[llvm] bd64ad3 - Recommit "[AArch64][GlobalISel] Make G_USUBO legal and select it."
Amara Emerson via llvm-commits
llvm-commits at lists.llvm.org
Fri Jan 22 17:30:20 PST 2021
Author: Cassie Jones
Date: 2021-01-22T17:29:54-08:00
New Revision: bd64ad3fe17506933ac2971dcc900271d6ae5969
URL: https://github.com/llvm/llvm-project/commit/bd64ad3fe17506933ac2971dcc900271d6ae5969
DIFF: https://github.com/llvm/llvm-project/commit/bd64ad3fe17506933ac2971dcc900271d6ae5969.diff
LOG: Recommit "[AArch64][GlobalISel] Make G_USUBO legal and select it."
The expansion for wide subtractions includes G_USUBO.
Differential Revision: https://reviews.llvm.org/D95032
This was miscompiling on ubsan bots.
Added:
llvm/test/CodeGen/AArch64/GlobalISel/select-saddo.mir
llvm/test/CodeGen/AArch64/GlobalISel/select-ssubo.mir
llvm/test/CodeGen/AArch64/GlobalISel/select-usubo.mir
Modified:
llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
llvm/test/CodeGen/AArch64/GlobalISel/legalize-add.mir
llvm/test/CodeGen/AArch64/GlobalISel/legalize-sub.mir
llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
Removed:
################################################################################
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp b/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
index 9619bb43ae9c..5259f4f5a4d0 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64InstructionSelector.cpp
@@ -2745,7 +2745,8 @@ bool AArch64InstructionSelector::select(MachineInstr &I) {
}
case TargetOpcode::G_SADDO:
case TargetOpcode::G_UADDO:
- case TargetOpcode::G_SSUBO: {
+ case TargetOpcode::G_SSUBO:
+ case TargetOpcode::G_USUBO: {
// Emit the operation and get the correct condition code.
MachineIRBuilder MIRBuilder(I);
auto OpAndCC = emitOverflowOp(Opcode, I.getOperand(0).getReg(),
@@ -4376,6 +4377,8 @@ AArch64InstructionSelector::emitOverflowOp(unsigned Opcode, Register Dst,
return std::make_pair(emitADDS(Dst, LHS, RHS, MIRBuilder), AArch64CC::HS);
case TargetOpcode::G_SSUBO:
return std::make_pair(emitSUBS(Dst, LHS, RHS, MIRBuilder), AArch64CC::VS);
+ case TargetOpcode::G_USUBO:
+ return std::make_pair(emitSUBS(Dst, LHS, RHS, MIRBuilder), AArch64CC::LO);
}
}
diff --git a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
index cc7aada211bb..5a6c904e3f5d 100644
--- a/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
+++ b/llvm/lib/Target/AArch64/GISel/AArch64LegalizerInfo.cpp
@@ -165,7 +165,8 @@ AArch64LegalizerInfo::AArch64LegalizerInfo(const AArch64Subtarget &ST)
getActionDefinitionsBuilder({G_SMULH, G_UMULH}).legalFor({s32, s64});
- getActionDefinitionsBuilder({G_UADDE, G_USUBE, G_SADDO, G_SSUBO, G_UADDO})
+ getActionDefinitionsBuilder(
+ {G_UADDE, G_USUBE, G_SADDO, G_SSUBO, G_UADDO, G_USUBO})
.legalFor({{s32, s1}, {s64, s1}})
.minScalar(0, s32);
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-add.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-add.mir
index ab8510bf9d92..4f97d153d28b 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-add.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-add.mir
@@ -73,6 +73,44 @@ body: |
%5:_(s64) = G_ANYEXT %4(s8)
$x0 = COPY %5(s64)
+...
