[llvm] 3e4160f - [X86] Skip debug instructions in tile copy lowering (#209640)

[via llvm-commits]

Author: Krisitan Erik Olsen
Date: 2026-07-15T11:18:18+02:00
New Revision: 3e4160fdc3d5bb0ed86480604bdfcd3130e7dd37

URL: https://github.com/llvm/llvm-project/commit/3e4160fdc3d5bb0ed86480604bdfcd3130e7dd37
DIFF: https://github.com/llvm/llvm-project/commit/3e4160fdc3d5bb0ed86480604bdfcd3130e7dd37.diff

LOG: [X86] Skip debug instructions in tile copy lowering (#209640)

X86LowerTileCopy iterates over instructions in reverse to track live
registers, calling LiveRegUnits::stepBackward on every instruction
unconditionally. Since commit 16b2ef32 added an assertion that
stepBackward must not receive debug instructions, functions containing
debug info hit the assertion during tile copy lowering.
This patch skips debug instructions early in the loop, matching the
guard pattern used in RegisterScavenging.cpp and X86FixupBWInsts.cpp.

Fixes #209512

Added: 
    llvm/test/CodeGen/X86/AMX/pr209512.ll

Modified: 
    llvm/lib/Target/X86/X86LowerTileCopy.cpp

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/X86/X86LowerTileCopy.cpp b/llvm/lib/Target/X86/X86LowerTileCopy.cpp
index e5a374dfcc0b6..628f691279600 100644
--- a/llvm/lib/Target/X86/X86LowerTileCopy.cpp
+++ b/llvm/lib/Target/X86/X86LowerTileCopy.cpp
@@ -87,6 +87,8 @@ static bool lowerTileCopy(MachineFunction &MF) {
     LiveRegUnits UsedRegs(*TRI);
     UsedRegs.addLiveOuts(MBB);
     for (MachineInstr &MI : llvm::make_early_inc_range(reverse(MBB))) {
+      if (MI.isDebugInstr())
+        continue;
       UsedRegs.stepBackward(MI);
       if (!MI.isCopy())
         continue;

diff  --git a/llvm/test/CodeGen/X86/AMX/pr209512.ll b/llvm/test/CodeGen/X86/AMX/pr209512.ll
new file mode 100644
index 0000000000000..975aa5c1e5f6c
--- /dev/null
+++ b/llvm/test/CodeGen/X86/AMX/pr209512.ll
@@ -0,0 +1,28 @@
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+amx-int8 -mattr=+avx512f -verify-machineinstrs -o /dev/null
+
+define void @test_debug_instr(ptr %arg) #0 !dbg !4 {
+  #dbg_declare(ptr %arg, !12, !DIExpression(), !15)
+  %1 = call x86_amx @llvm.x86.cast.vector.to.tile.v1024i8(<1024 x i8> zeroinitializer)
+  %2 = call x86_amx @llvm.x86.tdpbssd.internal(i16 0, i16 0, i16 0, x86_amx %1, x86_amx %1, x86_amx %1)
+  ret void
+}
+
+declare x86_amx @llvm.x86.cast.vector.to.tile.v1024i8(<1024 x i8>) #1
+declare x86_amx @llvm.x86.tdpbssd.internal(i16, i16, i16, x86_amx, x86_amx, x86_amx) #2
+
+attributes #0 = { "target-features"="+amx-int8" }
+attributes #1 = { nocallback nofree nosync nounwind willreturn memory(none) }
+attributes #2 = { nounwind }
+
+!llvm.module.flags = !{!0}
+!llvm.dbg.cu = !{!1}
+
+!0 = !{i32 2, !"Debug Info Version", i32 3}
+!1 = distinct !DICompileUnit(language: DW_LANG_C11, file: !2, producer: "clang", isOptimized: true, runtimeVersion: 0, emissionKind: FullDebug, nameTableKind: None)
+!2 = !DIFile(filename: "test.c", directory: "/tmp")
+!3 = !{}
+!4 = distinct !DISubprogram(name: "test_debug_instr", linkageName: "test_debug_instr", scope: !2, file: !2, line: 1, type: !9, scopeLine: 1, flags: DIFlagPrototyped, spFlags: DISPFlagDefinition | DISPFlagOptimized, unit: !1, retainedNodes: !3)
+!9 = distinct !DISubroutineType(types: !3)
+!12 = distinct !DILocalVariable(name: "a", arg: 1, scope: !4, file: !2, line: 1, type: !13)
+!13 = !DICompositeType(tag: DW_TAG_structure_type, name: "__tile1024i", scope: !4, file: !2, size: 16384, align: 8192, flags: DIFlagPublic, elements: !3, identifier: "__tile1024i")
+!15 = !DILocation(line: 1, column: 1, scope: !4)