commit 8445cbd1ca964ff490268e0854ecafaf97718639
author Matthias Braun <matze@braunis.de> Tue Mar 21 21:58:08 2017 +0000
committer Matthias Braun <matze@braunis.de> Tue Mar 21 21:58:08 2017 +0000
tree 0a2f4ecd4bab006b0dda7f1c69a9f2c0bd0f14de
parent fc16173cebfb61c13319d6ebada3bb2c4fad14e7

SplitKit: Fix subreg copy related problems

Fix two problems related to r298025:
- SplitKit would create duplicate VNIs in some cases leading to crashs
  when hoisting copies.
- VirtRegMap could fail expanding copies at the beginning of a basic
  block.

This fixes http://llvm.org/PR32353

llvm-svn: 298448

llvm/lib/CodeGen/SplitKit.cpp

diff --git a/llvm/lib/CodeGen/SplitKit.cpp b/llvm/lib/CodeGen/SplitKit.cpp
index 4e42987..3a50aaa 100644
--- a/llvm/lib/CodeGen/SplitKit.cpp
+++ b/llvm/lib/CodeGen/SplitKit.cpp
@@ -502,7 +502,6 @@
   if (FirstCopy) {
     SlotIndexes &Indexes = *LIS.getSlotIndexes();
     Def = Indexes.insertMachineInstrInMaps(*CopyMI, Late).getRegSlot();
-    DestLI.createDeadDef(Def, Allocator);
   } else {
     CopyMI->bundleWithPred();
   }

llvm/lib/CodeGen/VirtRegMap.cpp

diff --git a/llvm/lib/CodeGen/VirtRegMap.cpp b/llvm/lib/CodeGen/VirtRegMap.cpp
index 06a97fd..c894601 100644
--- a/llvm/lib/CodeGen/VirtRegMap.cpp
+++ b/llvm/lib/CodeGen/VirtRegMap.cpp
@@ -383,8 +383,10 @@
 
   if (MI.isBundledWithPred() && !MI.isBundledWithSucc()) {
     // Only do this when the complete bundle is made out of COPYs.
+    MachineBasicBlock &MBB = *MI.getParent();
     for (MachineBasicBlock::reverse_instr_iterator I =
-         std::next(MI.getReverseIterator()); I->isBundledWithSucc(); ++I) {
+         std::next(MI.getReverseIterator()), E = MBB.instr_rend();
+         I != E && I->isBundledWithSucc(); ++I) {
       if (!I->isCopy())
         return;
     }

llvm/test/CodeGen/AMDGPU/splitkit.mir

diff --git a/llvm/test/CodeGen/AMDGPU/splitkit.mir b/llvm/test/CodeGen/AMDGPU/splitkit.mir
index ee58138..41782af 100644
--- a/llvm/test/CodeGen/AMDGPU/splitkit.mir
+++ b/llvm/test/CodeGen/AMDGPU/splitkit.mir
@@ -2,6 +2,7 @@
 --- |
   define amdgpu_kernel void @func0() #0 { ret void }
   define amdgpu_kernel void @func1() #0 { ret void }
+  define amdgpu_kernel void @splitHoist() #0 { ret void }
 
   attributes #0 = { "amdgpu-num-sgpr"="12" }
 ...
@@ -62,3 +63,43 @@
     S_NOP 0, implicit %0.sub0
     S_NOP 0, implicit %0.sub2
 ...
+---
+# Check that copy hoisting out of loops works. This mainly should not crash the
+# compiler when it hoists a subreg copy sequence.
+# CHECK-LABEL: name: splitHoist
+# CHECK: S_NOP 0, implicit-def %sgpr0
+# CHECK: S_NOP 0, implicit-def %sgpr3
+# CHECK-NEXT: SI_SPILL_S128_SAVE
+name: splitHoist
+tracksRegLiveness: true
+body: |
+  bb.0:
+    successors: %bb.1, %bb.2
+    S_NOP 0, implicit-def undef %0.sub0 : sreg_128
+    S_NOP 0, implicit-def %0.sub3 : sreg_128
+
+    S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
+    S_BRANCH %bb.2
+
+  bb.1:
+    successors: %bb.1, %bb.3
+    S_NOP 0, implicit %0.sub0
+
+    ; Clobber registers
+    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1, implicit-def dead %sgpr2, implicit-def dead %sgpr3, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11
+
+    S_CBRANCH_VCCNZ %bb.1, implicit undef %vcc
+    S_BRANCH %bb.3
+
+  bb.2:
+    successors: %bb.3
+    ; Clobber registers
+    S_NOP 0, implicit-def dead %sgpr0, implicit-def dead %sgpr1, implicit-def dead %sgpr2, implicit-def dead %sgpr3, implicit-def dead %sgpr4, implicit-def dead %sgpr5, implicit-def dead %sgpr6, implicit-def dead %sgpr7, implicit-def dead %sgpr8, implicit-def dead %sgpr9, implicit-def dead %sgpr10, implicit-def dead %sgpr11
+    S_BRANCH %bb.3
+
+  bb.3:
+    S_NOP 0, implicit %0.sub0
+    S_NOP 0, implicit %0.sub3
+    S_NOP 0, implicit %0.sub0
+    S_NOP 0, implicit %0.sub3
+...