maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity
llvm-project/llvm/test/CodeGen/AMDGPU/GlobalISel/legalize-uaddo.mir

Ignoring revisions in .git-blame-ignore-revs. Click here to bypass and see the normal blame view.

362 lines
18 KiB
Plaintext
Raw Normal View History

AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
# 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
---
name: test_uaddo_s32
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_uaddo_s32
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[COPY]], [[COPY1]]
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[UADDO1]](s1)
; CHECK: $vgpr0 = COPY [[UADDO]](s32)
; CHECK: $vgpr1 = COPY [[ZEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s32), %3:_(s1) = G_UADDO %0, %1
%4:_(s32) = G_ZEXT %3
$vgpr0 = COPY %2
$vgpr1 = COPY %4
...
---
name: test_uaddo_s7
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_uaddo_s7
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 127
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[AND]], [[AND1]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[ADD]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[ADD]](s32), [[AND2]]
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[ADD]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
; CHECK: $vgpr0 = COPY [[AND3]](s32)
; CHECK: $vgpr1 = COPY [[ZEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s7) = G_TRUNC %0
%3:_(s7) = G_TRUNC %1
%4:_(s7), %5:_(s1) = G_UADDO %2, %3
%6:_(s32) = G_ZEXT %4
%7:_(s32) = G_ZEXT %5
$vgpr0 = COPY %6
$vgpr1 = COPY %7
...
---
name: test_uaddo_s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_uaddo_s16
; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $vgpr1
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[COPY]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[COPY1]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[AND]], [[AND1]]
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[ADD]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ne), [[ADD]](s32), [[AND2]]
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[ADD]](s32)
[GlobalISel] Enable CSE in the IRTranslator & legalizer for -O0 with constants only. Other opcodes shouldn't be CSE'd until we can be sure debug info quality won't be degraded. This change also improves the IRTranslator so that in most places, but not all, it creates constants using the MIRBuilder directly instead of first creating a new destination vreg and then creating a constant. By doing this, the buildConstant() method can just return the vreg of an existing G_CONSTANT instead of having to create a COPY from it. I measured a 0.2% improvement in compile time and a 0.9% improvement in code size at -O0 ARM64. Compile time: Program base cse diff test-suite...ark/tramp3d-v4/tramp3d-v4.test 9.04 9.12 0.8% test-suite...Mark/mafft/pairlocalalign.test 2.68 2.66 -0.7% test-suite...-typeset/consumer-typeset.test 5.53 5.51 -0.4% test-suite :: CTMark/lencod/lencod.test 5.30 5.28 -0.3% test-suite :: CTMark/Bullet/bullet.test 25.82 25.76 -0.2% test-suite...:: CTMark/ClamAV/clamscan.test 6.92 6.90 -0.2% test-suite...TMark/7zip/7zip-benchmark.test 34.24 34.17 -0.2% test-suite :: CTMark/SPASS/SPASS.test 6.25 6.24 -0.1% test-suite...:: CTMark/sqlite3/sqlite3.test 1.66 1.66 -0.1% test-suite :: CTMark/kimwitu++/kc.test 13.61 13.60 -0.0% Geomean difference -0.2% Code size: Program base cse diff test-suite...-typeset/consumer-typeset.test 1315632 1266480 -3.7% test-suite...:: CTMark/ClamAV/clamscan.test 1313892 1297508 -1.2% test-suite :: CTMark/lencod/lencod.test 1439504 1423112 -1.1% test-suite...TMark/7zip/7zip-benchmark.test 2936980 2904172 -1.1% test-suite :: CTMark/Bullet/bullet.test 3478276 3445460 -0.9% test-suite...ark/tramp3d-v4/tramp3d-v4.test 8082868 8033492 -0.6% test-suite :: CTMark/kimwitu++/kc.test 3870380 3853972 -0.4% test-suite :: CTMark/SPASS/SPASS.test 1434904 1434896 -0.0% test-suite...Mark/mafft/pairlocalalign.test 764528 764528 0.0% test-suite...:: CTMark/sqlite3/sqlite3.test 782092 782092 0.0% Geomean difference -0.9% Differential Revision: https://reviews.llvm.org/D60580 llvm-svn: 358369
2019-04-15 13:04:20 +08:00
; CHECK: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C]]
AMDGPU/GlobalISel: Widen small uaddo/usubo llvm-svn: 352294
2019-01-27 07:44:51 +08:00
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
; CHECK: $vgpr0 = COPY [[AND3]](s32)
; CHECK: $vgpr1 = COPY [[ZEXT]](s32)
%0:_(s32) = COPY $vgpr0
%1:_(s32) = COPY $vgpr1
%2:_(s16) = G_TRUNC %0
%3:_(s16) = G_TRUNC %1
%4:_(s16), %5:_(s1) = G_UADDO %2, %3
%6:_(s32) = G_ZEXT %4
%7:_(s32) = G_ZEXT %5
$vgpr0 = COPY %6
$vgpr1 = COPY %7
...
