Google Git
Sign in
llvm / llvm-project / 654c89d85a5108f2f04a8a748c44162e16260c7c / . / llvm / test / CodeGen / AMDGPU / GlobalISel / legalize-smulo.mir
blob: b6b85b530cc555f3bdc529d41705543c4b96c1b8 [file] [log] [blame]
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=fiji -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX8
# RUN: llc -mtriple=amdgcn-mesa-mesa3d -mcpu=gfx906 -O0 -run-pass=legalizer %s -o - | FileCheck %s --check-prefix=GFX9
---
name: test_smulo_s32
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: test_smulo_s32
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[COPY]], [[COPY1]]
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX8: $vgpr0 = COPY [[MUL]](s32)
; GFX8: $vgpr1 = COPY [[SEXT]](s32)
; GFX9-LABEL: name: test_smulo_s32
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[COPY]], [[COPY1]]
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[COPY]], [[COPY1]]
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX9: $vgpr0 = COPY [[MUL]](s32)
; GFX9: $vgpr1 = COPY [[SEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32), %3:_(s1) = G_SMULO %0, %1
%4:_(s32) = G_SEXT %3
$vgpr0 = COPY %2
$vgpr1 = COPY %4
...
---
name: test_smulo_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; GFX8-LABEL: name: test_smulo_v2s32
; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[UV]], [[UV2]]
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX8: [[SMULH1:%[0-9]+]]:_(s32) = G_SMULH [[UV1]], [[UV3]]
; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
; GFX8: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[MUL1]], [[C]](s32)
; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH1]](s32), [[ASHR1]]
; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG]](s32), [[SEXT_INREG1]](s32)
; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
; GFX9-LABEL: name: test_smulo_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: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[UV]], [[UV2]]
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[UV]], [[UV2]]
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX9: [[SMULH1:%[0-9]+]]:_(s32) = G_SMULH [[UV1]], [[UV3]]
; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[UV1]], [[UV3]]
; GFX9: [[ASHR1:%[0-9]+]]:_(s32) = G_ASHR [[MUL1]], [[C]](s32)
; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH1]](s32), [[ASHR1]]
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[MUL]](s32), [[MUL1]](s32)
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG]](s32), [[SEXT_INREG1]](s32)
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR1]](<2 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<2 x s32>), %3:_(<2 x s1>) = G_SMULO %0, %1
%4:_(<2 x s32>) = G_SEXT %3
$vgpr0_vgpr1 = COPY %2
$vgpr2_vgpr3 = COPY %4
...
---
name: test_smulo_s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: test_smulo_s16
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 16
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 16
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX8: $vgpr1 = COPY [[SEXT]](s32)
; GFX9-LABEL: name: test_smulo_s16
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 16
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 16
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX9: $vgpr1 = COPY [[SEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %0
%3:_(s16) = G_TRUNC %1
%4:_(s16), %6:_(s1) = G_SMULO %2, %3
%5:_(s32) = G_SEXT %4
%7:_(s32) = G_SEXT %6
$vgpr0 = COPY %5
$vgpr1 = COPY %7
...
---
name: test_smulo_s8
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: test_smulo_s8
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX8: $vgpr1 = COPY [[SEXT]](s32)
; GFX9-LABEL: name: test_smulo_s8
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[ICMP]](s1)
; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX9: $vgpr1 = COPY [[SEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s8) = G_TRUNC %0
%3:_(s8) = G_TRUNC %1
%4:_(s8), %6:_(s1) = G_SMULO %2, %3
%5:_(s32) = G_SEXT %4
%7:_(s32) = G_SEXT %6
$vgpr0 = COPY %5
$vgpr1 = COPY %7
...
