llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-fmad.s32.mir

626 lines
37 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 %s -o - | FileCheck -check-prefix=GFX6 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -run-pass=legalizer %s -o - | FileCheck -check-prefix=GFX7 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1010 -run-pass=legalizer %s -o - | FileCheck -check-prefix=GFX101 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1030 -run-pass=legalizer %s -o - | FileCheck -check-prefix=GFX103 %s
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx1031 -run-pass=legalizer %s -o - | FileCheck -check-prefix=GFX103 %s
---
name: test_fmad_s32_flush
machineFunctionInfo:
mode:
fp32-input-denormals: false
fp32-output-denormals: false
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: test_fmad_s32_flush
; GFX6: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX6: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX6: $vgpr0 = COPY [[FMAD]](s32)
; GFX7-LABEL: name: test_fmad_s32_flush
; GFX7: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX7: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX7: $vgpr0 = COPY [[FMAD]](s32)
; GFX101-LABEL: name: test_fmad_s32_flush
; GFX101: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX101: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX101: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX101: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX101: $vgpr0 = COPY [[FMAD]](s32)
; GFX103-LABEL: name: test_fmad_s32_flush
; GFX103: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX103: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX103: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[COPY2]]
; GFX103: $vgpr0 = COPY [[FADD]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = G_FMAD %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fmad_s32_flags_flush
machineFunctionInfo:
mode:
fp32-input-denormals: false
fp32-output-denormals: false
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: test_fmad_s32_flags_flush
; GFX6: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX6: [[FMAD:%[0-9]+]]:_(s32) = nnan G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX6: $vgpr0 = COPY [[FMAD]](s32)
; GFX7-LABEL: name: test_fmad_s32_flags_flush
; GFX7: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX7: [[FMAD:%[0-9]+]]:_(s32) = nnan G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX7: $vgpr0 = COPY [[FMAD]](s32)
; GFX101-LABEL: name: test_fmad_s32_flags_flush
; GFX101: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX101: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX101: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX101: [[FMAD:%[0-9]+]]:_(s32) = nnan G_FMAD [[COPY]], [[COPY1]], [[COPY2]]
; GFX101: $vgpr0 = COPY [[FMAD]](s32)
; GFX103-LABEL: name: test_fmad_s32_flags_flush
; GFX103: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX103: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX103: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[COPY]], [[COPY1]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = nnan G_FADD [[FMUL]], [[COPY2]]
; GFX103: $vgpr0 = COPY [[FADD]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = nnan G_FMAD %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fmad_v2s32_flush
machineFunctionInfo:
mode:
fp32-input-denormals: false
fp32-output-denormals: false
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; GFX6-LABEL: name: test_fmad_v2s32_flush
; GFX6: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX6: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX6: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX6: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX6: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX6: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV2]], [[UV4]]
; GFX6: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV3]], [[UV5]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32)
; GFX6: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX7-LABEL: name: test_fmad_v2s32_flush
; GFX7: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX7: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX7: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX7: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX7: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV2]], [[UV4]]
; GFX7: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV3]], [[UV5]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32)
; GFX7: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX101-LABEL: name: test_fmad_v2s32_flush
; GFX101: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX101: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX101: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX101: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX101: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX101: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV2]], [[UV4]]
; GFX101: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV3]], [[UV5]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32)
; GFX101: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX103-LABEL: name: test_fmad_v2s32_flush
; GFX103: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX103: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX103: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX103: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX103: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV4]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV5]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32)
; GFX103: $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>) = COPY $vgpr4_vgpr5
%3:_(<2 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fmad_v3s32_flush
machineFunctionInfo:
mode:
fp32-input-denormals: false
fp32-output-denormals: false
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5, $vgpr6_vgpr7_vgpr8
; GFX6-LABEL: name: test_fmad_v3s32_flush
; GFX6: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX6: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX6: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX6: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX6: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX6: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV3]], [[UV6]]
; GFX6: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV4]], [[UV7]]
; GFX6: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV5]], [[UV8]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32)
; GFX6: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX7-LABEL: name: test_fmad_v3s32_flush
; GFX7: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX7: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX7: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX7: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX7: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX7: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV3]], [[UV6]]
; GFX7: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV4]], [[UV7]]
; GFX7: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV5]], [[UV8]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32)
; GFX7: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX101-LABEL: name: test_fmad_v3s32_flush
; GFX101: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX101: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX101: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX101: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX101: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX101: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV3]], [[UV6]]
; GFX101: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV4]], [[UV7]]
; GFX101: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV5]], [[UV8]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32)
; GFX101: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX103-LABEL: name: test_fmad_v3s32_flush
; GFX103: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX103: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX103: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX103: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX103: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV6]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV7]]
; GFX103: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
; GFX103: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV8]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32)
; GFX103: $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>) = COPY $vgpr6_vgpr7_vgpr8
%3:_(<3 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2 = COPY %3
...