AMDGPU/GlobalISel: Lower 64-bit uaddo/usubo Summary: Add more test cases for signed and unsigned add/sub with overflow. Reviewers: arsenm, rampitec, kerbowa Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, rovka, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D75051
2020-01-24 17:02:47 +08:00
---
name: test_uaddo_s64
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: test_uaddo_s64
; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $vgpr2_vgpr3
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](s64)
; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](s64)
; CHECK: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[UV]], [[UV2]]
; CHECK: [[UADDE:%[0-9]+]]:_(s32), [[UADDE1:%[0-9]+]]:_(s1) = G_UADDE [[UV1]], [[UV3]], [[UADDO1]]
; CHECK: [[MV:%[0-9]+]]:_(s64) = G_MERGE_VALUES [[UADDO]](s32), [[UADDE]](s32)
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[MV]](s64), [[COPY1]]
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ICMP]](s1)
; CHECK: $vgpr0_vgpr1 = COPY [[MV]](s64)
; CHECK: $vgpr2 = COPY [[ZEXT]](s32)
%0:_(s64) = COPY $vgpr0_vgpr1
%1:_(s64) = COPY $vgpr2_vgpr3
%2:_(s64), %3:_(s1) = G_UADDO %0, %1
%4:_(s32) = G_ZEXT %3
$vgpr0_vgpr1 = COPY %2
$vgpr2 = COPY %4
...
---
name: test_uaddo_v2s16
body: |
bb.0:
liveins: $vgpr0, $vgpr1
; CHECK-LABEL: name: test_uaddo_v2s16
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr0
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s16>) = COPY $vgpr1
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[COPY]](<2 x s16>)
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
; CHECK: [[ADD:%[0-9]+]]:_(s16) = G_ADD [[TRUNC]], [[TRUNC2]]
; CHECK: [[ADD1:%[0-9]+]]:_(s16) = G_ADD [[TRUNC1]], [[TRUNC3]]
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ADD]](s16)
; CHECK: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ADD1]](s16)
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
; CHECK: [[BITCAST2:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[COPY1]](<2 x s16>)
; CHECK: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
; CHECK: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
; CHECK: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD]](s16), [[TRUNC4]]
; CHECK: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD1]](s16), [[TRUNC5]]
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C1]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C1]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32)
; CHECK: $vgpr0 = COPY [[BITCAST2]](<2 x s16>)
; CHECK: $vgpr1_vgpr2 = COPY [[BUILD_VECTOR]](<2 x s32>)
%0:_(<2 x s16>) = COPY $vgpr0
%1:_(<2 x s16>) = COPY $vgpr1
%2:_(<2 x s16>), %3:_(<2 x s1>) = G_UADDO %0, %1
%4:_(<2 x s32>) = G_ZEXT %3
$vgpr0 = COPY %2
$vgpr1_vgpr2 = COPY %4
...
---
name: test_uaddo_v3s16
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: test_uaddo_v3s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr1_vgpr2
; CHECK: [[EXTRACT:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[COPY]](<4 x s16>), 0
; CHECK: [[EXTRACT1:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[COPY]](<4 x s16>), 0
; CHECK: [[DEF:%[0-9]+]]:_(<4 x s16>) = G_IMPLICIT_DEF
; CHECK: [[INSERT:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF]], [[EXTRACT]](<3 x s16>), 0
; CHECK: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT]](<4 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: [[INSERT1:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF]], [[EXTRACT1]](<3 x s16>), 0
; CHECK: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT1]](<4 x s16>)
; CHECK: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
; CHECK: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
; CHECK: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
; CHECK: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
; CHECK: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
; CHECK: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
; CHECK: [[ADD:%[0-9]+]]:_(s16) = G_ADD [[TRUNC]], [[TRUNC3]]
; CHECK: [[ADD1:%[0-9]+]]:_(s16) = G_ADD [[TRUNC1]], [[TRUNC4]]
; CHECK: [[ADD2:%[0-9]+]]:_(s16) = G_ADD [[TRUNC2]], [[TRUNC5]]
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ADD]](s16)
; CHECK: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ADD1]](s16)
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
; CHECK: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[ADD2]](s16)
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 0
; CHECK: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[C1]], [[C]](s32)
; CHECK: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL1]]
; CHECK: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
GlobalISel: Merge FewerElements for G_BUILD_VECTOR/G_CONCAT_VECTORS This switches from using G_EXTRACT in odd cases to widen with undef and unmerge.