---
name: test_smulo_v2s16
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; GFX8-LABEL: name: test_smulo_v2s16
; GFX8: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; GFX8: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; GFX8: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; GFX8: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV]], 16
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV2]], 16
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV1]], 16
; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV3]], 16
; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 16
; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C]]
; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C]]
; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C1]](s32)
; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8: [[BITCAST:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX8: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
; GFX8: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
; GFX8: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG6]](s32), [[SEXT_INREG7]](s32)
; GFX8: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[BITCAST]](<2 x s16>)
; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C1]](s32)
; GFX8: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST1]], 16
; GFX8: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 16
; GFX8: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG8]](s32), [[SEXT_INREG9]](s32)
; GFX8: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
; GFX8: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
; GFX9-LABEL: name: test_smulo_v2s16
; 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: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV]], 16
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV2]], 16
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 16
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV1]], 16
; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[UV3]], 16
; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 16
; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
; GFX9: [[BUILD_VECTOR_TRUNC:%[0-9]+]]:_(<2 x s16>) = G_BUILD_VECTOR_TRUNC [[MUL]](s32), [[MUL1]](s32)
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX9: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT]], 1
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX9: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[ANYEXT1]], 1
; GFX9: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG6]](s32), [[SEXT_INREG7]](s32)
; GFX9: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[BUILD_VECTOR_TRUNC]](<2 x s16>)
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; GFX9: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[BITCAST]], 16
; GFX9: [[SEXT_INREG9:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 16
; GFX9: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[SEXT_INREG8]](s32), [[SEXT_INREG9]](s32)
; GFX9: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR1]](<2 x s32>)
; GFX9: $vgpr2_vgpr3 = COPY [[BUILD_VECTOR]](<2 x s32>)
%0:_(<2 x s32>) = COPY $vgpr0_vgpr1
%1:_(<2 x s32>) = COPY $vgpr2_vgpr3
%2:_(<2 x s16>) = G_TRUNC %0
%3:_(<2 x s16>) = G_TRUNC %1
%4:_(<2 x s16>), %6:_(<2 x s1>) = G_SMULO %2, %3
%7:_(<2 x s32>) = G_SEXT %6
%5:_(<2 x s32>) = G_SEXT %4
$vgpr0_vgpr1 = COPY %5
$vgpr2_vgpr3 = COPY %7
...
---
name: test_smulo_v2s8
body: |
bb.0:
liveins: $vgpr0, $vgpr1, $vgpr2, $vgpr3
; GFX8-LABEL: name: test_smulo_v2s8
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX8: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
; GFX8: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
; GFX8: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
; GFX8: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
; GFX8: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
; GFX8: [[AND1:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C]]
; GFX8: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
; GFX8: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND1]], [[C1]](s16)
; GFX8: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND]], [[SHL]]
; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
; GFX8: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX8: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX8: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX8: $vgpr1 = COPY [[ANYEXT1]](s32)
; GFX8: $vgpr2 = COPY [[ANYEXT2]](s32)
; GFX9-LABEL: name: test_smulo_v2s8
