA6:%[0-9]+]]:_(s64) = G_FMA [[INT9]], [[FMA5]], [[INT9]]
|
|
; GFX9: [[FMA7:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMA6]], [[C]]
|
|
; GFX9: [[INT10:%[0-9]+]]:_(s64), [[INT11:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 1
|
|
; GFX9: [[FMA8:%[0-9]+]]:_(s64) = G_FMA [[FMA6]], [[FMA7]], [[FMA6]]
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[INT10]], [[FMA8]]
|
|
; GFX9: [[FMA9:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMUL1]], [[INT10]]
|
|
; GFX9: [[INT12:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s64), [[FMA8]](s64), [[FMUL1]](s64), [[INT11]](s1)
|
|
; GFX9: [[INT13:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s64), [[UV3]](s64), [[UV1]](s64)
|
|
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[INT6]](s64), [[INT13]](s64)
|
|
; GFX9: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v2s64
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
|
; GFX9-UNSAFE: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV2]](s64)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[UV]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[UV3]](s64)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[UV1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[FMUL]](s64), [[FMUL1]](s64)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
|
; GFX10-LABEL: name: test_fdiv_v2s64
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
; GFX10: [[UV:%[0-9]+]]:_(s64), [[UV1:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY]](<2 x s64>)
|
|
; GFX10: [[UV2:%[0-9]+]]:_(s64), [[UV3:%[0-9]+]]:_(s64) = G_UNMERGE_VALUES [[COPY1]](<2 x s64>)
|
|
; GFX10: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 0
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV]](s64), [[UV2]](s64), 1
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[UV2]](s64), [[UV]](s64)
|
|
; GFX10: [[INT7:%[0-9]+]]:_(s64), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 0
|
|
; GFX10: [[FNEG1:%[0-9]+]]:_(s64) = G_FNEG [[INT7]]
|
|
; GFX10: [[INT9:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s64)
|
|
; GFX10: [[FMA5:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[INT9]], [[C]]
|
|
; GFX10: [[FMA6:%[0-9]+]]:_(s64) = G_FMA [[INT9]], [[FMA5]], [[INT9]]
|
|
; GFX10: [[FMA7:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMA6]], [[C]]
|
|
; GFX10: [[INT10:%[0-9]+]]:_(s64), [[INT11:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[UV1]](s64), [[UV3]](s64), 1
|
|
; GFX10: [[FMA8:%[0-9]+]]:_(s64) = G_FMA [[FMA6]], [[FMA7]], [[FMA6]]
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s64) = G_FMUL [[INT10]], [[FMA8]]
|
|
; GFX10: [[FMA9:%[0-9]+]]:_(s64) = G_FMA [[FNEG1]], [[FMUL1]], [[INT10]]
|
|
; GFX10: [[INT12:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s64), [[FMA8]](s64), [[FMUL1]](s64), [[INT11]](s1)
|
|
; GFX10: [[INT13:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s64), [[UV3]](s64), [[UV1]](s64)
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s64>) = G_BUILD_VECTOR [[INT6]](s64), [[INT13]](s64)
|
|
; GFX10: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s64>)
|
|
%0:_(<2 x s64>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
|
|
%1:_(<2 x s64>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
|
|
%2:_(<2 x s64>) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v2s16
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_v2s16
|
|
; SI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
|
; SI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
|
; SI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; SI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; SI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
|
|
; SI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; SI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; SI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; SI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C1]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[FPEXT3]](s32), [[FPEXT2]](s32)
|
|
; SI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT13]](s32)
|
|
; SI: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC]](s16)
|
|
; SI: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC1]](s16)
|
|
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
|
|
; SI: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
|
|
; SI: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
|
|
; SI: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
|
|
; VI-LABEL: name: test_fdiv_v2s16
|
|
; VI: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
|
; VI: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
|
; VI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; VI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; VI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
|
|
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; VI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; VI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; VI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; VI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; VI: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; VI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; VI: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC2]](s16), [[TRUNC]](s16)
|
|
; VI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; VI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; VI: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; VI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; VI: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC3]](s16), [[TRUNC1]](s16)
|
|
; VI: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[INT1]](s16)
|
|
; VI: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[INT3]](s16)
|
|
; VI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
|
|
; VI: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
|
|
; VI: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
|
|
; VI: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
|
|
; GFX9-LABEL: name: test_fdiv_v2s16
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
|
; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
|
|
; GFX9: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX9: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX9: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX9: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC2]](s16), [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX9: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX9: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC3]](s16), [[TRUNC1]](s16)