2020-08-04 06:37:29 +08:00
; CHECK: [[DEF1:%[0-9]+]]:_(<2 x s16>) = G_IMPLICIT_DEF
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<6 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>), [[DEF1]](<2 x s16>)
; CHECK: [[EXTRACT2:%[0-9]+]]:_(<3 x s16>) = G_EXTRACT [[CONCAT_VECTORS]](<6 x s16>), 0
AMDGPU/GlobalISel: Lower 64-bit uaddo/usubo Summary: Add more test cases for signed and unsigned add/sub with overflow. Reviewers: arsenm, rampitec, kerbowa Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, rovka, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D75051
2020-01-24 17:02:47 +08:00
; CHECK: [[INSERT2:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF]], [[EXTRACT1]](<3 x s16>), 0
; CHECK: [[UV4:%[0-9]+]]:_(<2 x s16>), [[UV5:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[INSERT2]](<4 x s16>)
; CHECK: [[BITCAST6:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
; CHECK: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST6]], [[C]](s32)
; CHECK: [[BITCAST7:%[0-9]+]]:_(s32) = G_BITCAST [[UV5]](<2 x s16>)
; CHECK: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST7]], [[C]](s32)
; CHECK: [[C2:%[0-9]+]]:_(s32) = G_CONSTANT i32 65535
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[BITCAST6]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C2]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[LSHR4]](s32)
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C2]]
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[BITCAST7]](s32)
; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C2]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<3 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32), [[AND2]](s32)
; CHECK: [[INSERT3:%[0-9]+]]:_(<4 x s16>) = G_INSERT [[DEF]], [[EXTRACT2]](<3 x s16>), 0
GlobalISel: Merge FewerElements for G_BUILD_VECTOR/G_CONCAT_VECTORS This switches from using G_EXTRACT in odd cases to widen with undef and unmerge.
2020-08-04 06:37:29 +08:00
; CHECK: [[DEF2:%[0-9]+]]:_(<4 x s32>) = G_IMPLICIT_DEF
; CHECK: [[INSERT4:%[0-9]+]]:_(<4 x s32>) = G_INSERT [[DEF2]], [[BUILD_VECTOR]](<3 x s32>), 0
AMDGPU/GlobalISel: Lower 64-bit uaddo/usubo Summary: Add more test cases for signed and unsigned add/sub with overflow. Reviewers: arsenm, rampitec, kerbowa Subscribers: kzhuravl, jvesely, wdng, nhaehnle, yaxunl, rovka, dstuttard, tpr, t-tye, hiraditya, llvm-commits Tags: #llvm Differential Revision: https://reviews.llvm.org/D75051
2020-01-24 17:02:47 +08:00
; CHECK: $vgpr0_vgpr1 = COPY [[INSERT3]](<4 x s16>)
; CHECK: $vgpr2_vgpr3_vgpr4_vgpr5 = COPY [[INSERT4]](<4 x s32>)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = COPY $vgpr1_vgpr2
%2:_(<3 x s16>) = G_EXTRACT %0(<4 x s16>), 0
%3:_(<3 x s16>) = G_EXTRACT %0(<4 x s16>), 0
%4:_(<3 x s16>), %5:_(<3 x s1>) = G_UADDO %2, %3
%6:_(<3 x s32>) = G_ZEXT %3
%7:_(<4 x s16>) = G_IMPLICIT_DEF
%8:_(<4 x s16>) = G_INSERT %7, %4(<3 x s16>), 0
%9:_(<4 x s32>) = G_IMPLICIT_DEF
%10:_(<4 x s32>) = G_INSERT %9, %6(<3 x s32>), 0
$vgpr0_vgpr1 = COPY %8
$vgpr2_vgpr3_vgpr4_vgpr5 = COPY %10
...