+---
+name: test_scalar_uaddo_32
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_uaddo_32
+ ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $w1
+ ; CHECK: [[UADDO:%[0-9]+]]:_(s32), [[UADDO1:%[0-9]+]]:_(s1) = G_UADDO [[COPY]], [[COPY1]]
+ ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[UADDO1]](s1)
+ ; CHECK: $w0 = COPY [[UADDO]](s32)
+ ; CHECK: $w1 = COPY [[ANYEXT]](s32)
+ %0:_(s32) = COPY $w0
+ %1:_(s32) = COPY $w1
+ %2:_(s32), %3:_(s1) = G_UADDO %0, %1
+ %4:_(s32) = G_ANYEXT %3
+ $w0 = COPY %2(s32)
+ $w1 = COPY %4(s32)
+
+...
+---
+name: test_scalar_saddo_32
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_saddo_32
+ ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $w1
+ ; CHECK: [[SADDO:%[0-9]+]]:_(s32), [[SADDO1:%[0-9]+]]:_(s1) = G_SADDO [[COPY]], [[COPY1]]
+ ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SADDO1]](s1)
+ ; CHECK: $w0 = COPY [[SADDO]](s32)
+ ; CHECK: $w1 = COPY [[ANYEXT]](s32)
+ %0:_(s32) = COPY $w0
+ %1:_(s32) = COPY $w1
+ %2:_(s32), %3:_(s1) = G_SADDO %0, %1
+ %4:_(s32) = G_ANYEXT %3
+ $w0 = COPY %2(s32)
+ $w1 = COPY %4(s32)
+
...
---
name: test_vector_add
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-sub.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-sub.mir
index 32796e0948cc..b372a32eb7fc 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalize-sub.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalize-sub.mir
@@ -1,6 +1,59 @@
# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
# RUN: llc -march=aarch64 -run-pass=legalizer %s -o - | FileCheck %s
---
+name: test_scalar_sub_big
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_sub_big
+ ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $x1
+ ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $x2
+ ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY $x3
+ ; CHECK: [[USUBO:%[0-9]+]]:_(s64), [[USUBO1:%[0-9]+]]:_(s1) = G_USUBO [[COPY]], [[COPY2]]
+ ; CHECK: [[USUBE:%[0-9]+]]:_(s64), [[USUBE1:%[0-9]+]]:_(s1) = G_USUBE [[COPY1]], [[COPY3]], [[USUBO1]]
+ ; CHECK: $x0 = COPY [[USUBO]](s64)
+ ; CHECK: $x1 = COPY [[USUBE]](s64)
+ %0:_(s64) = COPY $x0
+ %1:_(s64) = COPY $x1
+ %2:_(s64) = COPY $x2
+ %3:_(s64) = COPY $x3
+ %4:_(s128) = G_MERGE_VALUES %0(s64), %1(s64)
+ %5:_(s128) = G_MERGE_VALUES %2(s64), %3(s64)
+ %6:_(s128) = G_SUB %4, %5
+ %7:_(s64), %8:_(s64) = G_UNMERGE_VALUES %6(s128)
+ $x0 = COPY %7(s64)
+ $x1 = COPY %8(s64)
+
+...
+---
+name: test_scalar_sub_big_nonpow2
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_sub_big_nonpow2
+ ; CHECK: [[COPY:%[0-9]+]]:_(s64) = COPY $x0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s64) = COPY $x1
+ ; CHECK: [[COPY2:%[0-9]+]]:_(s64) = COPY $x2
+ ; CHECK: [[COPY3:%[0-9]+]]:_(s64) = COPY $x3
+ ; CHECK: [[USUBO:%[0-9]+]]:_(s64), [[USUBO1:%[0-9]+]]:_(s1) = G_USUBO [[COPY]], [[COPY1]]
+ ; CHECK: [[USUBE:%[0-9]+]]:_(s64), [[USUBE1:%[0-9]+]]:_(s1) = G_USUBE [[COPY1]], [[COPY2]], [[USUBO1]]
+ ; CHECK: [[USUBE2:%[0-9]+]]:_(s64), [[USUBE3:%[0-9]+]]:_(s1) = G_USUBE [[COPY2]], [[COPY3]], [[USUBE1]]
+ ; CHECK: $x0 = COPY [[USUBO]](s64)
+ ; CHECK: $x1 = COPY [[USUBE]](s64)
+ ; CHECK: $x2 = COPY [[USUBE2]](s64)
+ %0:_(s64) = COPY $x0
+ %1:_(s64) = COPY $x1
+ %2:_(s64) = COPY $x2
+ %3:_(s64) = COPY $x3
+ %4:_(s192) = G_MERGE_VALUES %0(s64), %1(s64), %2(s64)
+ %5:_(s192) = G_MERGE_VALUES %1(s64), %2(s64), %3(s64)
+ %6:_(s192) = G_SUB %4, %5
+ %7:_(s64), %8:_(s64), %9:_(s64) = G_UNMERGE_VALUES %6(s192)
+ $x0 = COPY %7(s64)
+ $x1 = COPY %8(s64)
+ $x2 = COPY %9(s64)
+
+...