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX9: $vgpr0 = COPY [[BUILD_VECTOR_TRUNC]](<2 x s16>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v2s16
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
|
; GFX9-UNSAFE: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9-UNSAFE: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9-UNSAFE: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9-UNSAFE: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9-UNSAFE: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC2]](s16)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC3]](s16)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL1]](s16)
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[BUILD_VECTOR_TRUNC]](<2 x s16>)
|
|
; GFX10-LABEL: name: test_fdiv_v2s16
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX10: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX10: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX10: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
|
|
; GFX10: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX10: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX10: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX10: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX10: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX10: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC2]](s16), [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX10: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX10: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC3]](s16), [[TRUNC1]](s16)
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX10: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX10: $vgpr0 = COPY [[BUILD_VECTOR_TRUNC]](<2 x s16>)
|
|
%0:_(<2 x s16>) = COPY $vgpr0
|
|
%1:_(<2 x s16>) = COPY $vgpr1
|
|
%2:_(<2 x s16>) = G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v3s16
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0, $vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_v3s16
|
|
; SI: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; SI: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; SI: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; SI: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
|
|
; SI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; SI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; SI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; SI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; SI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; SI: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF2]](<4 x s16>)
|
|
; SI: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; SI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; SI: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; SI: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; SI: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; SI: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; SI: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; SI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C1]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[FPEXT3]](s32), [[FPEXT2]](s32)
|
|
; SI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT13]](s32)
|
|
; SI: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; SI: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; SI: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT4]](s32), [[FPEXT5]](s32), 0
|
|
; SI: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT4]](s32), [[FPEXT5]](s32), 1
|
|
; SI: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; SI: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; SI: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C1]]
|
|
; SI: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; SI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; SI: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; SI: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; SI: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; SI: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; SI: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[FPEXT5]](s32), [[FPEXT4]](s32)
|
|
; SI: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT20]](s32)
|
|
; SI: [[DEF3:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
|
|
; SI: [[DEF4:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
|
|
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC]](s16)
|
|
; SI: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC1]](s16)
|
|
; SI: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC2]](s16)
|
|
; SI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
|
|
; SI: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s32>)
|
|
; VI-LABEL: name: test_fdiv_v3s16
|
|
; VI: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; VI: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; VI: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; VI: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
|
|
; VI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; VI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; VI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; VI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; VI: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF2]](<4 x s16>)
|
|
; VI: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; VI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; VI: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; VI: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; VI: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; VI: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; VI: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; VI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; VI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; VI: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; VI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; VI: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC3]](s16), [[TRUNC]](s16)
|
|
; VI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; VI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; VI: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; VI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; VI: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC4]](s16), [[TRUNC1]](s16)
|
|
; VI: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; VI: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; VI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; VI: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; VI: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC5]](s16), [[TRUNC2]](s16)