---
name: test_fmad_v4s32_flush
machineFunctionInfo:
mode:
fp32-input-denormals: false
fp32-output-denormals: false
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11
; GFX6-LABEL: name: test_fmad_v4s32_flush
; GFX6: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX6: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX6: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX6: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX6: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX6: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV4]], [[UV8]]
; GFX6: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV5]], [[UV9]]
; GFX6: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV6]], [[UV10]]
; GFX6: [[FMAD3:%[0-9]+]]:_(s32) = G_FMAD [[UV3]], [[UV7]], [[UV11]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32), [[FMAD3]](s32)
; GFX6: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX7-LABEL: name: test_fmad_v4s32_flush
; GFX7: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX7: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX7: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX7: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX7: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX7: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV4]], [[UV8]]
; GFX7: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV5]], [[UV9]]
; GFX7: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV6]], [[UV10]]
; GFX7: [[FMAD3:%[0-9]+]]:_(s32) = G_FMAD [[UV3]], [[UV7]], [[UV11]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32), [[FMAD3]](s32)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX101-LABEL: name: test_fmad_v4s32_flush
; GFX101: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX101: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX101: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX101: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX101: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX101: [[FMAD:%[0-9]+]]:_(s32) = G_FMAD [[UV]], [[UV4]], [[UV8]]
; GFX101: [[FMAD1:%[0-9]+]]:_(s32) = G_FMAD [[UV1]], [[UV5]], [[UV9]]
; GFX101: [[FMAD2:%[0-9]+]]:_(s32) = G_FMAD [[UV2]], [[UV6]], [[UV10]]
; GFX101: [[FMAD3:%[0-9]+]]:_(s32) = G_FMAD [[UV3]], [[UV7]], [[UV11]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FMAD]](s32), [[FMAD1]](s32), [[FMAD2]](s32), [[FMAD3]](s32)
; GFX101: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX103-LABEL: name: test_fmad_v4s32_flush
; GFX103: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX103: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX103: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX103: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX103: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV4]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV8]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV5]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV9]]
; GFX103: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV6]]
; GFX103: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV10]]
; GFX103: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[UV3]], [[UV7]]
; GFX103: [[FADD3:%[0-9]+]]:_(s32) = G_FADD [[FMUL3]], [[UV11]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32), [[FADD3]](s32)
; GFX103: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
%3:_(<4 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...
---
name: test_fmad_s32_denorm
machineFunctionInfo:
mode:
fp32-input-denormals: true
fp32-output-denormals: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: test_fmad_s32_denorm
; GFX6: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX6: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
; GFX6: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[COPY2]]
; GFX6: $vgpr0 = COPY [[FADD]](s32)
; GFX7-LABEL: name: test_fmad_s32_denorm
; GFX7: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX7: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
; GFX7: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[COPY2]]
; GFX7: $vgpr0 = COPY [[FADD]](s32)
; GFX101-LABEL: name: test_fmad_s32_denorm
; GFX101: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX101: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX101: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX101: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
; GFX101: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[COPY2]]
; GFX101: $vgpr0 = COPY [[FADD]](s32)
; GFX103-LABEL: name: test_fmad_s32_denorm
; GFX103: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX103: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX103: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[COPY]], [[COPY1]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[COPY2]]
; GFX103: $vgpr0 = COPY [[FADD]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = G_FMAD %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fmad_s32_flags_denorm
machineFunctionInfo:
mode:
fp32-input-denormals: true
fp32-output-denormals: true
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2
; GFX6-LABEL: name: test_fmad_s32_flags_denorm
; GFX6: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX6: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX6: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX6: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[COPY]], [[COPY1]]
; GFX6: [[FADD:%[0-9]+]]:_(s32) = nnan G_FADD [[FMUL]], [[COPY2]]
; GFX6: $vgpr0 = COPY [[FADD]](s32)
; GFX7-LABEL: name: test_fmad_s32_flags_denorm
; GFX7: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX7: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX7: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX7: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[COPY]], [[COPY1]]
; GFX7: [[FADD:%[0-9]+]]:_(s32) = nnan G_FADD [[FMUL]], [[COPY2]]
; GFX7: $vgpr0 = COPY [[FADD]](s32)
; GFX101-LABEL: name: test_fmad_s32_flags_denorm
; GFX101: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX101: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX101: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX101: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[COPY]], [[COPY1]]
; GFX101: [[FADD:%[0-9]+]]:_(s32) = nnan G_FADD [[FMUL]], [[COPY2]]
; GFX101: $vgpr0 = COPY [[FADD]](s32)
; GFX103-LABEL: name: test_fmad_s32_flags_denorm
; GFX103: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX103: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX103: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = nnan G_FMUL [[COPY]], [[COPY1]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = nnan G_FADD [[FMUL]], [[COPY2]]
; GFX103: $vgpr0 = COPY [[FADD]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = nnan G_FMAD %0, %1, %2
$vgpr0 = COPY %3
...
