[PATCH] D106879: GlobalISel: Fix infinite loop in legalization artifact combiner

[Petar Avramovic via Phabricator via llvm-commits]

Petar.Avramovic created this revision.
Petar.Avramovic added reviewers: aemerson, foad, arsenm, mbrkusanin.
Herald added subscribers: kerbowa, rovka, nhaehnle, jvesely.
Petar.Avramovic requested review of this revision.
Herald added subscribers: llvm-commits, wdng.
Herald added a project: LLVM.

ArtifactValueFinder keeps trying to combine g_unmerge_values in some cases.
Fix is to skip combine attempt for dead defs.


https://reviews.llvm.org/D106879

Files:
  llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
  llvm/test/CodeGen/AMDGPU/GlobalISel/bug-legalization-artifact-combiner-dead-def.ll


Index: llvm/test/CodeGen/AMDGPU/GlobalISel/bug-legalization-artifact-combiner-dead-def.ll
===================================================================
--- /dev/null
+++ llvm/test/CodeGen/AMDGPU/GlobalISel/bug-legalization-artifact-combiner-dead-def.ll
@@ -0,0 +1,21 @@
+; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
+; RUN: llc -global-isel -mtriple=amdgcn-amd-amdpal -mcpu=gfx1010 < %s | FileCheck -check-prefix=GFX10 %s
+
+define void @value_finder_bug(<2 x float> addrspace(5)* %store_ptr, <4 x float> addrspace(4)* %ptr) {
+; GFX10-LABEL: value_finder_bug:
+; GFX10:       ; %bb.0:
+; GFX10-NEXT:    s_waitcnt vmcnt(0) expcnt(0) lgkmcnt(0)
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT:    global_load_dwordx4 v[1:4], v[1:2], off
+; GFX10-NEXT:    s_waitcnt vmcnt(0)
+; GFX10-NEXT:    buffer_store_dword v3, v0, s[0:3], 0 offen
+; GFX10-NEXT:    buffer_store_dword v4, v0, s[0:3], 0 offen offset:4
+; GFX10-NEXT:    s_waitcnt_vscnt null, 0x0
+; GFX10-NEXT:    s_setpc_b64 s[30:31]
+  %vec = load <4 x float>, <4 x float> addrspace(4)* %ptr, align 4
+  %vec.3 = extractelement <4 x float> %vec, i32 3
+  %shuffle = shufflevector <4 x float> %vec, <4 x float> undef, <2 x i32> <i32 2, i32 undef>
+  %new_vec = insertelement <2 x float> %shuffle, float %vec.3, i32 1
+  store <2 x float> %new_vec, <2 x float> addrspace(5)* %store_ptr, align 8
+  ret void
+}
Index: llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
===================================================================
--- llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
+++ llvm/include/llvm/CodeGen/GlobalISel/LegalizationArtifactCombiner.h
@@ -767,6 +767,8 @@
       SmallBitVector DeadDefs(NumDefs);
       for (unsigned DefIdx = 0; DefIdx < NumDefs; ++DefIdx) {
         Register DefReg = MI.getReg(DefIdx);
+        if (MRI.use_empty(DefReg))
+          continue;
         Register FoundVal =
             ValueFinder.findValueFromDef(DefReg, 0, DestTy.getSizeInBits());
         if (!FoundVal || FoundVal == DefReg)


-------------- next part --------------
A non-text attachment was scrubbed...
Name: D106879.362033.patch
Type: text/x-patch
Size: 2078 bytes
Desc: not available
URL: <http://lists.llvm.org/pipermail/llvm-commits/attachments/20210727/c6e7e986/attachment.bin>