|
|
; VI: [[DEF3:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
|
|
; VI: [[DEF4:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
|
|
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; VI: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; VI: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[INT5]](s16)
|
|
; VI: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
|
|
; VI: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX9-LABEL: name: test_fdiv_v3s16
|
|
; GFX9: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
|
|
; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX9: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF2]](<4 x s16>)
|
|
; GFX9: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX9: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX9: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX9: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX9: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX9: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX9: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX9: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC3]](s16), [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX9: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX9: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC4]](s16), [[TRUNC1]](s16)
|
|
; GFX9: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX9: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; GFX9: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; GFX9: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC5]](s16), [[TRUNC2]](s16)
|
|
; GFX9: [[DEF3:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
|
|
; GFX9: [[DEF4:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[INT5]](s16)
|
|
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
|
|
; GFX9: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v3s16
|
|
; GFX9-UNSAFE: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9-UNSAFE: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9-UNSAFE: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
|
|
; GFX9-UNSAFE: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9-UNSAFE: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9-UNSAFE: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9-UNSAFE: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9-UNSAFE: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF2]](<4 x s16>)
|
|
; GFX9-UNSAFE: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX9-UNSAFE: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX9-UNSAFE: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX9-UNSAFE: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC3]](s16)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC4]](s16)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[INT2:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC5]](s16)
|
|
; GFX9-UNSAFE: [[FMUL2:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC2]], [[INT2]]
|
|
; GFX9-UNSAFE: [[DEF3:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
|
|
; GFX9-UNSAFE: [[DEF4:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL1]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL2]](s16)
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
|
|
; GFX9-UNSAFE: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s32>)
|
|
; GFX10-LABEL: name: test_fdiv_v3s16
|
|
; GFX10: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX10: [[DEF1:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX10: [[DEF2:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
|
|
; GFX10: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF]](<4 x s16>)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX10: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX10: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX10: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX10: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX10: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX10: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[DEF2]](<4 x s16>)
|
|
; GFX10: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX10: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX10: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX10: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX10: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX10: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX10: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX10: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX10: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX10: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC3]](s16), [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX10: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX10: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC4]](s16), [[TRUNC1]](s16)
|
|
; GFX10: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX10: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; GFX10: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; GFX10: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC5]](s16), [[TRUNC2]](s16)
|
|
; GFX10: [[DEF3:%[0-9]+]]:_(s16) = G_IMPLICIT_DEF
|
|
; GFX10: [[DEF4:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX10: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX10: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[INT5]](s16)
|
|
; GFX10: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[ANYEXT]](s32), [[ANYEXT1]](s32), [[ANYEXT2]](s32)
|
|
; GFX10: S_NOP 0, implicit [[BUILD_VECTOR]](<3 x s32>)
|
|
%0:_(<3 x s16>) = G_IMPLICIT_DEF
|
|
%1:_(<3 x s16>) = G_IMPLICIT_DEF
|
|
%2:_(<3 x s16>) = G_FDIV %0, %1
|
|
%3:_(<3 x s32>) = G_ANYEXT %2
|
|
S_NOP 0, implicit %3
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_v4s16
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
|
|
|
|
; SI-LABEL: name: test_fdiv_v4s16
|
|
; SI: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; SI: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; SI: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
|
; SI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; SI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; SI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; SI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; SI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; SI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; SI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; SI: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
