[llvm] 538a83e - RegisterCoalescer: Add undef flags in removePartialRedundancy (#75152)

[via llvm-commits]

Author: Matt Arsenault
Date: 2023-12-13T15:02:53+07:00
New Revision: 538a83e4b9ddaa6cc9e8680fa97b2e33cd03192d

URL: https://github.com/llvm/llvm-project/commit/538a83e4b9ddaa6cc9e8680fa97b2e33cd03192d
DIFF: https://github.com/llvm/llvm-project/commit/538a83e4b9ddaa6cc9e8680fa97b2e33cd03192d.diff

LOG: RegisterCoalescer: Add undef flags in removePartialRedundancy (#75152)

If the copy being hoisted was undef, we have the same problems that
eliminateUndefCopy needs to solve. We would effectively be introducing a
new live out implicit_def. We need to add an undef flag to avoid
artificially introducing a live through undef value. Previously, the
verifier would fail due to the dead def inside the loop providing the
live in value for the %1 use.

Added: 
    llvm/test/CodeGen/X86/coalescer-partial-redundancy-clear-dead-flag-undef-copy.mir

Modified: 
    llvm/lib/CodeGen/RegisterCoalescer.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/CodeGen/RegisterCoalescer.cpp b/llvm/lib/CodeGen/RegisterCoalescer.cpp
index c067d87a9fd81..2ef91e78f3370 100644
--- a/llvm/lib/CodeGen/RegisterCoalescer.cpp
+++ b/llvm/lib/CodeGen/RegisterCoalescer.cpp
@@ -1201,6 +1201,8 @@ bool RegisterCoalescer::removePartialRedundancy(const CoalescerPair &CP,
                       << printMBBReference(MBB) << '\t' << CopyMI);
   }
 
+  const bool IsUndefCopy = CopyMI.getOperand(1).isUndef();
+
   // Remove CopyMI.
   // Note: This is fine to remove the copy before updating the live-ranges.
   // While updating the live-ranges, we only look at slot indices and
@@ -1214,6 +1216,19 @@ bool RegisterCoalescer::removePartialRedundancy(const CoalescerPair &CP,
   LIS->pruneValue(*static_cast<LiveRange *>(&IntB), CopyIdx.getRegSlot(),
                   &EndPoints);
   BValNo->markUnused();
+
+  if (IsUndefCopy) {
+    // We're introducing an undef phi def, and need to set undef on any users of
+    // the previously local def to avoid artifically extending the lifetime
+    // through the block.
+    for (MachineOperand &MO : MRI->use_nodbg_operands(IntB.reg())) {
+      const MachineInstr &MI = *MO.getParent();
+      SlotIndex UseIdx = LIS->getInstructionIndex(MI);
+      if (!IntB.liveAt(UseIdx))
+        MO.setIsUndef(true);
+    }
+  }
+
   // Extend IntB to the EndPoints of its original live interval.
   LIS->extendToIndices(IntB, EndPoints);
 

diff  --git a/llvm/test/CodeGen/X86/coalescer-partial-redundancy-clear-dead-flag-undef-copy.mir b/llvm/test/CodeGen/X86/coalescer-partial-redundancy-clear-dead-flag-undef-copy.mir
new file mode 100644
index 0000000000000..5f33be0bc1555
--- /dev/null
+++ b/llvm/test/CodeGen/X86/coalescer-partial-redundancy-clear-dead-flag-undef-copy.mir
@@ -0,0 +1,47 @@
+# NOTE: Assertions have been autogenerated by utils/update_mir_test_checks.py UTC_ARGS: --version 4
+# RUN: llc -mtriple=x86_64-pc-linux-gnu -run-pass=register-coalescer -verify-coalescing -o - %s | FileCheck %s
+
+# Check for "Live range continues after dead def flag".
+
+# There are 2 copies of undef, but the registers also appear to be
+# live due to block live outs, and thus were not deleted as
+# eliminateUndefCopy only considered the live range, and not the undef
+# flag.
+#
+# removePartialRedundancy would move the COPY undef %0 in bb.1 to
+# bb.0.  The live range of %1 would then be extended to be live out of
+# %bb.1 for the backedge phi. This would then fail the verifier, since
+# the dead flag was no longer valid. This was fixed by directly
+# considering the undef flag to avoid considering this special case.
+
+---
+name: partial_redundancy_coalesce_undef_copy_live_out
+tracksRegLiveness: true
+body:             |
+  ; CHECK-LABEL: name: partial_redundancy_coalesce_undef_copy_live_out
+  ; CHECK: bb.0:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT:   liveins: $rdi
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gr32 = COPY $rdi
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT: bb.1:
+  ; CHECK-NEXT:   successors: %bb.1(0x80000000)
+  ; CHECK-NEXT: {{  $}}
+  ; CHECK-NEXT:   dead [[XOR32ri:%[0-9]+]]:gr32 = XOR32ri undef [[XOR32ri]], 1, implicit-def dead $eflags
+  ; CHECK-NEXT:   dead [[MOV32rr:%[0-9]+]]:gr32 = MOV32rr [[COPY]]
+  ; CHECK-NEXT:   [[COPY:%[0-9]+]]:gr32 = IMPLICIT_DEF
+  ; CHECK-NEXT:   JMP_1 %bb.1
+  bb.0:
+    liveins: $rdi
+
+    %0:gr32 = COPY $rdi
+
+  bb.1:
+    %1:gr32 = COPY undef %0
+    dead %1:gr32 = XOR32ri %1, 1, implicit-def dead $eflags
+    dead %2:gr32 = MOV32rr killed %0
+    %0:gr32 = COPY killed undef %1
+    JMP_1 %bb.1
+
+...