---
name: test_uaddo_v4s16
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: test_uaddo_v4s16
; CHECK: [[COPY:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<4 x s16>) = COPY $vgpr1_vgpr2
; CHECK: [[UV:%[0-9]+]]:_(<2 x s16>), [[UV1:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY]](<4 x s16>)
; CHECK: [[BITCAST:%[0-9]+]]:_(s32) = G_BITCAST [[UV]](<2 x s16>)
; CHECK: [[TRUNC:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST]](s32)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 16
; CHECK: [[LSHR:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST]], [[C]](s32)
; CHECK: [[TRUNC1:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR]](s32)
; CHECK: [[BITCAST1:%[0-9]+]]:_(s32) = G_BITCAST [[UV1]](<2 x s16>)
; CHECK: [[TRUNC2:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST1]](s32)
; CHECK: [[LSHR1:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST1]], [[C]](s32)
; CHECK: [[TRUNC3:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR1]](s32)
; CHECK: [[UV2:%[0-9]+]]:_(<2 x s16>), [[UV3:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
; CHECK: [[BITCAST2:%[0-9]+]]:_(s32) = G_BITCAST [[UV2]](<2 x s16>)
; CHECK: [[TRUNC4:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST2]](s32)
; CHECK: [[LSHR2:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST2]], [[C]](s32)
; CHECK: [[TRUNC5:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR2]](s32)
; CHECK: [[BITCAST3:%[0-9]+]]:_(s32) = G_BITCAST [[UV3]](<2 x s16>)
; CHECK: [[TRUNC6:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST3]](s32)
; CHECK: [[LSHR3:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST3]], [[C]](s32)
; CHECK: [[TRUNC7:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR3]](s32)
; CHECK: [[ADD:%[0-9]+]]:_(s16) = G_ADD [[TRUNC]], [[TRUNC4]]
; CHECK: [[ADD1:%[0-9]+]]:_(s16) = G_ADD [[TRUNC1]], [[TRUNC5]]
; CHECK: [[ADD2:%[0-9]+]]:_(s16) = G_ADD [[TRUNC2]], [[TRUNC6]]
; CHECK: [[ADD3:%[0-9]+]]:_(s16) = G_ADD [[TRUNC3]], [[TRUNC7]]
; CHECK: [[ZEXT:%[0-9]+]]:_(s32) = G_ZEXT [[ADD]](s16)
; CHECK: [[ZEXT1:%[0-9]+]]:_(s32) = G_ZEXT [[ADD1]](s16)
; CHECK: [[SHL:%[0-9]+]]:_(s32) = G_SHL [[ZEXT1]], [[C]](s32)
; CHECK: [[OR:%[0-9]+]]:_(s32) = G_OR [[ZEXT]], [[SHL]]
; CHECK: [[BITCAST4:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR]](s32)
; CHECK: [[ZEXT2:%[0-9]+]]:_(s32) = G_ZEXT [[ADD2]](s16)
; CHECK: [[ZEXT3:%[0-9]+]]:_(s32) = G_ZEXT [[ADD3]](s16)
; CHECK: [[SHL1:%[0-9]+]]:_(s32) = G_SHL [[ZEXT3]], [[C]](s32)
; CHECK: [[OR1:%[0-9]+]]:_(s32) = G_OR [[ZEXT2]], [[SHL1]]
; CHECK: [[BITCAST5:%[0-9]+]]:_(<2 x s16>) = G_BITCAST [[OR1]](s32)
; CHECK: [[CONCAT_VECTORS:%[0-9]+]]:_(<4 x s16>) = G_CONCAT_VECTORS [[BITCAST4]](<2 x s16>), [[BITCAST5]](<2 x s16>)
; CHECK: [[UV4:%[0-9]+]]:_(<2 x s16>), [[UV5:%[0-9]+]]:_(<2 x s16>) = G_UNMERGE_VALUES [[COPY1]](<4 x s16>)
; CHECK: [[BITCAST6:%[0-9]+]]:_(s32) = G_BITCAST [[UV4]](<2 x s16>)
; CHECK: [[TRUNC8:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST6]](s32)
; CHECK: [[LSHR4:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST6]], [[C]](s32)
; CHECK: [[TRUNC9:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR4]](s32)
; CHECK: [[BITCAST7:%[0-9]+]]:_(s32) = G_BITCAST [[UV5]](<2 x s16>)