|
; SI: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; SI: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; SI: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; SI: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; SI: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; SI: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; SI: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; SI: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; SI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; SI: [[INT7:%[0-9]+]]:_(s32), [[INT8:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 0
|
|
; SI: [[INT9:%[0-9]+]]:_(s32), [[INT10:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT2]](s32), [[FPEXT3]](s32), 1
|
|
; SI: [[INT11:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT7]](s32)
|
|
; SI: [[FNEG1:%[0-9]+]]:_(s32) = G_FNEG [[INT7]]
|
|
; SI: [[FMA5:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[INT11]], [[C1]]
|
|
; SI: [[FMA6:%[0-9]+]]:_(s32) = G_FMA [[FMA5]], [[INT11]], [[INT11]]
|
|
; SI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[INT9]], [[FMA6]]
|
|
; SI: [[FMA7:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMUL1]], [[INT9]]
|
|
; SI: [[FMA8:%[0-9]+]]:_(s32) = G_FMA [[FMA7]], [[FMA6]], [[FMUL1]]
|
|
; SI: [[FMA9:%[0-9]+]]:_(s32) = G_FMA [[FNEG1]], [[FMA8]], [[INT9]]
|
|
; SI: [[INT12:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA9]](s32), [[FMA6]](s32), [[FMA8]](s32), [[INT10]](s1)
|
|
; SI: [[INT13:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT12]](s32), [[FPEXT3]](s32), [[FPEXT2]](s32)
|
|
; SI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT13]](s32)
|
|
; SI: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; SI: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC6]](s16)
|
|
; SI: [[INT14:%[0-9]+]]:_(s32), [[INT15:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT4]](s32), [[FPEXT5]](s32), 0
|
|
; SI: [[INT16:%[0-9]+]]:_(s32), [[INT17:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT4]](s32), [[FPEXT5]](s32), 1
|
|
; SI: [[INT18:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT14]](s32)
|
|
; SI: [[FNEG2:%[0-9]+]]:_(s32) = G_FNEG [[INT14]]
|
|
; SI: [[FMA10:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[INT18]], [[C1]]
|
|
; SI: [[FMA11:%[0-9]+]]:_(s32) = G_FMA [[FMA10]], [[INT18]], [[INT18]]
|
|
; SI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[INT16]], [[FMA11]]
|
|
; SI: [[FMA12:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMUL2]], [[INT16]]
|
|
; SI: [[FMA13:%[0-9]+]]:_(s32) = G_FMA [[FMA12]], [[FMA11]], [[FMUL2]]
|
|
; SI: [[FMA14:%[0-9]+]]:_(s32) = G_FMA [[FNEG2]], [[FMA13]], [[INT16]]
|
|
; SI: [[INT19:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA14]](s32), [[FMA11]](s32), [[FMA13]](s32), [[INT17]](s1)
|
|
; SI: [[INT20:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT19]](s32), [[FPEXT5]](s32), [[FPEXT4]](s32)
|
|
; SI: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT20]](s32)
|
|
; SI: [[FPEXT6:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; SI: [[FPEXT7:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC7]](s16)
|
|
; SI: [[INT21:%[0-9]+]]:_(s32), [[INT22:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT6]](s32), [[FPEXT7]](s32), 0
|
|
; SI: [[INT23:%[0-9]+]]:_(s32), [[INT24:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT6]](s32), [[FPEXT7]](s32), 1
|
|
; SI: [[INT25:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT21]](s32)
|
|
; SI: [[FNEG3:%[0-9]+]]:_(s32) = G_FNEG [[INT21]]
|
|
; SI: [[FMA15:%[0-9]+]]:_(s32) = G_FMA [[FNEG3]], [[INT25]], [[C1]]
|
|
; SI: [[FMA16:%[0-9]+]]:_(s32) = G_FMA [[FMA15]], [[INT25]], [[INT25]]
|
|
; SI: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[INT23]], [[FMA16]]
|
|
; SI: [[FMA17:%[0-9]+]]:_(s32) = G_FMA [[FNEG3]], [[FMUL3]], [[INT23]]
|
|
; SI: [[FMA18:%[0-9]+]]:_(s32) = G_FMA [[FMA17]], [[FMA16]], [[FMUL3]]
|
|
; SI: [[FMA19:%[0-9]+]]:_(s32) = G_FMA [[FNEG3]], [[FMA18]], [[INT23]]
|
|
; SI: [[INT26:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA19]](s32), [[FMA16]](s32), [[FMA18]](s32), [[INT24]](s1)
|
|
; SI: [[INT27:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT26]](s32), [[FPEXT7]](s32), [[FPEXT6]](s32)
|
|
; SI: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT27]](s32)
|
|
; SI: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC]](s16)
|
|
; SI: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC1]](s16)
|
|
; SI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
|
|
; SI: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
|
|
; SI: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
|
|
; SI: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC2]](s16)
|
|
; SI: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[FPTRUNC3]](s16)
|
|
; SI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[ZEXT3]], [[C]](s32)
|
|
; SI: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL1]]
|
|
; SI: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
|
|
; SI: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>)
|
|
; SI: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
|
; VI-LABEL: name: test_fdiv_v4s16
|
|
; VI: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; VI: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; VI: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
|
; VI: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; VI: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; VI: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; VI: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; VI: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; VI: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; VI: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; VI: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
|
; VI: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; VI: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; VI: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; VI: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; VI: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; VI: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; VI: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; VI: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
|
|
; VI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; VI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; VI: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; VI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; VI: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC4]](s16), [[TRUNC]](s16)