+---
name: test_scalar_sub_small
body: |
bb.0.entry:
@@ -21,3 +74,41 @@ body: |
$x0 = COPY %5(s64)
...
+---
+name: test_scalar_usubo_32
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_usubo_32
+ ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $w1
+ ; CHECK: [[USUBO:%[0-9]+]]:_(s32), [[USUBO1:%[0-9]+]]:_(s1) = G_USUBO [[COPY]], [[COPY1]]
+ ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[USUBO1]](s1)
+ ; CHECK: $w0 = COPY [[USUBO]](s32)
+ ; CHECK: $w1 = COPY [[ANYEXT]](s32)
+ %0:_(s32) = COPY $w0
+ %1:_(s32) = COPY $w1
+ %2:_(s32), %3:_(s1) = G_USUBO %0, %1
+ %4:_(s32) = G_ANYEXT %3
+ $w0 = COPY %2(s32)
+ $w1 = COPY %4(s32)
+
+...
+---
+name: test_scalar_ssubo_32
+body: |
+ bb.0.entry:
+ ; CHECK-LABEL: name: test_scalar_ssubo_32
+ ; CHECK: [[COPY:%[0-9]+]]:_(s32) = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:_(s32) = COPY $w1
+ ; CHECK: [[SSUBO:%[0-9]+]]:_(s32), [[SSUBO1:%[0-9]+]]:_(s1) = G_SSUBO [[COPY]], [[COPY1]]
+ ; CHECK: [[ANYEXT:%[0-9]+]]:_(s32) = G_ANYEXT [[SSUBO1]](s1)
+ ; CHECK: $w0 = COPY [[SSUBO]](s32)
+ ; CHECK: $w1 = COPY [[ANYEXT]](s32)
+ %0:_(s32) = COPY $w0
+ %1:_(s32) = COPY $w1
+ %2:_(s32), %3:_(s1) = G_SSUBO %0, %1
+ %4:_(s32) = G_ANYEXT %3
+ $w0 = COPY %2(s32)
+ $w1 = COPY %4(s32)
+
+...
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir b/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
index a937e331757e..6c1af116e759 100644
--- a/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/legalizer-info-validation.mir
@@ -300,8 +300,9 @@
# DEBUG-NEXT: .. the first uncovered type index: 2, OK
# DEBUG-NEXT: .. the first uncovered imm index: 0, OK
# DEBUG-NEXT: G_USUBO (opcode {{[0-9]+}}): 2 type indices, 0 imm indices
-# DEBUG-NEXT: .. type index coverage check SKIPPED: no rules defined
-# DEBUG-NEXT: .. imm index coverage check SKIPPED: no rules defined
+# DEBUG-NEXT: .. opcode {{[0-9]+}} is aliased to {{[0-9]+}}
+# DEBUG-NEXT: .. the first uncovered type index: 2, OK
+# DEBUG-NEXT: .. the first uncovered imm index: 0, OK
# DEBUG-NEXT: G_USUBE (opcode {{[0-9]+}}): 2 type indices, 0 imm indices
# DEBUG-NEXT: .. opcode {{[0-9]+}} is aliased to {{[0-9]+}}
# DEBUG-NEXT: .. the first uncovered type index: 2, OK
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/select-saddo.mir b/llvm/test/CodeGen/AArch64/GlobalISel/select-saddo.mir
new file mode 100644
index 000000000000..39f2dc45525a
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/select-saddo.mir
@@ -0,0 +1,166 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -verify-machineinstrs -mtriple aarch64-unknown-uknown -global-isel -run-pass=instruction-select %s -o - | FileCheck %s
+
+...
