diff --git a/llvm/lib/CodeGen/MachineSink.cpp b/llvm/lib/CodeGen/MachineSink.cpp --- a/llvm/lib/CodeGen/MachineSink.cpp +++ b/llvm/lib/CodeGen/MachineSink.cpp @@ -1289,6 +1289,12 @@ SinkBlock->splice(SinkBlock->SkipPHIsAndLabels(SinkBlock->begin()), Preheader, I); + // Conservatively clear any kill flags on uses of sunk instruction + for (MachineOperand &MO : I.operands()) { + if (MO.isReg() && MO.readsReg()) + RegsToClearKillFlags.insert(MO.getReg()); + } + // The instruction is moved from its basic block, so do not retain the // debug information. assert(!I.isDebugInstr() && "Should not sink debug inst"); diff --git a/llvm/test/CodeGen/SystemZ/machinelicm-sunk-kill-flags.mir b/llvm/test/CodeGen/SystemZ/machinelicm-sunk-kill-flags.mir new file mode 100644 --- /dev/null +++ b/llvm/test/CodeGen/SystemZ/machinelicm-sunk-kill-flags.mir @@ -0,0 +1,75 @@ +# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py +# RUN: llc -mtriple=s390x-linux-gnu -sink-insts-to-avoid-spills -verify-machineinstrs -run-pass=machine-sink -o - %s | FileCheck %s + +# Test kill flags are cleared after sinking operations into cycle during MachineLICM. + +--- | + target datalayout = "E-m:e-i1:8:16-i8:8:16-i64:64-f128:64-a:8:16-n32:64" + target triple = "s390x-unknown-linux-gnu" + + %0 = type <{ i32, [3 x i8] }> + + @b = external dso_local global [1 x %0], align 2 + + define dso_local void @c() local_unnamed_addr { + ret void + } + +... +--- +name: c +tracksRegLiveness: true +body: | + ; CHECK-LABEL: name: c + ; CHECK: bb.0: + ; CHECK-NEXT: successors: %bb.1(0x80000000) + ; CHECK-NEXT: {{ $}} + ; CHECK-NEXT: [[LARL:%[0-9]+]]:addr64bit = LARL @b + ; CHECK-NEXT: {{ $}} + ; CHECK-NEXT: bb.1: + ; CHECK-NEXT: successors: %bb.1(0x80000000) + ; CHECK-NEXT: {{ $}} + ; CHECK-NEXT: [[LA:%[0-9]+]]:gr64bit = LA [[LARL]], 49, $noreg + ; CHECK-NEXT: [[LGHI:%[0-9]+]]:gr64bit = LGHI 7 + ; CHECK-NEXT: [[DEF:%[0-9]+]]:gr64bit = IMPLICIT_DEF + ; CHECK-NEXT: [[DEF1:%[0-9]+]]:gr64bit = IMPLICIT_DEF + ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0 + ; CHECK-NEXT: $r2d = COPY [[DEF]] + ; CHECK-NEXT: $r3d = COPY [[LA]] + ; CHECK-NEXT: $r4d = COPY [[LGHI]] + ; CHECK-NEXT: CallBRASL &memcpy, $r2d, $r3d, $r4d, csr_systemz_elf, implicit-def dead $r14d, implicit-def dead $cc, implicit $fpc, implicit-def $r2d + ; CHECK-NEXT: ADJCALLSTACKUP 0, 0 + ; CHECK-NEXT: ADJCALLSTACKDOWN 0, 0 + ; CHECK-NEXT: $r2d = COPY [[DEF1]] + ; CHECK-NEXT: $r3d = COPY [[LA]] + ; CHECK-NEXT: $r4d = COPY [[LGHI]] + ; CHECK-NEXT: CallBRASL &memcpy, $r2d, $r3d, $r4d, csr_systemz_elf, implicit-def dead $r14d, implicit-def dead $cc, implicit $fpc, implicit-def $r2d + ; CHECK-NEXT: ADJCALLSTACKUP 0, 0 + ; CHECK-NEXT: J %bb.1 + bb.0: + successors: %bb.1(0x80000000) + + %1:addr64bit = LARL @b + %0:gr64bit = LA killed %1, 49, $noreg + %2:gr64bit = LGHI 7 + %3:gr64bit = IMPLICIT_DEF + %5:gr64bit = IMPLICIT_DEF + + bb.1: + successors: %bb.1(0x80000000) + + ADJCALLSTACKDOWN 0, 0 + $r2d = COPY %3 + $r3d = COPY %0 + $r4d = COPY %2 + CallBRASL &memcpy, $r2d, $r3d, $r4d, csr_systemz_elf, implicit-def dead $r14d, implicit-def dead $cc, implicit $fpc, implicit-def $r2d + ADJCALLSTACKUP 0, 0 + ADJCALLSTACKDOWN 0, 0 + $r2d = COPY %5 + $r3d = COPY %0 + $r4d = COPY %2 + CallBRASL &memcpy, $r2d, $r3d, $r4d, csr_systemz_elf, implicit-def dead $r14d, implicit-def dead $cc, implicit $fpc, implicit-def $r2d + ADJCALLSTACKUP 0, 0 + J %bb.1 + +...