|
|
; VI: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; VI: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; VI: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; VI: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; VI: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; VI: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC5]](s16), [[TRUNC1]](s16)
|
|
; VI: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; VI: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC6]](s16)
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; VI: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; VI: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; VI: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC6]](s16), [[TRUNC2]](s16)
|
|
; VI: [[FPEXT6:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; VI: [[FPEXT7:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC7]](s16)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT7]](s32)
|
|
; VI: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT6]], [[INT6]]
|
|
; VI: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL3]](s32)
|
|
; VI: [[INT7:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC3]](s16), [[TRUNC7]](s16), [[TRUNC3]](s16)
|
|
; VI: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[INT1]](s16)
|
|
; VI: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[INT3]](s16)
|
|
; VI: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
|
|
; VI: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
|
|
; VI: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
|
|
; VI: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[INT5]](s16)
|
|
; VI: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[INT7]](s16)
|
|
; VI: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[ZEXT3]], [[C]](s32)
|
|
; VI: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL1]]
|
|
; VI: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
|
|
; VI: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>)
|
|
; VI: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
|
; GFX9-LABEL: name: test_fdiv_v4s16
|
|
; GFX9: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; GFX9: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
|
; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX9: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX9: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
|
; GFX9: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX9: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX9: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX9: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX9: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX9: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
|
|
; GFX9: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX9: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX9: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC4]](s16), [[TRUNC]](s16)
|
|
; GFX9: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX9: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX9: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX9: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC5]](s16), [[TRUNC1]](s16)
|
|
; GFX9: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX9: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC6]](s16)
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; GFX9: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; GFX9: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC6]](s16), [[TRUNC2]](s16)
|
|
; GFX9: [[FPEXT6:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX9: [[FPEXT7:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC7]](s16)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT7]](s32)
|
|
; GFX9: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT6]], [[INT6]]
|
|
; GFX9: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL3]](s32)
|
|
; GFX9: [[INT7:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC3]](s16), [[TRUNC7]](s16), [[TRUNC3]](s16)
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[INT5]](s16)
|
|
; GFX9: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[INT7]](s16)
|
|
; GFX9: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT2]](s32), [[ANYEXT3]](s32)
|
|
; GFX9: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_v4s16
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; GFX9-UNSAFE: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
|
; GFX9-UNSAFE: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX9-UNSAFE: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX9-UNSAFE: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX9-UNSAFE: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX9-UNSAFE: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX9-UNSAFE: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
|
; GFX9-UNSAFE: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX9-UNSAFE: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX9-UNSAFE: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX9-UNSAFE: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX9-UNSAFE: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX9-UNSAFE: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC4]](s16)
|
|
; GFX9-UNSAFE: [[FMUL:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC]], [[INT]]
|
|
; GFX9-UNSAFE: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC5]](s16)
|
|
; GFX9-UNSAFE: [[FMUL1:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC1]], [[INT1]]
|
|
; GFX9-UNSAFE: [[INT2:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC6]](s16)
|
|
; GFX9-UNSAFE: [[FMUL2:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC2]], [[INT2]]
|
|
; GFX9-UNSAFE: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC7]](s16)
|
|
; GFX9-UNSAFE: [[FMUL3:%[0-9]+]]:_(s16) = G_FMUL [[TRUNC3]], [[INT3]]
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL1]](s16)
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX9-UNSAFE: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL2]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[FMUL3]](s16)
|
|
; GFX9-UNSAFE: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT2]](s32), [[ANYEXT3]](s32)
|
|
; GFX9-UNSAFE: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
|
; GFX10-LABEL: name: test_fdiv_v4s16
|
|
; GFX10: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
; GFX10: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
|
|
; GFX10: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
|
|
; GFX10: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