; CHECK: [[TRUNC10:%[0-9]+]]:_(s16) = G_TRUNC [[BITCAST7]](s32)
; CHECK: [[LSHR5:%[0-9]+]]:_(s32) = G_LSHR [[BITCAST7]], [[C]](s32)
; CHECK: [[TRUNC11:%[0-9]+]]:_(s16) = G_TRUNC [[LSHR5]](s32)
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD]](s16), [[TRUNC8]]
; CHECK: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD1]](s16), [[TRUNC9]]
; CHECK: [[ICMP2:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD2]](s16), [[TRUNC10]]
; CHECK: [[ICMP3:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD3]](s16), [[TRUNC11]]
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; CHECK: [[ANYEXT2:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP2]](s1)
; CHECK: [[ANYEXT3:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP3]](s1)
; CHECK: [[C1:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C1]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C1]]
; CHECK: [[COPY4:%[0-9]+]]:_(s32) = COPY [[ANYEXT2]](s32)
; CHECK: [[AND2:%[0-9]+]]:_(s32) = G_AND [[COPY4]], [[C1]]
; CHECK: [[COPY5:%[0-9]+]]:_(s32) = COPY [[ANYEXT3]](s32)
; CHECK: [[AND3:%[0-9]+]]:_(s32) = G_AND [[COPY5]], [[C1]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<4 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32), [[AND2]](s32), [[AND3]](s32)
; CHECK: $vgpr0_vgpr1 = COPY [[CONCAT_VECTORS]](<4 x s16>)
; CHECK: $vgpr2_vgpr3_vgpr4_vgpr5 = COPY [[BUILD_VECTOR]](<4 x s32>)
%0:_(<4 x s16>) = COPY $vgpr0_vgpr1
%1:_(<4 x s16>) = COPY $vgpr1_vgpr2
%2:_(<4 x s16>), %3:_(<4 x s1>) = G_UADDO %0, %1
%4:_(<4 x s32>) = G_ZEXT %3
$vgpr0_vgpr1 = COPY %2
$vgpr2_vgpr3_vgpr4_vgpr5 = COPY %4
...
---
name: test_uaddo_v2s32
body: |
bb.0:
liveins: $vgpr0_vgpr1, $vgpr2_vgpr3
; CHECK-LABEL: name: test_uaddo_v2s32
; CHECK: [[COPY:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr0_vgpr1
; CHECK: [[COPY1:%[0-9]+]]:_(<2 x s32>) = COPY $vgpr2_vgpr3
; CHECK: [[UV:%[0-9]+]]:_(s32), [[UV1:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY]](<2 x s32>)
; CHECK: [[UV2:%[0-9]+]]:_(s32), [[UV3:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[ADD:%[0-9]+]]:_(s32) = G_ADD [[UV]], [[UV2]]
; CHECK: [[ADD1:%[0-9]+]]:_(s32) = G_ADD [[UV1]], [[UV3]]
; CHECK: [[BUILD_VECTOR:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[ADD]](s32), [[ADD1]](s32)
; CHECK: [[UV4:%[0-9]+]]:_(s32), [[UV5:%[0-9]+]]:_(s32) = G_UNMERGE_VALUES [[COPY1]](<2 x s32>)
; CHECK: [[ICMP:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD]](s32), [[UV4]]
; CHECK: [[ICMP1:%[0-9]+]]:_(s1) = G_ICMP intpred(ult), [[ADD1]](s32), [[UV5]]
; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP]](s1)
; CHECK: [[ANYEXT1:%[0-9]+]]:_(s32) = G_ANYEXT [[ICMP1]](s1)
; CHECK: [[C:%[0-9]+]]:_(s32) = G_CONSTANT i32 1
; CHECK: [[COPY2:%[0-9]+]]:_(s32) = COPY [[ANYEXT]](s32)
; CHECK: [[AND:%[0-9]+]]:_(s32) = G_AND [[COPY2]], [[C]]
; CHECK: [[COPY3:%[0-9]+]]:_(s32) = COPY [[ANYEXT1]](s32)
; CHECK: [[AND1:%[0-9]+]]:_(s32) = G_AND [[COPY3]], [[C]]
; CHECK: [[BUILD_VECTOR1:%[0-9]+]]:_(<2 x s32>) = G_BUILD_VECTOR [[AND]](s32), [[AND1]](s32)
; CHECK: $vgpr0_vgpr1 = COPY [[BUILD_VECTOR]](<2 x s32>)
; CHECK: $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_UADDO %0, %1
%4:_(<2 x s32>) = G_ZEXT %3
$vgpr0_vgpr1 = COPY %2
$vgpr2_vgpr3 = COPY %4
...