---
name: test_fmad_v2s32_denorm
machineFunctionInfo:
mode:
fp32-input-denormals: true
fp32-output-denormals: true
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3, $vgpr4_vgpr5
; GFX6-LABEL: name: test_fmad_v2s32_denorm
; GFX6: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX6: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX6: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX6: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX6: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX6: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
; GFX6: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV4]]
; GFX6: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
; GFX6: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV5]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32)
; GFX6: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX7-LABEL: name: test_fmad_v2s32_denorm
; GFX7: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX7: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX7: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX7: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX7: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX7: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
; GFX7: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV4]]
; GFX7: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
; GFX7: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV5]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32)
; GFX7: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX101-LABEL: name: test_fmad_v2s32_denorm
; GFX101: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX101: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX101: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX101: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX101: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX101: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
; GFX101: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV4]]
; GFX101: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
; GFX101: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV5]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32)
; GFX101: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX103-LABEL: name: test_fmad_v2s32_denorm
; GFX103: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX103: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX103: [[COPY2:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr4_vgpr5
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX103: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX103: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<2 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV2]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV4]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV3]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV5]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32)
; GFX103: $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>) = COPY $vgpr4_vgpr5
%3:_(<2 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1 = COPY %3
...
---
name: test_fmad_v3s32_denorm
machineFunctionInfo:
mode:
fp32-input-denormals: true
fp32-output-denormals: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2, $vgpr3_vgpr4_vgpr5, $vgpr6_vgpr7_vgpr8
; GFX6-LABEL: name: test_fmad_v3s32_denorm
; GFX6: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX6: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX6: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX6: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX6: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX6: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
; GFX6: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV6]]
; GFX6: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
; GFX6: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV7]]
; GFX6: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
; GFX6: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV8]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32)
; GFX6: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX7-LABEL: name: test_fmad_v3s32_denorm
; GFX7: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX7: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX7: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX7: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX7: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX7: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
; GFX7: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV6]]
; GFX7: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
; GFX7: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV7]]
; GFX7: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
; GFX7: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV8]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32)
; GFX7: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX101-LABEL: name: test_fmad_v3s32_denorm
; GFX101: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX101: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX101: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX101: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX101: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX101: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
; GFX101: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV6]]
; GFX101: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
; GFX101: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV7]]
; GFX101: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
; GFX101: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV8]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32)
; GFX101: $vgpr0_vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<3 x s32>)
; GFX103-LABEL: name: test_fmad_v3s32_denorm
; GFX103: [[COPY:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr0_vgpr1_vgpr2
; GFX103: [[COPY1:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr3_vgpr4_vgpr5
; GFX103: [[COPY2:%[0-9]+]]:_(<3 x s32>) = COPY $vgpr6_vgpr7_vgpr8
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<3 x s32>)
; GFX103: [[UV3:%[0-9]+]]:_(s32), [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<3 x s32>)
; GFX103: [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32), [[UV8:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<3 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV3]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV6]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV4]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV7]]
; GFX103: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV5]]
; GFX103: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV8]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32)
; GFX103: $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>) = COPY $vgpr6_vgpr7_vgpr8
%3:_(<3 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2 = COPY %3
...