|
|
; GFX10: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
|
|
; GFX10: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
|
|
; GFX10: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
|
|
; GFX10: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
|
|
; GFX10: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
|
|
; GFX10: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
|
|
; GFX10: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
|
|
; GFX10: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
|
|
; GFX10: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
|
|
; GFX10: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
|
|
; GFX10: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
|
|
; GFX10: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
|
|
; GFX10: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
|
|
; GFX10: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
|
|
; GFX10: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC4]](s16)
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT1]](s32)
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT]], [[INT]]
|
|
; GFX10: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL]](s32)
|
|
; GFX10: [[INT1:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC]](s16), [[TRUNC4]](s16), [[TRUNC]](s16)
|
|
; GFX10: [[FPEXT2:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC1]](s16)
|
|
; GFX10: [[FPEXT3:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC5]](s16)
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT3]](s32)
|
|
; GFX10: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT2]], [[INT2]]
|
|
; GFX10: [[FPTRUNC1:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL1]](s32)
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC1]](s16), [[TRUNC5]](s16), [[TRUNC1]](s16)
|
|
; GFX10: [[FPEXT4:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC2]](s16)
|
|
; GFX10: [[FPEXT5:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC6]](s16)
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT5]](s32)
|
|
; GFX10: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT4]], [[INT4]]
|
|
; GFX10: [[FPTRUNC2:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL2]](s32)
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC2]](s16), [[TRUNC6]](s16), [[TRUNC2]](s16)
|
|
; GFX10: [[FPEXT6:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC3]](s16)
|
|
; GFX10: [[FPEXT7:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC7]](s16)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FPEXT7]](s32)
|
|
; GFX10: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[FPEXT6]], [[INT6]]
|
|
; GFX10: [[FPTRUNC3:%[0-9]+]]:_(s16) = G_FPTRUNC [[FMUL3]](s32)
|
|
; GFX10: [[INT7:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[FPTRUNC3]](s16), [[TRUNC7]](s16), [[TRUNC3]](s16)
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT1]](s16)
|
|
; GFX10: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[INT3]](s16)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT]](s32), [[ANYEXT1]](s32)
|
|
; GFX10: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[INT5]](s16)
|
|
; GFX10: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[INT7]](s16)
|
|
; GFX10: [[BUILD_VECTOR_TRUNC1:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[ANYEXT2]](s32), [[ANYEXT3]](s32)
|
|
; GFX10: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BUILD_VECTOR_TRUNC]](<2 x s16>), [[BUILD_VECTOR_TRUNC1]](<2 x s16>)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
|
|
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
|
|
%1:_(<4 x s16>) = COPY $vgpr2_vgpr3
|
|
%2:_(<4 x s16>) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s16_constant_one_rcp
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
|
|
; SI-LABEL: name: test_fdiv_s16_constant_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xH3C00
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[C]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC]](s16)
|
|
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; VI-LABEL: name: test_fdiv_s16_constant_one_rcp
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; VI: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC]](s16)
|
|
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s16_constant_one_rcp
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC]](s16)
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s16_constant_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s16_constant_one_rcp
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX10: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[TRUNC]](s16)
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX10: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
%0:_(s16) = G_FCONSTANT half 1.0
|
|
%1:_(s32) = COPY $vgpr0
|
|
%2:_(s16) = G_TRUNC %1
|
|
%3:_(s16) = G_FDIV %0, %2
|
|
%4:_(s32) = G_ANYEXT %3
|
|
$vgpr0 = COPY %4
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s16_constant_negative_one_rcp
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
|
|
; SI-LABEL: name: test_fdiv_s16_constant_negative_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s16) = G_FCONSTANT half 0xHBC00
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; SI: [[FPEXT:%[0-9]+]]:_(s32) = G_FPEXT [[C]](s16)
|
|
; SI: [[FPEXT1:%[0-9]+]]:_(s32) = G_FPEXT [[TRUNC]](s16)
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[FPEXT]](s32), [[FPEXT1]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[FPEXT1]](s32), [[FPEXT]](s32)
|
|
; SI: [[FPTRUNC:%[0-9]+]]:_(s16) = G_FPTRUNC [[INT6]](s32)
|
|
; SI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[FPTRUNC]](s16)
|
|
; SI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; VI-LABEL: name: test_fdiv_s16_constant_negative_one_rcp
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s16) = G_FNEG [[TRUNC]]
|
|
; VI: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s16)
|
|
; VI: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; VI: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s16_constant_negative_one_rcp
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s16) = G_FNEG [[TRUNC]]
|
|
; GFX9: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s16)
|
|
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s16_constant_negative_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX9-UNSAFE: [[FNEG:%[0-9]+]]:_(s16) = G_FNEG [[TRUNC]]
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s16)
|
|
; GFX9-UNSAFE: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s16_constant_negative_one_rcp