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[COPY2:%[0-9]+]]:_(s32) = COPY $vgpr2
; GFX9: [[COPY3:%[0-9]+]]:_(s32) = COPY $vgpr3
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY2]], 8
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY3]], 8
; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL1]], 8
; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL1]](s32), [[SEXT_INREG5]]
; GFX9: [[C:%[0-9]+]]:_(s16) = G_CONSTANT i16 255
; GFX9: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[MUL]](s32)
; GFX9: [[AND:%[0-9]+]]:_(s16) = G_AND [[TRUNC]], [[C]]
; GFX9: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[MUL1]](s32)
; GFX9: [[AND1:%[0-9]+]]:_(s16) = G_AND [[TRUNC1]], [[C]]
; GFX9: [[C1:%[0-9]+]]:_(s16) = G_CONSTANT i16 8
; GFX9: [[SHL:%[0-9]+]]:_(s16) = G_SHL [[AND1]], [[C1]](s16)
; GFX9: [[OR:%[0-9]+]]:_(s16) = G_OR [[AND]], [[SHL]]
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[OR]](s16)
; GFX9: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX9: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; GFX9: $vgpr0 = COPY [[ANYEXT]](s32)
; GFX9: $vgpr1 = COPY [[ANYEXT1]](s32)
; GFX9: $vgpr2 = COPY [[ANYEXT2]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32) = COPY $vgpr2
%3:_(s32) = COPY $vgpr3
%5:_(s8) = G_TRUNC %0
%6:_(s8) = G_TRUNC %1
%7:_(s8) = G_TRUNC %2
%8:_(s8) = G_TRUNC %3
%11:_(<2 x s8>) = G_BUILD_VECTOR %5, %6
%12:_(<2 x s8>) = G_BUILD_VECTOR %7, %8
%13:_(<2 x s8>), %19:_(<2 x s1>) = G_SMULO %11, %12
%20:_(<2 x s32>) = G_SEXT %19
%14:_(s8), %15:_(s8) = G_UNMERGE_VALUES %13
%21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %19
%17:_(s16) = G_MERGE_VALUES %14, %15
%18:_(s32) = G_ANYEXT %17
%23:_(s32) = G_ANYEXT %21
%24:_(s32) = G_ANYEXT %22
$vgpr0 = COPY %18
$vgpr1 = COPY %23
$vgpr2 = COPY %24
...
---
name: test_smulo_v4s8
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: test_smulo_v4s8
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; GFX8: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
; GFX8: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX8: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
; GFX8: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
; GFX8: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
; GFX8: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
; GFX8: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
; GFX8: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 8
; GFX8: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR3]], 8
; GFX8: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX8: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR1]], 8
; GFX8: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR4]], 8
; GFX8: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG5]], [[SEXT_INREG6]]
; GFX8: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR2]], 8
; GFX8: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR5]], 8
; GFX8: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG7]], [[SEXT_INREG8]]
; GFX8: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
; GFX8: [[AND:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C3]]
; GFX8: [[AND1:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C3]]
; GFX8: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
; GFX8: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX8: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL2]], [[C3]]
; GFX8: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND2]], [[C1]](s32)
; GFX8: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
; GFX8: [[AND3:%[0-9]+]]:_(s32) = G_AND [[MUL3]], [[C3]]
; GFX8: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C2]](s32)
; GFX8: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
; GFX8: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX8: $vgpr0 = COPY [[OR2]](s32)
; GFX8: $vgpr1 = COPY [[ANYEXT]](s32)
; GFX9-LABEL: name: test_smulo_v4s8
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 8
; GFX9: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C]](s32)
; GFX9: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; GFX9: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C1]](s32)
; GFX9: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 24
; GFX9: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[COPY]], [[C2]](s32)
; GFX9: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C]](s32)
; GFX9: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C1]](s32)
; GFX9: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[COPY1]], [[C2]](s32)
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 8