+---
+name: saddo_s32
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+
+ ; CHECK-LABEL: name: saddo_s32
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr32 = COPY $w1
+ ; CHECK: [[ADDSWrr:%[0-9]+]]:gpr32 = ADDSWrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s32) = COPY $w0
+ %1:gpr(s32) = COPY $w1
+ %3:gpr(s32), %4:gpr(s1) = G_SADDO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: saddo_s64
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $x0, $x1, $x2
+
+ ; CHECK-LABEL: name: saddo_s64
+ ; CHECK: liveins: $x0, $x1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr64 = COPY $x1
+ ; CHECK: [[ADDSXrr:%[0-9]+]]:gpr64 = ADDSXrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s64) = COPY $x0
+ %1:gpr(s64) = COPY $x1
+ %3:gpr(s64), %4:gpr(s1) = G_SADDO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: saddo_s32_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWri when we can fold in a constant.
+ ;
+ ; CHECK-LABEL: name: saddo_s32_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = ADDSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %add:gpr(s32), %overflow:gpr(s1) = G_SADDO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: saddo_s32_shifted
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWrs when we can fold in a shift.
+ ;
+ ; CHECK-LABEL: name: saddo_s32_shifted
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy1:gpr32 = COPY $w0
+ ; CHECK: %copy2:gpr32 = COPY $w1
+ ; CHECK: %add:gpr32 = ADDSWrs %copy1, %copy2, 16, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy1:gpr(s32) = COPY $w0
+ %copy2:gpr(s32) = COPY $w1
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %shift:gpr(s32) = G_SHL %copy2(s32), %constant(s32)
+ %add:gpr(s32), %overflow:gpr(s1) = G_SADDO %copy1, %shift
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: saddo_s32_neg_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get SUBSWri when we can fold in a negative constant.
+ ;
+ ; CHECK-LABEL: name: saddo_s32_neg_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = SUBSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 -16
+ %add:gpr(s32), %overflow:gpr(s1) = G_SADDO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: saddo_arith_extended
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $x0
+ ; Check that we get ADDSXrx.
+ ; CHECK-LABEL: name: saddo_arith_extended
+ ; CHECK: liveins: $w0, $x0
+ ; CHECK: %reg0:gpr64sp = COPY $x0
+ ; CHECK: %reg1:gpr32 = COPY $w0
+ ; CHECK: %add:gpr64 = ADDSXrx %reg0, %reg1, 18, implicit-def $nzcv
+ ; CHECK: %flags:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $x0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $x0
+ %reg0:gpr(s64) = COPY $x0
+ %reg1:gpr(s32) = COPY $w0
+ %ext:gpr(s64) = G_ZEXT %reg1(s32)
+ %cst:gpr(s64) = G_CONSTANT i64 2
+ %shift:gpr(s64) = G_SHL %ext, %cst(s64)
+ %add:gpr(s64), %flags:gpr(s1) = G_SADDO %reg0, %shift
+ $x0 = COPY %add(s64)
+ RET_ReallyLR implicit $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/select-ssubo.mir b/llvm/test/CodeGen/AArch64/GlobalISel/select-ssubo.mir
new file mode 100644
index 000000000000..639776a7ecbd
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/select-ssubo.mir
@@ -0,0 +1,166 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -verify-machineinstrs -mtriple aarch64-unknown-uknown -global-isel -run-pass=instruction-select %s -o - | FileCheck %s
+
+...
+---
+name: ssubo_s32
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+
+ ; CHECK-LABEL: name: ssubo_s32
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr32 = COPY $w1
+ ; CHECK: [[SUBSWrr:%[0-9]+]]:gpr32 = SUBSWrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s32) = COPY $w0
+ %1:gpr(s32) = COPY $w1
+ %3:gpr(s32), %4:gpr(s1) = G_SSUBO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: ssubo_s64
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $x0, $x1, $x2
+
+ ; CHECK-LABEL: name: ssubo_s64
+ ; CHECK: liveins: $x0, $x1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr64 = COPY $x1
+ ; CHECK: [[SUBSXrr:%[0-9]+]]:gpr64 = SUBSXrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s64) = COPY $x0
+ %1:gpr(s64) = COPY $x1
+ %3:gpr(s64), %4:gpr(s1) = G_SSUBO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: ssubo_s32_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWri when we can fold in a constant.
