AMDGPU: Fix LCSSA phi lowering in SILowerI1Copies

Summary:
When an LCSSA phi survives through instruction selection, the pass
ends up removing that phi entirely because it is dominated by the
logic that does the lanemask merging.

This then used to trigger an assertion when processing a dependent
phi instruction.

Change-Id: Id4949719f8298062fe476a25718acccc109113b6

Reviewers: llvm-commits

Subscribers: kzhuravl, jvesely, wdng, yaxunl, t-tye, tpr, dstuttard, rtaylor, arsenm

Tags: #llvm

Differential Revision: https://reviews.llvm.org/D60999

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@358983 91177308-0d34-0410-b5e6-96231b3b80d8

diff --git a/lib/Target/AMDGPU/SILowerI1Copies.cpp b/lib/Target/AMDGPU/SILowerI1Copies.cpp
index 823c9040c8747fdb58aabc958240737e5d62c743..15ccef8ac83574b386513e2d693c2b4903b6901f 100644 (file)
--- a/lib/Target/AMDGPU/SILowerI1Copies.cpp
+++ b/lib/Target/AMDGPU/SILowerI1Copies.cpp
@@ -504,6 +504,9 @@ void SILowerI1Copies::lowerPhis() {
   SmallVector<MachineBasicBlock *, 4> IncomingBlocks;
   SmallVector<unsigned, 4> IncomingRegs;
   SmallVector<unsigned, 4> IncomingUpdated;
+#ifndef NDEBUG
+  DenseSet<unsigned> PhiRegisters;
+#endif
 
   for (MachineBasicBlock &MBB : *MF) {
     LF.initialize(MBB);
@@ -531,13 +534,17 @@ void SILowerI1Copies::lowerPhis() {
         } else if (IncomingDef->getOpcode() == AMDGPU::IMPLICIT_DEF) {
           continue;
         } else {
-          assert(IncomingDef->isPHI());
+          assert(IncomingDef->isPHI() || PhiRegisters.count(IncomingReg));
         }
 
         IncomingBlocks.push_back(IncomingMBB);
         IncomingRegs.push_back(IncomingReg);
       }
 
+#ifndef NDEBUG
+      PhiRegisters.insert(DstReg);
+#endif
+
       // Phis in a loop that are observed outside the loop receive a simple but
       // conservatively correct treatment.
       MachineBasicBlock *PostDomBound = &MBB;

diff --git a/test/CodeGen/AMDGPU/si-lower-i1-copies.mir b/test/CodeGen/AMDGPU/si-lower-i1-copies.mir
new file mode 100644 (file)
index 0000000..9312322
--- /dev/null
+++ b/test/CodeGen/AMDGPU/si-lower-i1-copies.mir
@@ -0,0 +1,33 @@
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -verify-machineinstrs -run-pass=si-i1-copies -o - %s | FileCheck -check-prefixes=GCN %s
+
+# GCN-LABEL: name: lcssa_phi
+---
+name:              lcssa_phi
+tracksRegLiveness: true
+body:             |
+  bb.0:
+    %0:sreg_64 = S_MOV_B64 0
+    %8:vreg_1 = IMPLICIT_DEF
+    %10:sreg_64 = IMPLICIT_DEF
+    %11:sreg_64 = SI_IF %10, %bb.3, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
+    S_BRANCH %bb.1
+
+  bb.1:
+    %1:sreg_64 = PHI %0, %bb.0, %3, %bb.1
+    %2:sreg_64 = IMPLICIT_DEF
+    %3:sreg_64 = SI_IF_BREAK %2, %1, implicit-def dead $scc
+    %4:sreg_64 = IMPLICIT_DEF
+    %5:vreg_1 = COPY %4
+    SI_LOOP %3, %bb.1, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
+    S_BRANCH %bb.2
+
+  bb.2:
+    %6:vreg_1 = PHI %5, %bb.1
+    SI_END_CF %3, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
+
+  bb.3:
+    %7:vreg_1 = PHI %6, %bb.2, %8, %bb.0
+    SI_END_CF %11, implicit-def dead $exec, implicit-def dead $scc, implicit $exec
+    S_ENDPGM 0
+
+...