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[COPY]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s16) = G_FNEG [[TRUNC]]
|
|
; GFX10: [[INT:%[0-9]+]]:_(s16) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s16)
|
|
; GFX10: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[INT]](s16)
|
|
; GFX10: $vgpr0 = COPY [[ANYEXT]](s32)
|
|
%0:_(s16) = G_FCONSTANT half -1.0
|
|
%1:_(s32) = COPY $vgpr0
|
|
%2:_(s16) = G_TRUNC %1
|
|
%3:_(s16) = G_FDIV %0, %2
|
|
%4:_(s32) = G_ANYEXT %3
|
|
$vgpr0 = COPY %4
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s32_constant_one_rcp
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
|
|
; SI-LABEL: name: test_fdiv_s32_constant_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; SI: $vgpr0 = COPY [[INT6]](s32)
|
|
; VI-LABEL: name: test_fdiv_s32_constant_one_rcp
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; VI: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s32_constant_one_rcp
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; GFX9: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s32_constant_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY]](s32)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[INT]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s32_constant_one_rcp
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; GFX10: $vgpr0 = COPY [[INT6]](s32)
|
|
%0:_(s32) = G_FCONSTANT float 1.0
|
|
%1:_(s32) = COPY $vgpr0
|
|
%2:_(s32) = G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s32_constant_negative_one_rcp
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0
|
|
|
|
; SI-LABEL: name: test_fdiv_s32_constant_negative_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float -1.000000e+00
|
|
; SI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; SI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; SI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; SI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; SI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; SI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; SI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; SI: $vgpr0 = COPY [[INT6]](s32)
|
|
; VI-LABEL: name: test_fdiv_s32_constant_negative_one_rcp
|
|
; VI: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float -1.000000e+00
|
|
; VI: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; VI: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; VI: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; VI: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; VI: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; VI: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; VI: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; VI: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-LABEL: name: test_fdiv_s32_constant_negative_one_rcp
|
|
; GFX9: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float -1.000000e+00
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; GFX9: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; GFX9: $vgpr0 = COPY [[INT6]](s32)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s32_constant_negative_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX9-UNSAFE: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[COPY]]
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s32)
|
|
; GFX9-UNSAFE: $vgpr0 = COPY [[INT]](s32)
|
|
; GFX10-LABEL: name: test_fdiv_s32_constant_negative_one_rcp
|
|
; GFX10: [[C:%[0-9]+]]:_(s32) = G_FCONSTANT float -1.000000e+00
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
|
|
; GFX10: [[C1:%[0-9]+]]:_(s32) = G_FCONSTANT float 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s32), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 0
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s32), [[INT3:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s32), [[COPY]](s32), 1
|
|
; GFX10: [[INT4:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s32)
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s32) = G_FNEG [[INT]]
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[INT4]], [[C1]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s32) = G_FMA [[FMA]], [[INT4]], [[INT4]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[INT2]], [[FMA1]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMUL]], [[INT2]]
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s32) = G_FMA [[FMA2]], [[FMA1]], [[FMUL]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s32) = G_FMA [[FNEG]], [[FMA3]], [[INT2]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s32), [[FMA1]](s32), [[FMA3]](s32), [[INT3]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s32) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s32), [[COPY]](s32), [[C]](s32)
|
|
; GFX10: $vgpr0 = COPY [[INT6]](s32)
|
|
%0:_(s32) = G_FCONSTANT float -1.0
|
|
%1:_(s32) = COPY $vgpr0
|
|
%2:_(s32) = G_FDIV %0, %1
|
|
$vgpr0 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s64_constant_one_rcp
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-output-denormals: true
|
|
fp64-fp16-input-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s64_constant_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; SI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; SI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; SI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; SI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; SI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; SI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; SI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[C]](s64)
|
|
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
|
|
; SI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT]](s64)
|
|
; SI: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT3]](s64)
|
|
; SI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV1]](s32), [[UV7]]
|
|
; SI: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV3]](s32), [[UV5]]
|
|
; SI: [[XOR:%[0-9]+]]:_(s1) = G_XOR [[ICMP]], [[ICMP1]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[XOR]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; SI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; VI-LABEL: name: test_fdiv_s64_constant_one_rcp
|
|
; VI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; VI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; VI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; VI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; VI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; VI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; VI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; VI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; VI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-LABEL: name: test_fdiv_s64_constant_one_rcp