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 8
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 8
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR]], 8
; GFX9: [[SEXT_INREG4:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR3]], 8
; GFX9: [[MUL1:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG3]], [[SEXT_INREG4]]
; GFX9: [[SEXT_INREG5:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR1]], 8
; GFX9: [[SEXT_INREG6:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR4]], 8
; GFX9: [[MUL2:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG5]], [[SEXT_INREG6]]
; GFX9: [[SEXT_INREG7:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR2]], 8
; GFX9: [[SEXT_INREG8:%[0-9]+]]:_(s32) = G_SEXT_INREG [[LSHR5]], 8
; GFX9: [[MUL3:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG7]], [[SEXT_INREG8]]
; GFX9: [[C3:%[0-9]+]]:_(s32) = G_CONSTANT i32 255
; GFX9: [[AND:%[0-9]+]]:_(s32) = G_AND [[MUL]], [[C3]]
; GFX9: [[AND1:%[0-9]+]]:_(s32) = G_AND [[MUL1]], [[C3]]
; GFX9: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[AND1]], [[C]](s32)
; GFX9: [[OR:%[0-9]+]]:_(s32) = G_OR [[AND]], [[SHL]]
; GFX9: [[AND2:%[0-9]+]]:_(s32) = G_AND [[MUL2]], [[C3]]
; GFX9: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[AND2]], [[C1]](s32)
; GFX9: [[OR1:%[0-9]+]]:_(s32) = G_OR [[OR]], [[SHL1]]
; GFX9: [[AND3:%[0-9]+]]:_(s32) = G_AND [[MUL3]], [[C3]]
; GFX9: [[SHL2:%[0-9]+]]:_(s32) = G_SHL [[AND3]], [[C2]](s32)
; GFX9: [[OR2:%[0-9]+]]:_(s32) = G_OR [[OR1]], [[SHL2]]
; GFX9: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; GFX9: $vgpr0 = COPY [[OR2]](s32)
; GFX9: $vgpr1 = COPY [[ANYEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8) = G_UNMERGE_VALUES %0
%6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8) = G_UNMERGE_VALUES %1
%10:_(<4 x s8>) = G_BUILD_VECTOR %2:_(s8), %3:_(s8), %4:_(s8), %5:_(s8)
%11:_(<4 x s8>) = G_BUILD_VECTOR %6:_(s8), %7:_(s8), %8:_(s8), %9:_(s8)
%12:_(<4 x s8>), %18:_(<4 x s1>) = G_SMULO %10:_, %11:_
%13:_(s8), %14:_(s8), %15:_(s8), %16:_(s8) = G_UNMERGE_VALUES %12:_(<4 x s8>)
%19:_(s1), %20:_(s1), %21:_(s1), %22:_(s1) = G_UNMERGE_VALUES %18:_(<4 x s1>)
%17:_(s32) = G_MERGE_VALUES %13, %14, %15, %16
%23:_(s32) = G_ANYEXT %19
$vgpr0 = COPY %17
$vgpr1 = COPY %23
...
---
name: test_smulo_s24
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; GFX8-LABEL: name: test_smulo_s24
; GFX8: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX8: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX8: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 24
; GFX8: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 24
; GFX8: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX8: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX8: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX8: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX8: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
; GFX8: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX8: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
; GFX8: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
; GFX8: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[OR]](s1)
; GFX8: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX8: $vgpr1 = COPY [[SEXT]](s32)
; GFX9-LABEL: name: test_smulo_s24
; GFX9: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; GFX9: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; GFX9: [[SEXT_INREG:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY]], 24
; GFX9: [[SEXT_INREG1:%[0-9]+]]:_(s32) = G_SEXT_INREG [[COPY1]], 24
; GFX9: [[SMULH:%[0-9]+]]:_(s32) = G_SMULH [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[MUL:%[0-9]+]]:_(s32) = G_MUL [[SEXT_INREG]], [[SEXT_INREG1]]
; GFX9: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 31
; GFX9: [[ASHR:%[0-9]+]]:_(s32) = G_ASHR [[MUL]], [[C]](s32)
; GFX9: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[SMULH]](s32), [[ASHR]]
; GFX9: [[SEXT_INREG2:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
; GFX9: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[MUL]](s32), [[SEXT_INREG2]]
; GFX9: [[OR:%[0-9]+]]:_(s1) = G_OR [[ICMP]], [[ICMP1]]
; GFX9: [[SEXT_INREG3:%[0-9]+]]:_(s32) = G_SEXT_INREG [[MUL]], 24
; GFX9: [[SEXT:%[0-9]+]]:_(s32) = G_SEXT [[OR]](s1)
; GFX9: $vgpr0 = COPY [[SEXT_INREG3]](s32)
; GFX9: $vgpr1 = COPY [[SEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s24) = G_TRUNC %0
%3:_(s24) = G_TRUNC %1
%4:_(s24), %6:_(s1) = G_SMULO %2, %3
%5:_(s32) = G_SEXT %4
%7:_(s32) = G_SEXT %6
$vgpr0 = COPY %5
$vgpr1 = COPY %7
...