+ ;
+ ; CHECK-LABEL: name: ssubo_s32_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = SUBSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %add:gpr(s32), %overflow:gpr(s1) = G_SSUBO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: ssubo_s32_shifted
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWrs when we can fold in a shift.
+ ;
+ ; CHECK-LABEL: name: ssubo_s32_shifted
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy1:gpr32 = COPY $w0
+ ; CHECK: %copy2:gpr32 = COPY $w1
+ ; CHECK: %add:gpr32 = SUBSWrs %copy1, %copy2, 16, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy1:gpr(s32) = COPY $w0
+ %copy2:gpr(s32) = COPY $w1
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %shift:gpr(s32) = G_SHL %copy2(s32), %constant(s32)
+ %add:gpr(s32), %overflow:gpr(s1) = G_SSUBO %copy1, %shift
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: ssubo_s32_neg_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get SUBSWri when we can fold in a negative constant.
+ ;
+ ; CHECK-LABEL: name: ssubo_s32_neg_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = ADDSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 -16
+ %add:gpr(s32), %overflow:gpr(s1) = G_SSUBO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: ssubo_arith_extended
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $x0
+ ; Check that we get ADDSXrx.
+ ; CHECK-LABEL: name: ssubo_arith_extended
+ ; CHECK: liveins: $w0, $x0
+ ; CHECK: %reg0:gpr64sp = COPY $x0
+ ; CHECK: %reg1:gpr32 = COPY $w0
+ ; CHECK: %add:gpr64 = SUBSXrx %reg0, %reg1, 18, implicit-def $nzcv
+ ; CHECK: %flags:gpr32 = CSINCWr $wzr, $wzr, 7, implicit $nzcv
+ ; CHECK: $x0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $x0
+ %reg0:gpr(s64) = COPY $x0
+ %reg1:gpr(s32) = COPY $w0
+ %ext:gpr(s64) = G_ZEXT %reg1(s32)
+ %cst:gpr(s64) = G_CONSTANT i64 2
+ %shift:gpr(s64) = G_SHL %ext, %cst(s64)
+ %add:gpr(s64), %flags:gpr(s1) = G_SSUBO %reg0, %shift
+ $x0 = COPY %add(s64)
+ RET_ReallyLR implicit $x0
diff --git a/llvm/test/CodeGen/AArch64/GlobalISel/select-usubo.mir b/llvm/test/CodeGen/AArch64/GlobalISel/select-usubo.mir
new file mode 100644
index 000000000000..2a23ffe816f6
--- /dev/null
+++ b/llvm/test/CodeGen/AArch64/GlobalISel/select-usubo.mir
@@ -0,0 +1,166 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py
+# RUN: llc -verify-machineinstrs -mtriple aarch64-unknown-uknown -global-isel -run-pass=instruction-select %s -o - | FileCheck %s
+
+...