|
|
; GFX9: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s64_constant_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[COPY]](s64)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[INT]](s64)
|
|
; GFX10-LABEL: name: test_fdiv_s64_constant_one_rcp
|
|
; GFX10: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C]]
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
%0:_(s64) = G_FCONSTANT double 1.0
|
|
%1:_(s64) = COPY $vgpr0_vgpr1
|
|
%2:_(s64) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|
|
|
|
---
|
|
name: test_fdiv_s64_constant_negative_one_rcp
|
|
machineFunctionInfo:
|
|
mode:
|
|
fp32-input-denormals: false
|
|
fp32-output-denormals: false
|
|
fp64-fp16-input-denormals: true
|
|
fp64-fp16-output-denormals: true
|
|
|
|
body: |
|
|
bb.0:
|
|
liveins: $vgpr0_vgpr1
|
|
|
|
; SI-LABEL: name: test_fdiv_s64_constant_negative_one_rcp
|
|
; SI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double -1.000000e+00
|
|
; SI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; SI: [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; SI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; SI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; SI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; SI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C1]]
|
|
; SI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; SI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C1]]
|
|
; SI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; SI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; SI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; SI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; SI: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[C]](s64)
|
|
; SI: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
|
|
; SI: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT]](s64)
|
|
; SI: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[INT3]](s64)
|
|
; SI: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV1]](s32), [[UV7]]
|
|
; SI: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(eq), [[UV3]](s32), [[UV5]]
|
|
; SI: [[XOR:%[0-9]+]]:_(s1) = G_XOR [[ICMP]], [[ICMP1]]
|
|
; SI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[XOR]](s1)
|
|
; SI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; SI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; VI-LABEL: name: test_fdiv_s64_constant_negative_one_rcp
|
|
; VI: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double -1.000000e+00
|
|
; VI: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; VI: [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; VI: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; VI: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; VI: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; VI: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C1]]
|
|
; VI: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; VI: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C1]]
|
|
; VI: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; VI: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; VI: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; VI: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; VI: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; VI: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; VI: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-LABEL: name: test_fdiv_s64_constant_negative_one_rcp
|
|
; GFX9: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double -1.000000e+00
|
|
; GFX9: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9: [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX9: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; GFX9: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX9: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX9: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C1]]
|
|
; GFX9: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX9: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C1]]
|
|
; GFX9: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; GFX9: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX9: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX9: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX9: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX9: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; GFX9: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
; GFX9-UNSAFE-LABEL: name: test_fdiv_s64_constant_negative_one_rcp
|
|
; GFX9-UNSAFE: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX9-UNSAFE: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[COPY]]
|
|
; GFX9-UNSAFE: [[INT:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[FNEG]](s64)
|
|
; GFX9-UNSAFE: $vgpr0_vgpr1 = COPY [[INT]](s64)
|
|
; GFX10-LABEL: name: test_fdiv_s64_constant_negative_one_rcp
|
|
; GFX10: [[C:%[0-9]+]]:_(s64) = G_FCONSTANT double -1.000000e+00
|
|
; GFX10: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
|
|
; GFX10: [[C1:%[0-9]+]]:_(s64) = G_FCONSTANT double 1.000000e+00
|
|
; GFX10: [[INT:%[0-9]+]]:_(s64), [[INT1:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 0
|
|
; GFX10: [[FNEG:%[0-9]+]]:_(s64) = G_FNEG [[INT]]
|
|
; GFX10: [[INT2:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.rcp), [[INT]](s64)
|
|
; GFX10: [[FMA:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[INT2]], [[C1]]
|
|
; GFX10: [[FMA1:%[0-9]+]]:_(s64) = G_FMA [[INT2]], [[FMA]], [[INT2]]
|
|
; GFX10: [[FMA2:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMA1]], [[C1]]
|
|
; GFX10: [[INT3:%[0-9]+]]:_(s64), [[INT4:%[0-9]+]]:_(s1) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.scale), [[C]](s64), [[COPY]](s64), 1
|
|
; GFX10: [[FMA3:%[0-9]+]]:_(s64) = G_FMA [[FMA1]], [[FMA2]], [[FMA1]]
|
|
; GFX10: [[FMUL:%[0-9]+]]:_(s64) = G_FMUL [[INT3]], [[FMA3]]
|
|
; GFX10: [[FMA4:%[0-9]+]]:_(s64) = G_FMA [[FNEG]], [[FMUL]], [[INT3]]
|
|
; GFX10: [[INT5:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fmas), [[FMA4]](s64), [[FMA3]](s64), [[FMUL]](s64), [[INT4]](s1)
|
|
; GFX10: [[INT6:%[0-9]+]]:_(s64) = G_INTRINSIC intrinsic(@llvm.amdgcn.div.fixup), [[INT5]](s64), [[COPY]](s64), [[C]](s64)
|
|
; GFX10: $vgpr0_vgpr1 = COPY [[INT6]](s64)
|
|
%0:_(s64) = G_FCONSTANT double -1.0
|
|
%1:_(s64) = COPY $vgpr0_vgpr1
|
|
%2:_(s64) = G_FDIV %0, %1
|
|
$vgpr0_vgpr1 = COPY %2
|
|
...
|