ScheduleDAGInstrs: Fix fixupKills() adding too many kill flags.

Remove invalid shortcut in fixupKills(): A register needs to be marked
live even when we are not adding a kill flag. This is because a
partially live register must not get a kill flags, but it still needs to
be fully marked live when walking backwards.

llvm-svn: 306352

2 files changed, 46 insertions, 1 deletions

diff --git a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
index 7dd66d799be..0f70b0e9ca0 100644
--- a/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
+++ b/llvm/lib/CodeGen/ScheduleDAGInstrs.cpp
@@ -1089,7 +1089,7 @@ static void toggleKills(const MachineRegisterInfo &MRI, LivePhysRegs &LiveRegs,
     // Things that are available after the instruction are killed by it.
     bool IsKill = LiveRegs.available(MRI, Reg);
     MO.setIsKill(IsKill);
-    if (IsKill && addToLiveRegs)
+    if (addToLiveRegs)
       LiveRegs.addReg(Reg);
   }
 }
diff --git a/llvm/test/CodeGen/AMDGPU/misched-killflags.mir b/llvm/test/CodeGen/AMDGPU/misched-killflags.mir
new file mode 100644
index 00000000000..ac3a25e5e4b
--- /dev/null
+++ b/llvm/test/CodeGen/AMDGPU/misched-killflags.mir
@@ -0,0 +1,45 @@
+# RUN: llc -mtriple=amdgcn-amd-amdhsa -mcpu=fiji -verify-machineinstrs -run-pass=post-RA-sched -o - %s | FileCheck %s
+# Make sure ScheduleDAGInstrs::fixupKills does not produce invalid kill flags.
+---
+name: func0
+tracksRegLiveness: true
+body: |
+  bb.0:
+    liveins: %sgpr7, %sgpr0_sgpr1_sgpr2_sgpr3
+
+    %sgpr33 = S_MOV_B32 %sgpr7
+    %sgpr32 = S_MOV_B32 %sgpr33
+    %sgpr10 = S_MOV_B32 5
+    %sgpr9 = S_MOV_B32 4
+    %sgpr8 = S_MOV_B32 3
+    BUNDLE implicit-def %sgpr6_sgpr7, implicit-def %sgpr6, implicit-def %sgpr7, implicit-def %scc {
+      %sgpr6_sgpr7 = S_GETPC_B64
+      %sgpr6 = S_ADD_U32 internal %sgpr6, 0, implicit-def %scc
+      %sgpr7 = S_ADDC_U32 internal %sgpr7,0, implicit-def %scc, implicit internal %scc
+    }
+    %sgpr4 = S_MOV_B32 %sgpr33
+    %vgpr0 = V_MOV_B32_e32 %sgpr8, implicit %exec, implicit-def %vgpr0_vgpr1_vgpr2_vgpr3, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+    %vgpr1 = V_MOV_B32_e32 %sgpr9, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+    %vgpr2 = V_MOV_B32_e32 %sgpr10, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+    %vgpr3 = V_MOV_B32_e32 %sgpr11, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11, implicit %exec
+    S_NOP 0, implicit killed %sgpr6_sgpr7, implicit %sgpr0_sgpr1_sgpr2_sgpr3, implicit %sgpr4, implicit killed %vgpr0_vgpr1_vgpr2_vgpr3
+    S_ENDPGM
+...
+# CHECK-LABEL: name: func0
+# CHECK: %sgpr10 = S_MOV_B32 5
+# CHECK: %sgpr9 = S_MOV_B32 4
+# CHECK: %sgpr8 = S_MOV_B32 3
+# CHECK: %sgpr33 = S_MOV_B32 killed %sgpr7
+# CHECK: %vgpr0 = V_MOV_B32_e32 %sgpr8, implicit %exec, implicit-def %vgpr0_vgpr1_vgpr2_vgpr3, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+# CHECK: BUNDLE implicit-def %sgpr6_sgpr7, implicit-def %sgpr6, implicit-def %sgpr7, implicit-def %scc {
+# CHECK:   %sgpr6_sgpr7 = S_GETPC_B64
+# CHECK:   %sgpr6 = S_ADD_U32 internal %sgpr6, 0, implicit-def %scc
+# CHECK:   %sgpr7 = S_ADDC_U32 internal %sgpr7, 0, implicit-def %scc, implicit internal %scc
+# CHECK: }
+# CHECK: %sgpr4 = S_MOV_B32 %sgpr33
+# CHECK: %vgpr1 = V_MOV_B32_e32 %sgpr9, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+# CHECK: %vgpr2 = V_MOV_B32_e32 %sgpr10, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11
+# CHECK: %vgpr3 = V_MOV_B32_e32 killed %sgpr11, implicit %exec, implicit %sgpr8_sgpr9_sgpr10_sgpr11, implicit %exec
+# CHECK: %sgpr32 = S_MOV_B32 killed %sgpr33
+# CHECK: S_NOP 0, implicit killed %sgpr6_sgpr7, implicit %sgpr0_sgpr1_sgpr2_sgpr3, implicit %sgpr4, implicit killed %vgpr0_vgpr1_vgpr2_vgpr3
+# CHECK: S_ENDPGM