+---
+name: usubo_s32
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+
+ ; CHECK-LABEL: name: usubo_s32
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr32 = COPY $w0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr32 = COPY $w1
+ ; CHECK: [[SUBSWrr:%[0-9]+]]:gpr32 = SUBSWrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s32) = COPY $w0
+ %1:gpr(s32) = COPY $w1
+ %3:gpr(s32), %4:gpr(s1) = G_USUBO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: usubo_s64
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $x0, $x1, $x2
+
+ ; CHECK-LABEL: name: usubo_s64
+ ; CHECK: liveins: $x0, $x1, $x2
+ ; CHECK: [[COPY:%[0-9]+]]:gpr64 = COPY $x0
+ ; CHECK: [[COPY1:%[0-9]+]]:gpr64 = COPY $x1
+ ; CHECK: [[SUBSXrr:%[0-9]+]]:gpr64 = SUBSXrr [[COPY]], [[COPY1]], implicit-def $nzcv
+ ; CHECK: [[CSINCWr:%[0-9]+]]:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: [[UBFMWri:%[0-9]+]]:gpr32 = UBFMWri [[CSINCWr]], 0, 0
+ ; CHECK: [[UBFMWri1:%[0-9]+]]:gpr32 = UBFMWri [[UBFMWri]], 0, 7
+ ; CHECK: $w0 = COPY [[UBFMWri1]]
+ ; CHECK: RET_ReallyLR implicit $w0
+ %0:gpr(s64) = COPY $x0
+ %1:gpr(s64) = COPY $x1
+ %3:gpr(s64), %4:gpr(s1) = G_USUBO %0, %1
+ %5:gpr(s8) = G_ZEXT %4(s1)
+ %6:gpr(s32) = G_ZEXT %5(s8)
+ $w0 = COPY %6(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: usubo_s32_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWri when we can fold in a constant.
+ ;
+ ; CHECK-LABEL: name: usubo_s32_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = SUBSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %add:gpr(s32), %overflow:gpr(s1) = G_USUBO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: usubo_s32_shifted
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get ADDSWrs when we can fold in a shift.
+ ;
+ ; CHECK-LABEL: name: usubo_s32_shifted
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy1:gpr32 = COPY $w0
+ ; CHECK: %copy2:gpr32 = COPY $w1
+ ; CHECK: %add:gpr32 = SUBSWrs %copy1, %copy2, 16, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy1:gpr(s32) = COPY $w0
+ %copy2:gpr(s32) = COPY $w1
+ %constant:gpr(s32) = G_CONSTANT i32 16
+ %shift:gpr(s32) = G_SHL %copy2(s32), %constant(s32)
+ %add:gpr(s32), %overflow:gpr(s1) = G_USUBO %copy1, %shift
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: usubo_s32_neg_imm
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $w1, $x2
+ ; Check that we get SUBSWri when we can fold in a negative constant.
+ ;
+ ; CHECK-LABEL: name: usubo_s32_neg_imm
+ ; CHECK: liveins: $w0, $w1, $x2
+ ; CHECK: %copy:gpr32sp = COPY $w0
+ ; CHECK: %add:gpr32 = ADDSWri %copy, 16, 0, implicit-def $nzcv
+ ; CHECK: %overflow:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: $w0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $w0
+ %copy:gpr(s32) = COPY $w0
+ %constant:gpr(s32) = G_CONSTANT i32 -16
+ %add:gpr(s32), %overflow:gpr(s1) = G_USUBO %copy, %constant
+ $w0 = COPY %add(s32)
+ RET_ReallyLR implicit $w0
+
+...
+---
+name: usubo_arith_extended
+alignment: 4
+legalized: true
+regBankSelected: true
+tracksRegLiveness: true
+body: |
+ bb.1.entry:
+ liveins: $w0, $x0
+ ; Check that we get ADDSXrx.
+ ; CHECK-LABEL: name: usubo_arith_extended
+ ; CHECK: liveins: $w0, $x0
+ ; CHECK: %reg0:gpr64sp = COPY $x0
+ ; CHECK: %reg1:gpr32 = COPY $w0
+ ; CHECK: %add:gpr64 = SUBSXrx %reg0, %reg1, 18, implicit-def $nzcv
+ ; CHECK: %flags:gpr32 = CSINCWr $wzr, $wzr, 2, implicit $nzcv
+ ; CHECK: $x0 = COPY %add
+ ; CHECK: RET_ReallyLR implicit $x0
+ %reg0:gpr(s64) = COPY $x0
+ %reg1:gpr(s32) = COPY $w0
+ %ext:gpr(s64) = G_ZEXT %reg1(s32)
+ %cst:gpr(s64) = G_CONSTANT i64 2
+ %shift:gpr(s64) = G_SHL %ext, %cst(s64)
+ %add:gpr(s64), %flags:gpr(s1) = G_USUBO %reg0, %shift
+ $x0 = COPY %add(s64)
+ RET_ReallyLR implicit $x0
More information about the llvm-commits
mailing list