---
name: test_fmad_v4s32_denorm
machineFunctionInfo:
mode:
fp32-input-denormals: true
fp32-output-denormals: true
body: |
bb.0:
liveins: $vgpr0_vgpr1_vgpr2_vgpr3, $vgpr4_vgpr5_vgpr6_vgpr7, $vgpr8_vgpr9_vgpr10_vgpr11
; GFX6-LABEL: name: test_fmad_v4s32_denorm
; GFX6: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX6: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX6: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX6: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX6: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX6: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX6: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV4]]
; GFX6: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV8]]
; GFX6: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV5]]
; GFX6: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV9]]
; GFX6: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV6]]
; GFX6: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV10]]
; GFX6: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[UV3]], [[UV7]]
; GFX6: [[FADD3:%[0-9]+]]:_(s32) = G_FADD [[FMUL3]], [[UV11]]
; GFX6: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32), [[FADD3]](s32)
; GFX6: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX7-LABEL: name: test_fmad_v4s32_denorm
; GFX7: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX7: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX7: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX7: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX7: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX7: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX7: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV4]]
; GFX7: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV8]]
; GFX7: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV5]]
; GFX7: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV9]]
; GFX7: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV6]]
; GFX7: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV10]]
; GFX7: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[UV3]], [[UV7]]
; GFX7: [[FADD3:%[0-9]+]]:_(s32) = G_FADD [[FMUL3]], [[UV11]]
; GFX7: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32), [[FADD3]](s32)
; GFX7: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX101-LABEL: name: test_fmad_v4s32_denorm
; GFX101: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX101: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX101: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX101: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX101: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX101: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX101: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV4]]
; GFX101: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV8]]
; GFX101: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV5]]
; GFX101: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV9]]
; GFX101: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV6]]
; GFX101: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV10]]
; GFX101: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[UV3]], [[UV7]]
; GFX101: [[FADD3:%[0-9]+]]:_(s32) = G_FADD [[FMUL3]], [[UV11]]
; GFX101: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32), [[FADD3]](s32)
; GFX101: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
; GFX103-LABEL: name: test_fmad_v4s32_denorm
; GFX103: [[COPY:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
; GFX103: [[COPY1:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
; GFX103: [[COPY2:%[0-9]+]]:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
; GFX103: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32), [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<4 x s32>)
; GFX103: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32), [[UV6:%[0-9]+]]:_(s32), [[UV7:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<4 x s32>)
; GFX103: [[UV8:%[0-9]+]]:_(s32), [[UV9:%[0-9]+]]:_(s32), [[UV10:%[0-9]+]]:_(s32), [[UV11:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY2]](<4 x s32>)
; GFX103: [[FMUL:%[0-9]+]]:_(s32) = G_FMUL [[UV]], [[UV4]]
; GFX103: [[FADD:%[0-9]+]]:_(s32) = G_FADD [[FMUL]], [[UV8]]
; GFX103: [[FMUL1:%[0-9]+]]:_(s32) = G_FMUL [[UV1]], [[UV5]]
; GFX103: [[FADD1:%[0-9]+]]:_(s32) = G_FADD [[FMUL1]], [[UV9]]
; GFX103: [[FMUL2:%[0-9]+]]:_(s32) = G_FMUL [[UV2]], [[UV6]]
; GFX103: [[FADD2:%[0-9]+]]:_(s32) = G_FADD [[FMUL2]], [[UV10]]
; GFX103: [[FMUL3:%[0-9]+]]:_(s32) = G_FMUL [[UV3]], [[UV7]]
; GFX103: [[FADD3:%[0-9]+]]:_(s32) = G_FADD [[FMUL3]], [[UV11]]
; GFX103: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[FADD]](s32), [[FADD1]](s32), [[FADD2]](s32), [[FADD3]](s32)
; GFX103: $vgpr0_vgpr1_vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<4 x s32>)
%0:_(<4 x s32>) = COPY $vgpr0_vgpr1_vgpr2_vgpr3
%1:_(<4 x s32>) = COPY $vgpr4_vgpr5_vgpr6_vgpr7
%2:_(<4 x s32>) = COPY $vgpr8_vgpr9_vgpr10_vgpr11
%3:_(<4 x s32>) = G_FMAD %0, %1, %2
$vgpr0_vgpr1_vgpr2_vgpr3 = COPY %3
...